bot: update RSS feed
This commit is contained in:
github-actions[bot]
563
feed.xml
563
feed.xml
@@ -7,286 +7,447 @@
|
|||||||
<docs>http://www.rssboard.org/rss-specification</docs>
|
<docs>http://www.rssboard.org/rss-specification</docs>
|
||||||
<generator>python-feedgen</generator>
|
<generator>python-feedgen</generator>
|
||||||
<language>en</language>
|
<language>en</language>
|
||||||
<lastBuildDate>Tue, 03 Jun 2025 00:02:29 +0000</lastBuildDate>
|
<lastBuildDate>Wed, 04 Jun 2025 00:02:34 +0000</lastBuildDate>
|
||||||
<item>
|
<item>
|
||||||
<title>Role-Playing Evaluation for Large Language Models</title>
|
<title>MIKU-PAL: An Automated and Standardized Multi-Modal Method for Speech Paralinguistic and Affect Labeling</title>
|
||||||
<link>https://arxiv.org/abs/2505.13157</link>
|
<link>https://arxiv.org/abs/2505.15772</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.13157.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yassine El Boudouri, Walter Nuninger, Julian Alvarez, Yvan Peter</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Large Language Models (LLMs) demonstrate a notable capacity for adopting personas and engaging in role-playing. However, evaluating this ability presents significant challenges, as human assessments are resource-intensive and automated evaluations can be biased. To address this, we introduce Role-Playing Eval (RPEval), a novel benchmark designed to assess LLM role-playing capabilities across four key dimensions: emotional understanding, decision-making, moral alignment, and in-character consistency. This article details the construction of RPEval and presents baseline evaluations. Our code and dataset are available at https://github.com/yelboudouri/RPEval</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.15772.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yifan Cheng, Ruoyi Zhang, Jiatong Shi</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Acquiring large-scale emotional speech data with strong consistency remains a challenge for speech synthesis. This paper presents MIKU-PAL, a fully automated multimodal pipeline for extracting high-consistency emotional speech from unlabeled video data. Leveraging face detection and tracking algorithms, we developed an automatic emotion analysis system using a multimodal large language model (MLLM). Our results demonstrate that MIKU-PAL can achieve human-level accuracy (68.5% on MELD) and superior consistency (0.93 Fleiss kappa score) while being much cheaper and faster than human annotation. With the high-quality, flexible, and consistent annotation from MIKU-PAL, we can annotate fine-grained speech emotion categories of up to 26 types, validated by human annotators with 83% rationality ratings. Based on our proposed system, we further released a fine-grained emotional speech dataset MIKU-EmoBench(131.2 hours) as a new benchmark for emotional text-to-speech and visual voice cloning.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.13157</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2505.15772</guid>
|
||||||
<pubDate>Mon, 19 May 2025 14:18:16 +0000</pubDate>
|
<pubDate>Wed, 21 May 2025 17:23:12 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Large Language Models for Data Synthesis</title>
|
<title>Pixels Versus Priors: Controlling Knowledge Priors in Vision-Language Models through Visual Counterfacts</title>
|
||||||
<link>https://arxiv.org/abs/2505.14752</link>
|
<link>https://arxiv.org/abs/2505.17127</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.14752.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yihong Tang, Menglin Kong, Lijun Sun</p><p><b>Upvotes:</b> 35</p><p><b>Summary:</b> Generating synthetic data that faithfully captures the statistical structure of real-world distributions is a fundamental challenge in data modeling. Classical approaches often depend on strong parametric assumptions or manual structural design and struggle in high-dimensional or heterogeneous domains. Recent progress in Large Language Models (LLMs) reveals their potential as flexible, high-dimensional priors over real-world distributions. However, when applied to data synthesis, standard LLM-based sampling is inefficient, constrained by fixed context limits, and fails to ensure statistical alignment. Given this, we introduce LLMSynthor, a general framework for data synthesis that transforms LLMs into structure-aware simulators guided by distributional feedback. LLMSynthor treats the LLM as a nonparametric copula simulator for modeling high-order dependencies and introduces LLM Proposal Sampling to generate grounded proposal distributions that improve sampling efficiency without requiring rejection. By minimizing discrepancies in the summary statistics space, the iterative synthesis loop aligns real and synthetic data while gradually uncovering and refining the latent generative structure. We evaluate LLMSynthor in both controlled and real-world settings using heterogeneous datasets in privacy-sensitive domains (e.g., e-commerce, population, and mobility) that encompass both structured and unstructured formats. The synthetic data produced by LLMSynthor shows high statistical fidelity, practical utility, and cross-data adaptability, positioning it as a valuable tool across economics, social science, urban studies, and beyond.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.17127.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Michal Golovanevsky, William Rudman, Michael Lepori, Amir Bar, Ritambhara Singh, Carsten Eickhoff</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Multimodal Large Language Models (MLLMs) perform well on tasks such as visual question answering, but it remains unclear whether their reasoning relies more on memorized world knowledge or on the visual information present in the input image. To investigate this, we introduce Visual CounterFact, a new dataset of visually-realistic counterfactuals that put world knowledge priors (e.g, red strawberry) into direct conflict with visual input (e.g, blue strawberry). Using Visual CounterFact, we show that model predictions initially reflect memorized priors, but shift toward visual evidence in mid-to-late layers. This dynamic reveals a competition between the two modalities, with visual input ultimately overriding priors during evaluation. To control this behavior, we propose Pixels Versus Priors (PvP) steering vectors, a mechanism for controlling model outputs toward either world knowledge or visual input through activation-level interventions. On average, PvP successfully shifts 92.5% of color and 74.6% of size predictions from priors to counterfactuals. Together, these findings offer new tools for interpreting and controlling factual behavior in multimodal models.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.14752</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2505.17127</guid>
|
||||||
<pubDate>Tue, 20 May 2025 13:35:38 +0000</pubDate>
|
<pubDate>Wed, 21 May 2025 22:56:55 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models</title>
|
<title>Plan and Budget: Effective and Efficient Test-Time Scaling on Large Language Model Reasoning</title>
|
||||||
<link>https://arxiv.org/abs/2505.21523</link>
|
<link>https://arxiv.org/abs/2505.16122</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.21523.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chengzhi Liu, Zhongxing Xu, Qingyue Wei, Juncheng Wu, James Zou, Xin Eric Wang, Yuyin Zhou, Sheng Liu</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Test-time compute has empowered multimodal large language models to generate extended reasoning chains, yielding strong performance on tasks such as multimodal math reasoning. However, this improved reasoning ability often comes with increased hallucination: as generations become longer, models tend to drift away from image-grounded content and rely more heavily on language priors. Attention analysis shows that longer reasoning chains lead to reduced focus on visual inputs, which contributes to hallucination. To systematically study this phenomenon, we introduce RH-AUC, a metric that quantifies how a model's perception accuracy changes with reasoning length, allowing us to evaluate whether the model preserves visual grounding during reasoning. We also release RH-Bench, a diagnostic benchmark that spans a variety of multimodal tasks, designed to assess the trade-off between reasoning ability and hallucination. Our analysis reveals that (i) larger models typically achieve a better balance between reasoning and perception, and (ii) this balance is influenced more by the types and domains of training data than by its overall volume. These findings underscore the importance of evaluation frameworks that jointly consider both reasoning quality and perceptual fidelity.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.16122.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junhong Lin, Xinyue Zeng, Jie Zhu, Song Wang, Julian Shun, Jun Wu, Dawei Zhou</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Large Language Models (LLMs) have achieved remarkable success in complex reasoning tasks, but their inference remains computationally inefficient. We observe a common failure mode in many prevalent LLMs, overthinking, where models generate verbose and tangential reasoning traces even for simple queries. Recent works have tried to mitigate this by enforcing fixed token budgets, however, this can lead to underthinking, especially on harder problems. Through empirical analysis, we identify that this inefficiency often stems from unclear problem-solving strategies. To formalize this, we develop a theoretical model, BBAM (Bayesian Budget Allocation Model), which models reasoning as a sequence of sub-questions with varying uncertainty, and introduce the E^3 metric to capture the trade-off between correctness and computation efficiency. Building on theoretical results from BBAM, we propose Plan-and-Budget, a model-agnostic, test-time framework that decomposes complex queries into sub-questions and allocates token budgets based on estimated complexity using adaptive scheduling. Plan-and-Budget improves reasoning efficiency across a range of tasks and models, achieving up to +70% accuracy gains, -39% token reduction, and +187.5% improvement in E^3. Notably, it elevates a smaller model (DS-Qwen-32B) to match the efficiency of a larger model (DS-LLaMA-70B)-demonstrating Plan-and-Budget's ability to close performance gaps without retraining. Our code is available at anonymous.4open.science/r/P-and-B-6513/.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.21523</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2505.16122</guid>
|
||||||
<pubDate>Fri, 23 May 2025 05:08:40 +0000</pubDate>
|
<pubDate>Thu, 22 May 2025 01:56:29 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Don't Look Only Once: Towards Multimodal Interactive Reasoning with Selective Visual Revisitation</title>
|
<title>Frankentext: Stitching random text fragments into long-form narratives</title>
|
||||||
<link>https://arxiv.org/abs/2505.18842</link>
|
<link>https://arxiv.org/abs/2505.18128</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.18842.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiwan Chung, Junhyeok Kim, Siyeol Kim, Jaeyoung Lee, Min Soo Kim, Youngjae Yu</p><p><b>Upvotes:</b> 29</p><p><b>Summary:</b> We present v1, a lightweight extension to Multimodal Large Language Models (MLLMs) that enables selective visual revisitation during inference. While current MLLMs typically consume visual input only once and reason purely over internal memory, v1 introduces a simple point-and-copy mechanism that allows the model to dynamically retrieve relevant image regions throughout the reasoning process. This mechanism augments existing architectures with minimal modifications, enabling contextual access to visual tokens based on the model's evolving hypotheses. To train this capability, we construct v1g, a dataset of 300K multimodal reasoning traces with interleaved visual grounding annotations. Experiments on three multimodal mathematical reasoning benchmarks -- MathVista, MathVision, and MathVerse -- demonstrate that v1 consistently improves performance over comparable baselines, particularly on tasks requiring fine-grained visual reference and multi-step reasoning. Our results suggest that dynamic visual access is a promising direction for enhancing grounded multimodal reasoning. Code, models, and data will be released to support future research.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.18128.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chau Minh Pham, Jenna Russell, Dzung Pham, Mohit Iyyer</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> We introduce Frankentexts, a new type of long-form narratives produced by LLMs under the extreme constraint that most tokens (e.g., 90%) must be copied verbatim from human writings. This task presents a challenging test of controllable generation, requiring models to satisfy a writing prompt, integrate disparate text fragments, and still produce a coherent narrative. To generate Frankentexts, we instruct the model to produce a draft by selecting and combining human-written passages, then iteratively revise the draft while maintaining a user-specified copy ratio. We evaluate the resulting Frankentexts along three axes: writing quality, instruction adherence, and detectability. Gemini-2.5-Pro performs surprisingly well on this task: 81% of its Frankentexts are coherent and 100% relevant to the prompt. Notably, up to 59% of these outputs are misclassified as human-written by detectors like Pangram, revealing limitations in AI text detectors. Human annotators can sometimes identify Frankentexts through their abrupt tone shifts and inconsistent grammar between segments, especially in longer generations. Beyond presenting a challenging generation task, Frankentexts invite discussion on building effective detectors for this new grey zone of authorship, provide training data for mixed authorship detection, and serve as a sandbox for studying human-AI co-writing processes.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.18842</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2505.18128</guid>
|
||||||
<pubDate>Sat, 24 May 2025 19:30:47 +0000</pubDate>
|
<pubDate>Fri, 23 May 2025 17:38:47 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Grammars of Formal Uncertainty: When to Trust LLMs in Automated Reasoning Tasks</title>
|
<title>Think Again! The Effect of Test-Time Compute on Preferences, Opinions, and Beliefs of Large Language Models</title>
|
||||||
<link>https://arxiv.org/abs/2505.20047</link>
|
<link>https://arxiv.org/abs/2505.19621</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.20047.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Debargha Ganguly, Vikash Singh, Sreehari Sankar, Biyao Zhang, Xuecen Zhang, Srinivasan Iyengar, Xiaotian Han, Amit Sharma, Shivkumar Kalyanaraman, Vipin Chaudhary</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Large language models (LLMs) show remarkable promise for democratizing automated reasoning by generating formal specifications. However, a fundamental tension exists: LLMs are probabilistic, while formal verification demands deterministic guarantees. This paper addresses this epistemological gap by comprehensively investigating failure modes and uncertainty quantification (UQ) in LLM-generated formal artifacts. Our systematic evaluation of five frontier LLMs reveals Satisfiability Modulo Theories (SMT) based autoformalization's domain-specific impact on accuracy (from +34.8% on logical tasks to -44.5% on factual ones), with known UQ techniques like the entropy of token probabilities failing to identify these errors. We introduce a probabilistic context-free grammar (PCFG) framework to model LLM outputs, yielding a refined uncertainty taxonomy. We find uncertainty signals are task-dependent (e.g., grammar entropy for logic, AUROC>0.93). Finally, a lightweight fusion of these signals enables selective verification, drastically reducing errors (14-100%) with minimal abstention, transforming LLM-driven formalization into a reliable engineering discipline.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.19621.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> George Kour, Itay Nakash, Ateret Anaby-Tavor, Michal Shmueli-Scheuer</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> As Large Language Models (LLMs) become deeply integrated into human life and increasingly influence decision-making, it's crucial to evaluate whether and to what extent they exhibit subjective preferences, opinions, and beliefs. These tendencies may stem from biases within the models, which may shape their behavior, influence the advice and recommendations they offer to users, and potentially reinforce certain viewpoints. This paper presents the Preference, Opinion, and Belief survey (POBs), a benchmark developed to assess LLMs' subjective inclinations across societal, cultural, ethical, and personal domains. We applied our benchmark to evaluate leading open- and closed-source LLMs, measuring desired properties such as reliability, neutrality, and consistency. In addition, we investigated the effect of increasing the test-time compute, through reasoning and self-reflection mechanisms, on those metrics. While effective in other tasks, our results show that these mechanisms offer only limited gains in our domain. Furthermore, we reveal that newer model versions are becoming less consistent and more biased toward specific viewpoints, highlighting a blind spot and a concerning trend. POBS: https://ibm.github.io/POBS</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.20047</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2505.19621</guid>
|
||||||
<pubDate>Mon, 26 May 2025 14:34:04 +0000</pubDate>
|
<pubDate>Mon, 26 May 2025 07:41:21 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Fork-Merge Decoding: Enhancing Multimodal Understanding in Audio-Visual Large Language Models</title>
|
<title>MaskSearch: A Universal Pre-Training Framework to Enhance Agentic Search Capability</title>
|
||||||
<link>https://arxiv.org/abs/2505.20873</link>
|
<link>https://arxiv.org/abs/2505.20285</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.20873.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chaeyoung Jung, Youngjoon Jang, Jongmin Choi, Joon Son Chung</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> The goal of this work is to enhance balanced multimodal understanding in audio-visual large language models (AV-LLMs) by addressing modality bias without requiring additional training. In current AV-LLMs, audio and video features are typically processed jointly in the decoder. While this strategy facilitates unified multimodal understanding, it may introduce modality bias, where the model tends to over-rely on one modality due to imbalanced training signals. To mitigate this, we propose Fork-Merge Decoding (FMD), a simple yet effective inference-time strategy that requires no additional training or architectural modifications. FMD first performs modality-specific reasoning by processing audio-only and video-only inputs through the early decoder layers (a fork phase), and then merges the resulting hidden states for joint reasoning in the remaining layers (a merge phase). This approach promotes balanced modality contributions and leverages complementary information across modalities. We evaluate our method on two representative AV-LLMs, VideoLLaMA2 and video-SALMONN, using three benchmark datasets. Experimental results demonstrate consistent performance improvements on tasks focused on audio, video, and combined audio-visual reasoning, demonstrating the effectiveness of inference-time interventions for robust multimodal understanding.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.20285.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Weiqi Wu, Xin Guan, Shen Huang, Yong Jiang, Pengjun Xie, Fei Huang, Jiuxin Cao, Hai Zhao, Jingren Zhou</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Retrieval-Augmented Language Models (RALMs) represent a classic paradigm where models enhance generative capabilities using external knowledge retrieved via a specialized module. Recent advancements in Agent techniques enable Large Language Models (LLMs) to autonomously utilize tools for retrieval, planning, and reasoning. While existing training-based methods show promise, their agentic abilities are limited by inherent characteristics of the task-specific data used during training. To further enhance the universal search capability of agents, we propose a novel pre-training framework, MaskSearch. In the pre-training stage, we introduce the Retrieval Augmented Mask Prediction (RAMP) task, where the model learns to leverage search tools to fill masked spans on a large number of pre-training data, thus acquiring universal retrieval and reasoning capabilities for LLMs. After that, the model is trained on downstream tasks to achieve further improvement. We apply both Supervised Fine-tuning (SFT) and Reinforcement Learning (RL) for training. For SFT, we combine agent-based and distillation-based methods to generate training data, starting with a multi-agent system consisting of a planner, rewriter, observer, and followed by a self-evolving teacher model. While for RL, we employ DAPO as the training framework and adopt a hybrid reward system consisting of answer rewards and format rewards. Additionally, we introduce a curriculum learning approach that allows the model to learn progressively from easier to more challenging instances based on the number of masked spans. We evaluate the effectiveness of our framework in the scenario of open-domain multi-hop question answering. Through extensive experiments, we demonstrate that MaskSearch significantly enhances the performance of LLM-based search agents on both in-domain and out-of-domain downstream tasks.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.20873</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2505.20285</guid>
|
||||||
<pubDate>Tue, 27 May 2025 08:22:56 +0000</pubDate>
|
<pubDate>Mon, 26 May 2025 17:58:50 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Evaluating and Steering Modality Preferences in Multimodal Large Language Model</title>
|
<title>Normalized Attention Guidance: Universal Negative Guidance for Diffusion Model</title>
|
||||||
<link>https://arxiv.org/abs/2505.20977</link>
|
<link>https://arxiv.org/abs/2505.21179</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.20977.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yu Zhang, Jinlong Ma, Yongshuai Hou, Xuefeng Bai, Kehai Chen, Yang Xiang, Jun Yu, Min Zhang</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Multimodal large language models (MLLMs) have achieved remarkable performance on complex tasks with multimodal context. However, it is still understudied whether they exhibit modality preference when processing multimodal contexts. To study this question, we first build a MC\textsuperscript{2} benchmark under controlled evidence conflict scenarios to systematically evaluate modality preference, which is the tendency to favor one modality over another when making decisions based on multimodal conflicting evidence. Our extensive evaluation reveals that all 18 tested MLLMs generally demonstrate clear modality bias, and modality preference can be influenced by external interventions. An in-depth analysis reveals that the preference direction can be captured within the latent representations of MLLMs. Built on this, we propose a probing and steering method based on representation engineering to explicitly control modality preference without additional fine-tuning or carefully crafted prompts. Our method effectively amplifies modality preference toward a desired direction and applies to downstream tasks such as hallucination mitigation and multimodal machine translation, yielding promising improvements.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.21179.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dar-Yen Chen, Hmrishav Bandyopadhyay, Kai Zou, Yi-Zhe Song</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Negative guidance -- explicitly suppressing unwanted attributes -- remains a fundamental challenge in diffusion models, particularly in few-step sampling regimes. While Classifier-Free Guidance (CFG) works well in standard settings, it fails under aggressive sampling step compression due to divergent predictions between positive and negative branches. We present Normalized Attention Guidance (NAG), an efficient, training-free mechanism that applies extrapolation in attention space with L1-based normalization and refinement. NAG restores effective negative guidance where CFG collapses while maintaining fidelity. Unlike existing approaches, NAG generalizes across architectures (UNet, DiT), sampling regimes (few-step, multi-step), and modalities (image, video), functioning as a universal plug-in with minimal computational overhead. Through extensive experimentation, we demonstrate consistent improvements in text alignment (CLIP Score), fidelity (FID, PFID), and human-perceived quality (ImageReward). Our ablation studies validate each design component, while user studies confirm significant preference for NAG-guided outputs. As a model-agnostic inference-time approach requiring no retraining, NAG provides effortless negative guidance for all modern diffusion frameworks -- pseudocode in the Appendix!</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.20977</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2505.21179</guid>
|
||||||
<pubDate>Tue, 27 May 2025 10:07:59 +0000</pubDate>
|
<pubDate>Tue, 27 May 2025 13:30:46 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>CoDA: Coordinated Diffusion Noise Optimization for Whole-Body Manipulation of Articulated Objects</title>
|
<title>R1-Code-Interpreter: Training LLMs to Reason with Code via Supervised and Reinforcement Learning</title>
|
||||||
<link>https://arxiv.org/abs/2505.21437</link>
|
<link>https://arxiv.org/abs/2505.21668</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.21437.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Huaijin Pi, Zhi Cen, Zhiyang Dou, Taku Komura</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Synthesizing whole-body manipulation of articulated objects, including body motion, hand motion, and object motion, is a critical yet challenging task with broad applications in virtual humans and robotics. The core challenges are twofold. First, achieving realistic whole-body motion requires tight coordination between the hands and the rest of the body, as their movements are interdependent during manipulation. Second, articulated object manipulation typically involves high degrees of freedom and demands higher precision, often requiring the fingers to be placed at specific regions to actuate movable parts. To address these challenges, we propose a novel coordinated diffusion noise optimization framework. Specifically, we perform noise-space optimization over three specialized diffusion models for the body, left hand, and right hand, each trained on its own motion dataset to improve generalization. Coordination naturally emerges through gradient flow along the human kinematic chain, allowing the global body posture to adapt in response to hand motion objectives with high fidelity. To further enhance precision in hand-object interaction, we adopt a unified representation based on basis point sets (BPS), where end-effector positions are encoded as distances to the same BPS used for object geometry. This unified representation captures fine-grained spatial relationships between the hand and articulated object parts, and the resulting trajectories serve as targets to guide the optimization of diffusion noise, producing highly accurate interaction motion. We conduct extensive experiments demonstrating that our method outperforms existing approaches in motion quality and physical plausibility, and enables various capabilities such as object pose control, simultaneous walking and manipulation, and whole-body generation from hand-only data.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.21668.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yongchao Chen, Yueying Liu, Junwei Zhou, Yilun Hao, Jingquan Wang, Yang Zhang, Chuchu Fan</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Despite advances in reasoning and planning of R1-like models, Large Language Models (LLMs) still struggle with tasks requiring precise computation, symbolic manipulation, optimization, and algorithmic reasoning, in which textual reasoning lacks the rigor of code execution. A key challenge is enabling LLMs to decide when to use textual reasoning versus code generation. While OpenAI trains models to invoke a Code Interpreter as needed, public research lacks guidance on aligning pre-trained LLMs to effectively leverage code and generalize across diverse tasks. We present R1-Code-Interpreter, an extension of a text-only LLM trained via multi-turn supervised fine-tuning (SFT) and reinforcement learning (RL) to autonomously generate multiple code queries during step-by-step reasoning. We curate 144 reasoning and planning tasks (107 for training, 37 for testing), each with over 200 diverse questions. We fine-tune Qwen-2.5 models (3B/7B/14B) using various SFT and RL strategies, investigating different answer formats, reasoning vs. non-reasoning models, cold vs. warm starts, GRPO vs. PPO, and masked vs. unmasked code outputs. Unlike prior RL work on narrow domains, we find that Code Interpreter training is significantly harder due to high task diversity and expensive code execution, highlighting the critical role of the SFT stage. Our final model, R1-CI-14B, improves average accuracy on the 37 test tasks from 44.0\% to 64.1\%, outperforming GPT-4o (text-only: 58.6\%) and approaching GPT-4o with Code Interpreter (70.9\%), with the emergent self-checking behavior via code generation. Datasets, Codes, and Models are available at https://github.com/yongchao98/R1-Code-Interpreter and https://huggingface.co/yongchao98.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.21437</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2505.21668</guid>
|
||||||
<pubDate>Tue, 27 May 2025 17:11:50 +0000</pubDate>
|
<pubDate>Tue, 27 May 2025 18:47:33 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Revisiting Bi-Linear State Transitions in Recurrent Neural Networks</title>
|
<title>OmniResponse: Online Multimodal Conversational Response Generation in Dyadic Interactions</title>
|
||||||
<link>https://arxiv.org/abs/2505.21749</link>
|
<link>https://arxiv.org/abs/2505.21724</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.21749.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> M. Reza Ebrahimi, Roland Memisevic</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> The role of hidden units in recurrent neural networks is typically seen as modeling memory, with research focusing on enhancing information retention through gating mechanisms. A less explored perspective views hidden units as active participants in the computation performed by the network, rather than passive memory stores. In this work, we revisit bi-linear operations, which involve multiplicative interactions between hidden units and input embeddings. We demonstrate theoretically and empirically that they constitute a natural inductive bias for representing the evolution of hidden states in state tracking tasks. These are the simplest type of task that require hidden units to actively contribute to the behavior of the network. We also show that bi-linear state updates form a natural hierarchy corresponding to state tracking tasks of increasing complexity, with popular linear recurrent networks such as Mamba residing at the lowest-complexity center of that hierarchy.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.21724.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Cheng Luo, Jianghui Wang, Bing Li, Siyang Song, Bernard Ghanem</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> In this paper, we introduce Online Multimodal Conversational Response Generation (OMCRG), a novel task that aims to online generate synchronized verbal and non-verbal listener feedback, conditioned on the speaker's multimodal input. OMCRG reflects natural dyadic interactions and poses new challenges in achieving synchronization between the generated audio and facial responses of the listener. To address these challenges, we innovatively introduce text as an intermediate modality to bridge the audio and facial responses. We hence propose OmniResponse, a Multimodal Large Language Model (MLLM) that autoregressively generates high-quality multi-modal listener responses. OmniResponse leverages a pretrained LLM enhanced with two novel components: Chrono-Text, which temporally anchors generated text tokens, and TempoVoice, a controllable online TTS module that produces speech synchronized with facial reactions. To support further OMCRG research, we present ResponseNet, a new dataset comprising 696 high-quality dyadic interactions featuring synchronized split-screen videos, multichannel audio, transcripts, and facial behavior annotations. Comprehensive evaluations conducted on ResponseNet demonstrate that OmniResponse significantly outperforms baseline models in terms of semantic speech content, audio-visual synchronization, and generation quality.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.21749</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2505.21724</guid>
|
||||||
<pubDate>Tue, 27 May 2025 20:38:19 +0000</pubDate>
|
<pubDate>Tue, 27 May 2025 20:12:46 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>DexUMI: Using Human Hand as the Universal Manipulation Interface for Dexterous Manipulation</title>
|
<title>BinauralFlow: A Causal and Streamable Approach for High-Quality Binaural Speech Synthesis with Flow Matching Models</title>
|
||||||
<link>https://arxiv.org/abs/2505.21864</link>
|
<link>https://arxiv.org/abs/2505.22865</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.21864.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mengda Xu, Han Zhang, Yifan Hou, Zhenjia Xu, Linxi Fan, Manuela Veloso, Shuran Song</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> We present DexUMI - a data collection and policy learning framework that uses the human hand as the natural interface to transfer dexterous manipulation skills to various robot hands. DexUMI includes hardware and software adaptations to minimize the embodiment gap between the human hand and various robot hands. The hardware adaptation bridges the kinematics gap using a wearable hand exoskeleton. It allows direct haptic feedback in manipulation data collection and adapts human motion to feasible robot hand motion. The software adaptation bridges the visual gap by replacing the human hand in video data with high-fidelity robot hand inpainting. We demonstrate DexUMI's capabilities through comprehensive real-world experiments on two different dexterous robot hand hardware platforms, achieving an average task success rate of 86%.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.22865.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Susan Liang, Dejan Markovic, Israel D. Gebru, Steven Krenn, Todd Keebler, Jacob Sandakly, Frank Yu, Samuel Hassel, Chenliang Xu, Alexander Richard</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Binaural rendering aims to synthesize binaural audio that mimics natural hearing based on a mono audio and the locations of the speaker and listener. Although many methods have been proposed to solve this problem, they struggle with rendering quality and streamable inference. Synthesizing high-quality binaural audio that is indistinguishable from real-world recordings requires precise modeling of binaural cues, room reverb, and ambient sounds. Additionally, real-world applications demand streaming inference. To address these challenges, we propose a flow matching based streaming binaural speech synthesis framework called BinauralFlow. We consider binaural rendering to be a generation problem rather than a regression problem and design a conditional flow matching model to render high-quality audio. Moreover, we design a causal U-Net architecture that estimates the current audio frame solely based on past information to tailor generative models for streaming inference. Finally, we introduce a continuous inference pipeline incorporating streaming STFT/ISTFT operations, a buffer bank, a midpoint solver, and an early skip schedule to improve rendering continuity and speed. Quantitative and qualitative evaluations demonstrate the superiority of our method over SOTA approaches. A perceptual study further reveals that our model is nearly indistinguishable from real-world recordings, with a 42% confusion rate.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.21864</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2505.22865</guid>
|
||||||
<pubDate>Wed, 28 May 2025 01:25:27 +0000</pubDate>
|
<pubDate>Wed, 28 May 2025 20:59:15 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>LegalSearchLM: Rethinking Legal Case Retrieval as Legal Elements Generation</title>
|
<title>Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents</title>
|
||||||
<link>https://arxiv.org/abs/2505.23832</link>
|
<link>https://arxiv.org/abs/2505.22954</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.23832.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chaeeun Kim, Jinu Lee, Wonseok Hwang</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Legal Case Retrieval (LCR), which retrieves relevant cases from a query case, is a fundamental task for legal professionals in research and decision-making. However, existing studies on LCR face two major limitations. First, they are evaluated on relatively small-scale retrieval corpora (e.g., 100-55K cases) and use a narrow range of criminal query types, which cannot sufficiently reflect the complexity of real-world legal retrieval scenarios. Second, their reliance on embedding-based or lexical matching methods often results in limited representations and legally irrelevant matches. To address these issues, we present: (1) LEGAR BENCH, the first large-scale Korean LCR benchmark, covering 411 diverse crime types in queries over 1.2M legal cases; and (2) LegalSearchLM, a retrieval model that performs legal element reasoning over the query case and directly generates content grounded in the target cases through constrained decoding. Experimental results show that LegalSearchLM outperforms baselines by 6-20% on LEGAR BENCH, achieving state-of-the-art performance. It also demonstrates strong generalization to out-of-domain cases, outperforming naive generative models trained on in-domain data by 15%.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.22954.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jenny Zhang, Shengran Hu, Cong Lu, Robert Lange, Jeff Clune</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Today's AI systems have human-designed, fixed architectures and cannot autonomously and continuously improve themselves. The advance of AI could itself be automated. If done safely, that would accelerate AI development and allow us to reap its benefits much sooner. Meta-learning can automate the discovery of novel algorithms, but is limited by first-order improvements and the human design of a suitable search space. The G\"odel machine proposed a theoretical alternative: a self-improving AI that repeatedly modifies itself in a provably beneficial manner. Unfortunately, proving that most changes are net beneficial is impossible in practice. We introduce the Darwin G\"odel Machine (DGM), a self-improving system that iteratively modifies its own code (thereby also improving its ability to modify its own codebase) and empirically validates each change using coding benchmarks. Inspired by Darwinian evolution and open-endedness research, the DGM maintains an archive of generated coding agents. It grows the archive by sampling an agent from it and using a foundation model to create a new, interesting, version of the sampled agent. This open-ended exploration forms a growing tree of diverse, high-quality agents and allows the parallel exploration of many different paths through the search space. Empirically, the DGM automatically improves its coding capabilities (e.g., better code editing tools, long-context window management, peer-review mechanisms), increasing performance on SWE-bench from 20.0% to 50.0%, and on Polyglot from 14.2% to 30.7%. Furthermore, the DGM significantly outperforms baselines without self-improvement or open-ended exploration. All experiments were done with safety precautions (e.g., sandboxing, human oversight). The DGM is a significant step toward self-improving AI, capable of gathering its own stepping stones along paths that unfold into endless innovation.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.23832</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2505.22954</guid>
|
||||||
<pubDate>Wed, 28 May 2025 09:02:41 +0000</pubDate>
|
<pubDate>Thu, 29 May 2025 00:26:15 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation</title>
|
<title>DyePack: Provably Flagging Test Set Contamination in LLMs Using Backdoors</title>
|
||||||
<link>https://arxiv.org/abs/2505.23844</link>
|
<link>https://arxiv.org/abs/2505.23001</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.23844.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhenglun Kong, Zheng Zhan, Shiyue Hou, Yifan Gong, Xin Meng, Pengwei Sui, Peiyan Dong, Xuan Shen, Zifeng Wang, Pu Zhao, Hao Tang, Stratis Ioannidis, Yanzhi Wang</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Large language models (LLMs) have shown remarkable promise but remain challenging to continually improve through traditional finetuning, particularly when integrating capabilities from other specialized LLMs. Popular methods like ensemble and weight merging require substantial memory and struggle to adapt to changing data environments. Recent efforts have transferred knowledge from multiple LLMs into a single target model; however, they suffer from interference and degraded performance among tasks, largely due to limited flexibility in candidate selection and training pipelines. To address these issues, we propose a framework that adaptively selects and aggregates knowledge from diverse LLMs to build a single, stronger model, avoiding the high memory overhead of ensemble and inflexible weight merging. Specifically, we design an adaptive selection network that identifies the most relevant source LLMs based on their scores, thereby reducing knowledge interference. We further propose a dynamic weighted fusion strategy that accounts for the inherent strengths of candidate LLMs, along with a feedback-driven loss function that prevents the selector from converging on a single subset of sources. Experimental results demonstrate that our method can enable a more stable and scalable knowledge aggregation process while reducing knowledge interference by up to 50% compared to existing approaches. Code is avaliable at https://github.com/ZLKong/LLM_Integration</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.23001.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yize Cheng, Wenxiao Wang, Mazda Moayeri, Soheil Feizi</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Open benchmarks are essential for evaluating and advancing large language models, offering reproducibility and transparency. However, their accessibility makes them likely targets of test set contamination. In this work, we introduce DyePack, a framework that leverages backdoor attacks to identify models that used benchmark test sets during training, without requiring access to the loss, logits, or any internal details of the model. Like how banks mix dye packs with their money to mark robbers, DyePack mixes backdoor samples with the test data to flag models that trained on it. We propose a principled design incorporating multiple backdoors with stochastic targets, enabling exact false positive rate (FPR) computation when flagging every model. This provably prevents false accusations while providing strong evidence for every detected case of contamination. We evaluate DyePack on five models across three datasets, covering both multiple-choice and open-ended generation tasks. For multiple-choice questions, it successfully detects all contaminated models with guaranteed FPRs as low as 0.000073% on MMLU-Pro and 0.000017% on Big-Bench-Hard using eight backdoors. For open-ended generation tasks, it generalizes well and identifies all contaminated models on Alpaca with a guaranteed false positive rate of just 0.127% using six backdoors.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.23844</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2505.23001</guid>
|
||||||
<pubDate>Wed, 28 May 2025 16:24:50 +0000</pubDate>
|
<pubDate>Thu, 29 May 2025 02:22:14 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>EmergentTTS-Eval: Evaluating TTS Models on Complex Prosodic, Expressiveness, and Linguistic Challenges Using Model-as-a-Judge</title>
|
<title>From Token to Action: State Machine Reasoning to Mitigate Overthinking in Information Retrieval</title>
|
||||||
<link>https://arxiv.org/abs/2505.23009</link>
|
<link>https://arxiv.org/abs/2505.23059</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.23009.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ruskin Raj Manku, Yuzhi Tang, Xingjian Shi, Mu Li, Alex Smola</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Text-to-Speech (TTS) benchmarks often fail to capture how well models handle nuanced and semantically complex text. Building on EmergentTTS, we introduce EmergentTTS-Eval, a comprehensive benchmark covering six challenging TTS scenarios: emotions, paralinguistics, foreign words, syntactic complexity, complex pronunciation (e.g. URLs, formulas), and questions. Crucially, our framework automates both test-case generation and evaluation, making the benchmark easily extensible. Starting from a small set of human-written seed prompts, we iteratively extend them using LLMs to target specific structural, phonetic and prosodic challenges, resulting in 1,645 diverse test cases. Moreover, we employ a model-as-a-judge approach, using a Large Audio Language Model (LALM) to assess the speech across multiple dimensions such as expressed emotion, prosodic, intonational, and pronunciation accuracy. We evaluate state-of-the-art open-source and proprietary TTS systems, such as 11Labs, Deepgram, and OpenAI's 4o-mini-TTS, on EmergentTTS-Eval, demonstrating its ability to reveal fine-grained performance differences. Results show that the model-as-a-judge approach offers robust TTS assessment and a high correlation with human preferences. We open source the evaluation https://github.com/boson-ai/EmergentTTS-Eval-public{code} and the https://huggingface.co/datasets/bosonai/EmergentTTS-Eval{dataset}.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.23059.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dohyeon Lee, Yeonseok Jeong, Seung-won Hwang</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Chain-of-Thought (CoT) prompting enables complex reasoning in large language models (LLMs), including applications in information retrieval (IR). However, it often leads to overthinking, where models produce excessively long and semantically redundant traces with little or no benefit. We identify two key challenges in IR: redundant trajectories that revisit similar states and misguided reasoning that diverges from user intent. To address these, we propose State Machine Reasoning (SMR), a transition-based reasoning framework composed of discrete actions (Refine, Rerank, Stop) that support early stopping and fine-grained control. Experiments on the BEIR and BRIGHT benchmarks show that SMR improves retrieval performance (nDCG@10) by 3.4% while reducing token usage by 74.4%. It generalizes across LLMs and retrievers without requiring task-specific tuning, offering a practical alternative to conventional CoT reasoning. The code and details are available at https://github.com/ldilab/SMR.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.23009</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2505.23059</guid>
|
||||||
<pubDate>Thu, 29 May 2025 02:36:24 +0000</pubDate>
|
<pubDate>Thu, 29 May 2025 04:04:25 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>OMNIGUARD: An Efficient Approach for AI Safety Moderation Across Modalities</title>
|
<title>VAU-R1: Advancing Video Anomaly Understanding via Reinforcement Fine-Tuning</title>
|
||||||
<link>https://arxiv.org/abs/2505.23856</link>
|
<link>https://arxiv.org/abs/2505.23504</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.23856.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sahil Verma, Keegan Hines, Jeff Bilmes, Charlotte Siska, Luke Zettlemoyer, Hila Gonen, Chandan Singh</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> The emerging capabilities of large language models (LLMs) have sparked concerns about their immediate potential for harmful misuse. The core approach to mitigate these concerns is the detection of harmful queries to the model. Current detection approaches are fallible, and are particularly susceptible to attacks that exploit mismatched generalization of model capabilities (e.g., prompts in low-resource languages or prompts provided in non-text modalities such as image and audio). To tackle this challenge, we propose OMNIGUARD, an approach for detecting harmful prompts across languages and modalities. Our approach (i) identifies internal representations of an LLM/MLLM that are aligned across languages or modalities and then (ii) uses them to build a language-agnostic or modality-agnostic classifier for detecting harmful prompts. OMNIGUARD improves harmful prompt classification accuracy by 11.57\% over the strongest baseline in a multilingual setting, by 20.44\% for image-based prompts, and sets a new SOTA for audio-based prompts. By repurposing embeddings computed during generation, OMNIGUARD is also very efficient (approx 120 times faster than the next fastest baseline). Code and data are available at: https://github.com/vsahil/OmniGuard.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.23504.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Liyun Zhu, Qixiang Chen, Xi Shen, Xiaodong Cun</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Video Anomaly Understanding (VAU) is essential for applications such as smart cities, security surveillance, and disaster alert systems, yet remains challenging due to its demand for fine-grained spatio-temporal perception and robust reasoning under ambiguity. Despite advances in anomaly detection, existing methods often lack interpretability and struggle to capture the causal and contextual aspects of abnormal events. This limitation is further compounded by the absence of comprehensive benchmarks for evaluating reasoning ability in anomaly scenarios. To address both challenges, we introduce VAU-R1, a data-efficient framework built upon Multimodal Large Language Models (MLLMs), which enhances anomaly reasoning through Reinforcement Fine-Tuning (RFT). Besides, we propose VAU-Bench, the first Chain-of-Thought benchmark tailored for video anomaly reasoning, featuring multiple-choice QA, detailed rationales, temporal annotations, and descriptive captions. Empirical results show that VAU-R1 significantly improves question answering accuracy, temporal grounding, and reasoning coherence across diverse contexts. Together, our method and benchmark establish a strong foundation for interpretable and reasoning-aware video anomaly understanding. Our code is available at https://github.com/GVCLab/VAU-R1.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.23856</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2505.23504</guid>
|
||||||
<pubDate>Thu, 29 May 2025 05:25:27 +0000</pubDate>
|
<pubDate>Thu, 29 May 2025 14:48:10 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>ChARM: Character-based Act-adaptive Reward Modeling for Advanced Role-Playing Language Agents</title>
|
<title>Jigsaw-R1: A Study of Rule-based Visual Reinforcement Learning with Jigsaw Puzzles</title>
|
||||||
<link>https://arxiv.org/abs/2505.23923</link>
|
<link>https://arxiv.org/abs/2505.23590</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.23923.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Feiteng Fang, Ting-En Lin, Yuchuan Wu, Xiong Liu, Xiang Huang, Dingwei Chen, Jing Ye, Haonan Zhang, Liang Zhu, Hamid Alinejad-Rokny, Min Yang, Fei Huang, Yongbin Li</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Role-Playing Language Agents (RPLAs) aim to simulate characters for realistic and engaging human-computer interactions. However, traditional reward models often struggle with scalability and adapting to subjective conversational preferences. We propose ChARM, a Character-based Act-adaptive Reward Model, addressing these challenges through two innovations: (1) an act-adaptive margin that significantly enhances learning efficiency and generalizability, and (2) a self-evolution mechanism leveraging large-scale unlabeled data to improve training coverage. Additionally, we introduce RoleplayPref, the first large-scale preference dataset specifically for RPLAs, featuring 1,108 characters, 13 subcategories, and 16,888 bilingual dialogues, alongside RoleplayEval, a dedicated evaluation benchmark. Experimental results show a 13% improvement over the conventional Bradley-Terry model in preference rankings. Furthermore, applying ChARM-generated rewards to preference learning techniques (e.g., direct preference optimization) achieves state-of-the-art results on CharacterEval and RoleplayEval. Code and dataset are available at https://github.com/calubkk/ChARM.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.23590.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zifu Wang, Junyi Zhu, Bo Tang, Zhiyu Li, Feiyu Xiong, Jiaqian Yu, Matthew B. Blaschko</p><p><b>Upvotes:</b> 24</p><p><b>Summary:</b> The application of rule-based reinforcement learning (RL) to multimodal large language models (MLLMs) introduces unique challenges and potential deviations from findings in text-only domains, particularly for perception-heavy tasks. This paper provides a comprehensive study of rule-based visual RL, using jigsaw puzzles as a structured experimental framework. Jigsaw puzzles offer inherent ground truth, adjustable difficulty, and demand complex decision-making, making them ideal for this study. Our research reveals several key findings: Firstly, we find that MLLMs, initially performing near to random guessing on the simplest jigsaw puzzles, achieve near-perfect accuracy and generalize to complex, unseen configurations through fine-tuning. Secondly, training on jigsaw puzzles can induce generalization to other visual tasks, with effectiveness tied to specific task configurations. Thirdly, MLLMs can learn and generalize with or without explicit reasoning, though open-source models often favor direct answering. Consequently, even when trained for step-by-step reasoning, they can ignore the thinking process in deriving the final answer. Fourthly, we observe that complex reasoning patterns appear to be pre-existing rather than emergent, with their frequency increasing alongside training and task difficulty. Finally, our results demonstrate that RL exhibits more effective generalization than Supervised Fine-Tuning (SFT), and an initial SFT cold start phase can hinder subsequent RL optimization. Although these observations are based on jigsaw puzzles and may vary across other visual tasks, this research contributes a valuable piece of jigsaw to the larger puzzle of collective understanding rule-based visual RL and its potential in multimodal learning. The code is available at: https://github.com/zifuwanggg/Jigsaw-R1.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.23923</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2505.23590</guid>
|
||||||
<pubDate>Thu, 29 May 2025 18:15:18 +0000</pubDate>
|
<pubDate>Thu, 29 May 2025 16:01:22 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Point-MoE: Towards Cross-Domain Generalization in 3D Semantic Segmentation via Mixture-of-Experts</title>
|
<title>Cora: Correspondence-aware image editing using few step diffusion</title>
|
||||||
<link>https://arxiv.org/abs/2505.23926</link>
|
<link>https://arxiv.org/abs/2505.23907</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.23926.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xuweiyi Chen, Wentao Zhou, Aruni RoyChowdhury, Zezhou Cheng</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> While scaling laws have transformed natural language processing and computer vision, 3D point cloud understanding has yet to reach that stage. This can be attributed to both the comparatively smaller scale of 3D datasets, as well as the disparate sources of the data itself. Point clouds are captured by diverse sensors (e.g., depth cameras, LiDAR) across varied domains (e.g., indoor, outdoor), each introducing unique scanning patterns, sampling densities, and semantic biases. Such domain heterogeneity poses a major barrier towards training unified models at scale, especially under the realistic constraint that domain labels are typically inaccessible at inference time. In this work, we propose Point-MoE, a Mixture-of-Experts architecture designed to enable large-scale, cross-domain generalization in 3D perception. We show that standard point cloud backbones degrade significantly in performance when trained on mixed-domain data, whereas Point-MoE with a simple top-k routing strategy can automatically specialize experts, even without access to domain labels. Our experiments demonstrate that Point-MoE not only outperforms strong multi-domain baselines but also generalizes better to unseen domains. This work highlights a scalable path forward for 3D understanding: letting the model discover structure in diverse 3D data, rather than imposing it via manual curation or domain supervision.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.23907.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Amirhossein Almohammadi, Aryan Mikaeili, Sauradip Nag, Negar Hassanpour, Andrea Tagliasacchi, Ali Mahdavi-Amiri</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Image editing is an important task in computer graphics, vision, and VFX, with recent diffusion-based methods achieving fast and high-quality results. However, edits requiring significant structural changes, such as non-rigid deformations, object modifications, or content generation, remain challenging. Existing few step editing approaches produce artifacts such as irrelevant texture or struggle to preserve key attributes of the source image (e.g., pose). We introduce Cora, a novel editing framework that addresses these limitations by introducing correspondence-aware noise correction and interpolated attention maps. Our method aligns textures and structures between the source and target images through semantic correspondence, enabling accurate texture transfer while generating new content when necessary. Cora offers control over the balance between content generation and preservation. Extensive experiments demonstrate that, quantitatively and qualitatively, Cora excels in maintaining structure, textures, and identity across diverse edits, including pose changes, object addition, and texture refinements. User studies confirm that Cora delivers superior results, outperforming alternatives.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.23926</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2505.23907</guid>
|
||||||
<pubDate>Thu, 29 May 2025 18:21:47 +0000</pubDate>
|
<pubDate>Thu, 29 May 2025 18:00:56 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Vision Language Models are Biased</title>
|
<title>VisualSphinx: Large-Scale Synthetic Vision Logic Puzzles for RL</title>
|
||||||
<link>https://arxiv.org/abs/2505.23941</link>
|
<link>https://arxiv.org/abs/2505.23977</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.23941.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> An Vo, Khai-Nguyen Nguyen, Mohammad Reza Taesiri, Vy Tuong Dang, Anh Totti Nguyen, Daeyoung Kim</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> Large language models (LLMs) memorize a vast amount of prior knowledge from the Internet that help them on downstream tasks but also may notoriously sway their outputs towards wrong or biased answers. In this work, we test how the knowledge about popular subjects hurt the accuracy of vision language models (VLMs) on standard, objective visual tasks of counting and identification. We find that state-of-the-art VLMs are strongly biased (e.g, unable to recognize a fourth stripe has been added to a 3-stripe Adidas logo) scoring an average of 17.05% accuracy in counting (e.g., counting stripes in an Adidas-like logo) across 7 diverse domains from animals, logos, chess, board games, optical illusions, to patterned grids. Insert text (e.g., "Adidas") describing the subject name into the counterfactual image further decreases VLM accuracy. The biases in VLMs are so strong that instructing them to double-check their results or rely exclusively on image details to answer improves counting accuracy by only +2 points, on average. Our work presents an interesting failure mode in VLMs and an automated framework for testing VLM biases. Code and data are available at: vlmsarebiased.github.io.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.23977.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yichen Feng, Zhangchen Xu, Fengqing Jiang, Yuetai Li, Bhaskar Ramasubramanian, Luyao Niu, Bill Yuchen Lin, Radha Poovendran</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Vision language models (VLMs) are expected to perform effective multimodal reasoning and make logically coherent decisions, which is critical to tasks such as diagram understanding and spatial problem solving. However, current VLM reasoning lacks large-scale and well-structured training datasets. To bridge this gap, we propose VisualSphinx, a first-of-its-kind large-scale synthetic visual logical reasoning training data. To tackle the challenge of image synthesis with grounding answers, we propose a rule-to-image synthesis pipeline, which extracts and expands puzzle rules from seed questions and generates the code of grounding synthesis image synthesis for puzzle sample assembly. Experiments demonstrate that VLM trained using GRPO on VisualSphinx benefit from logical coherence and readability of our dataset and exhibit improved performance on logical reasoning tasks. The enhanced reasoning capabilities developed from VisualSphinx also benefit other reasoning tasks such as algebraic reasoning, arithmetic reasoning and geometry reasoning.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.23941</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2505.23977</guid>
|
||||||
<pubDate>Thu, 29 May 2025 18:47:58 +0000</pubDate>
|
<pubDate>Thu, 29 May 2025 20:08:36 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>DINO-R1: Incentivizing Reasoning Capability in Vision Foundation Models</title>
|
<title>ComposeAnything: Composite Object Priors for Text-to-Image Generation</title>
|
||||||
<link>https://arxiv.org/abs/2505.24025</link>
|
<link>https://arxiv.org/abs/2505.24086</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.24025.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chenbin Pan, Wenbin He, Zhengzhong Tu, Liu Ren</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> The recent explosive interest in the reasoning capabilities of large language models, such as DeepSeek-R1, has demonstrated remarkable success through reinforcement learning-based fine-tuning frameworks, exemplified by methods like Group Relative Policy Optimization (GRPO). However, such reasoning abilities remain underexplored and notably absent in vision foundation models, including representation models like the DINO series. In this work, we propose DINO-R1, the first such attempt to incentivize visual in-context reasoning capabilities of vision foundation models using reinforcement learning. Specifically, DINO-R1 introduces Group Relative Query Optimization (GRQO), a novel reinforcement-style training strategy explicitly designed for query-based representation models, which computes query-level rewards based on group-normalized alignment quality. We also apply KL-regularization to stabilize the objectness distribution to reduce the training instability. This joint optimization enables dense and expressive supervision across queries while mitigating overfitting and distributional drift. Building upon Grounding-DINO, we train a series of DINO-R1 family models that integrate a visual prompt encoder and a visual-guided query selection mechanism. Extensive experiments on COCO, LVIS, and ODinW demonstrate that DINO-R1 significantly outperforms supervised fine-tuning baselines, achieving strong generalization in both open-vocabulary and closed-set visual prompting scenarios.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.24086.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zeeshan Khan, Shizhe Chen, Cordelia Schmid</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Generating images from text involving complex and novel object arrangements remains a significant challenge for current text-to-image (T2I) models. Although prior layout-based methods improve object arrangements using spatial constraints with 2D layouts, they often struggle to capture 3D positioning and sacrifice quality and coherence. In this work, we introduce ComposeAnything, a novel framework for improving compositional image generation without retraining existing T2I models. Our approach first leverages the chain-of-thought reasoning abilities of LLMs to produce 2.5D semantic layouts from text, consisting of 2D object bounding boxes enriched with depth information and detailed captions. Based on this layout, we generate a spatial and depth aware coarse composite of objects that captures the intended composition, serving as a strong and interpretable prior that replaces stochastic noise initialization in diffusion-based T2I models. This prior guides the denoising process through object prior reinforcement and spatial-controlled denoising, enabling seamless generation of compositional objects and coherent backgrounds, while allowing refinement of inaccurate priors. ComposeAnything outperforms state-of-the-art methods on the T2I-CompBench and NSR-1K benchmarks for prompts with 2D/3D spatial arrangements, high object counts, and surreal compositions. Human evaluations further demonstrate that our model generates high-quality images with compositions that faithfully reflect the text.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.24025</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2505.24086</guid>
|
||||||
<pubDate>Thu, 29 May 2025 21:58:06 +0000</pubDate>
|
<pubDate>Fri, 30 May 2025 00:13:36 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>HardTests: Synthesizing High-Quality Test Cases for LLM Coding</title>
|
<title>CodeV-R1: Reasoning-Enhanced Verilog Generation</title>
|
||||||
<link>https://arxiv.org/abs/2505.24098</link>
|
<link>https://arxiv.org/abs/2505.24183</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.24098.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhongmou He, Yee Man Choi, Kexun Zhang, Jiabao Ji, Junting Zhou, Dejia Xu, Ivan Bercovich, Aidan Zhang, Lei Li</p><p><b>Upvotes:</b> 35</p><p><b>Summary:</b> Verifiers play a crucial role in large language model (LLM) reasoning, needed by post-training techniques such as reinforcement learning. However, reliable verifiers are hard to get for difficult coding problems, because a well-disguised wrong solution may only be detected by carefully human-written edge cases that are difficult to synthesize. To address this issue, we propose HARDTESTGEN, a pipeline for high-quality test synthesis using LLMs. With this pipeline, we curate a comprehensive competitive programming dataset HARDTESTS with 47k problems and synthetic high-quality tests. Compared with existing tests, HARDTESTGEN tests demonstrate precision that is 11.3 percentage points higher and recall that is 17.5 percentage points higher when evaluating LLM-generated code. For harder problems, the improvement in precision can be as large as 40 points. HARDTESTS also proves to be more effective for model training, measured by downstream code generation performance. We will open-source our dataset and synthesis pipeline at https://leililab.github.io/HardTests/.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.24183.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yaoyu Zhu, Di Huang, Hanqi Lyu, Xiaoyun Zhang, Chongxiao Li, Wenxuan Shi, Yutong Wu, Jianan Mu, Jinghua Wang, Yang Zhao, Pengwei Jin, Shuyao Cheng, Shengwen Liang, Xishan Zhang, Rui Zhang, Zidong Du, Qi Guo, Xing Hu, Yunji Chen</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Large language models (LLMs) trained via reinforcement learning with verifiable reward (RLVR) have achieved breakthroughs on tasks with explicit, automatable verification, such as software programming and mathematical problems. Extending RLVR to electronic design automation (EDA), especially automatically generating hardware description languages (HDLs) like Verilog from natural-language (NL) specifications, however, poses three key challenges: the lack of automated and accurate verification environments, the scarcity of high-quality NL-code pairs, and the prohibitive computation cost of RLVR. To this end, we introduce CodeV-R1, an RLVR framework for training Verilog generation LLMs. First, we develop a rule-based testbench generator that performs robust equivalence checking against golden references. Second, we propose a round-trip data synthesis method that pairs open-source Verilog snippets with LLM-generated NL descriptions, verifies code-NL-code consistency via the generated testbench, and filters out inequivalent examples to yield a high-quality dataset. Third, we employ a two-stage "distill-then-RL" training pipeline: distillation for the cold start of reasoning abilities, followed by adaptive DAPO, our novel RLVR algorithm that can reduce training cost by adaptively adjusting sampling rate. The resulting model, CodeV-R1-7B, achieves 68.6% and 72.9% pass@1 on VerilogEval v2 and RTLLM v1.1, respectively, surpassing prior state-of-the-art by 12~20%, while matching or even exceeding the performance of 671B DeepSeek-R1. We will release our model, training pipeline, and dataset to facilitate research in EDA and LLM communities.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.24098</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2505.24183</guid>
|
||||||
<pubDate>Fri, 30 May 2025 01:00:34 +0000</pubDate>
|
<pubDate>Fri, 30 May 2025 03:51:06 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>The State of Multilingual LLM Safety Research: From Measuring the Language Gap to Mitigating It</title>
|
<title>Shuffle PatchMix Augmentation with Confidence-Margin Weighted Pseudo-Labels for Enhanced Source-Free Domain Adaptation</title>
|
||||||
<link>https://arxiv.org/abs/2505.24119</link>
|
<link>https://arxiv.org/abs/2505.24216</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.24119.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zheng-Xin Yong, Beyza Ermis, Marzieh Fadaee, Stephen H. Bach, Julia Kreutzer</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> This paper presents a comprehensive analysis of the linguistic diversity of LLM safety research, highlighting the English-centric nature of the field. Through a systematic review of nearly 300 publications from 2020--2024 across major NLP conferences and workshops at *ACL, we identify a significant and growing language gap in LLM safety research, with even high-resource non-English languages receiving minimal attention. We further observe that non-English languages are rarely studied as a standalone language and that English safety research exhibits poor language documentation practice. To motivate future research into multilingual safety, we make several recommendations based on our survey, and we then pose three concrete future directions on safety evaluation, training data generation, and crosslingual safety generalization. Based on our survey and proposed directions, the field can develop more robust, inclusive AI safety practices for diverse global populations.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.24216.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Prasanna Reddy Pulakurthi, Majid Rabbani, Jamison Heard, Sohail Dianat, Celso M. de Melo, Raghuveer Rao</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> This work investigates Source-Free Domain Adaptation (SFDA), where a model adapts to a target domain without access to source data. A new augmentation technique, Shuffle PatchMix (SPM), and a novel reweighting strategy are introduced to enhance performance. SPM shuffles and blends image patches to generate diverse and challenging augmentations, while the reweighting strategy prioritizes reliable pseudo-labels to mitigate label noise. These techniques are particularly effective on smaller datasets like PACS, where overfitting and pseudo-label noise pose greater risks. State-of-the-art results are achieved on three major benchmarks: PACS, VisDA-C, and DomainNet-126. Notably, on PACS, improvements of 7.3% (79.4% to 86.7%) and 7.2% are observed in single-target and multi-target settings, respectively, while gains of 2.8% and 0.7% are attained on DomainNet-126 and VisDA-C. This combination of advanced augmentation and robust pseudo-label reweighting establishes a new benchmark for SFDA. The code is available at: https://github.com/PrasannaPulakurthi/SPM</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.24119</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2505.24216</guid>
|
||||||
<pubDate>Fri, 30 May 2025 01:32:44 +0000</pubDate>
|
<pubDate>Fri, 30 May 2025 05:02:42 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Fine-Tune an SLM or Prompt an LLM? The Case of Generating Low-Code Workflows</title>
|
<title>AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning</title>
|
||||||
<link>https://arxiv.org/abs/2505.24189</link>
|
<link>https://arxiv.org/abs/2505.24298</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.24189.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Orlando Marquez Ayala, Patrice Bechard, Emily Chen, Maggie Baird, Jingfei Chen</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Large Language Models (LLMs) such as GPT-4o can handle a wide range of complex tasks with the right prompt. As per token costs are reduced, the advantages of fine-tuning Small Language Models (SLMs) for real-world applications -- faster inference, lower costs -- may no longer be clear. In this work, we present evidence that, for domain-specific tasks that require structured outputs, SLMs still have a quality advantage. We compare fine-tuning an SLM against prompting LLMs on the task of generating low-code workflows in JSON form. We observe that while a good prompt can yield reasonable results, fine-tuning improves quality by 10% on average. We also perform systematic error analysis to reveal model limitations.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.24298.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wei Fu, Jiaxuan Gao, Xujie Shen, Chen Zhu, Zhiyu Mei, Chuyi He, Shusheng Xu, Guo Wei, Jun Mei, Jiashu Wang, Tongkai Yang, Binhang Yuan, Yi Wu</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> Reinforcement learning (RL) has become a trending paradigm for training large language models (LLMs), particularly for reasoning tasks. Effective RL for LLMs requires massive parallelization and poses an urgent need for efficient training systems. Most existing large-scale RL systems for LLMs are synchronous by alternating generation and training in a batch setting, where the rollouts in each training batch are generated by the same (or latest) model. This stabilizes RL training but suffers from severe system-level inefficiency. Generation must wait until the longest output in the batch is completed before model update, resulting in GPU underutilization. We present AReaL, a fully asynchronous RL system that completely decouples generation from training. Rollout workers in AReaL continuously generate new outputs without waiting, while training workers update the model whenever a batch of data is collected. AReaL also incorporates a collection of system-level optimizations, leading to substantially higher GPU utilization. To stabilize RL training, AReaL balances the workload of rollout and training workers to control data staleness, and adopts a staleness-enhanced PPO variant to better handle outdated training samples. Extensive experiments on math and code reasoning benchmarks show that AReaL achieves up to 2.57times training speedup compared to the best synchronous systems with the same number of GPUs and matched or even improved final performance. The code of AReaL is available at https://github.com/inclusionAI/AReaL/.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.24189</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2505.24298</guid>
|
||||||
<pubDate>Fri, 30 May 2025 03:59:35 +0000</pubDate>
|
<pubDate>Fri, 30 May 2025 07:18:25 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>CLaSp: In-Context Layer Skip for Self-Speculative Decoding</title>
|
<title>Stepsize anything: A unified learning rate schedule for budgeted-iteration training</title>
|
||||||
<link>https://arxiv.org/abs/2505.24196</link>
|
<link>https://arxiv.org/abs/2505.24452</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.24196.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Longze Chen, Renke Shan, Huiming Wang, Lu Wang, Ziqiang Liu, Run Luo, Jiawei Wang, Hamid Alinejad-Rokny, Min Yang</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Speculative decoding (SD) is a promising method for accelerating the decoding process of Large Language Models (LLMs). The efficiency of SD primarily hinges on the consistency between the draft model and the verify model. However, existing drafting approaches typically require additional modules to be trained, which can be challenging to implement and ensure compatibility across various LLMs. In this paper, we propose CLaSp, an in-context layer-skipping strategy for self-speculative decoding. Unlike prior methods, CLaSp does not require additional drafting modules or extra training. Instead, it employs a plug-and-play mechanism by skipping intermediate layers of the verify model to construct a compressed draft model. Specifically, we develop a dynamic programming algorithm that optimizes the layer-skipping process by leveraging the complete hidden states from the last verification stage as an objective. This enables CLaSp to dynamically adjust its layer-skipping strategy after each verification stage, without relying on pre-optimized sets of skipped layers. Experimental results across diverse downstream tasks demonstrate that CLaSp achieves a speedup of 1.3x ~ 1.7x on LLaMA3 series models without altering the original distribution of the generated text.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.24452.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Anda Tang, Yiming Dong, Yutao Zeng, zhou Xun, Zhouchen Lin</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> The expanding computational costs and limited resources underscore the critical need for budgeted-iteration training, which aims to achieve optimal learning within predetermined iteration budgets.While learning rate schedules fundamentally govern the performance of different networks and tasks, particularly in budgeted-iteration scenarios, their design remains largely heuristic, lacking theoretical foundations.In addition, the optimal learning rate schedule requires extensive trial-and-error selection, making the training process inefficient.In this work, we propose the Unified Budget-Aware (UBA) schedule, a theoretically grounded learning rate schedule that consistently outperforms commonly-used schedules among diverse architectures and tasks under different constrained training budgets.First, we bridge the gap by constructing a novel training budget-aware optimization framework, which explicitly accounts for the robustness to landscape curvature variations.From this framework, we derive the UBA schedule, controlled by a single hyper-parameter varphi that provides a trade-off between flexibility and simplicity, eliminating the need for per-network numerical optimization. Moreover, we establish a theoretical connection between varphi and the condition number, adding interpretation and justification to our approach. Besides, we prove the convergence for different values of varphi.We offer practical guidelines for its selection via theoretical analysis and empirical results.xtensive experimental results show that UBA consistently surpasses the commonly-used schedules across diverse vision and language tasks, spanning network architectures (e.g., ResNet, OLMo) and scales, under different training-iteration budgets.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.24196</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2505.24452</guid>
|
||||||
<pubDate>Fri, 30 May 2025 04:15:06 +0000</pubDate>
|
<pubDate>Fri, 30 May 2025 10:38:03 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Large Language Models are Locally Linear Mappings</title>
|
<title>Stress-testing Machine Generated Text Detection: Shifting Language Models Writing Style to Fool Detectors</title>
|
||||||
<link>https://arxiv.org/abs/2505.24293</link>
|
<link>https://arxiv.org/abs/2505.24523</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.24293.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> James R. Golden</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> We demonstrate that the inference operations of several open-weight large language models (LLMs) can be mapped to an exactly equivalent linear system for an input sequence without modifying the model weights or altering output predictions. Extending techniques from image diffusion models that exhibit local or piecewise linearity, we strategically alter the gradient computation with respect to a given input sequence for a next-token prediction such that the Jacobian of the model nearly exactly reproduces the forward prediction with a linear system. We demonstrate this approach across models (Llama 3, Gemma 3, Qwen 3, Phi 4, Mistral Ministral and OLMo 2, up to Llama 3.3 70B Q4) and show through the singular value decomposition of the detached Jacobian that these LLMs operate in extremely low-dimensional subspaces where many of the largest singular vectors decode to concepts related to the most-likely output token. This approach also allows us to examine the operation of each successive layer (and its attention and MLP components) as nearly-exact linear systems and observe the emergence of semantic concepts. Despite their expressive power and global nonlinearity, modern LLMs can be interpreted through nearly-exact locally linear decompositions that provide insights into their internal representations and reveal interpretable semantic structures in the next-token prediction process.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.24523.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Andrea Pedrotti, Michele Papucci, Cristiano Ciaccio, Alessio Miaschi, Giovanni Puccetti, Felice Dell'Orletta, Andrea Esuli</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Recent advancements in Generative AI and Large Language Models (LLMs) have enabled the creation of highly realistic synthetic content, raising concerns about the potential for malicious use, such as misinformation and manipulation. Moreover, detecting Machine-Generated Text (MGT) remains challenging due to the lack of robust benchmarks that assess generalization to real-world scenarios. In this work, we present a pipeline to test the resilience of state-of-the-art MGT detectors (e.g., Mage, Radar, LLM-DetectAIve) to linguistically informed adversarial attacks. To challenge the detectors, we fine-tune language models using Direct Preference Optimization (DPO) to shift the MGT style toward human-written text (HWT). This exploits the detectors' reliance on stylistic clues, making new generations more challenging to detect. Additionally, we analyze the linguistic shifts induced by the alignment and which features are used by detectors to detect MGT texts. Our results show that detectors can be easily fooled with relatively few examples, resulting in a significant drop in detection performance. This highlights the importance of improving detection methods and making them robust to unseen in-domain texts.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.24293</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2505.24523</guid>
|
||||||
<pubDate>Fri, 30 May 2025 07:08:33 +0000</pubDate>
|
<pubDate>Fri, 30 May 2025 12:33:30 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>EasyText: Controllable Diffusion Transformer for Multilingual Text Rendering</title>
|
<title>Learning from Videos for 3D World: Enhancing MLLMs with 3D Vision Geometry Priors</title>
|
||||||
<link>https://arxiv.org/abs/2505.24417</link>
|
<link>https://arxiv.org/abs/2505.24625</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.24417.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Runnan Lu, Yuxuan Zhang, Jailing Liu, Haifa Wang, Yiren Song</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Generating accurate multilingual text with diffusion models has long been desired but remains challenging. Recent methods have made progress in rendering text in a single language, but rendering arbitrary languages is still an unexplored area. This paper introduces EasyText, a text rendering framework based on DiT (Diffusion Transformer), which connects denoising latents with multilingual character tokens encoded as character tokens. We propose character positioning encoding and position encoding interpolation techniques to achieve controllable and precise text rendering. Additionally, we construct a large-scale synthetic text image dataset with 1 million multilingual image-text annotations as well as a high-quality dataset of 20K annotated images, which are used for pretraining and fine-tuning respectively. Extensive experiments and evaluations demonstrate the effectiveness and advancement of our approach in multilingual text rendering, visual quality, and layout-aware text integration.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.24625.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Duo Zheng, Shijia Huang, Yanyang Li, Liwei Wang</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Previous research has investigated the application of Multimodal Large Language Models (MLLMs) in understanding 3D scenes by interpreting them as videos. These approaches generally depend on comprehensive 3D data inputs, such as point clouds or reconstructed Bird's-Eye View (BEV) maps. In our research, we advance this field by enhancing the capability of MLLMs to understand and reason in 3D spaces directly from video data, without the need for additional 3D input. We propose a novel and efficient method, the Video-3D Geometry Large Language Model (VG LLM). Our approach employs a 3D visual geometry encoder that extracts 3D prior information from video sequences. This information is integrated with visual tokens and fed into the MLLM. Extensive experiments have shown that our method has achieved substantial improvements in various tasks related to 3D scene understanding and spatial reasoning, all directly learned from video sources. Impressively, our 4B model, which does not rely on explicit 3D data inputs, achieves competitive results compared to existing state-of-the-art methods, and even surpasses the Gemini-1.5-Pro in the VSI-Bench evaluations.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.24417</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2505.24625</guid>
|
||||||
<pubDate>Fri, 30 May 2025 09:55:39 +0000</pubDate>
|
<pubDate>Fri, 30 May 2025 14:16:41 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>un^2CLIP: Improving CLIP's Visual Detail Capturing Ability via Inverting unCLIP</title>
|
<title>REASONING GYM: Reasoning Environments for Reinforcement Learning with Verifiable Rewards</title>
|
||||||
<link>https://arxiv.org/abs/2505.24517</link>
|
<link>https://arxiv.org/abs/2505.24760</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.24517.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yinqi Li, Jiahe Zhao, Hong Chang, Ruibing Hou, Shiguang Shan, Xilin Chen</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Contrastive Language-Image Pre-training (CLIP) has become a foundation model and has been applied to various vision and multimodal tasks. However, recent works indicate that CLIP falls short in distinguishing detailed differences in images and shows suboptimal performance on dense-prediction and vision-centric multimodal tasks. Therefore, this work focuses on improving existing CLIP models, aiming to capture as many visual details in images as possible. We find that a specific type of generative models, unCLIP, provides a suitable framework for achieving our goal. Specifically, unCLIP trains an image generator conditioned on the CLIP image embedding. In other words, it inverts the CLIP image encoder. Compared to discriminative models like CLIP, generative models are better at capturing image details because they are trained to learn the data distribution of images. Additionally, the conditional input space of unCLIP aligns with CLIP's original image-text embedding space. Therefore, we propose to invert unCLIP (dubbed un^2CLIP) to improve the CLIP model. In this way, the improved image encoder can gain unCLIP's visual detail capturing ability while preserving its alignment with the original text encoder simultaneously. We evaluate our improved CLIP across various tasks to which CLIP has been applied, including the challenging MMVP-VLM benchmark, the dense-prediction open-vocabulary segmentation task, and multimodal large language model tasks. Experiments show that un^2CLIP significantly improves the original CLIP and previous CLIP improvement methods. Code and models will be available at https://github.com/LiYinqi/un2CLIP.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.24760.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zafir Stojanovski, Oliver Stanley, Joe Sharratt, Richard Jones, Abdulhakeem Adefioye, Jean Kaddour, Andreas Köpf</p><p><b>Upvotes:</b> 47</p><p><b>Summary:</b> We introduce Reasoning Gym (RG), a library of reasoning environments for reinforcement learning with verifiable rewards. It provides over 100 data generators and verifiers spanning multiple domains including algebra, arithmetic, computation, cognition, geometry, graph theory, logic, and various common games. Its key innovation is the ability to generate virtually infinite training data with adjustable complexity, unlike most previous reasoning datasets, which are typically fixed. This procedural generation approach allows for continuous evaluation across varying difficulty levels. Our experimental results demonstrate the efficacy of RG in both evaluating and reinforcement learning of reasoning models.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.24517</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2505.24760</guid>
|
||||||
<pubDate>Fri, 30 May 2025 12:29:38 +0000</pubDate>
|
<pubDate>Fri, 30 May 2025 16:20:18 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>UniGeo: Taming Video Diffusion for Unified Consistent Geometry Estimation</title>
|
<title>Cascading Adversarial Bias from Injection to Distillation in Language Models</title>
|
||||||
<link>https://arxiv.org/abs/2505.24521</link>
|
<link>https://arxiv.org/abs/2505.24842</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.24521.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yang-Tian Sun, Xin Yu, Zehuan Huang, Yi-Hua Huang, Yuan-Chen Guo, Ziyi Yang, Yan-Pei Cao, Xiaojuan Qi</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Recently, methods leveraging diffusion model priors to assist monocular geometric estimation (e.g., depth and normal) have gained significant attention due to their strong generalization ability. However, most existing works focus on estimating geometric properties within the camera coordinate system of individual video frames, neglecting the inherent ability of diffusion models to determine inter-frame correspondence. In this work, we demonstrate that, through appropriate design and fine-tuning, the intrinsic consistency of video generation models can be effectively harnessed for consistent geometric estimation. Specifically, we 1) select geometric attributes in the global coordinate system that share the same correspondence with video frames as the prediction targets, 2) introduce a novel and efficient conditioning method by reusing positional encodings, and 3) enhance performance through joint training on multiple geometric attributes that share the same correspondence. Our results achieve superior performance in predicting global geometric attributes in videos and can be directly applied to reconstruction tasks. Even when trained solely on static video data, our approach exhibits the potential to generalize to dynamic video scenes.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.24842.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Harsh Chaudhari, Jamie Hayes, Matthew Jagielski, Ilia Shumailov, Milad Nasr, Alina Oprea</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Model distillation has become essential for creating smaller, deployable language models that retain larger system capabilities. However, widespread deployment raises concerns about resilience to adversarial manipulation. This paper investigates vulnerability of distilled models to adversarial injection of biased content during training. We demonstrate that adversaries can inject subtle biases into teacher models through minimal data poisoning, which propagates to student models and becomes significantly amplified. We propose two propagation modes: Untargeted Propagation, where bias affects multiple tasks, and Targeted Propagation, focusing on specific tasks while maintaining normal behavior elsewhere. With only 25 poisoned samples (0.25% poisoning rate), student models generate biased responses 76.9% of the time in targeted scenarios - higher than 69.4% in teacher models. For untargeted propagation, adversarial bias appears 6x-29x more frequently in student models on unseen tasks. We validate findings across six bias types (targeted advertisements, phishing links, narrative manipulations, insecure coding practices), various distillation methods, and different modalities spanning text and code generation. Our evaluation reveals shortcomings in current defenses - perplexity filtering, bias detection systems, and LLM-based autorater frameworks - against these attacks. Results expose significant security vulnerabilities in distilled models, highlighting need for specialized safeguards. We propose practical design principles for building effective adversarial bias mitigation strategies.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.24521</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2505.24842</guid>
|
||||||
<pubDate>Fri, 30 May 2025 12:31:59 +0000</pubDate>
|
<pubDate>Fri, 30 May 2025 17:41:58 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>GATE: General Arabic Text Embedding for Enhanced Semantic Textual Similarity with Matryoshka Representation Learning and Hybrid Loss Training</title>
|
<title>MiCRo: Mixture Modeling and Context-aware Routing for Personalized Preference Learning</title>
|
||||||
<link>https://arxiv.org/abs/2505.24581</link>
|
<link>https://arxiv.org/abs/2505.24846</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.24581.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Omer Nacar, Anis Koubaa, Serry Sibaee, Yasser Al-Habashi, Adel Ammar, Wadii Boulila</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Semantic textual similarity (STS) is a critical task in natural language processing (NLP), enabling applications in retrieval, clustering, and understanding semantic relationships between texts. However, research in this area for the Arabic language remains limited due to the lack of high-quality datasets and pre-trained models. This scarcity of resources has restricted the accurate evaluation and advance of semantic similarity in Arabic text. This paper introduces General Arabic Text Embedding (GATE) models that achieve state-of-the-art performance on the Semantic Textual Similarity task within the MTEB benchmark. GATE leverages Matryoshka Representation Learning and a hybrid loss training approach with Arabic triplet datasets for Natural Language Inference, which are essential for enhancing model performance in tasks that demand fine-grained semantic understanding. GATE outperforms larger models, including OpenAI, with a 20-25% performance improvement on STS benchmarks, effectively capturing the unique semantic nuances of Arabic.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.24846.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jingyan Shen, Jiarui Yao, Rui Yang, Yifan Sun, Feng Luo, Rui Pan, Tong Zhang, Han Zhao</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Reward modeling is a key step in building safe foundation models when applying reinforcement learning from human feedback (RLHF) to align Large Language Models (LLMs). However, reward modeling based on the Bradley-Terry (BT) model assumes a global reward function, failing to capture the inherently diverse and heterogeneous human preferences. Hence, such oversimplification limits LLMs from supporting personalization and pluralistic alignment. Theoretically, we show that when human preferences follow a mixture distribution of diverse subgroups, a single BT model has an irreducible error. While existing solutions, such as multi-objective learning with fine-grained annotations, help address this issue, they are costly and constrained by predefined attributes, failing to fully capture the richness of human values. In this work, we introduce MiCRo, a two-stage framework that enhances personalized preference learning by leveraging large-scale binary preference datasets without requiring explicit fine-grained annotations. In the first stage, MiCRo introduces context-aware mixture modeling approach to capture diverse human preferences. In the second stage, MiCRo integrates an online routing strategy that dynamically adapts mixture weights based on specific context to resolve ambiguity, allowing for efficient and scalable preference adaptation with minimal additional supervision. Experiments on multiple preference datasets demonstrate that MiCRo effectively captures diverse human preferences and significantly improves downstream personalization.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.24581</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2505.24846</guid>
|
||||||
<pubDate>Fri, 30 May 2025 13:29:03 +0000</pubDate>
|
<pubDate>Fri, 30 May 2025 17:44:28 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Harnessing Large Language Models for Scientific Novelty Detection</title>
|
<title>OWSM v4: Improving Open Whisper-Style Speech Models via Data Scaling and Cleaning</title>
|
||||||
<link>https://arxiv.org/abs/2505.24615</link>
|
<link>https://arxiv.org/abs/2506.00338</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.24615.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yan Liu, Zonglin Yang, Soujanya Poria, Thanh-Son Nguyen, Erik Cambria</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> In an era of exponential scientific growth, identifying novel research ideas is crucial and challenging in academia. Despite potential, the lack of an appropriate benchmark dataset hinders the research of novelty detection. More importantly, simply adopting existing NLP technologies, e.g., retrieving and then cross-checking, is not a one-size-fits-all solution due to the gap between textual similarity and idea conception. In this paper, we propose to harness large language models (LLMs) for scientific novelty detection (ND), associated with two new datasets in marketing and NLP domains. To construct the considerate datasets for ND, we propose to extract closure sets of papers based on their relationship, and then summarize their main ideas based on LLMs. To capture idea conception, we propose to train a lightweight retriever by distilling the idea-level knowledge from LLMs to align ideas with similar conception, enabling efficient and accurate idea retrieval for LLM novelty detection. Experiments show our method consistently outperforms others on the proposed benchmark datasets for idea retrieval and ND tasks. Codes and data are available at https://anonymous.4open.science/r/NoveltyDetection-10FB/.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.00338.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yifan Peng, Shakeel Muhammad, Yui Sudo, William Chen, Jinchuan Tian, Chyi-Jiunn Lin, Shinji Watanabe</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> The Open Whisper-style Speech Models (OWSM) project has developed a series of fully open speech foundation models using academic-scale resources, but their training data remains insufficient. This work enhances OWSM by integrating YODAS, a large-scale web-crawled dataset with a Creative Commons license. However, incorporating YODAS is nontrivial due to its wild nature, which introduces challenges such as incorrect language labels and audio-text misalignments. To address this, we develop a scalable data-cleaning pipeline using public toolkits, yielding a dataset with 166,000 hours of speech across 75 languages. Our new series of OWSM v4 models, trained on this curated dataset alongside existing OWSM data, significantly outperform previous versions on multilingual benchmarks. Our models even match or surpass frontier industrial models like Whisper and MMS in multiple scenarios. We will publicly release the cleaned YODAS data, pre-trained models, and all associated scripts via the ESPnet toolkit.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.24615</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2506.00338</guid>
|
||||||
<pubDate>Fri, 30 May 2025 14:08:13 +0000</pubDate>
|
<pubDate>Sat, 31 May 2025 01:44:44 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Context is Gold to find the Gold Passage: Evaluating and Training Contextual Document Embeddings</title>
|
<title>Neuro2Semantic: A Transfer Learning Framework for Semantic Reconstruction of Continuous Language from Human Intracranial EEG</title>
|
||||||
<link>https://arxiv.org/abs/2505.24782</link>
|
<link>https://arxiv.org/abs/2506.00381</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.24782.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Max Conti, Manuel Faysse, Gautier Viaud, Antoine Bosselut, Céline Hudelot, Pierre Colombo</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> A limitation of modern document retrieval embedding methods is that they typically encode passages (chunks) from the same documents independently, often overlooking crucial contextual information from the rest of the document that could greatly improve individual chunk representations. In this work, we introduce ConTEB (Context-aware Text Embedding Benchmark), a benchmark designed to evaluate retrieval models on their ability to leverage document-wide context. Our results show that state-of-the-art embedding models struggle in retrieval scenarios where context is required. To address this limitation, we propose InSeNT (In-sequence Negative Training), a novel contrastive post-training approach which combined with late chunking pooling enhances contextual representation learning while preserving computational efficiency. Our method significantly improves retrieval quality on ConTEB without sacrificing base model performance. We further find chunks embedded with our method are more robust to suboptimal chunking strategies and larger retrieval corpus sizes. We open-source all artifacts at https://github.com/illuin-tech/contextual-embeddings.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.00381.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Siavash Shams, Richard Antonello, Gavin Mischler, Stephan Bickel, Ashesh Mehta, Nima Mesgarani</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Decoding continuous language from neural signals remains a significant challenge in the intersection of neuroscience and artificial intelligence. We introduce Neuro2Semantic, a novel framework that reconstructs the semantic content of perceived speech from intracranial EEG (iEEG) recordings. Our approach consists of two phases: first, an LSTM-based adapter aligns neural signals with pre-trained text embeddings; second, a corrector module generates continuous, natural text directly from these aligned embeddings. This flexible method overcomes the limitations of previous decoding approaches and enables unconstrained text generation. Neuro2Semantic achieves strong performance with as little as 30 minutes of neural data, outperforming a recent state-of-the-art method in low-data settings. These results highlight the potential for practical applications in brain-computer interfaces and neural decoding technologies.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.24782</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2506.00381</guid>
|
||||||
<pubDate>Fri, 30 May 2025 16:43:28 +0000</pubDate>
|
<pubDate>Sat, 31 May 2025 04:17:19 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>EXP-Bench: Can AI Conduct AI Research Experiments?</title>
|
<title>MagiCodec: Simple Masked Gaussian-Injected Codec for High-Fidelity Reconstruction and Generation</title>
|
||||||
<link>https://arxiv.org/abs/2505.24785</link>
|
<link>https://arxiv.org/abs/2506.00385</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.24785.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Patrick Tser Jern Kon, Jiachen Liu, Xinyi Zhu, Qiuyi Ding, Jingjia Peng, Jiarong Xing, Yibo Huang, Yiming Qiu, Jayanth Srinivasa, Myungjin Lee, Mosharaf Chowdhury, Matei Zaharia, Ang Chen</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Automating AI research holds immense potential for accelerating scientific progress, yet current AI agents struggle with the complexities of rigorous, end-to-end experimentation. We introduce EXP-Bench, a novel benchmark designed to systematically evaluate AI agents on complete research experiments sourced from influential AI publications. Given a research question and incomplete starter code, EXP-Bench challenges AI agents to formulate hypotheses, design and implement experimental procedures, execute them, and analyze results. To enable the creation of such intricate and authentic tasks with high-fidelity, we design a semi-autonomous pipeline to extract and structure crucial experimental details from these research papers and their associated open-source code. With the pipeline, EXP-Bench curated 461 AI research tasks from 51 top-tier AI research papers. Evaluations of leading LLM-based agents, such as OpenHands and IterativeAgent on EXP-Bench demonstrate partial capabilities: while scores on individual experimental aspects such as design or implementation correctness occasionally reach 20-35%, the success rate for complete, executable experiments was a mere 0.5%. By identifying these bottlenecks and providing realistic step-by-step experiment procedures, EXP-Bench serves as a vital tool for future AI agents to improve their ability to conduct AI research experiments. EXP-Bench is open-sourced at https://github.com/Just-Curieous/Curie/tree/main/benchmark/exp_bench.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.00385.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yakun Song, Jiawei Chen, Xiaobin Zhuang, Chenpeng Du, Ziyang Ma, Jian Wu, Jian Cong, Dongya Jia, Zhuo Chen, Yuping Wang, Yuxuan Wang, Xie Chen</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Neural audio codecs have made significant strides in efficiently mapping raw audio waveforms into discrete token representations, which are foundational for contemporary audio generative models. However, most existing codecs are optimized primarily for reconstruction quality, often at the expense of the downstream modelability of the encoded tokens. Motivated by the need to overcome this bottleneck, we introduce MagiCodec, a novel single-layer, streaming Transformer-based audio codec. MagiCodec is designed with a multistage training pipeline that incorporates Gaussian noise injection and latent regularization, explicitly targeting the enhancement of semantic expressiveness in the generated codes while preserving high reconstruction fidelity. We analytically derive the effect of noise injection in the frequency domain, demonstrating its efficacy in attenuating high-frequency components and fostering robust tokenization. Extensive experimental evaluations show that MagiCodec surpasses state-of-the-art codecs in both reconstruction quality and downstream tasks. Notably, the tokens produced by MagiCodec exhibit Zipf-like distributions, as observed in natural languages, thereby improving compatibility with language-model-based generative architectures. The code and pre-trained models are available at https://github.com/Ereboas/MagiCodec.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.24785</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2506.00385</guid>
|
||||||
<pubDate>Fri, 30 May 2025 16:46:29 +0000</pubDate>
|
<pubDate>Sat, 31 May 2025 04:31:02 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Harnessing Negative Signals: Reinforcement Distillation from Teacher Data for LLM Reasoning</title>
|
<title>LoHoVLA: A Unified Vision-Language-Action Model for Long-Horizon Embodied Tasks</title>
|
||||||
<link>https://arxiv.org/abs/2505.24850</link>
|
<link>https://arxiv.org/abs/2506.00411</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.24850.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shuyao Xu, Cheng Peng, Jiangxuan Long, Weidi Xu, Wei Chu, Yuan Qi</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Recent advances in model distillation demonstrate that data from advanced reasoning models (e.g., DeepSeek-R1, OpenAI's o1) can effectively transfer complex reasoning abilities to smaller, efficient student models. However, standard practices employ rejection sampling, discarding incorrect reasoning examples -- valuable, yet often underutilized data. This paper addresses the critical question: How can both positive and negative distilled reasoning traces be effectively leveraged to maximize LLM reasoning performance in an offline setting? To this end, We propose Reinforcement Distillation (REDI), a two-stage framework. Stage 1 learns from positive traces via Supervised Fine-Tuning (SFT). Stage 2 further refines the model using both positive and negative traces through our proposed REDI objective. This novel objective is a simple, reference-free loss function that outperforms established methods like DPO and SimPO in this distillation context. Our empirical evaluations demonstrate REDI's superiority over baseline Rejection Sampling SFT or SFT combined with DPO/SimPO on mathematical reasoning tasks. Notably, the Qwen-REDI-1.5B model, post-trained on just 131k positive and negative examples from the open Open-R1 dataset, achieves an 83.1% score on MATH-500 (pass@1). Its performance matches or surpasses that of DeepSeek-R1-Distill-Qwen-1.5B (a model post-trained on 800k proprietary data) across various mathematical reasoning benchmarks, establishing a new state-of-the-art for 1.5B models post-trained offline with openly available data.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.00411.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yi Yang, Jiaxuan Sun, Siqi Kou, Yihan Wang, Zhijie Deng</p><p><b>Upvotes:</b> 23</p><p><b>Summary:</b> Real-world embodied agents face long-horizon tasks, characterized by high-level goals demanding multi-step solutions beyond single actions. Successfully navigating these requires both high-level task planning (i.e., decomposing goals into sub-tasks) and low-level motion control (i.e., generating precise robot actions). While existing vision language action (VLA) models and hierarchical architectures offer potential in embodied tasks, the former often falter in planning, and the latter can suffer from coordination issues, both hampering performance. We introduce a new unified VLA framework for long-horizon tasks, dubbed LoHoVLA, to overcome these limitations. LoHoVLA leverages a large pretrained vision language model (VLM) as the backbone to jointly generate language and action tokens for sub-task generation and robot action prediction, respectively. This shared representation promotes better generalization across tasks. Additionally, LoHoVLA embraces a hierarchical closed-loop control mechanism to mitigate errors originating from both high-level planning and low-level control. To train LoHoVLA, we introduce LoHoSet, a dataset built on the Ravens simulator, containing 20 long-horizon tasks, each with 1,000 expert demonstrations composed of visual observations, linguistic goals, sub-tasks, and robot actions. Experimental results show that LoHoVLA significantly surpasses both hierarchical and standard VLA approaches on long-horizon embodied tasks in the Ravens simulator. These findings underscore the promise of unified architectures for advancing generalizable embodied intelligence.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.24850</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2506.00411</guid>
|
||||||
<pubDate>Fri, 30 May 2025 17:47:17 +0000</pubDate>
|
<pubDate>Sat, 31 May 2025 06:01:03 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>MetaFaith: Faithful Natural Language Uncertainty Expression in LLMs</title>
|
<title>Massively Multilingual Adaptation of Large Language Models Using Bilingual Translation Data</title>
|
||||||
<link>https://arxiv.org/abs/2505.24858</link>
|
<link>https://arxiv.org/abs/2506.00469</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.24858.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Gabrielle Kaili-May Liu, Gal Yona, Avi Caciularu, Idan Szpektor, Tim G. J. Rudner, Arman Cohan</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> A critical component in the trustworthiness of LLMs is reliable uncertainty communication, yet LLMs often use assertive language when conveying false claims, leading to over-reliance and eroded trust. We present the first systematic study of faithful confidence calibration of LLMs, benchmarking models' ability to use linguistic expressions of uncertainty that faithfully reflect their intrinsic uncertainty, across a comprehensive array of models, datasets, and prompting strategies. Our results demonstrate that LLMs largely fail at this task, and that existing interventions are insufficient: standard prompt approaches provide only marginal gains, and existing, factuality-based calibration techniques can even harm faithful calibration. To address this critical gap, we introduce MetaFaith, a novel prompt-based calibration approach inspired by human metacognition. We show that MetaFaith robustly improves faithful calibration across diverse models and task domains, enabling up to 61% improvement in faithfulness and achieving an 83% win rate over original generations as judged by humans.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.00469.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shaoxiong Ji, Zihao Li, Jaakko Paavola, Indraneil Paul, Hengyu Luo, Jörg Tiedemann</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> This paper investigates a critical design decision in the practice of massively multilingual continual pre-training -- the inclusion of parallel data. Specifically, we study the impact of bilingual translation data for massively multilingual language adaptation of the Llama3 family of models to 500 languages. To this end, we construct the MaLA bilingual translation corpus, containing data from more than 2,500 language pairs. Subsequently, we develop the EMMA-500 Llama 3 suite of four massively multilingual models -- continually pre-trained from the Llama 3 family of base models extensively on diverse data mixes up to 671B tokens -- and explore the effect of continual pre-training with or without bilingual translation data. Comprehensive evaluation across 7 tasks and 12 benchmarks demonstrates that bilingual data tends to enhance language transfer and performance, particularly for low-resource languages. We open-source the MaLA corpus, EMMA-500 Llama 3 suite artefacts, code, and model generations.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.24858</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2506.00469</guid>
|
||||||
<pubDate>Fri, 30 May 2025 17:54:08 +0000</pubDate>
|
<pubDate>Sat, 31 May 2025 08:37:17 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>ViStoryBench: Comprehensive Benchmark Suite for Story Visualization</title>
|
<title>Pro3D-Editor : A Progressive-Views Perspective for Consistent and Precise 3D Editing</title>
|
||||||
<link>https://arxiv.org/abs/2505.24862</link>
|
<link>https://arxiv.org/abs/2506.00512</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.24862.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Cailin Zhuang, Ailin Huang, Wei Cheng, Jingwei Wu, Yaoqi Hu, Jiaqi Liao, Zhewei Huang, Hongyuan Wang, Xinyao Liao, Weiwei Cai, Hengyuan Xu, Xuanyang Zhang, Xianfang Zeng, Gang Yu, Chi Zhang</p><p><b>Upvotes:</b> 23</p><p><b>Summary:</b> Story visualization, which aims to generate a sequence of visually coherent images aligning with a given narrative and reference images, has seen significant progress with recent advancements in generative models. To further enhance the performance of story visualization frameworks in real-world scenarios, we introduce a comprehensive evaluation benchmark, ViStoryBench. We collect a diverse dataset encompassing various story types and artistic styles, ensuring models are evaluated across multiple dimensions such as different plots (e.g., comedy, horror) and visual aesthetics (e.g., anime, 3D renderings). ViStoryBench is carefully curated to balance narrative structures and visual elements, featuring stories with single and multiple protagonists to test models' ability to maintain character consistency. Additionally, it includes complex plots and intricate world-building to challenge models in generating accurate visuals. To ensure comprehensive comparisons, our benchmark incorporates a wide range of evaluation metrics assessing critical aspects. This structured and multifaceted framework enables researchers to thoroughly identify both the strengths and weaknesses of different models, fostering targeted improvements.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.00512.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yang Zheng, Mengqi Huang, Nan Chen, Zhendong Mao</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Text-guided 3D editing aims to precisely edit semantically relevant local 3D regions, which has significant potential for various practical applications ranging from 3D games to film production. Existing methods typically follow a view-indiscriminate paradigm: editing 2D views indiscriminately and projecting them back into 3D space. However, they overlook the different cross-view interdependencies, resulting in inconsistent multi-view editing. In this study, we argue that ideal consistent 3D editing can be achieved through a progressive-views paradigm, which propagates editing semantics from the editing-salient view to other editing-sparse views. Specifically, we propose Pro3D-Editor, a novel framework, which mainly includes Primary-view Sampler, Key-view Render, and Full-view Refiner. Primary-view Sampler dynamically samples and edits the most editing-salient view as the primary view. Key-view Render accurately propagates editing semantics from the primary view to other key views through its Mixture-of-View-Experts Low-Rank Adaption (MoVE-LoRA). Full-view Refiner edits and refines the 3D object based on the edited multi-views. Extensive experiments demonstrate that our method outperforms existing methods in editing accuracy and spatial consistency.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.24862</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2506.00512</guid>
|
||||||
<pubDate>Fri, 30 May 2025 17:58:21 +0000</pubDate>
|
<pubDate>Sat, 31 May 2025 11:11:55 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time</title>
|
<title>SenseFlow: Scaling Distribution Matching for Flow-based Text-to-Image Distillation</title>
|
||||||
<link>https://arxiv.org/abs/2505.24863</link>
|
<link>https://arxiv.org/abs/2506.00523</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.24863.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junyu Zhang, Runpei Dong, Han Wang, Xuying Ning, Haoran Geng, Peihao Li, Xialin He, Yutong Bai, Jitendra Malik, Saurabh Gupta, Huan Zhang</p><p><b>Upvotes:</b> 55</p><p><b>Summary:</b> This paper presents AlphaOne (alpha1), a universal framework for modulating reasoning progress in large reasoning models (LRMs) at test time. alpha1 first introduces alpha moment, which represents the scaled thinking phase with a universal parameter alpha. Within this scaled pre-alpha moment phase, it dynamically schedules slow thinking transitions by modeling the insertion of reasoning transition tokens as a Bernoulli stochastic process. After the alpha moment, alpha1 deterministically terminates slow thinking with the end-of-thinking token, thereby fostering fast reasoning and efficient answer generation. This approach unifies and generalizes existing monotonic scaling methods by enabling flexible and dense slow-to-fast reasoning modulation. Extensive empirical studies on various challenging benchmarks across mathematical, coding, and scientific domains demonstrate alpha1's superior reasoning capability and efficiency. Project page: https://alphaone-project.github.io/</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.00523.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xingtong Ge, Xin Zhang, Tongda Xu, Yi Zhang, Xinjie Zhang, Yan Wang, Jun Zhang</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> The Distribution Matching Distillation (DMD) has been successfully applied to text-to-image diffusion models such as Stable Diffusion (SD) 1.5. However, vanilla DMD suffers from convergence difficulties on large-scale flow-based text-to-image models, such as SD 3.5 and FLUX. In this paper, we first analyze the issues when applying vanilla DMD on large-scale models. Then, to overcome the scalability challenge, we propose implicit distribution alignment (IDA) to regularize the distance between the generator and fake distribution. Furthermore, we propose intra-segment guidance (ISG) to relocate the timestep importance distribution from the teacher model. With IDA alone, DMD converges for SD 3.5; employing both IDA and ISG, DMD converges for SD 3.5 and FLUX.1 dev. Along with other improvements such as scaled up discriminator models, our final model, dubbed SenseFlow, achieves superior performance in distillation for both diffusion based text-to-image models such as SDXL, and flow-matching models such as SD 3.5 Large and FLUX. The source code will be avaliable at https://github.com/XingtongGe/SenseFlow.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.24863</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2506.00523</guid>
|
||||||
<pubDate>Fri, 30 May 2025 17:58:36 +0000</pubDate>
|
<pubDate>Sat, 31 May 2025 11:59:02 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models</title>
|
<title>CityLens: Benchmarking Large Language-Vision Models for Urban Socioeconomic Sensing</title>
|
||||||
<link>https://arxiv.org/abs/2505.24864</link>
|
<link>https://arxiv.org/abs/2506.00530</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.24864.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mingjie Liu, Shizhe Diao, Ximing Lu, Jian Hu, Xin Dong, Yejin Choi, Jan Kautz, Yi Dong</p><p><b>Upvotes:</b> 80</p><p><b>Summary:</b> Recent advances in reasoning-centric language models have highlighted reinforcement learning (RL) as a promising method for aligning models with verifiable rewards. However, it remains contentious whether RL truly expands a model's reasoning capabilities or merely amplifies high-reward outputs already latent in the base model's distribution, and whether continually scaling up RL compute reliably leads to improved reasoning performance. In this work, we challenge prevailing assumptions by demonstrating that prolonged RL (ProRL) training can uncover novel reasoning strategies that are inaccessible to base models, even under extensive sampling. We introduce ProRL, a novel training methodology that incorporates KL divergence control, reference policy resetting, and a diverse suite of tasks. Our empirical analysis reveals that RL-trained models consistently outperform base models across a wide range of pass@k evaluations, including scenarios where base models fail entirely regardless of the number of attempts. We further show that reasoning boundary improvements correlates strongly with task competence of base model and training duration, suggesting that RL can explore and populate new regions of solution space over time. These findings offer new insights into the conditions under which RL meaningfully expands reasoning boundaries in language models and establish a foundation for future work on long-horizon RL for reasoning. We release model weights to support further research: https://huggingface.co/nvidia/Nemotron-Research-Reasoning-Qwen-1.5B</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.00530.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tianhui Liu, Jie Feng, Hetian Pang, Xin Zhang, Tianjian Ouyang, Zhiyuan Zhang, Yong Li</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Understanding urban socioeconomic conditions through visual data is a challenging yet essential task for sustainable urban development and policy planning. In this work, we introduce CityLens, a comprehensive benchmark designed to evaluate the capabilities of large language-vision models (LLVMs) in predicting socioeconomic indicators from satellite and street view imagery. We construct a multi-modal dataset covering a total of 17 globally distributed cities, spanning 6 key domains: economy, education, crime, transport, health, and environment, reflecting the multifaceted nature of urban life. Based on this dataset, we define 11 prediction tasks and utilize three evaluation paradigms: Direct Metric Prediction, Normalized Metric Estimation, and Feature-Based Regression. We benchmark 17 state-of-the-art LLVMs across these tasks. Our results reveal that while LLVMs demonstrate promising perceptual and reasoning capabilities, they still exhibit limitations in predicting urban socioeconomic indicators. CityLens provides a unified framework for diagnosing these limitations and guiding future efforts in using LLVMs to understand and predict urban socioeconomic patterns. Our codes and datasets are open-sourced via https://github.com/tsinghua-fib-lab/CityLens.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.24864</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2506.00530</guid>
|
||||||
<pubDate>Fri, 30 May 2025 17:59:01 +0000</pubDate>
|
<pubDate>Sat, 31 May 2025 12:25:33 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Time Blindness: Why Video-Language Models Can't See What Humans Can?</title>
|
<title>ARIA: Training Language Agents with Intention-Driven Reward Aggregation</title>
|
||||||
<link>https://arxiv.org/abs/2505.24867</link>
|
<link>https://arxiv.org/abs/2506.00539</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.24867.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ujjwal Upadhyay, Mukul Ranjan, Zhiqiang Shen, Mohamed Elhoseiny</p><p><b>Upvotes:</b> 55</p><p><b>Summary:</b> Recent advances in vision-language models (VLMs) have made impressive strides in understanding spatio-temporal relationships in videos. However, when spatial information is obscured, these models struggle to capture purely temporal patterns. We introduce SpookyBench, a benchmark where information is encoded solely in temporal sequences of noise-like frames, mirroring natural phenomena from biological signaling to covert communication. Interestingly, while humans can recognize shapes, text, and patterns in these sequences with over 98% accuracy, state-of-the-art VLMs achieve 0% accuracy. This performance gap highlights a critical limitation: an over-reliance on frame-level spatial features and an inability to extract meaning from temporal cues. Furthermore, when trained in data sets with low spatial signal-to-noise ratios (SNR), temporal understanding of models degrades more rapidly than human perception, especially in tasks requiring fine-grained temporal reasoning. Overcoming this limitation will require novel architectures or training paradigms that decouple spatial dependencies from temporal processing. Our systematic analysis shows that this issue persists across model scales and architectures. We release SpookyBench to catalyze research in temporal pattern recognition and bridge the gap between human and machine video understanding. Dataset and code has been made available on our project website: https://timeblindness.github.io/.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.00539.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ruihan Yang, Yikai Zhang, Aili Chen, Xintao Wang, Siyu Yuan, Jiangjie Chen, Deqing Yang, Yanghua Xiao</p><p><b>Upvotes:</b> 25</p><p><b>Summary:</b> Large language models (LLMs) have enabled agents to perform complex reasoning and decision-making through free-form language interactions. However, in open-ended language action environments (e.g., negotiation or question-asking games), the action space can be formulated as a joint distribution over tokens, resulting in an exponentially large action space. Sampling actions in such a space can lead to extreme reward sparsity, which brings large reward variance, hindering effective reinforcement learning (RL). To address this, we propose ARIA, a method that Aggregates Rewards in Intention space to enable efficient and effective language Agents training. ARIA aims to project natural language actions from the high-dimensional joint token distribution space into a low-dimensional intention space, where semantically similar actions are clustered and assigned shared rewards. This intention-aware reward aggregation reduces reward variance by densifying reward signals, fostering better policy optimization. Extensive experiments demonstrate that ARIA not only significantly reduces policy gradient variance, but also delivers substantial performance gains of an average of 9.95% across four downstream tasks, consistently outperforming offline and online RL baselines.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.24867</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2506.00539</guid>
|
||||||
<pubDate>Fri, 30 May 2025 17:59:12 +0000</pubDate>
|
<pubDate>Sat, 31 May 2025 12:54:49 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>SiLVR: A Simple Language-based Video Reasoning Framework</title>
|
<title>Reasoning Like an Economist: Post-Training on Economic Problems Induces Strategic Generalization in LLMs</title>
|
||||||
<link>https://arxiv.org/abs/2505.24869</link>
|
<link>https://arxiv.org/abs/2506.00577</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.24869.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ce Zhang, Yan-Bo Lin, Ziyang Wang, Mohit Bansal, Gedas Bertasius</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Recent advances in test-time optimization have led to remarkable reasoning capabilities in Large Language Models (LLMs), enabling them to solve highly complex problems in math and coding. However, the reasoning capabilities of multimodal LLMs (MLLMs) still significantly lag, especially for complex video-language tasks. To address this issue, we present SiLVR, a Simple Language-based Video Reasoning framework that decomposes complex video understanding into two stages. In the first stage, SiLVR transforms raw video into language-based representations using multisensory inputs, such as short clip captions and audio/speech subtitles. In the second stage, language descriptions are fed into a powerful reasoning LLM to solve complex video-language understanding tasks. To handle long-context multisensory inputs, we use an adaptive token reduction scheme, which dynamically determines the temporal granularity with which to sample the tokens. Our simple, modular, and training-free video reasoning framework achieves the best-reported results on Video-MME (long), Video-MMMU (comprehension), Video-MMLU, CGBench, and EgoLife. Furthermore, our empirical study focused on video reasoning capabilities shows that, despite not being explicitly trained on video, strong reasoning LLMs can effectively aggregate multisensory input information from video, speech, and audio for complex temporal, causal, long-context, and knowledge acquisition reasoning tasks in video. Code is available at https://github.com/CeeZh/SILVR.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.00577.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yufa Zhou, Shaobo Wang, Xingyu Dong, Xiangqi Jin, Yifang Chen, Yue Min, Kexin Yang, Xingzhang Ren, Dayiheng Liu, Linfeng Zhang</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Directly training Large Language Models (LLMs) for Multi-Agent Systems (MAS) remains challenging due to intricate reward modeling, dynamic agent interactions, and demanding generalization requirements. This paper explores whether post-training techniques, specifically Supervised Fine-Tuning (SFT) and Reinforcement Learning with Verifiable Rewards (RLVR), can effectively generalize to multi-agent scenarios. We use economic reasoning as a testbed, leveraging its strong foundations in mathematics and game theory, its demand for structured analytical reasoning, and its relevance to real-world applications such as market design, resource allocation, and policy analysis. We introduce Recon (Reasoning like an ECONomist), a 7B-parameter open-source LLM post-trained on a hand-curated dataset of 2,100 high-quality economic reasoning problems. Comprehensive evaluation on economic reasoning benchmarks and multi-agent games reveals clear improvements in structured reasoning and economic rationality. These results underscore the promise of domain-aligned post-training for enhancing reasoning and agent alignment, shedding light on the roles of SFT and RL in shaping model behavior. Code is available at https://github.com/MasterZhou1/Recon .</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.24869</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2506.00577</guid>
|
||||||
<pubDate>Fri, 30 May 2025 17:59:19 +0000</pubDate>
|
<pubDate>Sat, 31 May 2025 14:22:40 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>MoDoMoDo: Multi-Domain Data Mixtures for Multimodal LLM Reinforcement Learning</title>
|
<title>SATA-BENCH: Select All That Apply Benchmark for Multiple Choice Questions</title>
|
||||||
<link>https://arxiv.org/abs/2505.24871</link>
|
<link>https://arxiv.org/abs/2506.00643</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.24871.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yiqing Liang, Jielin Qiu, Wenhao Ding, Zuxin Liu, James Tompkin, Mengdi Xu, Mengzhou Xia, Zhengzhong Tu, Laixi Shi, Jiacheng Zhu</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Reinforcement Learning with Verifiable Rewards (RLVR) has recently emerged as a powerful paradigm for post-training large language models (LLMs), achieving state-of-the-art performance on tasks with structured, verifiable answers. Applying RLVR to Multimodal LLMs (MLLMs) presents significant opportunities but is complicated by the broader, heterogeneous nature of vision-language tasks that demand nuanced visual, logical, and spatial capabilities. As such, training MLLMs using RLVR on multiple datasets could be beneficial but creates challenges with conflicting objectives from interaction among diverse datasets, highlighting the need for optimal dataset mixture strategies to improve generalization and reasoning. We introduce a systematic post-training framework for Multimodal LLM RLVR, featuring a rigorous data mixture problem formulation and benchmark implementation. Specifically, (1) We developed a multimodal RLVR framework for multi-dataset post-training by curating a dataset that contains different verifiable vision-language problems and enabling multi-domain online RL learning with different verifiable rewards; (2) We proposed a data mixture strategy that learns to predict the RL fine-tuning outcome from the data mixture distribution, and consequently optimizes the best mixture. Comprehensive experiments showcase that multi-domain RLVR training, when combined with mixture prediction strategies, can significantly boost MLLM general reasoning capacities. Our best mixture improves the post-trained model's accuracy on out-of-distribution benchmarks by an average of 5.24% compared to the same model post-trained with uniform data mixture, and by a total of 20.74% compared to the pre-finetuning baseline.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.00643.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Weijie Xu, Shixian Cui, Xi Fang, Chi Xue, Stephanie Eckman, Chandan Reddy</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Large language models (LLMs) are increasingly evaluated on single-answer multiple-choice tasks, yet many real-world problems require identifying all correct answers from a set of options. This capability remains underexplored. We introduce SATA-BENCH, the first dedicated benchmark for evaluating LLMs on Select All That Apply (SATA) questions across diverse domains, including reading comprehension, law, and biomedicine. Our evaluation of 27 open-source and proprietary models reveals a significant gap: even the strongest model achieves only 41.8% exact match, exposing LLMs' inability to reliably identify all correct answers. We find that this weakness stems from two core challenges: selection bias - models favor certain choices regardless of content, and count bias - models fail to predict the correct number of answers. To address these issues, we propose Choice Funnel, a decoding strategy that combines token debiasing with adaptive thresholding to guide models toward complete and accurate selections. Choice Funnel achieves up to 29% higher exact match than competitive baselines while reducing inference cost by over 64%. Our findings expose fundamental limitations in current LLMs and introduce a new framework for diagnosing and improving multi-answer reasoning. We release SATA-BENCH and Choice Funnel to promote LLM development for robust decision-making in realistic, multi-answer applications.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.24871</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2506.00643</guid>
|
||||||
<pubDate>Fri, 30 May 2025 17:59:38 +0000</pubDate>
|
<pubDate>Sat, 31 May 2025 17:14:21 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>ReasonGen-R1: CoT for Autoregressive Image generation models through SFT and RL</title>
|
<title>Pitfalls in Evaluating Language Model Forecasters</title>
|
||||||
<link>https://arxiv.org/abs/2505.24875</link>
|
<link>https://arxiv.org/abs/2506.00723</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.24875.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yu Zhang, Yunqi Li, Yifan Yang, Rui Wang, Yuqing Yang, Dai Qi, Jianmin Bao, Dongdong Chen, Chong Luo, Lili Qiu</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Although chain-of-thought reasoning and reinforcement learning (RL) have driven breakthroughs in NLP, their integration into generative vision models remains underexplored. We introduce ReasonGen-R1, a two-stage framework that first imbues an autoregressive image generator with explicit text-based "thinking" skills via supervised fine-tuning on a newly generated reasoning dataset of written rationales, and then refines its outputs using Group Relative Policy Optimization. To enable the model to reason through text before generating images, We automatically generate and release a corpus of model crafted rationales paired with visual prompts, enabling controlled planning of object layouts, styles, and scene compositions. Our GRPO algorithm uses reward signals from a pretrained vision language model to assess overall visual quality, optimizing the policy in each update. Evaluations on GenEval, DPG, and the T2I benchmark demonstrate that ReasonGen-R1 consistently outperforms strong baselines and prior state-of-the-art models. More: aka.ms/reasongen.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.00723.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Daniel Paleka, Shashwat Goel, Jonas Geiping, Florian Tramèr</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Large language models (LLMs) have recently been applied to forecasting tasks, with some works claiming these systems match or exceed human performance. In this paper, we argue that, as a community, we should be careful about such conclusions as evaluating LLM forecasters presents unique challenges. We identify two broad categories of issues: (1) difficulty in trusting evaluation results due to many forms of temporal leakage, and (2) difficulty in extrapolating from evaluation performance to real-world forecasting. Through systematic analysis and concrete examples from prior work, we demonstrate how evaluation flaws can raise concerns about current and future performance claims. We argue that more rigorous evaluation methodologies are needed to confidently assess the forecasting abilities of LLMs.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.24875</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2506.00723</guid>
|
||||||
<pubDate>Fri, 30 May 2025 17:59:48 +0000</pubDate>
|
<pubDate>Sat, 31 May 2025 21:49:17 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Open CaptchaWorld: A Comprehensive Web-based Platform for Testing and Benchmarking Multimodal LLM Agents</title>
|
<title>LIFT the Veil for the Truth: Principal Weights Emerge after Rank Reduction for Reasoning-Focused Supervised Fine-Tuning</title>
|
||||||
<link>https://arxiv.org/abs/2505.24878</link>
|
<link>https://arxiv.org/abs/2506.00772</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.24878.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yaxin Luo, Zhaoyi Li, Jiacheng Liu, Jiacheng Cui, Xiaohan Zhao, Zhiqiang Shen</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> CAPTCHAs have been a critical bottleneck for deploying web agents in real-world applications, often blocking them from completing end-to-end automation tasks. While modern multimodal LLM agents have demonstrated impressive performance in static perception tasks, their ability to handle interactive, multi-step reasoning challenges like CAPTCHAs is largely untested. To address this gap, we introduce Open CaptchaWorld, the first web-based benchmark and platform specifically designed to evaluate the visual reasoning and interaction capabilities of MLLM-powered agents through diverse and dynamic CAPTCHA puzzles. Our benchmark spans 20 modern CAPTCHA types, totaling 225 CAPTCHAs, annotated with a new metric we propose: CAPTCHA Reasoning Depth, which quantifies the number of cognitive and motor steps required to solve each puzzle. Experimental results show that humans consistently achieve near-perfect scores, state-of-the-art MLLM agents struggle significantly, with success rates at most 40.0% by Browser-Use Openai-o3, far below human-level performance, 93.3%. This highlights Open CaptchaWorld as a vital benchmark for diagnosing the limits of current multimodal agents and guiding the development of more robust multimodal reasoning systems. Code and Data are available at this https URL.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.00772.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zihang Liu, Tianyu Pang, Oleg Balabanov, Chaoqun Yang, Tianjin Huang, Lu Yin, Yaoqing Yang, Shiwei Liu</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Recent studies have shown that supervised fine-tuning of LLMs on a small number of high-quality datasets can yield strong reasoning capabilities. However, full fine-tuning (Full FT), while powerful, is computationally expensive and susceptible to overfitting and catastrophic forgetting, particularly when data is limited. Sparse fine-tuning, which previously achieved notable success by updating only a small subset of model parameters, offers a promising trade-off between efficiency and effectiveness. Yet, it has lagged behind in the LLM era due to the difficulty of identifying parameters truly critical for reasoning. In this work, we state that weights with the largest magnitude after low-rank approximation are critical weights for fine-tuning, which we call Principal Weights. Surprisingly, while magnitude-based sparse fine-tuning performs poorly as a baseline on LLM fine-tuning, it becomes highly effective after rank reduction. These insights motivate our method: Low-rank Informed Sparse Fine-Tuning (LIFT). LIFT only updates the top 5% Principal Weights throughout training and consistently achieves better performance on reasoning tasks than Full FT, while maintaining memory efficiency on par with popular parameter-efficient fine-tuning methods. In addition to strong performance on target domains such as arithmetic reasoning, LIFT also retains up to 20% more source-domain knowledge, compared to Full FT and LoRA. Our code is available at: https://github.com/zihanghliu/LIFT.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2505.24878</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2506.00772</guid>
|
||||||
<pubDate>Fri, 30 May 2025 17:59:55 +0000</pubDate>
|
<pubDate>Sun, 01 Jun 2025 01:31:50 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>RARE: Retrieval-Aware Robustness Evaluation for Retrieval-Augmented Generation Systems</title>
|
||||||
|
<link>https://arxiv.org/abs/2506.00789</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.00789.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yixiao Zeng, Tianyu Cao, Danqing Wang, Xinran Zhao, Zimeng Qiu, Morteza Ziyadi, Tongshuang Wu, Lei Li</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Retrieval-Augmented Generation (RAG) enhances recency and factuality in answers. However, existing evaluations rarely test how well these systems cope with real-world noise, conflicting between internal and external retrieved contexts, or fast-changing facts. We introduce Retrieval-Aware Robustness Evaluation (RARE), a unified framework and large-scale benchmark that jointly stress-tests query and document perturbations over dynamic, time-sensitive corpora. One of the central features of RARE is a knowledge-graph-driven synthesis pipeline (RARE-Get) that automatically extracts single and multi-hop relations from the customized corpus and generates multi-level question sets without manual intervention. Leveraging this pipeline, we construct a dataset (RARE-Set) spanning 400 expert-level time-sensitive finance, economics, and policy documents and 48,322 questions whose distribution evolves as the underlying sources change. To quantify resilience, we formalize retrieval-conditioned robustness metrics (RARE-Met) that capture a model's ability to remain correct or recover when queries, documents, or real-world retrieval results are systematically altered. Our results show that RAG systems exhibit surprising vulnerability to perturbations, with document robustness consistently being the weakest point regardless of generator size or architecture. RAG systems consistently show lower robustness on multi-hop queries than single-hop queries across all domains.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2506.00789</guid>
|
||||||
|
<pubDate>Sun, 01 Jun 2025 02:42:36 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Aligning VLM Assistants with Personalized Situated Cognition</title>
|
||||||
|
<link>https://arxiv.org/abs/2506.00930</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.00930.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yongqi Li, Shen Zhou, Xiaohu Li, Xin Miao, Jintao Wen, Mayi Xu, Jianhao Chen, Birong Pan, Hankun Kang, Yuanyuan Zhu, Ming Zhong, Tieyun Qian</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Vision-language models (VLMs) aligned with general human objectives, such as being harmless and hallucination-free, have become valuable assistants of humans in managing visual tasks. However, people with diversified backgrounds have different cognition even in the same situation. Consequently, they may have personalized expectations for VLM assistants. This highlights the urgent need to align VLM assistants with personalized situated cognition for real-world assistance. To study this problem, we first simplify it by characterizing individuals based on the sociological concept of Role-Set. Then, we propose to evaluate the individuals' actions to examine whether the personalized alignment is achieved. Further, we construct a benchmark named PCogAlignBench, which includes 18k instances and 20 individuals with different Role-Sets. Finally, we present a framework called PCogAlign, which constructs a cognition-aware and action-based reward model for personalized alignment. Experimental results and human evaluations demonstrate the reliability of the PCogAlignBench and the effectiveness of our proposed PCogAlign. We will open-source the constructed benchmark and code at https://github.com/NLPGM/PCogAlign.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2506.00930</guid>
|
||||||
|
<pubDate>Sun, 01 Jun 2025 09:50:54 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>IVY-FAKE: A Unified Explainable Framework and Benchmark for Image and Video AIGC Detection</title>
|
||||||
|
<link>https://arxiv.org/abs/2506.00979</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.00979.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wayne Zhang, Changjiang Jiang, Zhonghao Zhang, Chenyang Si, Fengchang Yu, Wei Peng</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> The rapid advancement of Artificial Intelligence Generated Content (AIGC) in visual domains has resulted in highly realistic synthetic images and videos, driven by sophisticated generative frameworks such as diffusion-based architectures. While these breakthroughs open substantial opportunities, they simultaneously raise critical concerns about content authenticity and integrity. Many current AIGC detection methods operate as black-box binary classifiers, which offer limited interpretability, and no approach supports detecting both images and videos in a unified framework. This dual limitation compromises model transparency, reduces trustworthiness, and hinders practical deployment. To address these challenges, we introduce IVY-FAKE , a novel, unified, and large-scale dataset specifically designed for explainable multimodal AIGC detection. Unlike prior benchmarks, which suffer from fragmented modality coverage and sparse annotations, IVY-FAKE contains over 150,000 richly annotated training samples (images and videos) and 18,700 evaluation examples, each accompanied by detailed natural-language reasoning beyond simple binary labels. Building on this, we propose Ivy Explainable Detector (IVY-XDETECTOR), a unified AIGC detection and explainable architecture that jointly performs explainable detection for both image and video content. Our unified vision-language model achieves state-of-the-art performance across multiple image and video detection benchmarks, highlighting the significant advancements enabled by our dataset and modeling framework. Our data is publicly available at https://huggingface.co/datasets/AI-Safeguard/Ivy-Fake.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2506.00979</guid>
|
||||||
|
<pubDate>Sun, 01 Jun 2025 12:20:22 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Temporal In-Context Fine-Tuning for Versatile Control of Video Diffusion Models</title>
|
||||||
|
<link>https://arxiv.org/abs/2506.00996</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.00996.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kinam Kim, Junha Hyung, Jaegul Choo</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> Recent advances in text-to-video diffusion models have enabled high-quality video synthesis, but controllable generation remains challenging, particularly under limited data and compute. Existing fine-tuning methods for conditional generation often rely on external encoders or architectural modifications, which demand large datasets and are typically restricted to spatially aligned conditioning, limiting flexibility and scalability. In this work, we introduce Temporal In-Context Fine-Tuning (TIC-FT), an efficient and versatile approach for adapting pretrained video diffusion models to diverse conditional generation tasks. Our key idea is to concatenate condition and target frames along the temporal axis and insert intermediate buffer frames with progressively increasing noise levels. These buffer frames enable smooth transitions, aligning the fine-tuning process with the pretrained model's temporal dynamics. TIC-FT requires no architectural changes and achieves strong performance with as few as 10-30 training samples. We validate our method across a range of tasks, including image-to-video and video-to-video generation, using large-scale base models such as CogVideoX-5B and Wan-14B. Extensive experiments show that TIC-FT outperforms existing baselines in both condition fidelity and visual quality, while remaining highly efficient in both training and inference. For additional results, visit https://kinam0252.github.io/TIC-FT/</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2506.00996</guid>
|
||||||
|
<pubDate>Sun, 01 Jun 2025 12:57:43 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Taming LLMs by Scaling Learning Rates with Gradient Grouping</title>
|
||||||
|
<link>https://arxiv.org/abs/2506.01049</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.01049.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Siyuan Li, Juanxi Tian, Zedong Wang, Xin Jin, Zicheng Liu, Wentao Zhang, Dan Xu</p><p><b>Upvotes:</b> 32</p><p><b>Summary:</b> Training large language models (LLMs) poses challenges due to their massive scale and heterogeneous architectures. While adaptive optimizers like AdamW help address gradient variations, they still struggle with efficient and effective parameter-wise learning rate estimation, resulting in training instability, slow convergence, and poor compatibility with parameter-efficient fine-tuning (PEFT) techniques. This work introduces Scaling with Gradient Grouping (SGG), an optimizer wrapper that improves adaptive learning rate estimation by dynamic grouping and group-specific scaling. SGG first groups gradient statistics in each layer into clusters and then applies cluster-specific scaling to calibrate learning rates for each parameter, thus imposing collective group-wise constraints while maintaining precise per-parameter adaptation. Experiments on diverse (M)LLM benchmarks show that SGG integrates seamlessly with existing optimizers, and offers consistent gains and faster convergence over baselines, with various model sizes. Its stability across varying batch sizes and learning rates establishes SGG as a robust choice for LLM optimization.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2506.01049</guid>
|
||||||
|
<pubDate>Sun, 01 Jun 2025 15:30:37 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>SealQA: Raising the Bar for Reasoning in Search-Augmented Language Models</title>
|
||||||
|
<link>https://arxiv.org/abs/2506.01062</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.01062.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Thinh Pham, Nguyen Nguyen, Pratibha Zunjare, Weiyuan Chen, Yu-Min Tseng, Tu Vu</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> We introduce SealQA, a new challenge benchmark for evaluating SEarch-Augmented Language models on fact-seeking questions where web search yields conflicting, noisy, or unhelpful results. SealQA comes in three flavors: (1) Seal-0 (main) and (2) Seal-Hard, which assess factual accuracy and reasoning capabilities, with Seal-0 focusing on the most challenging questions where chat models (e.g., GPT-4.1) typically achieve near-zero accuracy; and (3) LongSeal, which extends SealQA to test long-context, multi-document reasoning in "needle-in-a-haystack" settings. Our evaluation reveals critical limitations in current models: Even frontier LLMs perform poorly across all SealQA flavors. On Seal-0, frontier agentic models equipped with tools like o3 and o4-mini achieve only 17.1% and 6.3% accuracy, respectively, at their best reasoning efforts. We find that advanced reasoning models such as DeepSeek-R1-671B and o3-mini are highly vulnerable to noisy search results. Notably, increasing test-time compute does not yield reliable gains across o3-mini, o4-mini, and o3, with performance often plateauing or even declining early. Additionally, while recent models are less affected by the "lost-in-the-middle" issue, they still fail to reliably identify relevant documents in LongSeal when faced with numerous distractors. To facilitate future work, we release SealQA at huggingface.co/datasets/vtllms/sealqa.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2506.01062</guid>
|
||||||
|
<pubDate>Sun, 01 Jun 2025 16:04:34 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>How Programming Concepts and Neurons Are Shared in Code Language Models</title>
|
||||||
|
<link>https://arxiv.org/abs/2506.01074</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.01074.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Amir Hossein Kargaran, Yihong Liu, François Yvon, Hinrich Schütze</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Several studies have explored the mechanisms of large language models (LLMs) in coding tasks, but most have focused on programming languages (PLs) in a monolingual setting. In this paper, we investigate the relationship between multiple PLs and English in the concept space of LLMs. We perform a few-shot translation task on 21 PL pairs using two Llama-based models. By decoding the embeddings of intermediate layers during this task, we observe that the concept space is closer to English (including PL keywords) and assigns high probabilities to English tokens in the second half of the intermediate layers. We analyze neuron activations for 11 PLs and English, finding that while language-specific neurons are primarily concentrated in the bottom layers, those exclusive to each PL tend to appear in the top layers. For PLs that are highly aligned with multiple other PLs, identifying language-specific neurons is not feasible. These PLs also tend to have a larger keyword set than other PLs and are closer to the model's concept space regardless of the input/output PL in the translation task. Our findings provide insights into how LLMs internally represent PLs, revealing structural patterns in the model's concept space. Code is available at https://github.com/cisnlp/code-specific-neurons.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2506.01074</guid>
|
||||||
|
<pubDate>Sun, 01 Jun 2025 16:24:13 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>zip2zip: Inference-Time Adaptive Vocabularies for Language Models via Token Compression</title>
|
||||||
|
<link>https://arxiv.org/abs/2506.01084</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.01084.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Saibo Geng, Nathan Ranchin, Yunzhen yao, Maxime Peyrard, Chris Wendler, Michael Gastpar, Robert West</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Tokenization efficiency plays a critical role in the performance and cost of large language models (LLMs), yet most models rely on static tokenizers optimized for general-purpose corpora. These tokenizers' fixed vocabularies often fail to adapt to domain- or language-specific inputs, leading to longer token sequences and higher computational costs. We introduce zip2zip, a framework that enables LLMs to dynamically adjust token vocabulary at inference time, allowing for fewer generated tokens and thus faster inference. zip2zip consists of three key components: (1) a tokenizer based on Lempel-Ziv-Welch (LZW) compression that incrementally compresses tokens into reusable "hypertokens" on the fly; (2) an embedding layer that computes embeddings for newly formed hypertokens at runtime; and (3) a causal language modeling variant that trains the model to operate on hypertokenized, compressed sequences. We show that an existing LLM can be zip2zip-fied in 10 GPU-hours via parameter-efficient finetuning. The resulting zip2zip LLMs effectively learn to use hypertokens at inference time, reducing input and output sequence length by 20-60\%, with significant improvements in inference latency.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2506.01084</guid>
|
||||||
|
<pubDate>Sun, 01 Jun 2025 17:03:02 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Incentivizing Reasoning for Advanced Instruction-Following of Large Language Models</title>
|
||||||
|
<link>https://arxiv.org/abs/2506.01413</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.01413.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yulei Qin, Gang Li, Zongyi Li, Zihan Xu, Yuchen Shi, Zhekai Lin, Xiao Cui, Ke Li, Xing Sun</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Existing large language models (LLMs) face challenges of following complex instructions, especially when multiple constraints are present and organized in paralleling, chaining, and branching structures. One intuitive solution, namely chain-of-thought (CoT), is expected to universally improve capabilities of LLMs. However, we find that the vanilla CoT exerts a negative impact on performance due to its superficial reasoning pattern of simply paraphrasing the instructions. It fails to peel back the compositions of constraints for identifying their relationship across hierarchies of types and dimensions. To this end, we propose a systematic method to boost LLMs in dealing with complex instructions via incentivizing reasoning for test-time compute scaling. First, we stem from the decomposition of complex instructions under existing taxonomies and propose a reproducible data acquisition method. Second, we exploit reinforcement learning (RL) with verifiable rule-centric reward signals to cultivate reasoning specifically for instruction following. We address the shallow, non-essential nature of reasoning under complex instructions via sample-wise contrast for superior CoT enforcement. We also exploit behavior cloning of experts to facilitate steady distribution shift from fast-thinking LLMs to skillful reasoners. Extensive evaluations on seven comprehensive benchmarks confirm the validity of the proposed method, where a 1.5B LLM achieves 11.74% gains with performance comparable to a 8B LLM. Codes and data are available at https://github.com/yuleiqin/RAIF.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2506.01413</guid>
|
||||||
|
<pubDate>Mon, 02 Jun 2025 08:11:44 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>LLM in the Loop: Creating the PARADEHATE Dataset for Hate Speech Detoxification</title>
|
||||||
|
<link>https://arxiv.org/abs/2506.01484</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.01484.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shuzhou Yuan, Ercong Nie, Lukas Kouba, Ashish Yashwanth Kangen, Helmut Schmid, Hinrich Schutze, Michael Farber</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Detoxification, the task of rewriting harmful language into non-toxic text, has become increasingly important amid the growing prevalence of toxic content online. However, high-quality parallel datasets for detoxification, especially for hate speech, remain scarce due to the cost and sensitivity of human annotation. In this paper, we propose a novel LLM-in-the-loop pipeline leveraging GPT-4o-mini for automated detoxification. We first replicate the ParaDetox pipeline by replacing human annotators with an LLM and show that the LLM performs comparably to human annotation. Building on this, we construct PARADEHATE, a large-scale parallel dataset specifically for hatespeech detoxification. We release PARADEHATE as a benchmark of over 8K hate/non-hate text pairs and evaluate a wide range of baseline methods. Experimental results show that models such as BART, fine-tuned on PARADEHATE, achieve better performance in style accuracy, content preservation, and fluency, demonstrating the effectiveness of LLM-generated detoxification text as a scalable alternative to human annotation.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2506.01484</guid>
|
||||||
|
<pubDate>Mon, 02 Jun 2025 09:45:05 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Synthesis of discrete-continuous quantum circuits with multimodal diffusion models</title>
|
||||||
|
<link>https://arxiv.org/abs/2506.01666</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.01666.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Florian Fürrutter, Zohim Chandani, Ikko Hamamura, Hans J. Briegel, Gorka Muñoz-Gil</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Efficiently compiling quantum operations remains a major bottleneck in scaling quantum computing. Today's state-of-the-art methods achieve low compilation error by combining search algorithms with gradient-based parameter optimization, but they incur long runtimes and require multiple calls to quantum hardware or expensive classical simulations, making their scaling prohibitive. Recently, machine-learning models have emerged as an alternative, though they are currently restricted to discrete gate sets. Here, we introduce a multimodal denoising diffusion model that simultaneously generates a circuit's structure and its continuous parameters for compiling a target unitary. It leverages two independent diffusion processes, one for discrete gate selection and one for parameter prediction. We benchmark the model over different experiments, analyzing the method's accuracy across varying qubit counts, circuit depths, and proportions of parameterized gates. Finally, by exploiting its rapid circuit generation, we create large datasets of circuits for particular operations and use these to extract valuable heuristics that can help us discover new insights into quantum circuit synthesis.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2506.01666</guid>
|
||||||
|
<pubDate>Mon, 02 Jun 2025 13:35:33 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>EarthMind: Towards Multi-Granular and Multi-Sensor Earth Observation with Large Multimodal Models</title>
|
||||||
|
<link>https://arxiv.org/abs/2506.01667</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.01667.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yan Shu, Bin Ren, Zhitong Xiong, Danda Pani Paudel, Luc Van Gool, Begum Demir, Nicu Sebe, Paolo Rota</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> Large Multimodal Models (LMMs) have demonstrated strong performance in various vision-language tasks. However, they often struggle to comprehensively understand Earth Observation (EO) data, which is critical for monitoring the environment and the effects of human activity on it. In this work, we present EarthMind, a novel vision-language framework for multi-granular and multi-sensor EO data understanding. EarthMind features two core components: (1) Spatial Attention Prompting (SAP), which reallocates attention within the LLM to enhance pixel-level understanding; and (2) Cross-modal Fusion, which aligns heterogeneous modalities into a shared space and adaptively reweighs tokens based on their information density for effective fusion. To facilitate multi-sensor fusion evaluation, we propose EarthMind-Bench, a comprehensive benchmark with over 2,000 human-annotated multi-sensor image-question pairs, covering a wide range of perception and reasoning tasks. Extensive experiments demonstrate the effectiveness of EarthMind. It achieves state-of-the-art performance on EarthMind-Bench, surpassing GPT-4o despite being only 4B in scale. Moreover, EarthMind outperforms existing methods on multiple public EO benchmarks, showcasing its potential to handle both multi-granular and multi-sensor challenges in a unified framework.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2506.01667</guid>
|
||||||
|
<pubDate>Mon, 02 Jun 2025 13:36:05 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>SRPO: Enhancing Multimodal LLM Reasoning via Reflection-Aware Reinforcement Learning</title>
|
||||||
|
<link>https://arxiv.org/abs/2506.01713</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.01713.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhongwei Wan, Zhihao Dou, Che Liu, Yu Zhang, Dongfei Cui, Qinjian Zhao, Hui Shen, Jing Xiong, Yi Xin, Yifan Jiang, Yangfan He, Mi Zhang, Shen Yan</p><p><b>Upvotes:</b> 20</p><p><b>Summary:</b> Multimodal large language models (MLLMs) have shown promising capabilities in reasoning tasks, yet still struggle with complex problems requiring explicit self-reflection and self-correction, especially compared to their unimodal text-based counterparts. Existing reflection methods are simplistic and struggle to generate meaningful and instructive feedback, as the reasoning ability and knowledge limits of pre-trained models are largely fixed during initial training. To overcome these challenges, we propose Multimodal Self-Reflection enhanced reasoning with Group Relative Policy Optimization (SRPO), a two-stage reflection-aware reinforcement learning (RL) framework explicitly designed to enhance multimodal LLM reasoning. In the first stage, we construct a high-quality, reflection-focused dataset under the guidance of an advanced MLLM, which generates reflections based on initial responses to help the policy model learn both reasoning and self-reflection. In the second stage, we introduce a novel reward mechanism within the GRPO framework that encourages concise and cognitively meaningful reflection while avoiding redundancy. Extensive experiments across multiple multimodal reasoning benchmarks, including MathVista, MathVision, MathVerse, and MMMU-Pro, using Qwen-2.5-VL-7B and Qwen-2.5-VL-32B demonstrate that SRPO significantly outperforms state-of-the-art models, achieving notable improvements in both reasoning accuracy and reflection quality.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2506.01713</guid>
|
||||||
|
<pubDate>Mon, 02 Jun 2025 14:21:44 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics</title>
|
||||||
|
<link>https://arxiv.org/abs/2506.01844</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.01844.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mustafa Shukor, Dana Aubakirova, Francesco Capuano, Pepijn Kooijmans, Steven Palma, Adil Zouitine, Michel Aractingi, Caroline Pascal, Martino Russi, Andres Marafioti, Simon Alibert, Matthieu Cord, Thomas Wolf, Remi Cadene</p><p><b>Upvotes:</b> 43</p><p><b>Summary:</b> Vision-language models (VLMs) pretrained on large-scale multimodal datasets encode rich visual and linguistic knowledge, making them a strong foundation for robotics. Rather than training robotic policies from scratch, recent approaches adapt VLMs into vision-language-action (VLA) models that enable natural language-driven perception and control. However, existing VLAs are typically massive--often with billions of parameters--leading to high training costs and limited real-world deployability. Moreover, they rely on academic and industrial datasets, overlooking the growing availability of community-collected data from affordable robotic platforms. In this work, we present SmolVLA, a small, efficient, and community-driven VLA that drastically reduces both training and inference costs, while retaining competitive performance. SmolVLA is designed to be trained on a single GPU and deployed on consumer-grade GPUs or even CPUs. To further improve responsiveness, we introduce an asynchronous inference stack decoupling perception and action prediction from action execution, allowing higher control rates with chunked action generation. Despite its compact size, SmolVLA achieves performance comparable to VLAs that are 10x larger. We evaluate SmolVLA on a range of both simulated as well as real-world robotic benchmarks and release all code, pretrained models, and training data.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2506.01844</guid>
|
||||||
|
<pubDate>Mon, 02 Jun 2025 16:30:19 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>ShapeLLM-Omni: A Native Multimodal LLM for 3D Generation and Understanding</title>
|
||||||
|
<link>https://arxiv.org/abs/2506.01853</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.01853.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junliang Ye, Zhengyi Wang, Ruowen Zhao, Shenghao Xie, Jun Zhu</p><p><b>Upvotes:</b> 23</p><p><b>Summary:</b> Recently, the powerful text-to-image capabilities of ChatGPT-4o have led to growing appreciation for native multimodal large language models. However, its multimodal capabilities remain confined to images and text. Yet beyond images, the ability to understand and generate 3D content is equally crucial. To address this gap, we propose ShapeLLM-Omni-a native 3D large language model capable of understanding and generating 3D assets and text in any sequence. First, we train a 3D vector-quantized variational autoencoder (VQVAE), which maps 3D objects into a discrete latent space to achieve efficient and accurate shape representation and reconstruction. Building upon the 3D-aware discrete tokens, we innovatively construct a large-scale continuous training dataset named 3D-Alpaca, encompassing generation, comprehension, and editing, thus providing rich resources for future research and training. Finally, by performing instruction-based training of the Qwen-2.5-vl-7B-Instruct model on the 3D-Alpaca dataset. Our work provides an effective attempt at extending multimodal models with basic 3D capabilities, which contributes to future research in 3D-native AI. Project page: https://github.com/JAMESYJL/ShapeLLM-Omni</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2506.01853</guid>
|
||||||
|
<pubDate>Mon, 02 Jun 2025 16:40:50 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Unified Scaling Laws for Compressed Representations</title>
|
||||||
|
<link>https://arxiv.org/abs/2506.01863</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.01863.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Andrei Panferov, Alexandra Volkova, Ionut-Vlad Modoranu, Vage Egiazarian, Mher Safaryan, Dan Alistarh</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Scaling laws have shaped recent advances in machine learning by enabling predictable scaling of model performance based on model size, computation, and data volume. Concurrently, the rise in computational cost for AI has motivated model compression techniques, notably quantization and sparsification, which have emerged to mitigate the steep computational demands associated with large-scale training and inference. This paper investigates the interplay between scaling laws and compression formats, exploring whether a unified scaling framework can accurately predict model performance when training occurs over various compressed representations, such as sparse, scalar-quantized, sparse-quantized or even vector-quantized formats. Our key contributions include validating a general scaling law formulation and showing that it is applicable both individually but also composably across compression types. Based on this, our main finding is demonstrating both theoretically and empirically that there exists a simple "capacity" metric -- based on the representation's ability to fit random Gaussian data -- which can robustly predict parameter efficiency across multiple compressed representations. On the practical side, we extend our formulation to directly compare the accuracy potential of different compressed formats, and to derive better algorithms for training over sparse-quantized formats.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2506.01863</guid>
|
||||||
|
<pubDate>Mon, 02 Jun 2025 16:52:51 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>WHEN TO ACT, WHEN TO WAIT: Modeling Structural Trajectories for Intent Triggerability in Task-Oriented Dialogue</title>
|
||||||
|
<link>https://arxiv.org/abs/2506.01881</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.01881.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yaoyao Qian, Jindan Huang, Yuanli Wang, Simon Yu, Kyrie Zhixuan Zhou, Jiayuan Mao, Mingfu Liang, Hanhan Zhou</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Task-oriented dialogue systems often face difficulties when user utterances seem semantically complete but lack necessary structural information for appropriate system action. This arises because users frequently do not fully understand their own needs, while systems require precise intent definitions. Current LLM-based agents cannot effectively distinguish between linguistically complete and contextually triggerable expressions, lacking frameworks for collaborative intent formation. We present STORM, a framework modeling asymmetric information dynamics through conversations between UserLLM (full internal access) and AgentLLM (observable behavior only). STORM produces annotated corpora capturing expression trajectories and latent cognitive transitions, enabling systematic analysis of collaborative understanding development. Our contributions include: (1) formalizing asymmetric information processing in dialogue systems; (2) modeling intent formation tracking collaborative understanding evolution; and (3) evaluation metrics measuring internal cognitive improvements alongside task performance. Experiments across four language models reveal that moderate uncertainty (40-60%) can outperform complete transparency in certain scenarios, with model-specific patterns suggesting reconsideration of optimal information completeness in human-AI collaboration. These findings contribute to understanding asymmetric reasoning dynamics and inform uncertainty-calibrated dialogue system design.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2506.01881</guid>
|
||||||
|
<pubDate>Mon, 02 Jun 2025 17:11:10 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>From Guidelines to Practice: A New Paradigm for Arabic Language Model Evaluation</title>
|
||||||
|
<link>https://arxiv.org/abs/2506.01920</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.01920.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Serry Sibaee, Omer Nacar, Adel Ammar, Yasser Al-Habashi, Abdulrahman Al-Batati, Wadii Boulila</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> This paper addresses critical gaps in Arabic language model evaluation by establishing comprehensive theoretical guidelines and introducing a novel evaluation framework. We first analyze existing Arabic evaluation datasets, identifying significant issues in linguistic accuracy, cultural alignment, and methodological rigor. To address these limitations in LLMs, we present the Arabic Depth Mini Dataset (ADMD), a carefully curated collection of 490 challenging questions spanning ten major domains (42 sub-domains, see Figure 1. Using ADMD, we evaluate five leading language models: GPT-4, Claude 3.5 Sonnet, Gemini Flash 1.5, CommandR 100B, and Qwen-Max. Our results reveal significant variations in model performance across different domains, with particular challenges in areas requiring deep cultural understanding and specialized knowledge. Claude 3.5 Sonnet demonstrated the highest overall accuracy at 30\%, showing relative strength in mathematical theory in Arabic, Arabic language, and islamic domains. This work provides both theoretical foundations and practical insights for improving Arabic language model evaluation, emphasizing the importance of cultural competence alongside technical capabilities.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2506.01920</guid>
|
||||||
|
<pubDate>Mon, 02 Jun 2025 17:39:50 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>From Guidelines to Practice: A New Paradigm for Arabic Language Model Evaluation</title>
|
||||||
|
<link>https://arxiv.org/abs/2506.01920</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.01920.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Serry Sibaee, Omer Nacar, Adel Ammar, Yasser Al-Habashi, Abdulrahman Al-Batati, Wadii Boulila</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> This paper addresses critical gaps in Arabic language model evaluation by establishing comprehensive theoretical guidelines and introducing a novel evaluation framework. We first analyze existing Arabic evaluation datasets, identifying significant issues in linguistic accuracy, cultural alignment, and methodological rigor. To address these limitations in LLMs, we present the Arabic Depth Mini Dataset (ADMD), a carefully curated collection of 490 challenging questions spanning ten major domains (42 sub-domains, see Figure 1. Using ADMD, we evaluate five leading language models: GPT-4, Claude 3.5 Sonnet, Gemini Flash 1.5, CommandR 100B, and Qwen-Max. Our results reveal significant variations in model performance across different domains, with particular challenges in areas requiring deep cultural understanding and specialized knowledge. Claude 3.5 Sonnet demonstrated the highest overall accuracy at 30\%, showing relative strength in mathematical theory in Arabic, Arabic language, and islamic domains. This work provides both theoretical foundations and practical insights for improving Arabic language model evaluation, emphasizing the importance of cultural competence alongside technical capabilities.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2506.01920</guid>
|
||||||
|
<pubDate>Mon, 02 Jun 2025 17:39:50 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Esoteric Language Models</title>
|
||||||
|
<link>https://arxiv.org/abs/2506.01928</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.01928.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Subham Sekhar Sahoo, Zhihan Yang, Yash Akhauri, Johnna Liu, Deepansha Singh, Zhoujun Cheng, Zhengzhong Liu, Eric Xing, John Thickstun, Arash Vahdat</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Diffusion-based language models offer a compelling alternative to autoregressive (AR) models by enabling parallel and controllable generation. Among this family of models, Masked Diffusion Models (MDMs) achieve the strongest performance but still underperform AR models in perplexity and lack key inference-time efficiency features--most notably, KV caching. In this work, we introduce Eso-LMs, a new family of models that fuses AR and MDM paradigms, enabling smooth interpolation between their perplexities while overcoming their respective limitations. Eso-LMs set a new state of the art on standard language modeling benchmarks. Crucially, we are the **first to introduce KV caching for MDMs** while preserving parallel generation, significantly improving inference efficiency. Combined with an optimized sampling schedule, our method achieves up to **65x** faster inference than standard MDMs and **4x** faster inference than prior semi-autoregressive approaches. We provide the code and model checkpoints on the project page: [http://s-sahoo.github.io/Eso-LMs](http://s-sahoo.github.io/Eso-LMs)</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2506.01928</guid>
|
||||||
|
<pubDate>Mon, 02 Jun 2025 17:47:27 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning</title>
|
||||||
|
<link>https://arxiv.org/abs/2506.01939</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.01939.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shenzhi Wang, Le Yu, Chang Gao, Chujie Zheng, Shixuan Liu, Rui Lu, Kai Dang, Xionghui Chen, Jianxin Yang, Zhenru Zhang, Yuqiong Liu, An Yang, Andrew Zhao, Yang Yue, Shiji Song, Bowen Yu, Gao Huang, Junyang Lin</p><p><b>Upvotes:</b> 93</p><p><b>Summary:</b> Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a powerful approach to enhancing the reasoning capabilities of Large Language Models (LLMs), while its mechanisms are not yet well understood. In this work, we undertake a pioneering exploration of RLVR through the novel perspective of token entropy patterns, comprehensively analyzing how different tokens influence reasoning performance. By examining token entropy patterns in Chain-of-Thought (CoT) reasoning, we observe that only a small fraction of tokens exhibit high entropy, and these tokens act as critical forks that steer the model toward diverse reasoning pathways. Furthermore, studying how entropy patterns evolve during RLVR training reveals that RLVR largely adheres to the base model's entropy patterns, primarily adjusting the entropy of high-entropy tokens. These findings highlight the significance of high-entropy tokens (i.e., forking tokens) to RLVR. We ultimately improve RLVR by restricting policy gradient updates to forking tokens and uncover a finding even beyond the 80/20 rule: utilizing only 20% of the tokens while maintaining performance comparable to full-gradient updates on the Qwen3-8B base model and significantly surpassing full-gradient updates on the Qwen3-32B (+11.04 on AIME'25 and +7.71 on AIME'24) and Qwen3-14B (+4.79 on AIME'25 and +5.21 on AIME'24) base models, highlighting a strong scaling trend. In contrast, training exclusively on the 80% lowest-entropy tokens leads to a marked decline in performance. These findings indicate that the efficacy of RLVR primarily arises from optimizing the high-entropy tokens that decide reasoning directions. Collectively, our results highlight the potential to understand RLVR through a token-entropy perspective and optimize RLVR by leveraging high-entropy minority tokens to further improve LLM reasoning.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2506.01939</guid>
|
||||||
|
<pubDate>Mon, 02 Jun 2025 17:54:39 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Learning Video Generation for Robotic Manipulation with Collaborative Trajectory Control</title>
|
||||||
|
<link>https://arxiv.org/abs/2506.01943</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.01943.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiao Fu, Xintao Wang, Xian Liu, Jianhong Bai, Runsen Xu, Pengfei Wan, Di Zhang, Dahua Lin</p><p><b>Upvotes:</b> 20</p><p><b>Summary:</b> Recent advances in video diffusion models have demonstrated strong potential for generating robotic decision-making data, with trajectory conditions further enabling fine-grained control. However, existing trajectory-based methods primarily focus on individual object motion and struggle to capture multi-object interaction crucial in complex robotic manipulation. This limitation arises from multi-feature entanglement in overlapping regions, which leads to degraded visual fidelity. To address this, we present RoboMaster, a novel framework that models inter-object dynamics through a collaborative trajectory formulation. Unlike prior methods that decompose objects, our core is to decompose the interaction process into three sub-stages: pre-interaction, interaction, and post-interaction. Each stage is modeled using the feature of the dominant object, specifically the robotic arm in the pre- and post-interaction phases and the manipulated object during interaction, thereby mitigating the drawback of multi-object feature fusion present during interaction in prior work. To further ensure subject semantic consistency throughout the video, we incorporate appearance- and shape-aware latent representations for objects. Extensive experiments on the challenging Bridge V2 dataset, as well as in-the-wild evaluation, demonstrate that our method outperforms existing approaches, establishing new state-of-the-art performance in trajectory-controlled video generation for robotic manipulation.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2506.01943</guid>
|
||||||
|
<pubDate>Mon, 02 Jun 2025 17:57:06 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>WebChoreArena: Evaluating Web Browsing Agents on Realistic Tedious Web Tasks</title>
|
||||||
|
<link>https://arxiv.org/abs/2506.01952</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.01952.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Atsuyuki Miyai, Zaiying Zhao, Kazuki Egashira, Atsuki Sato, Tatsumi Sunada, Shota Onohara, Hiromasa Yamanishi, Mashiro Toyooka, Kunato Nishina, Ryoma Maeda, Kiyoharu Aizawa, Toshihiko Yamasaki</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Powered by a large language model (LLM), a web browsing agent operates web browsers in a human-like manner and offers a highly transparent path toward automating a wide range of everyday tasks. As web agents become increasingly capable and demonstrate proficiency in general browsing tasks, a critical question emerges: Can they go beyond general browsing to robustly handle tasks that are tedious and complex, or chores that humans often avoid doing themselves? In this paper, we introduce WebChoreArena, a new fully reproducible benchmark comprising 532 carefully curated tasks designed to extend the scope of WebArena beyond general browsing to more labor-intensive and tedious tasks. WebChoreArena systematically integrates three key challenges: (i) Massive Memory tasks requiring accurate retrieval of large amounts of information in the observations, (ii) Calculation tasks demanding precise mathematical reasoning, and (iii) Long-Term Memory tasks necessitating long-term memory across multiple webpages. Built on top of the fully reproducible and widely adopted four WebArena simulation environments, WebChoreArena ensures strict reproducibility and enables fair, direct comparisons with the established WebArena benchmark, offering key insights into agent progress. Our experimental results demonstrate that as LLMs evolve, represented by GPT-4o, Claude 3.7 Sonnet, and Gemini 2.5 Pro, significant improvements in performance are observed on WebChoreArena. These findings suggest that WebChoreArena is well-suited to measure the advancement of state-of-the-art LLMs with greater clarity. Nevertheless, the results also indicate that even with Gemini 2.5 Pro, there remains substantial room for improvement compared to WebArena, highlighting the increased challenges posed by WebChoreArena.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2506.01952</guid>
|
||||||
|
<pubDate>Mon, 02 Jun 2025 17:59:45 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
</channel>
|
</channel>
|
||||||
</rss>
|
</rss>
|
||||||
|
|||||||
Reference in New Issue
Block a user