diff --git a/feed.xml b/feed.xml index 093dcd6..514fd70 100644 --- a/feed.xml +++ b/feed.xml @@ -7,104 +7,139 @@ http://www.rssboard.org/rss-specification python-feedgen en - Wed, 30 Apr 2025 00:02:32 +0000 + Thu, 01 May 2025 00:02:38 +0000 - TrustGeoGen: Scalable and Formal-Verified Data Engine for Trustworthy Multi-modal Geometric Problem Solving - https://arxiv.org/abs/2504.15780 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2504.15780.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Daocheng Fu, Zijun Chen, Renqiu Xia, Qi Liu, Yuan Feng, Hongbin Zhou, Renrui Zhang, Shiyang Feng, Peng Gao, Junchi Yan, Botian Shi, Bo Zhang, Yu Qiao</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Mathematical geometric problem solving (GPS) often requires effective integration of multimodal information and verifiable logical coherence. Despite the fast development of large language models in general problem solving, it remains unresolved regarding with both methodology and benchmarks, especially given the fact that exiting synthetic GPS benchmarks are often not self-verified and contain noise and self-contradicted information due to the illusion of LLMs. In this paper, we propose a scalable data engine called TrustGeoGen for problem generation, with formal verification to provide a principled benchmark, which we believe lays the foundation for the further development of methods for GPS. The engine synthesizes geometric data through four key innovations: 1) multimodal-aligned generation of diagrams, textual descriptions, and stepwise solutions; 2) formal verification ensuring rule-compliant reasoning paths; 3) a bootstrapping mechanism enabling complexity escalation via recursive state generation and 4) our devised GeoExplore series algorithms simultaneously produce multi-solution variants and self-reflective backtracking traces. By formal logical verification, TrustGeoGen produces GeoTrust-200K dataset with guaranteed modality integrity, along with GeoTrust-test testset. Experiments reveal the state-of-the-art models achieve only 49.17\% accuracy on GeoTrust-test, demonstrating its evaluation stringency. Crucially, models trained on GeoTrust achieve OOD generalization on GeoQA, significantly reducing logical inconsistencies relative to pseudo-label annotated by OpenAI-o1. Our code is available at https://github.com/Alpha-Innovator/TrustGeoGen</p> - https://arxiv.org/abs/2504.15780 - Tue, 22 Apr 2025 10:45:23 +0000 + Certified Mitigation of Worst-Case LLM Copyright Infringement + https://arxiv.org/abs/2504.16046 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2504.16046.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jingyu Zhang, Jiacan Yu, Marc Marone, Benjamin Van Durme, Daniel Khashabi</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> The exposure of large language models (LLMs) to copyrighted material during pre-training raises concerns about unintentional copyright infringement post deployment. This has driven the development of "copyright takedown" methods, post-training approaches aimed at preventing models from generating content substantially similar to copyrighted ones. While current mitigation approaches are somewhat effective for average-case risks, we demonstrate that they overlook worst-case copyright risks exhibits by the existence of long, verbatim quotes from copyrighted sources. We propose BloomScrub, a remarkably simple yet highly effective inference-time approach that provides certified copyright takedown. Our method repeatedly interleaves quote detection with rewriting techniques to transform potentially infringing segments. By leveraging efficient data sketches (Bloom filters), our approach enables scalable copyright screening even for large-scale real-world corpora. When quotes beyond a length threshold cannot be removed, the system can abstain from responding, offering certified risk reduction. Experimental results show that BloomScrub reduces infringement risk, preserves utility, and accommodates different levels of enforcement stringency with adaptive abstention. Our results suggest that lightweight, inference-time methods can be surprisingly effective for copyright prevention.</p> + https://arxiv.org/abs/2504.16046 + Tue, 22 Apr 2025 17:16:53 +0000 - MMInference: Accelerating Pre-filling for Long-Context VLMs via Modality-Aware Permutation Sparse Attention - https://arxiv.org/abs/2504.16083 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2504.16083.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yucheng Li, Huiqiang Jiang, Chengruidong Zhang, Qianhui Wu, Xufang Luo, Surin Ahn, Amir H. Abdi, Dongsheng Li, Jianfeng Gao, Yuqing Yang, Lili Qiu</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> The integration of long-context capabilities with visual understanding unlocks unprecedented potential for Vision Language Models (VLMs). However, the quadratic attention complexity during the pre-filling phase remains a significant obstacle to real-world deployment. To overcome this limitation, we introduce MMInference (Multimodality Million tokens Inference), a dynamic sparse attention method that accelerates the prefilling stage for long-context multi-modal inputs. First, our analysis reveals that the temporal and spatial locality of video input leads to a unique sparse pattern, the Grid pattern. Simultaneously, VLMs exhibit markedly different sparse distributions across different modalities. We introduce a permutation-based method to leverage the unique Grid pattern and handle modality boundary issues. By offline search the optimal sparse patterns for each head, MMInference constructs the sparse distribution dynamically based on the input. We also provide optimized GPU kernels for efficient sparse computations. Notably, MMInference integrates seamlessly into existing VLM pipelines without any model modifications or fine-tuning. Experiments on multi-modal benchmarks-including Video QA, Captioning, VisionNIAH, and Mixed-Modality NIAH-with state-of-the-art long-context VLMs (LongVila, LlavaVideo, VideoChat-Flash, Qwen2.5-VL) show that MMInference accelerates the pre-filling stage by up to 8.3x at 1M tokens while maintaining accuracy. Our code is available at https://aka.ms/MMInference.</p> - https://arxiv.org/abs/2504.16083 - Tue, 22 Apr 2025 17:59:51 +0000 + Learning Explainable Dense Reward Shapes via Bayesian Optimization + https://arxiv.org/abs/2504.16272 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2504.16272.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ryan Koo, Ian Yang, Vipul Raheja, Mingyi Hong, Kwang-Sung Jun, Dongyeop Kang</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Current reinforcement learning from human feedback (RLHF) pipelines for large language model (LLM) alignment typically assign scalar rewards to sequences, using the final token as a surrogate indicator for the quality of the entire sequence. However, this leads to sparse feedback and suboptimal token-level credit assignment. In this work, we frame reward shaping as an optimization problem focused on token-level credit assignment. We propose a reward-shaping function leveraging explainability methods such as SHAP and LIME to estimate per-token rewards from the reward model. To learn parameters of this shaping function, we employ a bilevel optimization framework that integrates Bayesian Optimization and policy training to handle noise from the token reward estimates. Our experiments show that achieving a better balance of token-level reward attribution leads to performance improvements over baselines on downstream tasks and finds an optimal policy faster during training. Furthermore, we show theoretically that explainability methods that are feature additive attribution functions maintain the optimal policy as the original reward.</p> + https://arxiv.org/abs/2504.16272 + Tue, 22 Apr 2025 21:09:33 +0000 - Group Downsampling with Equivariant Anti-aliasing - https://arxiv.org/abs/2504.17258 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2504.17258.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Md Ashiqur Rahman, Raymond A. Yeh</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Downsampling layers are crucial building blocks in CNN architectures, which help to increase the receptive field for learning high-level features and reduce the amount of memory/computation in the model. In this work, we study the generalization of the uniform downsampling layer for group equivariant architectures, e.g., G-CNNs. That is, we aim to downsample signals (feature maps) on general finite groups with anti-aliasing. This involves the following: (a) Given a finite group and a downsampling rate, we present an algorithm to form a suitable choice of subgroup. (b) Given a group and a subgroup, we study the notion of bandlimited-ness and propose how to perform anti-aliasing. Notably, our method generalizes the notion of downsampling based on classical sampling theory. When the signal is on a cyclic group, i.e., periodic, our method recovers the standard downsampling of an ideal low-pass filter followed by a subsampling operation. Finally, we conducted experiments on image classification tasks demonstrating that the proposed downsampling operation improves accuracy, better preserves equivariance, and reduces model size when incorporated into G-equivariant networks</p> - https://arxiv.org/abs/2504.17258 - Thu, 24 Apr 2025 05:29:51 +0000 + CaRL: Learning Scalable Planning Policies with Simple Rewards + https://arxiv.org/abs/2504.17838 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2504.17838.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bernhard Jaeger, Daniel Dauner, Jens Beißwenger, Simon Gerstenecker, Kashyap Chitta, Andreas Geiger</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> We investigate reinforcement learning (RL) for privileged planning in autonomous driving. State-of-the-art approaches for this task are rule-based, but these methods do not scale to the long tail. RL, on the other hand, is scalable and does not suffer from compounding errors like imitation learning. Contemporary RL approaches for driving use complex shaped rewards that sum multiple individual rewards, \eg~progress, position, or orientation rewards. We show that PPO fails to optimize a popular version of these rewards when the mini-batch size is increased, which limits the scalability of these approaches. Instead, we propose a new reward design based primarily on optimizing a single intuitive reward term: route completion. Infractions are penalized by terminating the episode or multiplicatively reducing route completion. We find that PPO scales well with higher mini-batch sizes when trained with our simple reward, even improving performance. Training with large mini-batch sizes enables efficient scaling via distributed data parallelism. We scale PPO to 300M samples in CARLA and 500M samples in nuPlan with a single 8-GPU node. The resulting model achieves 64 DS on the CARLA longest6 v2 benchmark, outperforming other RL methods with more complex rewards by a large margin. Requiring only minimal adaptations from its use in CARLA, the same method is the best learning-based approach on nuPlan. It scores 91.3 in non-reactive and 90.6 in reactive traffic on the Val14 benchmark while being an order of magnitude faster than prior work.</p> + https://arxiv.org/abs/2504.17838 + Thu, 24 Apr 2025 17:56:01 +0000 - Benchmarking Multimodal Mathematical Reasoning with Explicit Visual Dependency - https://arxiv.org/abs/2504.18589 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2504.18589.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhikai Wang, Jiashuo Sun, Wenqi Zhang, Zhiqiang Hu, Xin Li, Fan Wang, Deli Zhao</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Recent advancements in Large Vision-Language Models (LVLMs) have significantly enhanced their ability to integrate visual and linguistic information, achieving near-human proficiency in tasks like object recognition, captioning, and visual question answering. However, current benchmarks typically focus on knowledge-centric evaluations that assess domain-specific expertise, often neglecting the core ability to reason about fundamental mathematical elements and visual concepts. We identify a gap in evaluating elementary-level math problems, which rely on explicit visual dependencies-requiring models to discern, integrate, and reason across multiple images while incorporating commonsense knowledge, all of which are crucial for advancing toward broader AGI capabilities. To address this gap, we introduce VCBENCH, a comprehensive benchmark for multimodal mathematical reasoning with explicit visual dependencies. VCBENCH includes 1,720 problems across six cognitive domains, featuring 6,697 images (averaging 3.9 per question) to ensure multi-image reasoning. We evaluate 26 state-of-the-art LVLMs on VCBENCH, revealing substantial performance disparities, with even the top models unable to exceed 50% accuracy. Our findings highlight the ongoing challenges in visual-mathematical integration and suggest avenues for future LVLM advancements.</p> - https://arxiv.org/abs/2504.18589 - Thu, 24 Apr 2025 06:16:38 +0000 + RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning + https://arxiv.org/abs/2504.20073 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2504.20073.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zihan Wang, Kangrui Wang, Qineng Wang, Pingyue Zhang, Linjie Li, Zhengyuan Yang, Kefan Yu, Minh Nhat Nguyen, Licheng Liu, Eli Gottlieb, Monica Lam, Yiping Lu, Kyunghyun Cho, Jiajun Wu, Li Fei-Fei, Lijuan Wang, Yejin Choi, Manling Li</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Training large language models (LLMs) as interactive agents presents unique challenges including long-horizon decision making and interacting with stochastic environment feedback. While reinforcement learning (RL) has enabled progress in static tasks, multi-turn agent RL training remains underexplored. We propose StarPO (State-Thinking-Actions-Reward Policy Optimization), a general framework for trajectory-level agent RL, and introduce RAGEN, a modular system for training and evaluating LLM agents. Our study on three stylized environments reveals three core findings. First, our agent RL training shows a recurring mode of Echo Trap where reward variance cliffs and gradient spikes; we address this with StarPO-S, a stabilized variant with trajectory filtering, critic incorporation, and decoupled clipping. Second, we find the shaping of RL rollouts would benefit from diverse initial states, medium interaction granularity and more frequent sampling. Third, we show that without fine-grained, reasoning-aware reward signals, agent reasoning hardly emerge through multi-turn RL and they may show shallow strategies or hallucinated thoughts. Code and environments are available at https://github.com/RAGEN-AI/RAGEN.</p> + https://arxiv.org/abs/2504.20073 + Thu, 24 Apr 2025 17:57:08 +0000 - Clinical knowledge in LLMs does not translate to human interactions - https://arxiv.org/abs/2504.18919 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2504.18919.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Andrew M. Bean, Rebecca Payne, Guy Parsons, Hannah Rose Kirk, Juan Ciro, Rafael Mosquera, Sara Hincapié Monsalve, Aruna S. Ekanayaka, Lionel Tarassenko, Luc Rocher, Adam Mahdi</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> Global healthcare providers are exploring use of large language models (LLMs) to provide medical advice to the public. LLMs now achieve nearly perfect scores on medical licensing exams, but this does not necessarily translate to accurate performance in real-world settings. We tested if LLMs can assist members of the public in identifying underlying conditions and choosing a course of action (disposition) in ten medical scenarios in a controlled study with 1,298 participants. Participants were randomly assigned to receive assistance from an LLM (GPT-4o, Llama 3, Command R+) or a source of their choice (control). Tested alone, LLMs complete the scenarios accurately, correctly identifying conditions in 94.9% of cases and disposition in 56.3% on average. However, participants using the same LLMs identified relevant conditions in less than 34.5% of cases and disposition in less than 44.2%, both no better than the control group. We identify user interactions as a challenge to the deployment of LLMs for medical advice. Standard benchmarks for medical knowledge and simulated patient interactions do not predict the failures we find with human participants. Moving forward, we recommend systematic human user testing to evaluate interactive capabilities prior to public deployments in healthcare.</p> - https://arxiv.org/abs/2504.18919 - Sat, 26 Apr 2025 13:32:49 +0000 + Disentangle Identity, Cooperate Emotion: Correlation-Aware Emotional Talking Portrait Generation + https://arxiv.org/abs/2504.18087 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2504.18087.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Weipeng Tan, Chuming Lin, Chengming Xu, FeiFan Xu, Xiaobin Hu, Xiaozhong Ji, Junwei Zhu, Chengjie Wang, Yanwei Fu</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Recent advances in Talking Head Generation (THG) have achieved impressive lip synchronization and visual quality through diffusion models; yet existing methods struggle to generate emotionally expressive portraits while preserving speaker identity. We identify three critical limitations in current emotional talking head generation: insufficient utilization of audio's inherent emotional cues, identity leakage in emotion representations, and isolated learning of emotion correlations. To address these challenges, we propose a novel framework dubbed as DICE-Talk, following the idea of disentangling identity with emotion, and then cooperating emotions with similar characteristics. First, we develop a disentangled emotion embedder that jointly models audio-visual emotional cues through cross-modal attention, representing emotions as identity-agnostic Gaussian distributions. Second, we introduce a correlation-enhanced emotion conditioning module with learnable Emotion Banks that explicitly capture inter-emotion relationships through vector quantization and attention-based feature aggregation. Third, we design an emotion discrimination objective that enforces affective consistency during the diffusion process through latent-space classification. Extensive experiments on MEAD and HDTF datasets demonstrate our method's superiority, outperforming state-of-the-art approaches in emotion accuracy while maintaining competitive lip-sync performance. Qualitative results and user studies further confirm our method's ability to generate identity-preserving portraits with rich, correlated emotional expressions that naturally adapt to unseen identities.</p> + https://arxiv.org/abs/2504.18087 + Fri, 25 Apr 2025 05:28:21 +0000 - Versatile Framework for Song Generation with Prompt-based Control - https://arxiv.org/abs/2504.19062 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2504.19062.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yu Zhang, Wenxiang Guo, Changhao Pan, Zhiyuan Zhu, Ruiqi Li, Jingyu Lu, Rongjie Huang, Ruiyuan Zhang, Zhiqing Hong, Ziyue Jiang, Zhou Zhao</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Song generation focuses on producing controllable high-quality songs based on various prompts. However, existing methods struggle to generate vocals and accompaniments with prompt-based control and proper alignment. Additionally, they fall short in supporting various tasks. To address these challenges, we introduce VersBand, a multi-task song generation framework for synthesizing high-quality, aligned songs with prompt-based control. VersBand comprises these primary models: 1) VocalBand, a decoupled model, leverages the flow-matching method for generating singing styles, pitches, and mel-spectrograms, allowing fast, high-quality vocal generation with style control. 2) AccompBand, a flow-based transformer model, incorporates the Band-MOE, selecting suitable experts for enhanced quality, alignment, and control. This model allows for generating controllable, high-quality accompaniments aligned with vocals. 3) Two generation models, LyricBand for lyrics and MelodyBand for melodies, contribute to the comprehensive multi-task song generation system, allowing for extensive control based on multiple prompts. Experimental results demonstrate that VersBand performs better over baseline models across multiple song generation tasks using objective and subjective metrics. Audio samples are available at https://VersBand.github.io.</p> - https://arxiv.org/abs/2504.19062 - Sun, 27 Apr 2025 01:00:06 +0000 + A Review of 3D Object Detection with Vision-Language Models + https://arxiv.org/abs/2504.18738 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2504.18738.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ranjan Sapkota, Konstantinos I Roumeliotis, Rahul Harsha Cheppally, Marco Flores Calero, Manoj Karkee</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> This review provides a systematic analysis of comprehensive survey of 3D object detection with vision-language models(VLMs) , a rapidly advancing area at the intersection of 3D vision and multimodal AI. By examining over 100 research papers, we provide the first systematic analysis dedicated to 3D object detection with vision-language models. We begin by outlining the unique challenges of 3D object detection with vision-language models, emphasizing differences from 2D detection in spatial reasoning and data complexity. Traditional approaches using point clouds and voxel grids are compared to modern vision-language frameworks like CLIP and 3D LLMs, which enable open-vocabulary detection and zero-shot generalization. We review key architectures, pretraining strategies, and prompt engineering methods that align textual and 3D features for effective 3D object detection with vision-language models. Visualization examples and evaluation benchmarks are discussed to illustrate performance and behavior. Finally, we highlight current challenges, such as limited 3D-language datasets and computational demands, and propose future research directions to advance 3D object detection with vision-language models. >Object Detection, Vision-Language Models, Agents, VLMs, LLMs, AI</p> + https://arxiv.org/abs/2504.18738 + Fri, 25 Apr 2025 23:27:26 +0000 - CipherBank: Exploring the Boundary of LLM Reasoning Capabilities through Cryptography Challenges - https://arxiv.org/abs/2504.19093 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2504.19093.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yu Li, Qizhi Pei, Mengyuan Sun, Honglin Lin, Chenlin Ming, Xin Gao, Jiang Wu, Conghui He, Lijun Wu</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> Large language models (LLMs) have demonstrated remarkable capabilities, especially the recent advancements in reasoning, such as o1 and o3, pushing the boundaries of AI. Despite these impressive achievements in mathematics and coding, the reasoning abilities of LLMs in domains requiring cryptographic expertise remain underexplored. In this paper, we introduce CipherBank, a comprehensive benchmark designed to evaluate the reasoning capabilities of LLMs in cryptographic decryption tasks. CipherBank comprises 2,358 meticulously crafted problems, covering 262 unique plaintexts across 5 domains and 14 subdomains, with a focus on privacy-sensitive and real-world scenarios that necessitate encryption. From a cryptographic perspective, CipherBank incorporates 3 major categories of encryption methods, spanning 9 distinct algorithms, ranging from classical ciphers to custom cryptographic techniques. We evaluate state-of-the-art LLMs on CipherBank, e.g., GPT-4o, DeepSeek-V3, and cutting-edge reasoning-focused models such as o1 and DeepSeek-R1. Our results reveal significant gaps in reasoning abilities not only between general-purpose chat LLMs and reasoning-focused LLMs but also in the performance of current reasoning-focused models when applied to classical cryptographic decryption tasks, highlighting the challenges these models face in understanding and manipulating encrypted data. Through detailed analysis and error investigations, we provide several key observations that shed light on the limitations and potential improvement areas for LLMs in cryptographic reasoning. These findings underscore the need for continuous advancements in LLM reasoning capabilities.</p> - https://arxiv.org/abs/2504.19093 - Sun, 27 Apr 2025 03:41:17 +0000 + LawFlow : Collecting and Simulating Lawyers' Thought Processes + https://arxiv.org/abs/2504.18942 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2504.18942.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Debarati Das, Khanh Chi Le, Ritik Sachin Parkar, Karin De Langis, Brendan Madson, Chad M. Berryman, Robin M. Willis, Daniel H. Moses, Brett McDonnell, Daniel Schwarcz, Dongyeop Kang</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Legal practitioners, particularly those early in their careers, face complex, high-stakes tasks that require adaptive, context-sensitive reasoning. While AI holds promise in supporting legal work, current datasets and models are narrowly focused on isolated subtasks and fail to capture the end-to-end decision-making required in real-world practice. To address this gap, we introduce LawFlow, a dataset of complete end-to-end legal workflows collected from trained law students, grounded in real-world business entity formation scenarios. Unlike prior datasets focused on input-output pairs or linear chains of thought, LawFlow captures dynamic, modular, and iterative reasoning processes that reflect the ambiguity, revision, and client-adaptive strategies of legal practice. Using LawFlow, we compare human and LLM-generated workflows, revealing systematic differences in structure, reasoning flexibility, and plan execution. Human workflows tend to be modular and adaptive, while LLM workflows are more sequential, exhaustive, and less sensitive to downstream implications. Our findings also suggest that legal professionals prefer AI to carry out supportive roles, such as brainstorming, identifying blind spots, and surfacing alternatives, rather than executing complex workflows end-to-end. Building on these findings, we propose a set of design suggestions, rooted in empirical observations, that align AI assistance with human goals of clarity, completeness, creativity, and efficiency, through hybrid planning, adaptive execution, and decision-point support. Our results highlight both the current limitations of LLMs in supporting complex legal workflows and opportunities for developing more collaborative, reasoning-aware legal AI systems. All data and code are available on our project page (https://minnesotanlp.github.io/LawFlow-website/).</p> + https://arxiv.org/abs/2504.18942 + Sat, 26 Apr 2025 15:01:55 +0000 - ChiseLLM: Unleashing the Power of Reasoning LLMs for Chisel Agile Hardware Development - https://arxiv.org/abs/2504.19144 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2504.19144.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bowei Wang, Jiaran Gao, Yelai Feng, Renzhi Chen, Shanshan Li, Lei Wang</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> The growing demand for Domain-Specific Architecture (DSA) has driven the development of Agile Hardware Development Methodology (AHDM). Hardware Construction Language (HCL) like Chisel offers high-level abstraction features, making it an ideal language for HCL-Based AHDM. While Large Language Models (LLMs) excel in code generation tasks, they still face challenges with Chisel generation, particularly regarding syntax correctness and design variability. Recent reasoning models have significantly enhanced code generation capabilities through test-time scaling techniques. However, we found that reasoning models without domain adaptation cannot bring substantial benefits to Chisel code generation tasks. This paper presents ChiseLLM, a solution comprising data processing and transformation, prompt-guided reasoning trace synthesis, and domain-adapted model training. We constructed high-quality datasets from public RTL code resources and guided the model to adopt structured thinking patterns through prompt enhancement methods. Experiments demonstrate that our ChiseLLM-7B and ChiseLLM-32B models improved syntax correctness by 18.85% and 26.32% respectively over base models, while increasing variability design ability by 47.58% compared to baseline reasoning models. Our datasets and models are publicly available, providing high-performance, cost-effective models for HCL-Based AHDM, and offering an effective baseline for future research. Github repository: https://github.com/observerw/ChiseLLM</p> - https://arxiv.org/abs/2504.19144 - Sun, 27 Apr 2025 07:56:49 +0000 + TreeHop: Generate and Filter Next Query Embeddings Efficiently for Multi-hop Question Answering + https://arxiv.org/abs/2504.20114 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2504.20114.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhonghao Li, Kunpeng Zhang, Jinghuai Ou, Shuliang Liu, Xuming Hu</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Retrieval-augmented generation (RAG) systems face significant challenges in multi-hop question answering (MHQA), where complex queries require synthesizing information across multiple document chunks. Existing approaches typically rely on iterative LLM-based query rewriting and routing, resulting in high computational costs due to repeated LLM invocations and multi-stage processes. To address these limitations, we propose TreeHop, an embedding-level framework without the need for LLMs in query refinement. TreeHop dynamically updates query embeddings by fusing semantic information from prior queries and retrieved documents, enabling iterative retrieval through embedding-space operations alone. This method replaces the traditional "Retrieve-Rewrite-Vectorize-Retrieve" cycle with a streamlined "Retrieve-Embed-Retrieve" loop, significantly reducing computational overhead. Moreover, a rule-based stop criterion is introduced to further prune redundant retrievals, balancing efficiency and recall rate. Experimental results show that TreeHop rivals advanced RAG methods across three open-domain MHQA datasets, achieving comparable performance with only 5\%-0.4\% of the model parameter size and reducing the query latency by approximately 99\% compared to concurrent approaches. This makes TreeHop a faster and more cost-effective solution for deployment in a range of knowledge-intensive applications. For reproducibility purposes, codes and data are available here: https://github.com/allen-li1231/TreeHop.</p> + https://arxiv.org/abs/2504.20114 + Mon, 28 Apr 2025 01:56:31 +0000 - SPC: Evolving Self-Play Critic via Adversarial Games for LLM Reasoning - https://arxiv.org/abs/2504.19162 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2504.19162.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiaqi Chen, Bang Zhang, Ruotian Ma, Peisong Wang, Xiaodan Liang, Zhaopeng Tu, Xiaolong Li, Kwan-Yee K. Wong</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Evaluating the step-by-step reliability of large language model (LLM) reasoning, such as Chain-of-Thought, remains challenging due to the difficulty and cost of obtaining high-quality step-level supervision. In this paper, we introduce Self-Play Critic (SPC), a novel approach where a critic model evolves its ability to assess reasoning steps through adversarial self-play games, eliminating the need for manual step-level annotation. SPC involves fine-tuning two copies of a base model to play two roles, namely a "sneaky generator" that deliberately produces erroneous steps designed to be difficult to detect, and a "critic" that analyzes the correctness of reasoning steps. These two models engage in an adversarial game in which the generator aims to fool the critic, while the critic model seeks to identify the generator's errors. Using reinforcement learning based on the game outcomes, the models iteratively improve; the winner of each confrontation receives a positive reward and the loser receives a negative reward, driving continuous self-evolution. Experiments on three reasoning process benchmarks (ProcessBench, PRM800K, DeltaBench) demonstrate that our SPC progressively enhances its error detection capabilities (e.g., accuracy increases from 70.8% to 77.7% on ProcessBench) and surpasses strong baselines, including distilled R1 model. Furthermore, applying SPC to guide the test-time search of diverse LLMs significantly improves their mathematical reasoning performance on MATH500 and AIME2024, outperforming state-of-the-art process reward models.</p> - https://arxiv.org/abs/2504.19162 - Sun, 27 Apr 2025 08:45:06 +0000 + Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models + https://arxiv.org/abs/2504.20157 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2504.20157.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zae Myung Kim, Chanwoo Park, Vipul Raheja, Dongyeop Kang</p><p><b>Upvotes:</b> 28</p><p><b>Summary:</b> Reward-based alignment methods for large language models (LLMs) face two key limitations: vulnerability to reward hacking, where models exploit flaws in the reward signal; and reliance on brittle, labor-intensive prompt engineering when LLMs are used as reward models. We introduce Meta Policy Optimization (MPO), a framework that addresses these challenges by integrating a meta-reward model that dynamically refines the reward model's prompt throughout training. In MPO, the meta-reward model monitors the evolving training context and continuously adjusts the reward model's prompt to maintain high alignment, providing an adaptive reward signal that resists exploitation by the policy. This meta-learning approach promotes a more stable policy optimization, and greatly reduces the need for manual reward prompt design. It yields performance on par with or better than models guided by extensively hand-crafted reward prompts. Furthermore, we show that MPO maintains its effectiveness across diverse tasks, such as question answering and mathematical reasoning, without requiring specialized reward designs. Beyond standard RLAIF, MPO's meta-learning formulation is readily extensible to higher-level alignment frameworks. Overall, this method addresses theoretical and practical challenges in reward-based RL alignment for LLMs, paving the way for more robust and adaptable alignment strategies. The code and models will be publicly shared.</p> + https://arxiv.org/abs/2504.20157 + Mon, 28 Apr 2025 18:02:35 +0000 - ICL CIPHERS: Quantifying "Learning'' in In-Context Learning via Substitution Ciphers - https://arxiv.org/abs/2504.19395 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2504.19395.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhouxiang Fang, Aayush Mishra, Muhan Gao, Anqi Liu, Daniel Khashabi</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Recent works have suggested that In-Context Learning (ICL) operates in dual modes, i.e. task retrieval (remember learned patterns from pre-training) and task learning (inference-time ``learning'' from demonstrations). However, disentangling these the two modes remains a challenging goal. We introduce ICL CIPHERS, a class of task reformulations based on substitution ciphers borrowed from classic cryptography. In this approach, a subset of tokens in the in-context inputs are substituted with other (irrelevant) tokens, rendering English sentences less comprehensible to human eye. However, by design, there is a latent, fixed pattern to this substitution, making it reversible. This bijective (reversible) cipher ensures that the task remains a well-defined task in some abstract sense, despite the transformations. It is a curious question if LLMs can solve ICL CIPHERS with a BIJECTIVE mapping, which requires deciphering the latent cipher. We show that LLMs are better at solving ICL CIPHERS with BIJECTIVE mappings than the NON-BIJECTIVE (irreversible) baseline, providing a novel approach to quantify ``learning'' in ICL. While this gap is small, it is consistent across the board on four datasets and six models. Finally, we examine LLMs' internal representations and identify evidence in their ability to decode the ciphered inputs.</p> - https://arxiv.org/abs/2504.19395 - Mon, 28 Apr 2025 00:05:29 +0000 + Reinforcement Learning for Reasoning in Large Language Models with One Training Example + https://arxiv.org/abs/2504.20571 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2504.20571.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yiping Wang, Qing Yang, Zhiyuan Zeng, Liliang Ren, Lucas Liu, Baolin Peng, Hao Cheng, Xuehai He, Kuan Wang, Jianfeng Gao, Weizhu Chen, Shuohang Wang, Simon Shaolei Du, Yelong Shen</p><p><b>Upvotes:</b> 47</p><p><b>Summary:</b> We show that reinforcement learning with verifiable reward using one training example (1-shot RLVR) is effective in incentivizing the math reasoning capabilities of large language models (LLMs). Applying RLVR to the base model Qwen2.5-Math-1.5B, we identify a single example that elevates model performance on MATH500 from 36.0% to 73.6%, and improves the average performance across six common mathematical reasoning benchmarks from 17.6% to 35.7%. This result matches the performance obtained using the 1.2k DeepScaleR subset (MATH500: 73.6%, average: 35.9%), which includes the aforementioned example. Similar substantial improvements are observed across various models (Qwen2.5-Math-7B, Llama3.2-3B-Instruct, DeepSeek-R1-Distill-Qwen-1.5B), RL algorithms (GRPO and PPO), and different math examples (many of which yield approximately 30% or greater improvement on MATH500 when employed as a single training example). In addition, we identify some interesting phenomena during 1-shot RLVR, including cross-domain generalization, increased frequency of self-reflection, and sustained test performance improvement even after the training accuracy has saturated, a phenomenon we term post-saturation generalization. Moreover, we verify that the effectiveness of 1-shot RLVR primarily arises from the policy gradient loss, distinguishing it from the "grokking" phenomenon. We also show the critical role of promoting exploration (e.g., by adding entropy loss with an appropriate coefficient) in 1-shot RLVR training. As a bonus, we observe that applying entropy loss alone, without any outcome reward, significantly enhances Qwen2.5-Math-1.5B's performance on MATH500 by 27.4%. These findings can inspire future work on RLVR data efficiency and encourage a re-examination of both recent progress and the underlying mechanisms in RLVR. Our code, model, and data are open source at https://github.com/ypwang61/One-Shot-RLVR</p> + https://arxiv.org/abs/2504.20571 + Tue, 29 Apr 2025 09:24:30 +0000 - Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory - https://arxiv.org/abs/2504.19413 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2504.19413.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Prateek Chhikara, Dev Khant, Saket Aryan, Taranjeet Singh, Deshraj Yadav</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Large Language Models (LLMs) have demonstrated remarkable prowess in generating contextually coherent responses, yet their fixed context windows pose fundamental challenges for maintaining consistency over prolonged multi-session dialogues. We introduce Mem0, a scalable memory-centric architecture that addresses this issue by dynamically extracting, consolidating, and retrieving salient information from ongoing conversations. Building on this foundation, we further propose an enhanced variant that leverages graph-based memory representations to capture complex relational structures among conversational elements. Through comprehensive evaluations on LOCOMO benchmark, we systematically compare our approaches against six baseline categories: (i) established memory-augmented systems, (ii) retrieval-augmented generation (RAG) with varying chunk sizes and k-values, (iii) a full-context approach that processes the entire conversation history, (iv) an open-source memory solution, (v) a proprietary model system, and (vi) a dedicated memory management platform. Empirical results show that our methods consistently outperform all existing memory systems across four question categories: single-hop, temporal, multi-hop, and open-domain. Notably, Mem0 achieves 26% relative improvements in the LLM-as-a-Judge metric over OpenAI, while Mem0 with graph memory achieves around 2% higher overall score than the base configuration. Beyond accuracy gains, we also markedly reduce computational overhead compared to full-context method. In particular, Mem0 attains a 91% lower p95 latency and saves more than 90% token cost, offering a compelling balance between advanced reasoning capabilities and practical deployment constraints. Our findings highlight critical role of structured, persistent memory mechanisms for long-term conversational coherence, paving the way for more reliable and efficient LLM-driven AI agents.</p> - https://arxiv.org/abs/2504.19413 - Mon, 28 Apr 2025 01:46:35 +0000 + ReasonIR: Training Retrievers for Reasoning Tasks + https://arxiv.org/abs/2504.20595 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2504.20595.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Rulin Shao, Rui Qiao, Varsha Kishore, Niklas Muennighoff, Xi Victoria Lin, Daniela Rus, Bryan Kian Hsiang Low, Sewon Min, Wen-tau Yih, Pang Wei Koh, Luke Zettlemoyer</p><p><b>Upvotes:</b> 35</p><p><b>Summary:</b> We present ReasonIR-8B, the first retriever specifically trained for general reasoning tasks. Existing retrievers have shown limited gains on reasoning tasks, in part because existing training datasets focus on short factual queries tied to documents that straightforwardly answer them. We develop a synthetic data generation pipeline that, for each document, our pipeline creates a challenging and relevant query, along with a plausibly related but ultimately unhelpful hard negative. By training on a mixture of our synthetic data and existing public data, ReasonIR-8B achieves a new state-of-the-art of 29.9 nDCG@10 without reranker and 36.9 nDCG@10 with reranker on BRIGHT, a widely-used reasoning-intensive information retrieval (IR) benchmark. When applied to RAG tasks, ReasonIR-8B improves MMLU and GPQA performance by 6.4% and 22.6% respectively, relative to the closed-book baseline, outperforming other retrievers and search engines. In addition, ReasonIR-8B uses test-time compute more effectively: on BRIGHT, its performance consistently increases with longer and more information-rich rewritten queries; it continues to outperform other retrievers when combined with an LLM reranker. Our training recipe is general and can be easily extended to future LLMs; to this end, we open-source our code, data, and model.</p> + https://arxiv.org/abs/2504.20595 + Tue, 29 Apr 2025 09:49:28 +0000 - RepText: Rendering Visual Text via Replicating - https://arxiv.org/abs/2504.19724 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2504.19724.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haofan Wang, Yujia Xu, Yimeng Li, Junchen Li, Chaowei Zhang, Jing Wang, Kejia Yang, Zhibo Chen</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> Although contemporary text-to-image generation models have achieved remarkable breakthroughs in producing visually appealing images, their capacity to generate precise and flexible typographic elements, especially non-Latin alphabets, remains constrained. To address these limitations, we start from an naive assumption that text understanding is only a sufficient condition for text rendering, but not a necessary condition. Based on this, we present RepText, which aims to empower pre-trained monolingual text-to-image generation models with the ability to accurately render, or more precisely, replicate, multilingual visual text in user-specified fonts, without the need to really understand them. Specifically, we adopt the setting from ControlNet and additionally integrate language agnostic glyph and position of rendered text to enable generating harmonized visual text, allowing users to customize text content, font and position on their needs. To improve accuracy, a text perceptual loss is employed along with the diffusion loss. Furthermore, to stabilize rendering process, at the inference phase, we directly initialize with noisy glyph latent instead of random initialization, and adopt region masks to restrict the feature injection to only the text region to avoid distortion of the background. We conducted extensive experiments to verify the effectiveness of our RepText relative to existing works, our approach outperforms existing open-source methods and achieves comparable results to native multi-language closed-source models. To be more fair, we also exhaustively discuss its limitations in the end.</p> - https://arxiv.org/abs/2504.19724 - Mon, 28 Apr 2025 12:19:53 +0000 + ISDrama: Immersive Spatial Drama Generation through Multimodal Prompting + https://arxiv.org/abs/2504.20630 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2504.20630.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yu Zhang, Wenxiang Guo, Changhao Pan, Zhiyuan Zhu, Tao Jin, Zhou Zhao</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Multimodal immersive spatial drama generation focuses on creating continuous multi-speaker binaural speech with dramatic prosody based on multimodal prompts, with potential applications in AR, VR, and others. This task requires simultaneous modeling of spatial information and dramatic prosody based on multimodal inputs, with high data collection costs. To the best of our knowledge, our work is the first attempt to address these challenges. We construct MRSDrama, the first multimodal recorded spatial drama dataset, containing binaural drama audios, scripts, videos, geometric poses, and textual prompts. Then, we propose ISDrama, the first immersive spatial drama generation model through multimodal prompting. ISDrama comprises these primary components: 1) Multimodal Pose Encoder, based on contrastive learning, considering the Doppler effect caused by moving speakers to extract unified pose information from multimodal prompts. 2) Immersive Drama Transformer, a flow-based mamba-transformer model that generates high-quality drama, incorporating Drama-MOE to select proper experts for enhanced prosody and pose control. We also design a context-consistent classifier-free guidance strategy to coherently generate complete drama. Experimental results show that ISDrama outperforms baseline models on objective and subjective metrics. The demos and dataset are available at https://aaronz345.github.io/ISDramaDemo.</p> + https://arxiv.org/abs/2504.20630 + Tue, 29 Apr 2025 10:56:44 +0000 - LLM-Powered GUI Agents in Phone Automation: Surveying Progress and Prospects - https://arxiv.org/abs/2504.19838 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2504.19838.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Guangyi Liu, Pengxiang Zhao, Liang Liu, Yaxuan Guo, Han Xiao, Weifeng Lin, Yuxiang Chai, Yue Han, Shuai Ren, Hao Wang, Xiaoyu Liang, Wenhao Wang, Tianze Wu, Linghao Li, Hao Wang, Guanjing Xiong, Yong Liu, Hongsheng Li</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> With the rapid rise of large language models (LLMs), phone automation has undergone transformative changes. This paper systematically reviews LLM-driven phone GUI agents, highlighting their evolution from script-based automation to intelligent, adaptive systems. We first contextualize key challenges, (i) limited generality, (ii) high maintenance overhead, and (iii) weak intent comprehension, and show how LLMs address these issues through advanced language understanding, multimodal perception, and robust decision-making. We then propose a taxonomy covering fundamental agent frameworks (single-agent, multi-agent, plan-then-act), modeling approaches (prompt engineering, training-based), and essential datasets and benchmarks. Furthermore, we detail task-specific architectures, supervised fine-tuning, and reinforcement learning strategies that bridge user intent and GUI operations. Finally, we discuss open challenges such as dataset diversity, on-device deployment efficiency, user-centric adaptation, and security concerns, offering forward-looking insights into this rapidly evolving field. By providing a structured overview and identifying pressing research gaps, this paper serves as a definitive reference for researchers and practitioners seeking to harness LLMs in designing scalable, user-friendly phone GUI agents.</p> - https://arxiv.org/abs/2504.19838 - Mon, 28 Apr 2025 14:39:25 +0000 + In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer + https://arxiv.org/abs/2504.20690 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2504.20690.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zechuan Zhang, Ji Xie, Yu Lu, Zongxin Yang, Yi Yang</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Instruction-based image editing enables robust image modification via natural language prompts, yet current methods face a precision-efficiency tradeoff. Fine-tuning methods demand significant computational resources and large datasets, while training-free techniques struggle with instruction comprehension and edit quality. We resolve this dilemma by leveraging large-scale Diffusion Transformer (DiT)' enhanced generation capacity and native contextual awareness. Our solution introduces three contributions: (1) an in-context editing framework for zero-shot instruction compliance using in-context prompting, avoiding structural changes; (2) a LoRA-MoE hybrid tuning strategy that enhances flexibility with efficient adaptation and dynamic expert routing, without extensive retraining; and (3) an early filter inference-time scaling method using vision-language models (VLMs) to select better initial noise early, improving edit quality. Extensive evaluations demonstrate our method's superiority: it outperforms state-of-the-art approaches while requiring only 0.5% training data and 1% trainable parameters compared to conventional baselines. This work establishes a new paradigm that enables high-precision yet efficient instruction-guided editing. Codes and demos can be found in https://river-zhang.github.io/ICEdit-gh-pages/.</p> + https://arxiv.org/abs/2504.20690 + Tue, 29 Apr 2025 12:14:47 +0000 - NORA: A Small Open-Sourced Generalist Vision Language Action Model for Embodied Tasks - https://arxiv.org/abs/2504.19854 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2504.19854.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chia-Yu Hung, Qi Sun, Pengfei Hong, Amir Zadeh, Chuan Li, U-Xuan Tan, Navonil Majumder, Soujanya Poria</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Existing Visual-Language-Action (VLA) models have shown promising performance in zero-shot scenarios, demonstrating impressive task execution and reasoning capabilities. However, a significant challenge arises from the limitations of visual encoding, which can result in failures during tasks such as object grasping. Moreover, these models typically suffer from high computational overhead due to their large sizes, often exceeding 7B parameters. While these models excel in reasoning and task planning, the substantial computational overhead they incur makes them impractical for real-time robotic environments, where speed and efficiency are paramount. To address the limitations of existing VLA models, we propose NORA, a 3B-parameter model designed to reduce computational overhead while maintaining strong task performance. NORA adopts the Qwen-2.5-VL-3B multimodal model as its backbone, leveraging its superior visual-semantic understanding to enhance visual reasoning and action grounding. Additionally, our is trained on 970k real-world robot demonstrations and equipped with the FAST+ tokenizer for efficient action sequence generation. Experimental results demonstrate that NORA outperforms existing large-scale VLA models, achieving better task performance with significantly reduced computational overhead, making it a more practical solution for real-time robotic autonomy.</p> - https://arxiv.org/abs/2504.19854 - Mon, 28 Apr 2025 14:47:34 +0000 + UniversalRAG: Retrieval-Augmented Generation over Multiple Corpora with Diverse Modalities and Granularities + https://arxiv.org/abs/2504.20734 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2504.20734.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Woongyeong Yeo, Kangsan Kim, Soyeong Jeong, Jinheon Baek, Sung Ju Hwang</p><p><b>Upvotes:</b> 42</p><p><b>Summary:</b> Retrieval-Augmented Generation (RAG) has shown substantial promise in improving factual accuracy by grounding model responses with external knowledge relevant to queries. However, most existing RAG approaches are limited to a text-only corpus, and while recent efforts have extended RAG to other modalities such as images and videos, they typically operate over a single modality-specific corpus. In contrast, real-world queries vary widely in the type of knowledge they require, which a single type of knowledge source cannot address. To address this, we introduce UniversalRAG, a novel RAG framework designed to retrieve and integrate knowledge from heterogeneous sources with diverse modalities and granularities. Specifically, motivated by the observation that forcing all modalities into a unified representation space derived from a single combined corpus causes a modality gap, where the retrieval tends to favor items from the same modality as the query, we propose a modality-aware routing mechanism that dynamically identifies the most appropriate modality-specific corpus and performs targeted retrieval within it. Also, beyond modality, we organize each modality into multiple granularity levels, enabling fine-tuned retrieval tailored to the complexity and scope of the query. We validate UniversalRAG on 8 benchmarks spanning multiple modalities, showing its superiority over modality-specific and unified baselines.</p> + https://arxiv.org/abs/2504.20734 + Tue, 29 Apr 2025 13:18:58 +0000 + + + Chain-of-Defensive-Thought: Structured Reasoning Elicits Robustness in Large Language Models against Reference Corruption + https://arxiv.org/abs/2504.20769 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2504.20769.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wenxiao Wang, Parsa Hosseini, Soheil Feizi</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Chain-of-thought prompting has demonstrated great success in facilitating the reasoning abilities of large language models. In this work, we explore how these enhanced reasoning abilities can be exploited to improve the robustness of large language models in tasks that are not necessarily reasoning-focused. In particular, we show how a wide range of large language models exhibit significantly improved robustness against reference corruption using a simple method called chain-of-defensive-thought, where only a few exemplars with structured and defensive reasoning are provided as demonstrations. Empirically, the improvements can be astounding, especially given the simplicity and applicability of the method. For example, in the Natural Questions task, the accuracy of GPT-4o degrades from 60% to as low as 3% with standard prompting when 1 out of 10 references provided is corrupted with prompt injection attacks. In contrast, GPT-4o using chain-of-defensive-thought prompting maintains an accuracy of 50%.</p> + https://arxiv.org/abs/2504.20769 + Tue, 29 Apr 2025 13:50:05 +0000 + + + The Leaderboard Illusion + https://arxiv.org/abs/2504.20879 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2504.20879.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shivalika Singh, Yiyang Nan, Alex Wang, Daniel D'Souza, Sayash Kapoor, Ahmet Üstün, Sanmi Koyejo, Yuntian Deng, Shayne Longpre, Noah Smith, Beyza Ermis, Marzieh Fadaee, Sara Hooker</p><p><b>Upvotes:</b> 33</p><p><b>Summary:</b> Measuring progress is fundamental to the advancement of any scientific field. As benchmarks play an increasingly central role, they also grow more susceptible to distortion. Chatbot Arena has emerged as the go-to leaderboard for ranking the most capable AI systems. Yet, in this work we identify systematic issues that have resulted in a distorted playing field. We find that undisclosed private testing practices benefit a handful of providers who are able to test multiple variants before public release and retract scores if desired. We establish that the ability of these providers to choose the best score leads to biased Arena scores due to selective disclosure of performance results. At an extreme, we identify 27 private LLM variants tested by Meta in the lead-up to the Llama-4 release. We also establish that proprietary closed models are sampled at higher rates (number of battles) and have fewer models removed from the arena than open-weight and open-source alternatives. Both these policies lead to large data access asymmetries over time. Providers like Google and OpenAI have received an estimated 19.2% and 20.4% of all data on the arena, respectively. In contrast, a combined 83 open-weight models have only received an estimated 29.7% of the total data. We show that access to Chatbot Arena data yields substantial benefits; even limited additional data can result in relative performance gains of up to 112% on the arena distribution, based on our conservative estimates. Together, these dynamics result in overfitting to Arena-specific dynamics rather than general model quality. The Arena builds on the substantial efforts of both the organizers and an open community that maintains this valuable evaluation platform. We offer actionable recommendations to reform the Chatbot Arena's evaluation framework and promote fairer, more transparent benchmarking for the field</p> + https://arxiv.org/abs/2504.20879 + Tue, 29 Apr 2025 15:48:49 +0000 + + + TesserAct: Learning 4D Embodied World Models + https://arxiv.org/abs/2504.20995 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2504.20995.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haoyu Zhen, Qiao Sun, Hongxin Zhang, Junyan Li, Siyuan Zhou, Yilun Du, Chuang Gan</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> This paper presents an effective approach for learning novel 4D embodied world models, which predict the dynamic evolution of 3D scenes over time in response to an embodied agent's actions, providing both spatial and temporal consistency. We propose to learn a 4D world model by training on RGB-DN (RGB, Depth, and Normal) videos. This not only surpasses traditional 2D models by incorporating detailed shape, configuration, and temporal changes into their predictions, but also allows us to effectively learn accurate inverse dynamic models for an embodied agent. Specifically, we first extend existing robotic manipulation video datasets with depth and normal information leveraging off-the-shelf models. Next, we fine-tune a video generation model on this annotated dataset, which jointly predicts RGB-DN (RGB, Depth, and Normal) for each frame. We then present an algorithm to directly convert generated RGB, Depth, and Normal videos into a high-quality 4D scene of the world. Our method ensures temporal and spatial coherence in 4D scene predictions from embodied scenarios, enables novel view synthesis for embodied environments, and facilitates policy learning that significantly outperforms those derived from prior video-based world models.</p> + https://arxiv.org/abs/2504.20995 + Tue, 29 Apr 2025 17:59:30 +0000 + + + X-Fusion: Introducing New Modality to Frozen Large Language Models + https://arxiv.org/abs/2504.20996 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2504.20996.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sicheng Mo, Thao Nguyen, Xun Huang, Siddharth Srinivasan Iyer, Yijun Li, Yuchen Liu, Abhishek Tandon, Eli Shechtman, Krishna Kumar Singh, Yong Jae Lee, Bolei Zhou, Yuheng Li</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> We propose X-Fusion, a framework that extends pretrained Large Language Models (LLMs) for multimodal tasks while preserving their language capabilities. X-Fusion employs a dual-tower design with modality-specific weights, keeping the LLM's parameters frozen while integrating vision-specific information for both understanding and generation. Our experiments demonstrate that X-Fusion consistently outperforms alternative architectures on both image-to-text and text-to-image tasks. We find that incorporating understanding-focused data improves generation quality, reducing image data noise enhances overall performance, and feature alignment accelerates convergence for smaller models but has minimal impact on larger ones. Our findings provide valuable insights into building efficient unified multimodal models.</p> + https://arxiv.org/abs/2504.20996 + Tue, 29 Apr 2025 17:59:45 +0000 + + + YoChameleon: Personalized Vision and Language Generation + https://arxiv.org/abs/2504.20998 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2504.20998.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Thao Nguyen, Krishna Kumar Singh, Jing Shi, Trung Bui, Yong Jae Lee, Yuheng Li</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Large Multimodal Models (e.g., GPT-4, Gemini, Chameleon) have evolved into powerful tools with millions of users. However, they remain generic models and lack personalized knowledge of specific user concepts. Previous work has explored personalization for text generation, yet it remains unclear how these methods can be adapted to new modalities, such as image generation. In this paper, we introduce Yo'Chameleon, the first attempt to study personalization for large multimodal models. Given 3-5 images of a particular concept, Yo'Chameleon leverages soft-prompt tuning to embed subject-specific information to (i) answer questions about the subject and (ii) recreate pixel-level details to produce images of the subject in new contexts. Yo'Chameleon is trained with (i) a self-prompting optimization mechanism to balance performance across multiple modalities, and (ii) a ``soft-positive" image generation approach to enhance image quality in a few-shot setting.</p> + https://arxiv.org/abs/2504.20998 + Tue, 29 Apr 2025 17:59:57 +0000