bot: update RSS feed
This commit is contained in:
github-actions[bot]
407
feed.xml
407
feed.xml
@@ -7,209 +7,314 @@
|
|||||||
<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>Fri, 03 Apr 2026 00:07:11 +0000</lastBuildDate>
|
<lastBuildDate>Sat, 04 Apr 2026 00:06:15 +0000</lastBuildDate>
|
||||||
<item>
|
<item>
|
||||||
<title>Brevity Constraints Reverse Performance Hierarchies in Language Models</title>
|
<title>Working Notes on Late Interaction Dynamics: Analyzing Targeted Behaviors of Late Interaction Models</title>
|
||||||
<link>https://arxiv.org/abs/2604.00025</link>
|
<link>https://arxiv.org/abs/2603.26259</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.00025.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> MD Azizul Hakim</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> Standard evaluation protocols reveal a counterintuitive phenomenon: on 7.7% of benchmark problems spanning five datasets, larger language models underperform smaller ones by 28.4 percentage points despite 10-100x more parameters. Through systematic evaluation of 31 models (0.5B-405B parameters) across 1,485 problems, we identify the mechanism as spontaneous scale-dependent verbosity that introduces errors through overelaboration. Causal intervention experiments demonstrate this reflects correctable prompt design rather than fundamental capability limitations. Constraining large models to produce brief responses improves accuracy by 26 percentage points and reduces performance gaps by up to two-thirds. Most critically, brevity constraints completely reverse performance hierarchies on mathematical reasoning and scientific knowledge benchmarks, with large models achieving 7.7-15.9 percentage point advantages over small models -- direct inversions of the original gaps. These reversals prove large models possess superior latent capabilities that universal prompting masks. We validate findings through three independent contamination tests and demonstrate inverse scaling operates continuously across the full parameter spectrum, with dataset-specific optimal scales ranging from 0.5B to 3.0B parameters. Our results establish that maximizing large model performance requires scale-aware prompt engineering rather than universal evaluation protocols, with immediate implications for deployment: prompt adaptation simultaneously improves accuracy and reduces computational costs.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.26259.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Antoine Edy, Max Conti, Quentin Macé</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> While Late Interaction models exhibit strong retrieval performance, many of their underlying dynamics remain understudied, potentially hiding performance bottlenecks. In this work, we focus on two topics in Late Interaction retrieval: a length bias that arises when using multi-vector scoring, and the similarity distribution beyond the best scores pooled by the MaxSim operator. We analyze these behaviors for state-of-the-art models on the NanoBEIR benchmark. Results show that while the theoretical length bias of causal Late Interaction models holds in practice, bi-directional models can also suffer from it in extreme cases. We also note that no significant similarity trend lies beyond the top-1 document token, validating that the MaxSim operator efficiently exploits the token-level similarity scores.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.00025</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.26259</guid>
|
||||||
<pubDate>Wed, 11 Mar 2026 06:47:41 +0000</pubDate>
|
<pubDate>Fri, 27 Mar 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>AI Generalisation Gap In Comorbid Sleep Disorder Staging</title>
|
<title>DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models</title>
|
||||||
<link>https://arxiv.org/abs/2603.23582</link>
|
<link>https://arxiv.org/abs/2603.26164</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.23582.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Saswata Bose, Suvadeep Maiti, Shivam Kumar Sharma, Mythirayee S, Tapabrata Chakraborti, Srijitesh Rajendran, Raju S. Bapi</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Accurate sleep staging is essential for diagnosing OSA and hypopnea in stroke patients. Although PSG is reliable, it is costly, labor-intensive, and manually scored. While deep learning enables automated EEG-based sleep staging in healthy subjects, our analysis shows poor generalization to clinical populations with disrupted sleep. Using Grad-CAM interpretations, we systematically demonstrate this limitation. We introduce iSLEEPS, a newly clinically annotated ischemic stroke dataset (to be publicly released), and evaluate a SE-ResNet plus bidirectional LSTM model for single-channel EEG sleep staging. As expected, cross-domain performance between healthy and diseased subjects is poor. Attention visualizations, supported by clinical expert feedback, show the model focuses on physiologically uninformative EEG regions in patient data. Statistical and computational analyses further confirm significant sleep architecture differences between healthy and ischemic stroke cohorts, highlighting the need for subject-aware or disease-specific models with clinical validation before deployment. A summary of the paper and the code is available at https://himalayansaswatabose.github.io/iSLEEPS_Explainability.github.io/</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.26164.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hao Liang, Zhengyang Zhao, Meiyi Qiang, Mingrui Chen, Lu Ma, Rongyi Yu, Hengyi Feng, Shixuan Sun, Zimo Meng, Xiaochen Ma, Xuanlin Yang, Qifeng Cai, Ruichuan An, Bohan Zeng, Zhen Hao Wong, Chengyu Shen, Runming He, Zhaoyang Han, Yaowei Zheng, Fangcheng Fu, Conghui He, Bin Cui, Zhiyu Li, Weinan E, Wentao Zhang</p><p><b>Upvotes:</b> 139</p><p><b>Summary:</b> Data-centric training has emerged as a promising direction for improving large language models (LLMs) by optimizing not only model parameters but also the selection, composition, and weighting of training data during optimization. However, existing approaches to data selection, data mixture optimization, and data reweighting are often developed in isolated codebases with inconsistent interfaces, hindering reproducibility, fair comparison, and practical integration. In this paper, we present DataFlex, a unified data-centric dynamic training framework built upon LLaMA-Factory. DataFlex supports three major paradigms of dynamic data optimization: sample selection, domain mixture adjustment, and sample reweighting, while remaining fully compatible with the original training workflow. It provides extensible trainer abstractions and modular components, enabling a drop-in replacement for standard LLM training, and unifies key model-dependent operations such as embedding extraction, inference, and gradient computation, with support for large-scale settings including DeepSpeed ZeRO-3. We conduct comprehensive experiments across multiple data-centric methods. Dynamic data selection consistently outperforms static full-data training on MMLU across both Mistral-7B and Llama-3.2-3B. For data mixture, DoReMi and ODM improve both MMLU accuracy and corpus-level perplexity over default proportions when pretraining Qwen2.5-1.5B on SlimPajama at 6B and 30B token scales. DataFlex also achieves consistent runtime improvements over original implementations. These results demonstrate that DataFlex provides an effective, efficient, and reproducible infrastructure for data-centric dynamic training of LLMs.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.23582</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.26164</guid>
|
||||||
<pubDate>Tue, 24 Mar 2026 15:02:35 +0000</pubDate>
|
<pubDate>Fri, 27 Mar 2026 08:28:02 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>ClawKeeper: Comprehensive Safety Protection for OpenClaw Agents Through Skills, Plugins, and Watchers</title>
|
<title>Ask or Assume? Uncertainty-Aware Clarification-Seeking in Coding Agents</title>
|
||||||
<link>https://arxiv.org/abs/2603.24414</link>
|
<link>https://arxiv.org/abs/2603.26233</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.24414.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Songyang Liu, Chaozhuo Li, Chenxu Wang, Jinyu Hou, Zejian Chen, Litian Zhang, Zheng Liu, Qiwei Ye, Yiming Hei, Xi Zhang, Zhongyuan Wang</p><p><b>Upvotes:</b> 166</p><p><b>Summary:</b> OpenClaw has rapidly established itself as a leading open-source autonomous agent runtime, offering powerful capabilities including tool integration, local file access, and shell command execution. However, these broad operational privileges introduce critical security vulnerabilities, transforming model errors into tangible system-level threats such as sensitive data leakage, privilege escalation, and malicious third-party skill execution. Existing security measures for the OpenClaw ecosystem remain highly fragmented, addressing only isolated stages of the agent lifecycle rather than providing holistic protection. To bridge this gap, we present ClawKeeper, a real-time security framework that integrates multi-dimensional protection mechanisms across three complementary architectural layers. (1) Skill-based protection operates at the instruction level, injecting structured security policies directly into the agent context to enforce environment-specific constraints and cross-platform boundaries. (2) Plugin-based protection serves as an internal runtime enforcer, providing configuration hardening, proactive threat detection, and continuous behavioral monitoring throughout the execution pipeline. (3) Watcher-based protection introduces a novel, decoupled system-level security middleware that continuously verifies agent state evolution. It enables real-time execution intervention without coupling to the agent's internal logic, supporting operations such as halting high-risk actions or enforcing human confirmation. We argue that this Watcher paradigm holds strong potential to serve as a foundational building block for securing next-generation autonomous agent systems. Extensive qualitative and quantitative evaluations demonstrate the effectiveness and robustness of ClawKeeper across diverse threat scenarios. We release our code.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.26233.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Nicholas Edwards, Sebastian Schuster</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> As Large Language Model (LLM) agents are increasingly deployed in open-ended domains like software engineering, they frequently encounter underspecified instructions that lack crucial context. While human developers naturally resolve underspecification by asking clarifying questions, current agents are largely optimized for autonomous execution. In this work, we systematically evaluate the clarification-seeking abilities of LLM agents on an underspecified variant of SWE-bench Verified. We propose an uncertainty-aware multi-agent scaffold that explicitly decouples underspecification detection from code execution. Our results demonstrate that this multi-agent system using OpenHands + Claude Sonnet 4.5 achieves a 69.40% task resolve rate, significantly outperforming a standard single-agent setup (61.20%) and closing the performance gap with agents operating on fully specified instructions. Furthermore, we find that the multi-agent system exhibits well-calibrated uncertainty, conserving queries on simple tasks while proactively seeking information on more complex issues. These findings indicate that current models can be turned into proactive collaborators, where agents independently recognize when to ask questions to elicit missing information in real-world, underspecified tasks.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.24414</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.26233</guid>
|
||||||
<pubDate>Wed, 25 Mar 2026 15:27:54 +0000</pubDate>
|
<pubDate>Fri, 27 Mar 2026 09:56:26 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Consistency Amplifies: How Behavioral Variance Shapes Agent Accuracy</title>
|
<title>Gated Condition Injection without Multimodal Attention: Towards Controllable Linear-Attention Transformers</title>
|
||||||
<link>https://arxiv.org/abs/2603.25764</link>
|
<link>https://arxiv.org/abs/2603.27666</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.25764.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Aman Mehta</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> As LLM-based agents are deployed in production systems, understanding their behavioral consistency (whether they produce similar action sequences when given identical tasks) becomes critical for reliability. We study consistency in the context of SWE-bench, a challenging software engineering benchmark requiring complex, multi-step reasoning. Comparing Claude~4.5~Sonnet, GPT-5, and Llama-3.1-70B across 50 runs each (10 tasks times 5 runs), we find that across models, higher consistency aligns with higher accuracy: Claude achieves the lowest variance (CV: 15.2\%) and highest accuracy (58\%), GPT-5 is intermediate (CV: 32.2\%, accuracy: 32\%), and Llama shows the highest variance (CV: 47.0\%) with lowest accuracy (4\%). However, within a model, consistency can amplify both correct and incorrect interpretations. Our analysis reveals a critical nuance: consistency amplifies outcomes rather than guaranteeing correctness. 71\% of Claude's failures stem from "consistent wrong interpretation": making the same incorrect assumption across all runs. Interestingly, GPT-5 achieves similar early strategic agreement as Claude (diverging at step 3.4 vs.\ 3.2) but exhibits 2.1times higher variance, suggesting that divergence timing alone does not determine consistency. These findings suggest that for production deployment, interpretation accuracy matters more than execution consistency, with implications for agent evaluation and training.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.27666.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuhe Liu, Zhenxiong Tan, Yujia Hu, Songhua Liu, Xinchao Wang</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Recent advances in diffusion-based controllable visual generation have led to remarkable improvements in image quality. However, these powerful models are typically deployed on cloud servers due to their large computational demands, raising serious concerns about user data privacy. To enable secure and efficient on-device generation, we explore in this paper controllable diffusion models built upon linear attention architectures, which offer superior scalability and efficiency, even on edge devices. Yet, our experiments reveal that existing controllable generation frameworks, such as ControlNet and OminiControl, either lack the flexibility to support multiple heterogeneous condition types or suffer from slow convergence on such linear-attention models. To address these limitations, we propose a novel controllable diffusion framework tailored for linear attention backbones like SANA. The core of our method lies in a unified gated conditioning module working in a dual-path pipeline, which effectively integrates multi-type conditional inputs, such as spatially aligned and non-aligned cues. Extensive experiments on multiple tasks and benchmarks demonstrate that our approach achieves state-of-the-art controllable generation performance based on linear-attention models, surpassing existing methods in terms of fidelity and controllability.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.25764</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.27666</guid>
|
||||||
<pubDate>Thu, 26 Mar 2026 00:00:00 +0000</pubDate>
|
<pubDate>Sun, 29 Mar 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>MMaDA-VLA: Large Diffusion Vision-Language-Action Model with Unified Multi-Modal Instruction and Generation</title>
|
<title>MultiGen: Level-Design for Editable Multiplayer Worlds in Diffusion Game Engines</title>
|
||||||
<link>https://arxiv.org/abs/2603.25406</link>
|
<link>https://arxiv.org/abs/2603.06679</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.25406.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yang Liu, Pengxiang Ding, Tengyue Jiang, Xudong Wang, Wenxuan Song, Minghui Lin, Han Zhao, Hongyin Zhang, Zifeng Zhuang, Wei Zhao, Siteng Huang, Jinkui Shi, Donglin Wang</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Vision-Language-Action (VLA) models aim to control robots for manipulation from visual observations and natural-language instructions. However, existing hierarchical and autoregressive paradigms often introduce architectural overhead, suffer from temporal inconsistency and long-horizon error accumulation, and lack a mechanism to capture environment dynamics without extra modules. To this end, we present MMaDA-VLA, a fully native pre-trained large diffusion VLA model that unifies multi-modal understanding and generation in a single framework. Our key idea is a native discrete diffusion formulation that embeds language, images, and continuous robot controls into one discrete token space and trains a single backbone with masked token denoising to jointly generate a future goal observation and an action chunk in parallel. Iterative denoising enables global, order-free refinement, improving long-horizon consistency while grounding actions in predicted future visual outcomes without auxiliary world models. Experiments across simulation benchmarks and real-world tasks show state-of-the-art performance, achieving 98.0% average success on LIBERO and 4.78 average length on CALVIN.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.06679.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ryan Po, David Junhao Zhang, Amir Hertz, Gordon Wetzstein, Neal Wadhwa, Nataniel Ruiz</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Video world models have shown immense promise for interactive simulation and entertainment, but current systems still struggle with two important aspects of interactivity: user control over the environment for reproducible, editable experiences, and shared inference where players hold influence over a common world. To address these limitations, we introduce an explicit external memory into the system, a persistent state operating independent of the model's context window, that is continually updated by user actions and queried throughout the generation roll-out. Unlike conventional diffusion game engines that operate as next-frame predictors, our approach decomposes generation into Memory, Observation, and Dynamics modules. This design gives users direct, editable control over environment structure via an editable memory representation, and it naturally extends to real-time multiplayer rollouts with coherent viewpoints and consistent cross-player interactions.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.25406</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.06679</guid>
|
||||||
<pubDate>Thu, 26 Mar 2026 12:55:51 +0000</pubDate>
|
<pubDate>Mon, 30 Mar 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>ViGoR-Bench: How Far Are Visual Generative Models From Zero-Shot Visual Reasoners?</title>
|
<title>An Empirical Recipe for Universal Phone Recognition</title>
|
||||||
<link>https://arxiv.org/abs/2603.25823</link>
|
<link>https://arxiv.org/abs/2603.29042</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.25823.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haonan Han, Jiancheng Huang, Xiaopeng Sun, Junyan He, Rui Yang, Jie Hu, Xiaojiang Peng, Lin Ma, Xiaoming Wei, Xiu Li</p><p><b>Upvotes:</b> 36</p><p><b>Summary:</b> Beneath the stunning visual fidelity of modern AIGC models lies a "logical desert", where systems fail tasks that require physical, causal, or complex spatial reasoning. Current evaluations largely rely on superficial metrics or fragmented benchmarks, creating a ``performance mirage'' that overlooks the generative process. To address this, we introduce ViGoR Vision-G}nerative Reasoning-centric Benchmark), a unified framework designed to dismantle this mirage. ViGoR distinguishes itself through four key innovations: 1) holistic cross-modal coverage bridging Image-to-Image and Video tasks; 2) a dual-track mechanism evaluating both intermediate processes and final results; 3) an evidence-grounded automated judge ensuring high human alignment; and 4) granular diagnostic analysis that decomposes performance into fine-grained cognitive dimensions. Experiments on over 20 leading models reveal that even state-of-the-art systems harbor significant reasoning deficits, establishing ViGoR as a critical ``stress test'' for the next generation of intelligent vision models. The demo have been available at https://vincenthancoder.github.io/ViGoR-Bench/</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.29042.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shikhar Bharadwaj, Chin-Jou Li, Kwanghee Choi, Eunjung Yeo, William Chen, Shinji Watanabe, David R. Mortensen</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Phone recognition (PR) is a key enabler of multilingual and low-resource speech processing tasks, yet robust performance remains elusive. Highly performant English-focused models do not generalize across languages, while multilingual models underutilize pretrained representations. It also remains unclear how data scale, architecture, and training objective contribute to multilingual PR. We present PhoneticXEUS -- trained on large-scale multilingual data and achieving state-of-the-art performance on both multilingual (17.7% PFER) and accented English speech (10.6% PFER). Through controlled ablations with evaluations across 100+ languages under a unified scheme, we empirically establish our training recipe and quantify the impact of SSL representations, data scale, and loss objectives. In addition, we analyze error patterns across language families, accented speech, and articulatory features. All data and code are released openly.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.25823</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.29042</guid>
|
||||||
<pubDate>Thu, 26 Mar 2026 18:40:09 +0000</pubDate>
|
<pubDate>Mon, 30 Mar 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>QuitoBench: A High-Quality Open Time Series Forecasting Benchmark</title>
|
<title>Memory-Augmented Vision-Language Agents for Persistent and Semantically Consistent Object Captioning</title>
|
||||||
<link>https://arxiv.org/abs/2603.26017</link>
|
<link>https://arxiv.org/abs/2603.24257</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.26017.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Siqiao Xue, Zhaoyang Zhu, Wei Zhang, Rongyao Cai, Rui Wang, Yixiang Mu, Fan Zhou, Jianguo Li, Peng Di, Hang Yu</p><p><b>Upvotes:</b> 25</p><p><b>Summary:</b> Time series forecasting is critical across finance, healthcare, and cloud computing, yet progress is constrained by a fundamental bottleneck: the scarcity of large-scale, high-quality benchmarks. To address this gap, we introduce QuitoBench, a regime-balanced benchmark for time series forecasting with coverage across eight trendtimesseasonalitytimesforecastability (TSF) regimes, designed to capture forecasting-relevant properties rather than application-defined domain labels. The benchmark is built upon Quito, a billion-scale time series corpus of application traffic from Alipay spanning nine business domains. Benchmarking 10 models from deep learning, foundation models, and statistical baselines across 232,200 evaluation instances, we report four key findings: (i) a context-length crossover where deep learning models lead at short context (L=96) but foundation models dominate at long context (L ge 576); (ii) forecastability is the dominant difficulty driver, producing a 3.64 times MAE gap across regimes; (iii) deep learning models match or surpass foundation models at 59 times fewer parameters; and (iv) scaling the amount of training data provides substantially greater benefit than scaling model size for both model families. These findings are validated by strong cross-benchmark and cross-metric consistency. Our open-source release enables reproducible, regime-aware evaluation for time series forecasting research.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.24257.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tommaso Galliena, Stefano Rosa, Tommaso Apicella, Pietro Morerio, Alessio Del Bue, Lorenzo Natale</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Vision-Language Models (VLMs) often yield inconsistent descriptions of the same object across viewpoints, hindering the ability of embodied agents to construct consistent semantic representations over time. Previous methods resolved inconsistencies using offline multi-view aggregation or multi-stage pipelines that decouple exploration, data association, and caption learning, with limited capacity to reason over previously observed objects. In this paper, we introduce a unified, memory-augmented Vision-Language agent that simultaneously handles data association, object captioning, and exploration policy within a single autoregressive framework. The model processes the current RGB observation, a top-down explored map, and an object-level episodic memory serialized into object-level tokens, ensuring persistent object identity and semantic consistency across extended sequences. To train the model in a self-supervised manner, we collect a dataset in photorealistic 3D environments using a disagreement-based policy and a pseudo-captioning model that enforces consistency across multi-view caption histories. Extensive evaluation on a manually annotated object-level test set, demonstrate improvements of up to +11.86% in standard captioning scores and +7.39% in caption self-similarity over baseline models, while enabling scalable performance through a compact scene representation. Code, model weights, and data are available at https://hsp-iit.github.io/epos-vlm/.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.26017</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.24257</guid>
|
||||||
<pubDate>Fri, 27 Mar 2026 02:24:34 +0000</pubDate>
|
<pubDate>Mon, 30 Mar 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Vision2Web: A Hierarchical Benchmark for Visual Website Development with Agent Verification</title>
|
<title>MDPBench: A Benchmark for Multilingual Document Parsing in Real-World Scenarios</title>
|
||||||
<link>https://arxiv.org/abs/2603.26648</link>
|
<link>https://arxiv.org/abs/2603.28130</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.26648.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zehai He, Wenyi Hong, Zhen Yang, Ziyang Pan, Mingdao Liu, Xiaotao Gu, Jie Tang</p><p><b>Upvotes:</b> 32</p><p><b>Summary:</b> Recent advances in large language models have improved the capabilities of coding agents, yet systematic evaluation of complex, end-to-end website development remains limited. To address this gap, we introduce Vision2Web, a hierarchical benchmark for visual website development, spanning from static UI-to-code generation, interactive multi-page frontend reproduction, to long-horizon full-stack website development. The benchmark is constructed from real-world websites and comprises a total of 193 tasks across 16 categories, with 918 prototype images and 1,255 test cases. To support flexible, thorough and reliable evaluation, we propose workflow-based agent verification paradigm based on two complementary components: a GUI agent verifier and a VLM-based judge. We evaluate multiple visual language models instantiated under different coding-agent frameworks, revealing substantial performance gaps at all task levels, with state-of-the-art models still struggling on full-stack development.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.28130.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhang Li, Zhibo Lin, Qiang Liu, Ziyang Zhang, Shuo Zhang, Zidun Guo, Jiajun Song, Jiarui Zhang, Xiang Bai, Yuliang Liu</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> We introduce Multilingual Document Parsing Benchmark, the first benchmark for multilingual digital and photographed document parsing. Document parsing has made remarkable strides, yet almost exclusively on clean, digital, well-formatted pages in a handful of dominant languages. No systematic benchmark exists to evaluate how models perform on digital and photographed documents across diverse scripts and low-resource languages. MDPBench comprises 3,400 document images spanning 17 languages, diverse scripts, and varied photographic conditions, with high-quality annotations produced through a rigorous pipeline of expert model labeling, manual correction, and human verification. To ensure fair comparison and prevent data leakage, we maintain separate public and private evaluation splits. Our comprehensive evaluation of both open-source and closed-source models uncovers a striking finding: while closed-source models (notably Gemini3-Pro) prove relatively robust, open-source alternatives suffer dramatic performance collapse, particularly on non-Latin scripts and real-world photographed documents, with an average drop of 17.8% on photographed documents and 14.0% on non-Latin scripts. These results reveal significant performance imbalances across languages and conditions, and point to concrete directions for building more inclusive, deployment-ready parsing systems. Source available at https://github.com/Yuliang-Liu/MultimodalOCR.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.26648</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.28130</guid>
|
||||||
<pubDate>Fri, 27 Mar 2026 17:50:45 +0000</pubDate>
|
<pubDate>Mon, 30 Mar 2026 07:47:46 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>PerceptionComp: A Video Benchmark for Complex Perception-Centric Reasoning</title>
|
<title>AIBench: Evaluating Visual-Logical Consistency in Academic Illustration Generation</title>
|
||||||
<link>https://arxiv.org/abs/2603.26653</link>
|
<link>https://arxiv.org/abs/2603.28068</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.26653.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shaoxuan Li, Zhixuan Zhao, Hanze Deng, Zirun Ma, Shulin Tian, Zuyan Liu, Yushi Hu, Haoning Wu, Yuhao Dong, Benlin Liu, Ziwei Liu, Ranjay Krishna</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> We introduce PerceptionComp, a manually annotated benchmark for complex, long-horizon, perception-centric video reasoning. PerceptionComp is designed so that no single moment is sufficient: answering each question requires multiple temporally separated pieces of visual evidence and compositional constraints under conjunctive and sequential logic, spanning perceptual subtasks such as objects, attributes, relations, locations, actions, and events, and requiring skills including semantic recognition, visual correspondence, temporal reasoning, and spatial reasoning. The benchmark contains 1,114 highly complex questions on 279 videos from diverse domains including city walk tours, indoor villa tours, video games, and extreme outdoor sports, with 100% manual annotation. Human studies show that PerceptionComp requires substantial test-time thinking and repeated perception steps: participants take much longer than on prior benchmarks, and accuracy drops to near chance (18.97%) when rewatching is disallowed. State-of-the-art MLLMs also perform substantially worse on PerceptionComp than on existing benchmarks: the best model in our evaluation, Gemini-3-Flash, reaches only 45.96% accuracy in the five-choice setting, while open-source models remain below 40%. These results suggest that perception-centric long-horizon video reasoning remains a major bottleneck, and we hope PerceptionComp will help drive progress in perceptual reasoning.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.28068.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhaohe Liao, Kaixun Jiang, Zhihang Liu, Yujie Wei, Junqiu Yu, Quanhao Li, Hong-Tao Yu, Pandeng Li, Yuzheng Wang, Zhen Xing, Shiwei Zhang, Chen-Wei Xie, Yun Zheng, Xihui Liu</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Although image generation has boosted various applications via its rapid evolution, whether the state-of-the-art models are able to produce ready-to-use academic illustrations for papers is still largely unexplored. Directly comparing or evaluating the illustration with VLM is native but requires oracle multi-modal understanding ability, which is unreliable for long and complex texts and illustrations. To address this, we propose AIBench, the first benchmark using VQA for evaluating logic correctness of the academic illustrations and VLMs for assessing aesthetics. In detail, we designed four levels of questions proposed from a logic diagram summarized from the method part of the paper, which query whether the generated illustration aligns with the paper on different scales. Our VQA-based approach raises more accurate and detailed evaluations on visual-logical consistency while relying less on the ability of the judger VLM. With our high-quality AIBench, we conduct extensive experiments and conclude that the performance gap between models on this task is significantly larger than general ones, reflecting their various complex reasoning and high-density generation ability. Further, the logic and aesthetics are hard to optimize simultaneously as in handcrafted illustrations. Additional experiments further state that test-time scaling on both abilities significantly boosts the performance on this task.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.26653</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.28068</guid>
|
||||||
<pubDate>Fri, 27 Mar 2026 17:54:36 +0000</pubDate>
|
<pubDate>Tue, 31 Mar 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>GaussianGPT: Towards Autoregressive 3D Gaussian Scene Generation</title>
|
<title>Video Models Reason Early: Exploiting Plan Commitment for Maze Solving</title>
|
||||||
<link>https://arxiv.org/abs/2603.26661</link>
|
<link>https://arxiv.org/abs/2603.30043</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.26661.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Nicolas von Lützow, Barbara Rössle, Katharina Schmid, Matthias Nießner</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Most recent advances in 3D generative modeling rely on diffusion or flow-matching formulations. We instead explore a fully autoregressive alternative and introduce GaussianGPT, a transformer-based model that directly generates 3D Gaussians via next-token prediction, thus facilitating full 3D scene generation. We first compress Gaussian primitives into a discrete latent grid using a sparse 3D convolutional autoencoder with vector quantization. The resulting tokens are serialized and modeled using a causal transformer with 3D rotary positional embedding, enabling sequential generation of spatial structure and appearance. Unlike diffusion-based methods that refine scenes holistically, our formulation constructs scenes step-by-step, naturally supporting completion, outpainting, controllable sampling via temperature, and flexible generation horizons. This formulation leverages the compositional inductive biases and scalability of autoregressive modeling while operating on explicit representations compatible with modern neural rendering pipelines, positioning autoregressive transformers as a complementary paradigm for controllable and context-aware 3D generation.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.30043.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kaleb Newman, Tyler Zhu, Olga Russakovsky</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Video diffusion models exhibit emergent reasoning capabilities like solving mazes and puzzles, yet little is understood about how they reason during generation. We take a first step towards understanding this and study the internal planning dynamics of video models using 2D maze solving as a controlled testbed. Our investigations reveal two findings. Our first finding is early plan commitment: video diffusion models commit to a high-level motion plan within the first few denoising steps, after which further denoising alters visual details but not the underlying trajectory. Our second finding is that path length, not obstacle density, is the dominant predictor of maze difficulty, with a sharp failure threshold at 12 steps. This means video models can only reason over long mazes by chaining together multiple sequential generations. To demonstrate the practical benefits of our findings, we introduce Chaining with Early Planning, or ChEaP, which only spends compute on seeds with promising early plans and chains them together to tackle complex mazes. This improves accuracy from 7% to 67% on long-horizon mazes and by 2.5x overall on hard tasks in Frozen Lake and VR-Bench across Wan2.2-14B and HunyuanVideo-1.5. Our analysis reveals that current video models possess deeper reasoning capabilities than previously recognized, which can be elicited more reliably with better inference-time scaling.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.26661</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.30043</guid>
|
||||||
<pubDate>Fri, 27 Mar 2026 17:58:05 +0000</pubDate>
|
<pubDate>Tue, 31 Mar 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>MiroEval: Benchmarking Multimodal Deep Research Agents in Process and Outcome</title>
|
<title>ASI-Evolve: AI Accelerates AI</title>
|
||||||
<link>https://arxiv.org/abs/2603.28407</link>
|
<link>https://arxiv.org/abs/2603.29640</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.28407.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Fangda Ye, Yuxin Hu, Pengxiang Zhu, Yibo Li, Ziqi Jin, Yao Xiao, Yibo Wang, Lei Wang, Zhen Zhang, Lu Wang, Yue Deng, Bin Wang, Yifan Zhang, Liangcai Su, Xinyu Wang, He Zhao, Chen Wei, Qiang Ren, Bryan Hooi, An Bo, Shuicheng Yan, Lidong Bing</p><p><b>Upvotes:</b> 52</p><p><b>Summary:</b> Recent progress in deep research systems has been impressive, but evaluation still lags behind real user needs. Existing benchmarks predominantly assess final reports using fixed rubrics, failing to evaluate the underlying research process. Most also offer limited multimodal coverage, rely on synthetic tasks that do not reflect real-world query complexity, and cannot be refreshed as knowledge evolves. To address these gaps, we introduce MiroEval, a benchmark and evaluation framework for deep research systems. The benchmark comprises 100 tasks (70 text-only, 30 multimodal), all grounded in real user needs and constructed via a dual-path pipeline that supports periodic updates, enabling a live and evolving setting. The proposed evaluation suite assesses deep research systems along three complementary dimensions: adaptive synthesis quality evaluation with task-specific rubrics, agentic factuality verification via active retrieval and reasoning over both web sources and multimodal attachments, and process-centric evaluation audits how the system searches, reasons, and refines throughout its investigation. Evaluation across 13 systems yields three principal findings: the three evaluation dimensions capture complementary aspects of system capability, with each revealing distinct strengths and weaknesses across systems; process quality serves as a reliable predictor of overall outcome while revealing weaknesses invisible to output-level metrics; and multimodal tasks pose substantially greater challenges, with most systems declining by 3 to 10 points. The MiroThinker series achieves the most balanced performance, with MiroThinker-H1 ranking the highest overall in both settings. Human verification and robustness results confirm the reliability of the benchmark and evaluation framework. MiroEval provides a holistic diagnostic tool for the next generation of deep research agents.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.29640.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Weixian Xu, Tiantian Mi, Yixiu Liu, Yang Nan, Zhimeng Zhou, Lyumanshan Ye, Lin Zhang, Yu Qiao, Pengfei Liu</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Can AI accelerate the development of AI itself? While recent agentic systems have shown strong performance on well-scoped tasks with rapid feedback, it remains unclear whether they can tackle the costly, long-horizon, and weakly supervised research loops that drive real AI progress. We present ASI-Evolve, an agentic framework for AI-for-AI research that closes this loop through a learn-design-experiment-analyze cycle. ASI-Evolve augments standard evolutionary agents with two key components: a cognition base that injects accumulated human priors into each round of exploration, and a dedicated analyzer that distills complex experimental outcomes into reusable insights for future iterations. To our knowledge, ASI-Evolve is the first unified framework to demonstrate AI-driven discovery across three central components of AI development: data, architectures, and learning algorithms. In neural architecture design, it discovered 105 SOTA linear attention architectures, with the best discovered model surpassing DeltaNet by +0.97 points, nearly 3x the gain of recent human-designed improvements. In pretraining data curation, the evolved pipeline improves average benchmark performance by +3.96 points, with gains exceeding 18 points on MMLU. In reinforcement learning algorithm design, discovered algorithms outperform GRPO by up to +12.5 points on AMC32, +11.67 points on AIME24, and +5.04 points on OlympiadBench. We further provide initial evidence that this AI-for-AI paradigm can transfer beyond the AI stack through experiments in mathematics and biomedicine. Together, these results suggest that ASI-Evolve represents a promising step toward enabling AI to accelerate AI across the foundational stages of development, offering early evidence for the feasibility of closed-loop AI research.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.28407</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.29640</guid>
|
||||||
<pubDate>Mon, 30 Mar 2026 13:16:03 +0000</pubDate>
|
<pubDate>Tue, 31 Mar 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Understand and Accelerate Memory Processing Pipeline for Disaggregated LLM Inference</title>
|
<title>Friends and Grandmothers in Silico: Localizing Entity Cells in Language Models</title>
|
||||||
<link>https://arxiv.org/abs/2603.29002</link>
|
<link>https://arxiv.org/abs/2604.01404</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.29002.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zifan He, Rui Ma, Yizhou Sun, Jason Cong</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Modern large language models (LLMs) increasingly depends on efficient long-context processing and generation mechanisms, including sparse attention, retrieval-augmented generation (RAG), and compressed contextual memory, to support complex reasoning. We show that these optimizations can be unified into a four-step memory processing pipeline: Prepare Memory, Compute Relevancy, Retrieval, and Apply to Inference. Through systematic profiling, we identify a 22%-97% memory processing overhead in LLM inference and strong heterogeneity in its computational characteristics. Motivated by this insight, we argue that heterogeneous systems are well-suited to accelerate memory processing and thus end-to-end inference. We demonstrate this approach on a GPU-FPGA system by offloading sparse, irregular, and memory-bounded operations to FPGAs while retaining compute-intensive operations on GPUs. Evaluated on an AMD MI210 GPU and an Alveo U55C FPGA, our system is 1.04sim2.2times faster and requires 1.11sim4.7times less energy across multiple LLM inference optimizations than the GPU baseline (similar results hold on NVIDIA A100). These results establish heterogeneous systems as a practical direction for efficient LLM memory processing and inform future heterogeneous hardware design.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.01404.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Itay Yona, Dan Barzilay, Michael Karasik, Mor Geva</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Language models can answer many entity-centric factual questions, but it remains unclear which internal mechanisms are involved in this process. We study this question across multiple language models. We localize entity-selective MLP neurons using templated prompts about each entity, and then validate them with causal interventions on PopQA-based QA examples. On a curated set of 200 entities drawn from PopQA, localized neurons concentrate in early layers. Negative ablation produces entity-specific amnesia, while controlled injection at a placeholder token improves answer retrieval relative to mean-entity and wrong-cell controls. For many entities, activating a single localized neuron is sufficient to recover entity-consistent predictions once the context is initialized, consistent with compact entity retrieval rather than purely gradual enrichment across depth. Robustness to aliases, acronyms, misspellings, and multilingual forms supports a canonicalization interpretation. The effect is strong but not universal: not every entity admits a reliable single-neuron handle, and coverage is higher for popular entities. Overall, these results identify sparse, causally actionable access points for analyzing and modulating entity-conditioned factual behavior.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.29002</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.01404</guid>
|
||||||
<pubDate>Mon, 30 Mar 2026 21:03:39 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>MemRerank: Preference Memory for Personalized Product Reranking</title>
|
|
||||||
<link>https://arxiv.org/abs/2603.29247</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.29247.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhiyuan Peng, Xuyang Wu, Huaixiao Tou, Yi Fang, Yi Gong</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> LLM-based shopping agents increasingly rely on long purchase histories and multi-turn interactions for personalization, yet naively appending raw history to prompts is often ineffective due to noise, length, and relevance mismatch. We propose MemRerank, a preference memory framework that distills user purchase history into concise, query-independent signals for personalized product reranking. To study this problem, we build an end-to-end benchmark and evaluation framework centered on an LLM-based 1-in-5 selection task, which measures both memory quality and downstream reranking utility. We further train the memory extractor with reinforcement learning (RL), using downstream reranking performance as supervision. Experiments with two LLM-based rerankers show that MemRerank consistently outperforms no-memory, raw-history, and off-the-shelf memory baselines, yielding up to +10.61 absolute points in 1-in-5 accuracy. These results suggest that explicit preference memory is a practical and effective building block for personalization in agentic e-commerce systems.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.29247</guid>
|
|
||||||
<pubDate>Tue, 31 Mar 2026 04:16:18 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>Terminal Agents Suffice for Enterprise Automation</title>
|
|
||||||
<link>https://arxiv.org/abs/2604.00073</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.00073.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Patrice Bechard, Orlando Marquez Ayala, Emily Chen, Jordan Skelton, Sagar Davasam, Srinivas Sunkara, Vikas Yadav, Sai Rajeswar</p><p><b>Upvotes:</b> 68</p><p><b>Summary:</b> There has been growing interest in building agents that can interact with digital platforms to execute meaningful enterprise tasks autonomously. Among the approaches explored are tool-augmented agents built on abstractions such as Model Context Protocol (MCP) and web agents that operate through graphical interfaces. Yet, it remains unclear whether such complex agentic systems are necessary given their cost and operational overhead. We argue that a coding agent equipped only with a terminal and a filesystem can solve many enterprise tasks more effectively by interacting directly with platform APIs. We evaluate this hypothesis across diverse real-world systems and show that these low-level terminal agents match or outperform more complex agent architectures. Our findings suggest that simple programmatic interfaces, combined with strong foundation models, are sufficient for practical enterprise automation.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.00073</guid>
|
|
||||||
<pubDate>Tue, 31 Mar 2026 14:14:47 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>When Users Change Their Mind: Evaluating Interruptible Agents in Long-Horizon Web Navigation</title>
|
|
||||||
<link>https://arxiv.org/abs/2604.00892</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.00892.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Henry Peng Zou, Chunyu Miao, Wei-Chieh Huang, Yankai Chen, Yue Zhou, Hanrong Zhang, Yaozu Wu, Liancheng Fang, Zhengyao Gu, Zhen Zhang, Kening Zheng, Fangxin Wang, Yi Nian, Shanghao Li, Wenzhe Fan, Langzhou He, Weizhi Zhang, Xue Liu, Philip S. Yu</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> As LLM agents transition from short, static problem solving to executing complex, long-horizon tasks in dynamic environments, the ability to handle user interruptions, such as adding requirement or revising goals, during mid-task execution is becoming a core requirement for realistic deployment. However, existing benchmarks largely assume uninterrupted agent behavior or study interruptions only in short, unconstrained language tasks. In this paper, we present the first systematic study of interruptible agents in long-horizon, environmentally grounded web navigation tasks, where actions induce persistent state changes. We formalize three realistic interruption types, including addition, revision, and retraction, and introduce InterruptBench, a benchmark derived from WebArena-Lite that synthesizes high-quality interruption scenarios under strict semantic constraints. Using a unified interruption simulation framework, we evaluate six strong LLM backbones across single- and multi-turn interruption settings, analyzing both their effectiveness in adapting to updated intents and their efficiency in recovering from mid-task changes. Our results show that handling user interruptions effectively and efficiently during long-horizon agentic tasks remains challenging for powerful large-scale LLMs. Code and dataset are available at https://github.com/HenryPengZou/InterruptBench.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.00892</guid>
|
|
||||||
<pubDate>Wed, 01 Apr 2026 00:00:00 +0000</pubDate>
|
<pubDate>Wed, 01 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Think, Act, Build: An Agentic Framework with Vision Language Models for Zero-Shot 3D Visual Grounding</title>
|
<title>Signals: Trajectory Sampling and Triage for Agentic Interactions</title>
|
||||||
<link>https://arxiv.org/abs/2604.00528</link>
|
<link>https://arxiv.org/abs/2604.00356</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.00528.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haibo Wang, Zihao Lin, Zhiyang Xu, Lifu Huang</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> 3D Visual Grounding (3D-VG) aims to localize objects in 3D scenes via natural language descriptions. While recent advancements leveraging Vision-Language Models (VLMs) have explored zero-shot possibilities, they typically suffer from a static workflow relying on preprocessed 3D point clouds, essentially degrading grounding into proposal matching. To bypass this reliance, our core motivation is to decouple the task: leveraging 2D VLMs to resolve complex spatial semantics, while relying on deterministic multi-view geometry to instantiate the 3D structure. Driven by this insight, we propose "Think, Act, Build (TAB)", a dynamic agentic framework that reformulates 3D-VG tasks as a generative 2D-to-3D reconstruction paradigm operating directly on raw RGB-D streams. Specifically, guided by a specialized 3D-VG skill, our VLM agent dynamically invokes visual tools to track and reconstruct the target across 2D frames. Crucially, to overcome the multi-view coverage deficit caused by strict VLM semantic tracking, we introduce the Semantic-Anchored Geometric Expansion, a mechanism that first anchors the target in a reference video clip and then leverages multi-view geometry to propagate its spatial location across unobserved frames. This enables the agent to "Build" the target's 3D representation by aggregating these multi-view features via camera parameters, directly mapping 2D visual cues to 3D coordinates. Furthermore, to ensure rigorous assessment, we identify flaws such as reference ambiguity and category errors in existing benchmarks and manually refine the incorrect queries. Extensive experiments on ScanRefer and Nr3D demonstrate that our framework, relying entirely on open-source models, significantly outperforms previous zero-shot methods and even surpasses fully supervised baselines.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.00356.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shuguang Chen, Adil Hafeez, Salman Paracha</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Agentic applications based on large language models increasingly rely on multi-step interaction loops involving planning, action execution, and environment feedback. While such systems are now deployed at scale, improving them post-deployment remains challenging. Agent trajectories are voluminous and non-deterministic, and reviewing each one, whether through human review or auxiliary LLMs, is slow and cost-prohibitive. We propose a lightweight, signal-based framework for triaging agentic interaction trajectories. Our approach computes cheap, broadly applicable signals from live interactions and attaches them as structured attributes for trajectory triage, identifying interactions likely to be informative without affecting online agent behavior. We organize signals into a coarse-grained taxonomy spanning interaction (misalignment, stagnation, disengagement, satisfaction), execution (failure, loop), and environment (exhaustion), designed for computation without model calls. In a controlled annotation study on τ-bench, a widely used benchmark for tool-augmented agent evaluation, we show that signal-based sampling achieves an 82\% informativeness rate compared to 74\% for heuristic filtering and 54\% for random sampling, with a 1.52x efficiency gain per informative trajectory. The advantage is robust across reward strata and task domains, confirming that signals provide genuine per-trajectory informativeness gains rather than merely oversampling obvious failures. These results show that lightweight signals can serve as practical sampling infrastructure for agentic systems, and suggest a path toward preference data construction and post-deployment optimization.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.00528</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.00356</guid>
|
||||||
<pubDate>Wed, 01 Apr 2026 06:12:16 +0000</pubDate>
|
<pubDate>Wed, 01 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>UniMixer: A Unified Architecture for Scaling Laws in Recommendation Systems</title>
|
<title>UniRecGen: Unifying Multi-View 3D Reconstruction and Generation</title>
|
||||||
<link>https://arxiv.org/abs/2604.00590</link>
|
<link>https://arxiv.org/abs/2604.01479</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.00590.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mingming Ha, Guanchen Wang, Linxun Chen, Xuan Rao, Yuexin Shi, Tianbao Ma, Zhaojie Liu, Yunqian Fan, Zilong Lu, Yanan Niu, Han Li, Kun Gai</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> In recent years, the scaling laws of recommendation models have attracted increasing attention, which govern the relationship between performance and parameters/FLOPs of recommenders. Currently, there are three mainstream architectures for achieving scaling in recommendation models, namely attention-based, TokenMixer-based, and factorization-machine-based methods, which exhibit fundamental differences in both design philosophy and architectural structure. In this paper, we propose a unified scaling architecture for recommendation systems, namely UniMixer, to improve scaling efficiency and establish a unified theoretical framework that unifies the mainstream scaling blocks. By transforming the rule-based TokenMixer to an equivalent parameterized structure, we construct a generalized parameterized feature mixing module that allows the token mixing patterns to be optimized and learned during model training. Meanwhile, the generalized parameterized token mixing removes the constraint in TokenMixer that requires the number of heads to be equal to the number of tokens. Furthermore, we establish a unified scaling module design framework for recommender systems, which bridges the connections among attention-based, TokenMixer-based, and factorization-machine-based methods. To further boost scaling ROI, a lightweight UniMixing module is designed, UniMixing-Lite, which further compresses the model parameters and computational cost while significantly improve the model performance. The scaling curves are shown in the following figure. Extensive offline and online experiments are conducted to verify the superior scaling abilities of UniMixer.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.01479.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhisheng Huang, Jiahao Chen, Cheng Lin, Chenyu Hu, Hanzhuo Huang, Zhengming Yu, Mengfei Li, Yuheng Liu, Zekai Gu, Zibo Zhao, Yuan Liu, Xin Li, Wenping Wang</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Sparse-view 3D modeling represents a fundamental tension between reconstruction fidelity and generative plausibility. While feed-forward reconstruction excels in efficiency and input alignment, it often lacks the global priors needed for structural completeness. Conversely, diffusion-based generation provides rich geometric details but struggles with multi-view consistency. We present UniRecGen, a unified framework that integrates these two paradigms into a single cooperative system. To overcome inherent conflicts in coordinate spaces, 3D representations, and training objectives, we align both models within a shared canonical space. We employ disentangled cooperative learning, which maintains stable training while enabling seamless collaboration during inference. Specifically, the reconstruction module is adapted to provide canonical geometric anchors, while the diffusion generator leverages latent-augmented conditioning to refine and complete the geometric structure. Experimental results demonstrate that UniRecGen achieves superior fidelity and robustness, outperforming existing methods in creating complete and consistent 3D models from sparse observations.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.00590</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.01479</guid>
|
||||||
<pubDate>Wed, 01 Apr 2026 07:57:40 +0000</pubDate>
|
<pubDate>Wed, 01 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>A Survey of On-Policy Distillation for Large Language Models</title>
|
<title>Executing as You Generate: Hiding Execution Latency in LLM Code Generation</title>
|
||||||
<link>https://arxiv.org/abs/2604.00626</link>
|
<link>https://arxiv.org/abs/2604.00491</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.00626.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mingyang Song, Mao Zheng</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Knowledge distillation has become a primary mechanism for transferring reasoning and domain expertise from frontier Large Language Models (LLMs) to smaller, deployable students. However, the dominant paradigm remains off-policy: students train on static teacher-generated data and never encounter their own errors during learning. This train--test mismatch, an instance of exposure bias, causes prediction errors to compound autoregressively at inference time. On-Policy Distillation (OPD) addresses this by letting the student generate its own trajectories and receive teacher feedback on these self-generated outputs, grounding distillation in the theory of interactive imitation learning. Despite rapid growth spanning divergence minimization, reward-guided learning, and self-play, the OPD literature remains fragmented with no unified treatment. This survey provides the first comprehensive overview of OPD for LLMs. We introduce a unified f-divergence framework over on-policy samples and organize the landscape along three orthogonal dimensions: feedback signal (logit-based, outcome-based, or self-play), teacher access (white-box, black-box, or teacher-free), and loss granularity (token-level, sequence-level, or hybrid). We systematically analyze representative methods, examine industrial deployments, and identify open problems including distillation scaling laws, uncertainty-aware feedback, and agent-level distillation.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.00491.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhensu Sun, Zhihao Lin, Zhi Chen, Chengran Yang, Mingyi Zhou, Li Li, David Lo</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Current LLM-based coding agents follow a serial execution paradigm: the model first generates the complete code, then invokes an interpreter to execute it. This sequential workflow leaves the executor idle during generation and the generator idle during execution, resulting in unnecessary end-to-end latency. We observe that, unlike human developers, LLMs produce code tokens sequentially without revision, making it possible to execute code as it is being generated. We formalize this parallel execution paradigm, modeling it as a three-stage pipeline of generation, detection, and execution, and derive closed-form latency bounds that characterize its speedup potential and operating regimes. We then present Eager, a concrete implementation featuring AST-based chunking, dynamic batching with gated execution, and early error interruption. We evaluate Eager across four benchmarks, seven LLMs, and three execution environments. Results show that Eager reduces the non-overlapped execution latency by up to 99.9% and the end-to-end latency by up to 55% across seven LLMs and four benchmarks.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.00626</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.00491</guid>
|
||||||
<pubDate>Wed, 01 Apr 2026 08:32:34 +0000</pubDate>
|
<pubDate>Wed, 01 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Proactive Agent Research Environment: Simulating Active Users to Evaluate Proactive Assistants</title>
|
<title>Efficient and Principled Scientific Discovery through Bayesian Optimization: A Tutorial</title>
|
||||||
<link>https://arxiv.org/abs/2604.00842</link>
|
<link>https://arxiv.org/abs/2604.01328</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.00842.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Deepak Nathani, Cheng Zhang, Chang Huan, Jiaming Shan, Yinfei Yang, Alkesh Patel, Zhe Gan, William Yang Wang, Michael Saxon, Xin Eric Wang</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Proactive agents that anticipate user needs and autonomously execute tasks hold great promise as digital assistants, yet the lack of realistic user simulation frameworks hinders their development. Existing approaches model apps as flat tool-calling APIs, failing to capture the stateful and sequential nature of user interaction in digital environments and making realistic user simulation infeasible. We introduce Proactive Agent Research Environment (Pare), a framework for building and evaluating proactive agents in digital environments. Pare models applications as finite state machines with stateful navigation and state-dependent action space for the user simulator, enabling active user simulation. Building on this foundation, we present Pare-Bench, a benchmark of 143 diverse tasks spanning communication, productivity, scheduling, and lifestyle apps, designed to test context observation, goal inference, intervention timing, and multi-app orchestration.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.01328.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhongwei Yu, Rasul Tutunov, Alexandre Max Maraval, Zikai Xie, Zhenzhi Tan, Jiankang Wang, Zijing Li, Liangliang Xu, Qi Yang, Jun Jiang, Sanzhong Luo, Zhenxiao Guo, Haitham Bou-Ammar, Jun Wang</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Traditional scientific discovery relies on an iterative hypothesise-experiment-refine cycle that has driven progress for centuries, but its intuitive, ad-hoc implementation often wastes resources, yields inefficient designs, and misses critical insights. This tutorial presents Bayesian Optimisation (BO), a principled probability-driven framework that formalises and automates this core scientific cycle. BO uses surrogate models (e.g., Gaussian processes) to model empirical observations as evolving hypotheses, and acquisition functions to guide experiment selection, balancing exploitation of known knowledge and exploration of uncharted domains to eliminate guesswork and manual trial-and-error. We first frame scientific discovery as an optimisation problem, then unpack BO's core components, end-to-end workflows, and real-world efficacy via case studies in catalysis, materials science, organic synthesis, and molecule discovery. We also cover critical technical extensions for scientific applications, including batched experimentation, heteroscedasticity, contextual optimisation, and human-in-the-loop integration. Tailored for a broad audience, this tutorial bridges AI advances in BO with practical natural science applications, offering tiered content to empower cross-disciplinary researchers to design more efficient experiments and accelerate principled scientific discovery.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.00842</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.01328</guid>
|
||||||
<pubDate>Wed, 01 Apr 2026 12:53:01 +0000</pubDate>
|
<pubDate>Wed, 01 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Benchmarking and Mechanistic Analysis of Vision-Language Models for Cross-Depiction Assembly Instruction Alignment</title>
|
<title>Forecasting Supply Chain Disruptions with Foresight Learning</title>
|
||||||
<link>https://arxiv.org/abs/2604.00913</link>
|
<link>https://arxiv.org/abs/2604.01298</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.00913.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhuchenyang Liu, Yao Zhang, Yu Xiao</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> 2D assembly diagrams are often abstract and hard to follow, creating a need for intelligent assistants that can monitor progress, detect errors, and provide step-by-step guidance. In mixed reality settings, such systems must recognize completed and ongoing steps from the camera feed and align them with the diagram instructions. Vision Language Models (VLMs) show promise for this task, but face a depiction gap because assembly diagrams and video frames share few visual features. To systematically assess this gap, we construct IKEA-Bench, a benchmark of 1,623 questions across 6 task types on 29 IKEA furniture products, and evaluate 19 VLMs (2B-38B) under three alignment strategies. Our key findings: (1) assembly instruction understanding is recoverable via text, but text simultaneously degrades diagram-to-video alignment; (2) architecture family predicts alignment accuracy more strongly than parameter count; (3) video understanding remains a hard bottleneck unaffected by strategy. A three-level mechanistic analysis further reveals that diagrams and video occupy disjoint ViT subspaces, and that adding text shifts models from visual to text-driven reasoning. These results identify visual encoding as the primary target for improving cross-depiction robustness. Project page: https://ryenhails.github.io/IKEA-Bench/</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.01298.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Benjamin Turtel, Paul Wilczewski, Kris Skotheim</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Anticipating supply chain disruptions before they materialize is a core challenge for firms and policymakers alike. A key difficulty is learning to reason reliably about infrequent, high-impact events from noisy and unstructured inputs - a setting where general-purpose models struggle without task-specific adaptation. We introduce an end-to-end framework that trains LLMs to produce calibrated probabilistic forecasts using realized disruption outcomes as supervision. The resulting model substantially outperforms strong baselines - including GPT-5 - on accuracy, calibration, and precision. We also show that training induces more structured and reliable probabilistic reasoning without explicit prompting. These results suggest a general pathway for training domain-specific forecasting models that produce decision-ready signals. To support transparency we open-source the evaluation dataset used in this study. Dataset: https://huggingface.co/datasets/LightningRodLabs/supply-chain-predictions</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.00913</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.01298</guid>
|
||||||
<pubDate>Wed, 01 Apr 2026 13:55:28 +0000</pubDate>
|
<pubDate>Wed, 01 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Do Phone-Use Agents Respect Your Privacy?</title>
|
<title>LinguDistill: Recovering Linguistic Ability in Vision- Language Models via Selective Cross-Modal Distillation</title>
|
||||||
<link>https://arxiv.org/abs/2604.00986</link>
|
<link>https://arxiv.org/abs/2604.00829</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.00986.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhengyang Tang, Ke Ji, Xidong Wang, Zihan Ye, Xinyuan Wang, Yiduo Guo, Ziniu Li, Chenxin Li, Jingyuan Hu, Shunian Chen, Tongxu Luo, Jiaxi Bi, Zeyu Qin, Shaobo Wang, Xin Lai, Pengyuan Lyu, Junyi Li, Can Xu, Chengquan Zhang, Han Hu, Ming Yan, Benyou Wang</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> We study whether phone-use agents respect privacy while completing benign mobile tasks. This question has remained hard to answer because privacy-compliant behavior is not operationalized for phone-use agents, and ordinary apps do not reveal exactly what data agents type into which form entries during execution. To make this question measurable, we introduce MyPhoneBench, a verifiable evaluation framework for privacy behavior in mobile agents. We operationalize privacy-respecting phone use as permissioned access, minimal disclosure, and user-controlled memory through a minimal privacy contract, iMy, and pair it with instrumented mock apps plus rule-based auditing that make unnecessary permission requests, deceptive re-disclosure, and unnecessary form filling observable and reproducible. Across five frontier models on 10 mobile apps and 300 tasks, we find that task success, privacy-compliant task completion, and later-session use of saved preferences are distinct capabilities, and no single model dominates all three. Evaluating success and privacy jointly reshuffles the model ordering relative to either metric alone. The most persistent failure mode across models is simple data minimization: agents still fill optional personal entries that the task does not require. These results show that privacy failures arise from over-helpful execution of benign tasks, and that success-only evaluation overestimates the deployment readiness of current phone-use agents. All code, mock apps, and agent trajectories are publicly available at~ https://github.com/tangzhy/MyPhoneBench.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.00829.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Patrick Amadeus Irawan, Erland Hilman Fuadi, Shanu Kumar, Alham Fikri Aji, Yova Kementchedjhieva</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Adapting pretrained language models (LMs) into vision-language models (VLMs) can degrade their native linguistic capability due to representation shift and cross-modal interference introduced during multimodal adaptation. Such loss is difficult to recover, even with targeted task-specific fine-tuning using standard objectives. Prior recovery approaches typically introduce additional modules that act as intermediate alignment layers to maintain or isolate modality-specific subspaces, which increases architectural complexity, adds parameters at inference time, and limits flexibility across models and settings. We propose LinguDistill, an adapter-free distillation method that restores linguistic capability by utilizing the original frozen LM as a teacher. We overcome the key challenge of enabling vision-conditioned teacher supervision by introducing layer-wise KV-cache sharing, which exposes the teacher to the student's multimodal representations without modifying the architecture of either model. We then selectively distill the teacher's strong linguistic signal on language-intensive data to recover language capability, while preserving the student's visual grounding on multimodal tasks. As a result, LinguDistill recovers sim10% of the performance lost on language and knowledge benchmarks, while maintaining comparable performance on vision-heavy tasks. Our findings demonstrate that linguistic capability can be recovered without additional modules, providing an efficient and practical solution to modality-specific degradation in multimodal models.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.00986</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.00829</guid>
|
||||||
<pubDate>Wed, 01 Apr 2026 14:50:50 +0000</pubDate>
|
<pubDate>Wed, 01 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Revision or Re-Solving? Decomposing Second-Pass Gains in Multi-LLM Pipelines</title>
|
<title>Investigating Autonomous Agent Contributions in the Wild: Activity Patterns and Code Change over Time</title>
|
||||||
<link>https://arxiv.org/abs/2604.01029</link>
|
<link>https://arxiv.org/abs/2604.00917</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.01029.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jingjie Ning, Xueqi Li, Chengyu Yu</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Multi-LLM revision pipelines, in which a second model reviews and improves a draft produced by a first, are widely assumed to derive their gains from genuine error correction. We question this assumption with a controlled decomposition experiment that uses four matched conditions to separate second-pass gains into three additive components: re-solving, scaffold, and content. We evaluate this design across two model pairs on three benchmarks spanning knowledge-intensive MCQ and competitive programming. Our results show that the gains of multi-LLM revision are not monolithic, but depend on task structure, draft quality, and the type of draft information. On MCQ tasks, where the answer space is constrained and drafts provide little structural guidance, most gains are consistent with stronger-model re-solving, and directly routing queries to the stronger model can be more effective than revising a weak draft. On code generation tasks, however, two-stage prompting remains useful because even semantically null drafts can provide substantial structural scaffolding, while weak draft content can be harmful. Finally, role-reversed experiments show that strong drafts clearly benefit weak reviewers. Ultimately, our findings demonstrate that the utility of multi-LLM revision is dynamically bottlenecked by task structure and draft quality, necessitating more targeted pipeline designs rather than blanket revision strategies.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.00917.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Razvan Mihai Popescu, David Gros, Andrei Botocan, Rahul Pandita, Prem Devanbu, Maliheh Izadi</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> The rise of large language models for code has reshaped software development. Autonomous coding agents, able to create branches, open pull requests, and perform code reviews, now actively contribute to real-world projects. Their growing role offers a unique and timely opportunity to investigate AI-driven contributions and their effects on code quality, team dynamics, and software maintainability. In this work, we construct a novel dataset of approximately 110,000 open-source pull requests, including associated commits, comments, reviews, issues, and file changes, collectively representing millions of lines of source code. We compare five popular coding agents, including OpenAI Codex, Claude Code, GitHub Copilot, Google Jules, and Devin, examining how their usage differs in various development aspects such as merge frequency, edited file types, and developer interaction signals, including comments and reviews. Furthermore, we emphasize that code authoring and review are only a small part of the larger software engineering process, as the resulting code must also be maintained and updated over time. Hence, we offer several longitudinal estimates of survival and churn rates for agent-generated versus human-authored code. Ultimately, our findings indicate an increasing agent activity in open-source projects, although their contributions are associated with more churn over time compared to human-authored code.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.01029</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.00917</guid>
|
||||||
<pubDate>Wed, 01 Apr 2026 15:39:40 +0000</pubDate>
|
<pubDate>Wed, 01 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Paper Reconstruction Evaluation: Evaluating Presentation and Hallucination in AI-written Papers</title>
|
<title>EgoSim: Egocentric World Simulator for Embodied Interaction Generation</title>
|
||||||
<link>https://arxiv.org/abs/2604.01128</link>
|
<link>https://arxiv.org/abs/2604.01001</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.01128.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Atsuyuki Miyai, Mashiro Toyooka, Zaiying Zhao, Kenta Watanabe, Toshihiko Yamasaki, Kiyoharu Aizawa</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> This paper introduces the first systematic evaluation framework for quantifying the quality and risks of papers written by modern coding agents. While AI-driven paper writing has become a growing concern, rigorous evaluation of the quality and potential risks of AI-written papers remains limited, and a unified understanding of their reliability is still lacking. We introduce Paper Reconstruction Evaluation (PaperRecon), an evaluation framework in which an overview (overview.md) is created from an existing paper, after which an agent generates a full paper based on the overview and minimal additional resources, and the result is subsequently compared against the original paper. PaperRecon disentangles the evaluation of the AI-written papers into two orthogonal dimensions, Presentation and Hallucination, where Presentation is evaluated using a rubric and Hallucination is assessed via agentic evaluation grounded in the original paper source. For evaluation, we introduce PaperWrite-Bench, a benchmark of 51 papers from top-tier venues across diverse domains published after 2025. Our experiments reveal a clear trade-off: while both ClaudeCode and Codex improve with model advances, ClaudeCode achieves higher presentation quality at the cost of more than 10 hallucinations per paper on average, whereas Codex produces fewer hallucinations but lower presentation quality. This work takes a first step toward establishing evaluation frameworks for AI-driven paper writing and improving the understanding of its risks within the research community.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.01001.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jinkun Hao, Mingda Jia, Ruiyan Wang, Xihui Liu, Ran Yi, Lizhuang Ma, Jiangmiao Pang, Xudong Xu</p><p><b>Upvotes:</b> 30</p><p><b>Summary:</b> We introduce EgoSim, a closed-loop egocentric world simulator that generates spatially consistent interaction videos and persistently updates the underlying 3D scene state for continuous simulation. Existing egocentric simulators either lack explicit 3D grounding, causing structural drift under viewpoint changes, or treat the scene as static, failing to update world states across multi-stage interactions. EgoSim addresses both limitations by modeling 3D scenes as updatable world states. We generate embodiment interactions via a Geometry-action-aware Observation Simulation model, with spatial consistency from an Interaction-aware State Updating module. To overcome the critical data bottleneck posed by the difficulty in acquiring densely aligned scene-interaction training pairs, we design a scalable pipeline that extracts static point clouds, camera trajectories, and embodiment actions from in-the-wild large-scale monocular egocentric videos. We further introduce EgoCap, a capture system that enables low-cost real-world data collection with uncalibrated smartphones. Extensive experiments demonstrate that EgoSim significantly outperforms existing methods in terms of visual quality, spatial consistency, and generalization to complex scenes and in-the-wild dexterous interactions, while supporting cross-embodiment transfer to robotic manipulation. Codes and datasets will be open soon. The project page is at egosimulator.github.io.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.01128</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.01001</guid>
|
||||||
<pubDate>Wed, 01 Apr 2026 16:48:04 +0000</pubDate>
|
<pubDate>Wed, 01 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Reasoning Shift: How Context Silently Shortens LLM Reasoning</title>
|
<title>AutoMIA: Improved Baselines for Membership Inference Attack via Agentic Self-Exploration</title>
|
||||||
<link>https://arxiv.org/abs/2604.01161</link>
|
<link>https://arxiv.org/abs/2604.01014</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.01161.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Gleb Rodionov</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> Large language models (LLMs) exhibiting test-time scaling behavior, such as extended reasoning traces and self-verification, have demonstrated remarkable performance on complex, long-term reasoning tasks. However, the robustness of these reasoning behaviors remains underexplored. To investigate this, we conduct a systematic evaluation of multiple reasoning models across three scenarios: (1) problems augmented with lengthy, irrelevant context; (2) multi-turn conversational settings with independent tasks; and (3) problems presented as a subtask within a complex task. We observe an interesting phenomenon: reasoning models tend to produce much shorter reasoning traces (up to 50%) for the same problem under different context conditions compared to the traces produced when the problem is presented in isolation. A finer-grained analysis reveals that this compression is associated with a decrease in self-verification and uncertainty management behaviors, such as double-checking. While this behavioral shift does not compromise performance on straightforward problems, it might affect performance on more challenging tasks. We hope our findings draw additional attention to both the robustness of reasoning models and the problem of context management for LLMs and LLM-based agents.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.01014.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ruhao Liu, Weiqi Huang, Qi Li, Xinchao Wang</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Membership Inference Attacks (MIAs) serve as a fundamental auditing tool for evaluating training data leakage in machine learning models. However, existing methodologies predominantly rely on static, handcrafted heuristics that lack adaptability, often leading to suboptimal performance when transferred across different large models. In this work, we propose AutoMIA, an agentic framework that reformulates membership inference as an automated process of self-exploration and strategy evolution. Given high-level scenario specifications, AutoMIA self-explores the attack space by generating executable logits-level strategies and progressively refining them through closed-loop evaluation feedback. By decoupling abstract strategy reasoning from low-level execution, our framework enables a systematic, model-agnostic traversal of the attack search space. Extensive experiments demonstrate that AutoMIA consistently matches or outperforms state-of-the-art baselines while eliminating the need for manual feature engineering.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.01161</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.01014</guid>
|
||||||
<pubDate>Wed, 01 Apr 2026 17:14:18 +0000</pubDate>
|
<pubDate>Wed, 01 Apr 2026 15:17:45 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>S0 Tuning: Zero-Overhead Adaptation of Hybrid Recurrent-Attention Models</title>
|
<title>Brainstacks: Cross-Domain Cognitive Capabilities via Frozen MoE-LoRA Stacks for Continual LLM Learning</title>
|
||||||
<link>https://arxiv.org/abs/2604.01168</link>
|
<link>https://arxiv.org/abs/2604.01152</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.01168.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jack Young</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Using roughly 48 execution-verified HumanEval training solutions, tuning a single initial state matrix per recurrent layer, with zero inference overhead, outperforms LoRA by +10.8 pp (p < 0.001) on HumanEval. The method, which we call S0 tuning, optimizes one state matrix per recurrent layer while freezing all model weights. On Qwen3.5-4B (GatedDeltaNet hybrid), S0 tuning improves greedy pass@1 by +23.6 +/- 1.7 pp (10 seeds). On FalconH1-7B (Mamba-2 hybrid), S0 reaches 71.8% +/- 1.3 and LoRA reaches 71.4% +/- 2.4 (3 seeds), statistically indistinguishable at this sample size while requiring no weight merging. Cross-domain transfer is significant on MATH-500 (+4.8 pp, p = 0.00002, 8 seeds) and GSM8K (+2.8 pp, p = 0.0003, 10 seeds); a text-to-SQL benchmark (Spider) shows no transfer, consistent with the trajectory-steering mechanism. A prefix-tuning control on a pure Transformer (Qwen2.5-3B) degrades performance by -13.9 pp under all nine configurations tested. On Qwen3.5, a per-step state-offset variant reaches +27.1 pp, above both S0 and LoRA but with per-step inference cost. Taken together, the results show that recurrent state initialization is a strong zero-inference-overhead PEFT surface for hybrid language models when verified supervision is scarce. The tuned state is a ~48 MB file; task switching requires no weight merging or model reload. Code and library: https://github.com/jackyoung27/s0-tuning.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.01152.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mohammad R. Abu Ayyash</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> We present Brainstacks, a modular architecture for continual multi-domain fine-tuning of large language models that packages domain expertise as frozen adapter stacks composing additively on a shared frozen base at inference. Five interlocking components: (1) MoE-LoRA with Shazeer-style noisy top-2 routing across all seven transformer projections under QLoRA 4-bit quantization with rsLoRA scaling; (2) an inner loop performing residual boosting by freezing trained stacks and adding new ones; (3) an outer loop training sequential domain-specific stacks with curriculum-ordered dependencies; (4) null-space projection via randomized SVD constraining new stacks to subspaces orthogonal to prior directions, achieving zero forgetting in isolation; (5) an outcome-based sigmoid meta-router trained on empirically discovered domain-combination targets that selectively weights stacks, enabling cross-domain composition. Two boundary experiments: (6) PSN pretraining on a randomly initialized model; (7) per-domain RL (DPO/GRPO) validating compatibility with post-SFT alignment. Validated on TinyLlama-1.1B (4 domains, 9 stacks) and Gemma 3 12B IT (5 domains, 10 stacks), MoE-LoRA achieves 2.5x faster convergence than parameter-matched single LoRA, residual boosting breaks through the single-stack ceiling, and the routed system recovers generation quality destroyed by ungated stack accumulation. The central finding: the outcome-based router discovers that domain stacks encode transferable cognitive primitives (instruction-following clarity, numerical reasoning, procedural logic, chain-of-thought structure) rather than domain-specific knowledge, with medical prompts routing to chat+math stacks in 97% of cases despite zero medical data in those stacks.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.01168</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.01152</guid>
|
||||||
<pubDate>Wed, 01 Apr 2026 17:21:15 +0000</pubDate>
|
<pubDate>Wed, 01 Apr 2026 17:08:25 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Embarrassingly Simple Self-Distillation Improves Code Generation</title>
|
<title>Automatic Image-Level Morphological Trait Annotation for Organismal Images</title>
|
||||||
<link>https://arxiv.org/abs/2604.01193</link>
|
<link>https://arxiv.org/abs/2604.01619</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.01193.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ruixiang Zhang, Richard He Bai, Huangjie Zheng, Navdeep Jaitly, Ronan Collobert, Yizhe Zhang</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Can a large language model (LLM) improve at code generation using only its own raw outputs, without a verifier, a teacher model, or reinforcement learning? We answer in the affirmative with simple self-distillation (SSD): sample solutions from the model with certain temperature and truncation configurations, then fine-tune on those samples with standard supervised fine-tuning. SSD improves Qwen3-30B-Instruct from 42.4% to 55.3% pass@1 on LiveCodeBench v6, with gains concentrating on harder problems, and it generalizes across Qwen and Llama models at 4B, 8B, and 30B scale, including both instruct and thinking variants. To understand why such a simple method can work, we trace these gains to a precision-exploration conflict in LLM decoding and show that SSD reshapes token distributions in a context-dependent way, suppressing distractor tails where precision matters while preserving useful diversity where exploration matters. Taken together, SSD offers a complementary post-training direction for improving LLM code generation.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.01619.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Vardaan Pahuja, Samuel Stevens, Alyson East, Sydne Record, Yu Su</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Morphological traits are physical characteristics of biological organisms that provide vital clues on how organisms interact with their environment. Yet extracting these traits remains a slow, expert-driven process, limiting their use in large-scale ecological studies. A major bottleneck is the absence of high-quality datasets linking biological images to trait-level annotations. In this work, we demonstrate that sparse autoencoders trained on foundation-model features yield monosemantic, spatially grounded neurons that consistently activate on meaningful morphological parts. Leveraging this property, we introduce a trait annotation pipeline that localizes salient regions and uses vision-language prompting to generate interpretable trait descriptions. Using this approach, we construct Bioscan-Traits, a dataset of 80K trait annotations spanning 19K insect images from BIOSCAN-5M. Human evaluation confirms the biological plausibility of the generated morphological descriptions. We assess design sensitivity through a comprehensive ablation study, systematically varying key design choices and measuring their impact on the quality of the resulting trait descriptions. By annotating traits with a modular pipeline rather than prohibitively expensive manual efforts, we offer a scalable way to inject biologically meaningful supervision into foundation models, enable large-scale morphological analyses, and bridge the gap between ecological relevance and machine-learning practicality.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.01193</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.01619</guid>
|
||||||
<pubDate>Wed, 01 Apr 2026 17:39:50 +0000</pubDate>
|
<pubDate>Thu, 02 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>AgentWatcher: A Rule-based Prompt Injection Monitor</title>
|
<title>Woosh: A Sound Effects Foundation Model</title>
|
||||||
<link>https://arxiv.org/abs/2604.01194</link>
|
<link>https://arxiv.org/abs/2604.01929</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.01194.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yanting Wang, Wei Zou, Runpeng Geng, Jinyuan Jia</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Large language models (LLMs) and their applications, such as agents, are highly vulnerable to prompt injection attacks. State-of-the-art prompt injection detection methods have the following limitations: (1) their effectiveness degrades significantly as context length increases, and (2) they lack explicit rules that define what constitutes prompt injection, causing detection decisions to be implicit, opaque, and difficult to reason about. In this work, we propose AgentWatcher to address the above two limitations. To address the first limitation, AgentWatcher attributes the LLM's output (e.g., the action of an agent) to a small set of causally influential context segments. By focusing detection on a relatively short text, AgentWatcher can be scalable to long contexts. To address the second limitation, we define a set of rules specifying what does and does not constitute a prompt injection, and use a monitor LLM to reason over these rules based on the attributed text, making the detection decisions more explainable. We conduct a comprehensive evaluation on tool-use agent benchmarks and long-context understanding datasets. The experimental results demonstrate that AgentWatcher can effectively detect prompt injection and maintain utility without attacks. The code is available at https://github.com/wang-yanting/AgentWatcher.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.01929.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Gaëtan Hadjeres, Marc Ferras, Khaled Koutini, Benno Weck, Alexandre Bittar, Thomas Hummel, Zineb Lahrici, Hakim Missoum, Joan Serrà, Yuki Mitsufuji</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> The audio research community depends on open generative models as foundational tools for building novel approaches and establishing baselines. In this report, we present Woosh, Sony AI's publicly released sound effect foundation model, detailing its architecture, training process, and an evaluation against other popular open models. Being optimized for sound effects, we provide (1) a high-quality audio encoder/decoder model and (2) a text-audio alignment model for conditioning, together with (3) text-to-audio and (4) video-to-audio generative models. Distilled text-to-audio and video-to-audio models are also included in the release, allowing for low-resource operation and fast inference. Our evaluation on both public and private data shows competitive or better performance for each module when compared to existing open alternatives like StableAudio-Open and TangoFlux. Inference code and model weights are available at https://github.com/SonyResearch/Woosh. Demo samples can be found at https://sonyresearch.github.io/Woosh/.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.01194</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.01929</guid>
|
||||||
<pubDate>Wed, 01 Apr 2026 17:40:03 +0000</pubDate>
|
<pubDate>Thu, 02 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Universal YOCO for Efficient Depth Scaling</title>
|
<title>ActionParty: Multi-Subject Action Binding in Generative Video Games</title>
|
||||||
<link>https://arxiv.org/abs/2604.01220</link>
|
<link>https://arxiv.org/abs/2604.02330</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.01220.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yutao Sun, Li Dong, Tianzhu Ye, Shaohan Huang, Jianyong Wang, Furu Wei</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> The rise of test-time scaling has remarkably boosted the reasoning and agentic proficiency of Large Language Models (LLMs). Yet, standard Transformers struggle to scale inference-time compute efficiently, as conventional looping strategies suffer from high computational overhead and a KV cache that inflates alongside model depth. We present Universal YOCO (YOCO-U), which combines the YOCO decoder-decoder architecture with recursive computation to achieve a synergistic effect greater than either alone. Built on the YOCO framework, YOCO-U implements a Universal Self-Decoder that performs multiple iterations via parameter sharing, while confining the iterative process to shallow, efficient-attention layers. This combination yields a favorable capability-efficiency tradeoff that neither YOCO nor recursion achieves independently. The YOCO architecture provides a constant global KV cache and linear pre-filling, while partial recursion enhances representational depth with limited overhead. Together, YOCO-U improves token utility and scaling behavior while maintaining efficient inference. Empirical results confirm that YOCO-U remains highly competitive in general and long-context benchmarks, demonstrating that the integration of efficient-attention architectures and recursive computation is a promising direction for scalable LLMs.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.02330.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Alexander Pondaven, Ziyi Wu, Igor Gilitschenski, Philip Torr, Sergey Tulyakov, Fabio Pizzati, Aliaksandr Siarohin</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Recent advances in video diffusion have enabled the development of "world models" capable of simulating interactive environments. However, these models are largely restricted to single-agent settings, failing to control multiple agents simultaneously in a scene. In this work, we tackle a fundamental issue of action binding in existing video diffusion models, which struggle to associate specific actions with their corresponding subjects. For this purpose, we propose ActionParty, an action controllable multi-subject world model for generative video games. It introduces subject state tokens, i.e. latent variables that persistently capture the state of each subject in the scene. By jointly modeling state tokens and video latents with a spatial biasing mechanism, we disentangle global video frame rendering from individual action-controlled subject updates. We evaluate ActionParty on the Melting Pot benchmark, demonstrating the first video world model capable of controlling up to seven players simultaneously across 46 diverse environments. Our results show significant improvements in action-following accuracy and identity consistency, while enabling robust autoregressive tracking of subjects through complex interactions.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.01220</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.02330</guid>
|
||||||
<pubDate>Wed, 01 Apr 2026 17:58:21 +0000</pubDate>
|
<pubDate>Thu, 02 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>HippoCamp: Benchmarking Contextual Agents on Personal Computers</title>
|
<title>FlowSlider: Training-Free Continuous Image Editing via Fidelity-Steering Decomposition</title>
|
||||||
<link>https://arxiv.org/abs/2604.01221</link>
|
<link>https://arxiv.org/abs/2604.02088</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.01221.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhe Yang, Shulin Tian, Kairui Hu, Shuai Liu, Hoang-Nhat Nguyen, Yichi Zhang, Zujin Guo, Mengying Yu, Zinan Zhang, Jingkang Yang, Chen Change Loy, Ziwei Liu</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> We present HippoCamp, a new benchmark designed to evaluate agents' capabilities on multimodal file management. Unlike existing agent benchmarks that focus on tasks like web interaction, tool use, or software automation in generic settings, HippoCamp evaluates agents in user-centric environments to model individual user profiles and search massive personal files for context-aware reasoning. Our benchmark instantiates device-scale file systems over real-world profiles spanning diverse modalities, comprising 42.4 GB of data across over 2K real-world files. Building upon the raw files, we construct 581 QA pairs to assess agents' capabilities in search, evidence perception, and multi-step reasoning. To facilitate fine-grained analysis, we provide 46.1K densely annotated structured trajectories for step-wise failure diagnosis. We evaluate a wide range of state-of-the-art multimodal large language models (MLLMs) and agentic methods on HippoCamp. Our comprehensive experiments reveal a significant performance gap: even the most advanced commercial models achieve only 48.3% accuracy in user profiling, struggling particularly with long-horizon retrieval and cross-modal reasoning within dense personal file systems. Furthermore, our step-wise failure diagnosis identifies multimodal perception and evidence grounding as the primary bottlenecks. Ultimately, HippoCamp exposes the critical limitations of current agents in realistic, user-centric environments and provides a robust foundation for developing next-generation personal AI assistants.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.02088.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Taichi Endo, Guoqing Hao, Kazuhiko Sumi</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Continuous image editing aims to provide slider-style control of edit strength while preserving source-image fidelity and maintaining a consistent edit direction. Existing learning-based slider methods typically rely on auxiliary modules trained with synthetic or proxy supervision. This introduces additional training overhead and couples slider behavior to the training distribution, which can reduce reliability under distribution shifts in edits or domains. We propose FlowSlider, a training-free method for continuous editing in Rectified Flow that requires no post-training. FlowSlider decomposes FlowEdit's update into (i) a fidelity term, which acts as a source-conditioned stabilizer that preserves identity and structure, and (ii) a steering term that drives semantic transition toward the target edit. Geometric analysis and empirical measurements show that these terms are approximately orthogonal, enabling stable strength control by scaling only the steering term while keeping the fidelity term unchanged. As a result, FlowSlider provides smooth and reliable control without post-training, improving continuous editing quality across diverse tasks.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.01221</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.02088</guid>
|
||||||
<pubDate>Wed, 01 Apr 2026 17:58:33 +0000</pubDate>
|
<pubDate>Thu, 02 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Apriel-Reasoner: RL Post-Training for General-Purpose and Efficient Reasoning</title>
|
||||||
|
<link>https://arxiv.org/abs/2604.02007</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.02007.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Rafael Pardinas, Ehsan Kamalloo, David Vazquez, Alexandre Drouin</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Building general-purpose reasoning models using reinforcement learning with verifiable rewards (RLVR) across diverse domains has been widely adopted by frontier open-weight models. However, their training recipes and domain mixtures are often not disclosed. Joint optimization across domains poses significant challenges: domains vary widely in rollout length, problem difficulty and sample efficiency. Further, models with long chain-of-thought traces increase inference cost and latency, making efficiency critical for practical deployment. We present Apriel-Reasoner, trained with a fully reproducible multi-domain RL post-training recipe on Apriel-Base, a 15B-parameter open-weight LLM, across five domains using public datasets: mathematics, code generation, instruction following, logical puzzles and function calling. We introduce an adaptive domain sampling mechanism that preserves target domain ratios despite heterogeneous rollout dynamics, and a difficulty-aware extension of the standard length penalty that, with no additional training overhead, encourages longer reasoning for difficult problems and shorter traces for easy ones. Trained with a strict 16K-token output budget, Apriel-Reasoner generalizes to 32K tokens at inference and improves over Apriel-Base on AIME 2025, GPQA, MMLU-Pro, and LiveCodeBench while producing 30-50% shorter reasoning traces. It matches strong open-weight models of similar size at lower token cost, thereby pushing the Pareto frontier of accuracy versus token budget.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.02007</guid>
|
||||||
|
<pubDate>Thu, 02 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>T5Gemma-TTS Technical Report</title>
|
||||||
|
<link>https://arxiv.org/abs/2604.01760</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.01760.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chihiro Arata, Kiyoshi Kurihara</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Autoregressive neural codec language models have shown strong zero-shot voice cloning ability, but decoder-only architectures treat input text as a prefix that competes with the growing audio sequence for positional capacity, weakening text conditioning over long utterances. We present T5Gemma-TTS, an encoder-decoder codec language model that maintains persistent text conditioning by routing bidirectional text representations through cross-attention at every decoder layer. Built on the T5Gemma pretrained encoder-decoder backbone (2B encoder + 2B decoder; 4B parameters), it inherits rich linguistic knowledge without phoneme conversion and processes text directly at the subword level. To improve duration control, we introduce Progress-Monitoring Rotary Position Embedding (PM-RoPE) in all 26 cross-attention layers, injecting normalized progress signals that help the decoder track target speech length. Trained on 170,000 hours of multilingual speech in English, Chinese, and Japanese, T5Gemma-TTS achieves a statistically significant speaker-similarity gain on Japanese over XTTSv2 (0.677 vs. 0.622; non-overlapping 95% confidence intervals) and the highest numerical Korean speaker similarity (0.747) despite Korean not being included in training, although this margin over XTTSv2 (0.741) is not statistically conclusive. It also attains the lowest numerical Japanese character error rate among five baselines (0.126), though this ranking should be interpreted cautiously because of partial confidence-interval overlap with Kokoro. English results on LibriSpeech should be viewed as an upper-bound estimate because LibriHeavy is a superset of LibriSpeech. Using the same checkpoint, disabling PM-RoPE at inference causes near-complete synthesis failure: CER degrades from 0.129 to 0.982 and duration accuracy drops from 79% to 46%. Code and weights are available at https://github.com/Aratako/T5Gemma-TTS.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.01760</guid>
|
||||||
|
<pubDate>Thu, 02 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>DynaVid: Learning to Generate Highly Dynamic Videos using Synthetic Motion Data</title>
|
||||||
|
<link>https://arxiv.org/abs/2604.01666</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.01666.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wonjoon Jin, Jiyun Won, Janghyeok Han, Qi Dai, Chong Luo, Seung-Hwan Baek, Sunghyun Cho</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Despite recent progress, video diffusion models still struggle to synthesize realistic videos involving highly dynamic motions or requiring fine-grained motion controllability. A central limitation lies in the scarcity of such examples in commonly used training datasets. To address this, we introduce DynaVid, a video synthesis framework that leverages synthetic motion data in training, which is represented as optical flow and rendered using computer graphics pipelines. This approach offers two key advantages. First, synthetic motion offers diverse motion patterns and precise control signals that are difficult to obtain from real data. Second, unlike rendered videos with artificial appearances, rendered optical flow encodes only motion and is decoupled from appearance, thereby preventing models from reproducing the unnatural look of synthetic videos. Building on this idea, DynaVid adopts a two-stage generation framework: a motion generator first synthesizes motion, and then a motion-guided video generator produces video frames conditioned on that motion. This decoupled formulation enables the model to learn dynamic motion patterns from synthetic data while preserving visual realism from real-world videos. We validate our framework on two challenging scenarios, vigorous human motion generation and extreme camera motion control, where existing datasets are particularly limited. Extensive experiments demonstrate that DynaVid improves the realism and controllability in dynamic motion generation and camera motion control.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.01666</guid>
|
||||||
|
<pubDate>Thu, 02 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Omni123: Exploring 3D Native Foundation Models with Limited 3D Data by Unifying Text to 2D and 3D Generation</title>
|
||||||
|
<link>https://arxiv.org/abs/2604.02289</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.02289.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chongjie Ye, Cheng Cao, Chuanyu Pan, Yiming Hao, Yihao Zhi, Yuanming Hu, Xiaoguang Han</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Recent multimodal large language models have achieved strong performance in unified text and image understanding and generation, yet extending such native capability to 3D remains challenging due to limited data. Compared to abundant 2D imagery, high-quality 3D assets are scarce, making 3D synthesis under-constrained. Existing methods often rely on indirect pipelines that edit in 2D and lift results into 3D via optimization, sacrificing geometric consistency. We present Omni123, a 3D-native foundation model that unifies text-to-2D and text-to-3D generation within a single autoregressive framework. Our key insight is that cross-modal consistency between images and 3D can serve as an implicit structural constraint. By representing text, images, and 3D as discrete tokens in a shared sequence space, the model leverages abundant 2D data as a geometric prior to improve 3D representations. We introduce an interleaved X-to-X training paradigm that coordinates diverse cross-modal tasks over heterogeneous paired datasets without requiring fully aligned text-image-3D triplets. By traversing semantic-visual-geometric cycles (e.g., text to image to 3D to image) within autoregressive sequences, the model jointly enforces semantic alignment, appearance fidelity, and multi-view geometric consistency. Experiments show that Omni123 significantly improves text-guided 3D generation and editing, demonstrating a scalable path toward multimodal 3D world models.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.02289</guid>
|
||||||
|
<pubDate>Thu, 02 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>VideoZeroBench: Probing the Limits of Video MLLMs with Spatio-Temporal Evidence Verification</title>
|
||||||
|
<link>https://arxiv.org/abs/2604.01569</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.01569.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiahao Meng, Tan Yue, Qi Xu, Haochen Wang, Zhongwei Ren, Weisong Liu, Yuhao Wang, Renrui Zhang, Yunhai Tong, Haodong Duan</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Recent video multimodal large language models achieve impressive results across various benchmarks. However, current evaluations suffer from two critical limitations: (1) inflated scores can mask deficiencies in fine-grained visual understanding and reasoning, and (2) answer correctness is often measured without verifying whether models identify the precise spatio-temporal evidence supporting their predictions. To address this, we present VideoZeroBench, a hierarchical benchmark designed for challenging long-video question answering that rigorously verifies spatio-temporal evidence. It comprises 500 manually annotated questions across 13 domains, paired with temporal intervals and spatial bounding boxes as evidence. To disentangle answering generation, temporal grounding, and spatial grounding, we introduce a five-level evaluation protocol that progressively tightens evidence requirements. Experiments show that even Gemini-3-Pro correctly answers fewer than 17% of questions under the standard end-to-end QA setting (Level-3). When grounding constraints are imposed, performance drops sharply: No model exceeds 1% accuracy when both correct answering and accurate spatio-temporal localization are required (Level-5), with most failing to achieve any correct grounded predictions. These results expose a significant gap between surface-level answer correctness and genuine evidence-based reasoning, revealing that grounded video understanding remains a bottleneck for long-video QA. We further analyze performance across minimal evidence spans, atomic abilities, and inference paradigms, providing insights for future research in grounded video reasoning. The benchmark and code will be made publicly available.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.01569</guid>
|
||||||
|
<pubDate>Thu, 02 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Tex3D: Objects as Attack Surfaces via Adversarial 3D Textures for Vision-Language-Action Models</title>
|
||||||
|
<link>https://arxiv.org/abs/2604.01618</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.01618.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiawei Chen, Simin Huang, Jiawei Du, Shuaihang Chen, Yu Tian, Mingjie Wei, Chao Yu, Zhaoxia Yin</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Vision-language-action (VLA) models have shown strong performance in robotic manipulation, yet their robustness to physically realizable adversarial attacks remains underexplored. Existing studies reveal vulnerabilities through language perturbations and 2D visual attacks, but these attack surfaces are either less representative of real deployment or limited in physical realism. In contrast, adversarial 3D textures pose a more physically plausible and damaging threat, as they are naturally attached to manipulated objects and are easier to deploy in physical environments. Bringing adversarial 3D textures to VLA systems is nevertheless nontrivial. A central obstacle is that standard 3D simulators do not provide a differentiable optimization path from the VLA objective function back to object appearance, making it difficult to optimize through an end-to-end manner. To address this, we introduce Foreground-Background Decoupling (FBD), which enables differentiable texture optimization through dual-renderer alignment while preserving the original simulation environment. To further ensure that the attack remains effective across long-horizon and diverse viewpoints in the physical world, we propose Trajectory-Aware Adversarial Optimization (TAAO), which prioritizes behaviorally critical frames and stabilizes optimization with a vertex-based parameterization. Built on these designs, we present Tex3D, the first framework for end-to-end optimization of 3D adversarial textures directly within the VLA simulation environment. Experiments in both simulation and real-robot settings show that Tex3D significantly degrades VLA performance across multiple manipulation tasks, achieving task failure rates of up to 96.7\%. Our empirical results expose critical vulnerabilities of VLA systems to physically grounded 3D adversarial attacks and highlight the need for robustness-aware training.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.01618</guid>
|
||||||
|
<pubDate>Thu, 02 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>GPA: Learning GUI Process Automation from Demonstrations</title>
|
||||||
|
<link>https://arxiv.org/abs/2604.01676</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.01676.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zirui Zhao, Jun Hao Liew, Yan Yang, Wenzhuo Yang, Ziyang Luo, Doyen Sahoo, Silvio Savarese, Junnan Li</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> GUI Process Automation (GPA) is a lightweight but general vision-based Robotic Process Automation (RPA), which enables fast and stable process replay with only a single demo. Addressing the fragility of traditional RPA and the non-deterministic risks of current vision language model-based GUI agents, GPA introduces three core benefits: (1) Robustness via Sequential Monte Carlo-based localization to handle rescaling and detection uncertainty; (2) Deterministic and Reliability safeguarded by readiness calibration; and (3) Privacy through fast, fully local execution. This approach delivers the adaptability, robustness, and security required for enterprise workflows. It can also be used as an MCP/CLI tool by other agents with coding capabilities so that the agent only reasons and orchestrates while GPA handles the GUI execution. We conducted a pilot experiment to compare GPA with Gemini 3 Pro (with CUA tools) and found that GPA achieves higher success rate with 10 times faster execution speed in finishing long-horizon GUI tasks.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.01676</guid>
|
||||||
|
<pubDate>Thu, 02 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discovery</title>
|
||||||
|
<link>https://arxiv.org/abs/2604.01658</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.01658.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ao Qu, Han Zheng, Zijian Zhou, Yihao Yan, Yihong Tang, Shao Yong Ong, Fenglu Hong, Kaichen Zhou, Chonghe Jiang, Minwei Kong, Jiacheng Zhu, Xuan Jiang, Sirui Li, Cathy Wu, Bryan Kian Hsiang Low, Jinhua Zhao, Paul Pu Liang</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Large language model (LLM)-based evolution is a promising approach for open-ended discovery, where progress requires sustained search and knowledge accumulation. Existing methods still rely heavily on fixed heuristics and hard-coded exploration rules, which limit the autonomy of LLM agents. We present CORAL, the first framework for autonomous multi-agent evolution on open-ended problems. CORAL replaces rigid control with long-running agents that explore, reflect, and collaborate through shared persistent memory, asynchronous multi-agent execution, and heartbeat-based interventions. It also provides practical safeguards, including isolated workspaces, evaluator separation, resource management, and agent session and health management. Evaluated on diverse mathematical, algorithmic, and systems optimization tasks, CORAL sets new state-of-the-art results on 10 tasks, achieving 3-10 times higher improvement rates with far fewer evaluations than fixed evolutionary search baselines across tasks. On Anthropic's kernel engineering task, four co-evolving agents improve the best known score from 1363 to 1103 cycles. Mechanistic analyses further show how these gains arise from knowledge reuse and multi-agent exploration and communication. Together, these results suggest that greater agent autonomy and multi-agent evolution can substantially improve open-ended discovery. Code is available at https://github.com/Human-Agent-Society/CORAL.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.01658</guid>
|
||||||
|
<pubDate>Thu, 02 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>UniDriveVLA: Unifying Understanding, Perception, and Action Planning for Autonomous Driving</title>
|
||||||
|
<link>https://arxiv.org/abs/2604.02190</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.02190.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yongkang Li, Lijun Zhou, Sixu Yan, Bencheng Liao, Tianyi Yan, Kaixin Xiong, Long Chen, Hongwei Xie, Bing Wang, Guang Chen, Hangjun Ye, Wenyu Liu, Haiyang Sun, Xinggang Wang</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> Vision-Language-Action (VLA) models have recently emerged in autonomous driving, with the promise of leveraging rich world knowledge to improve the cognitive capabilities of driving systems. However, adapting such models for driving tasks currently faces a critical dilemma between spatial perception and semantic reasoning. Consequently, existing VLA systems are forced into suboptimal compromises: directly adopting 2D Vision-Language Models yields limited spatial perception, whereas enhancing them with 3D spatial representations often impairs the native reasoning capacity of VLMs. We argue that this dilemma largely stems from the coupled optimization of spatial perception and semantic reasoning within shared model parameters. To overcome this, we propose UniDriveVLA, a Unified Driving Vision-Language-Action model based on Mixture-of-Transformers that addresses the perception-reasoning conflict via expert decoupling. Specifically, it comprises three experts for driving understanding, scene perception, and action planning, which are coordinated through masked joint attention. In addition, we combine a sparse perception paradigm with a three-stage progressive training strategy to improve spatial perception while maintaining semantic reasoning capability. Extensive experiments show that UniDriveVLA achieves state-of-the-art performance in open-loop evaluation on nuScenes and closed-loop evaluation on Bench2Drive. Moreover, it demonstrates strong performance across a broad range of perception, prediction, and understanding tasks, including 3D detection, online mapping, motion forecasting, and driving-oriented VQA, highlighting its broad applicability as a unified model for autonomous driving. Code and model have been released at https://github.com/xiaomi-research/unidrivevla</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.02190</guid>
|
||||||
|
<pubDate>Thu, 02 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Therefore I am. I Think</title>
|
||||||
|
<link>https://arxiv.org/abs/2604.01202</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.01202.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Esakkivel Esakkiraja, Sai Rajeswar, Denis Akhiyarov, Rajagopal Venkatesaramani</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> We consider the question: when a large language reasoning model makes a choice, did it think first and then decide to, or decide first and then think? In this paper, we present evidence that detectable, early-encoded decisions shape chain-of-thought in reasoning models. Specifically, we show that a simple linear probe successfully decodes tool-calling decisions from pre-generation activations with very high confidence, and in some cases, even before a single reasoning token is produced. Activation steering supports this causally: perturbing the decision direction leads to inflated deliberation, and flips behavior in many examples (between 7 - 79% depending on model and benchmark). We also show through behavioral analysis that, when steering changes the decision, the chain-of-thought process often rationalizes the flip rather than resisting it. Together, these results suggest that reasoning models can encode action choices before they begin to deliberate in text.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.01202</guid>
|
||||||
|
<pubDate>Thu, 02 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Omni-SimpleMem: Autoresearch-Guided Discovery of Lifelong Multimodal Agent Memory</title>
|
||||||
|
<link>https://arxiv.org/abs/2604.01007</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.01007.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiaqi Liu, Zipeng Ling, Shi Qiu, Yanqing Liu, Siwei Han, Peng Xia, Haoqin Tu, Zeyu Zheng, Cihang Xie, Charles Fleming, Mingyu Ding, Huaxiu Yao</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> AI agents increasingly operate over extended time horizons, yet their ability to retain, organize, and recall multimodal experiences remains a critical bottleneck. Building effective lifelong memory requires navigating a vast design space spanning architecture, retrieval strategies, prompt engineering, and data pipelines; this space is too large and interconnected for manual exploration or traditional AutoML to explore effectively. We deploy an autonomous research pipeline to discover Omni-SimpleMem, a unified multimodal memory framework for lifelong AI agents. Starting from a naïve baseline (F1=0.117 on LoCoMo), the pipeline autonomously executes {sim}50 experiments across two benchmarks, diagnosing failure modes, proposing architectural modifications, and repairing data pipeline bugs, all without human intervention in the inner loop. The resulting system achieves state-of-the-art on both benchmarks, improving F1 by +411% on LoCoMo (0.117to0.598) and +214% on Mem-Gallery (0.254to0.797) relative to the initial configurations. Critically, the most impactful discoveries are not hyperparameter adjustments: bug fixes (+175%), architectural changes (+44%), and prompt engineering (+188% on specific categories) each individually exceed the cumulative contribution of all hyperparameter tuning, demonstrating capabilities fundamentally beyond the reach of traditional AutoML. We provide a taxonomy of six discovery types and identify four properties that make multimodal memory particularly suited for autoresearch, offering guidance for applying autonomous research pipelines to other AI system domains. Code is available at this https://github.com/aiming-lab/SimpleMem.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.01007</guid>
|
||||||
|
<pubDate>Thu, 02 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>VOID: Video Object and Interaction Deletion</title>
|
||||||
|
<link>https://arxiv.org/abs/2604.02296</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.02296.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Saman Motamed, William Harvey, Benjamin Klein, Luc Van Gool, Zhuoning Yuan, Ta-Ying Cheng</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Existing video object removal methods excel at inpainting content "behind" the object and correcting appearance-level artifacts such as shadows and reflections. However, when the removed object has more significant interactions, such as collisions with other objects, current models fail to correct them and produce implausible results. We present VOID, a video object removal framework designed to perform physically-plausible inpainting in these complex scenarios. To train the model, we generate a new paired dataset of counterfactual object removals using Kubric and HUMOTO, where removing an object requires altering downstream physical interactions. During inference, a vision-language model identifies regions of the scene affected by the removed object. These regions are then used to guide a video diffusion model that generates physically consistent counterfactual outcomes. Experiments on both synthetic and real data show that our approach better preserves consistent scene dynamics after object removal compared to prior video object removal methods. We hope this framework sheds light on how to make video editing models better simulators of the world through high-level causal reasoning.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.02296</guid>
|
||||||
|
<pubDate>Thu, 02 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>NearID: Identity Representation Learning via Near-identity Distractors</title>
|
||||||
|
<link>https://arxiv.org/abs/2604.01973</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.01973.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Aleksandar Cvejic, Rameen Abdal, Abdelrahman Eldesokey, Bernard Ghanem, Peter Wonka</p><p><b>Upvotes:</b> 20</p><p><b>Summary:</b> When evaluating identity-focused tasks such as personalized generation and image editing, existing vision encoders entangle object identity with background context, leading to unreliable representations and metrics. We introduce the first principled framework to address this vulnerability using Near-identity (NearID) distractors, where semantically similar but distinct instances are placed on the exact same background as a reference image, eliminating contextual shortcuts and isolating identity as the sole discriminative signal. Based on this principle, we present the NearID dataset (19K identities, 316K matched-context distractors) together with a strict margin-based evaluation protocol. Under this setting, pre-trained encoders perform poorly, achieving Sample Success Rates (SSR), a strict margin-based identity discrimination metric, as low as 30.7% and often ranking distractors above true cross-view matches. We address this by learning identity-aware representations on a frozen backbone using a two-tier contrastive objective enforcing the hierarchy: same identity > NearID distractor > random negative. This improves SSR to 99.2%, enhances part-level discrimination by 28.0%, and yields stronger alignment with human judgments on DreamBench++, a human-aligned benchmark for personalization. Project page: https://gorluxor.github.io/NearID/</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.01973</guid>
|
||||||
|
<pubDate>Thu, 02 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>LatentUM: Unleashing the Potential of Interleaved Cross-Modal Reasoning via a Latent-Space Unified Model</title>
|
||||||
|
<link>https://arxiv.org/abs/2604.02097</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.02097.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiachun Jin, Zetong Zhou, Xiao Yang, Hao Zhang, Pengfei Liu, Jun Zhu, Zhijie Deng</p><p><b>Upvotes:</b> 20</p><p><b>Summary:</b> Unified models (UMs) hold promise for their ability to understand and generate content across heterogeneous modalities. Compared to merely generating visual content, the use of UMs for interleaved cross-modal reasoning is more promising and valuable, e.g., for solving understanding problems that require dense visual thinking, improving visual generation through self-reflection, or modeling visual dynamics of the physical world guided by stepwise action interventions. However, existing UMs necessitate pixel decoding as a bridge due to their disjoint visual representations for understanding and generation, which is both ineffective and inefficient. In this paper, we introduce LatentUM, a novel unified model that represents all modalities within a shared semantic latent space, eliminating the need for pixel-space mediation between visual understanding and generation. This design naturally enables flexible interleaved cross-modal reasoning and generation. Beyond improved computational efficiency, the shared representation substantially alleviates codec bias and strengthens cross-modal alignment, allowing LatentUM to achieve state-of-the-art performance on the Visual Spatial Planning benchmark, push the limits of visual generation through self-reflection, and support world modeling by predicting future visual states within the shared semantic latent space.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.02097</guid>
|
||||||
|
<pubDate>Thu, 02 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Steerable Visual Representations</title>
|
||||||
|
<link>https://arxiv.org/abs/2604.02327</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.02327.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jona Ruthardt, Manu Gaur, Deva Ramanan, Makarand Tapaswi, Yuki M. Asano</p><p><b>Upvotes:</b> 28</p><p><b>Summary:</b> Pretrained Vision Transformers (ViTs) such as DINOv2 and MAE provide generic image features that can be applied to a variety of downstream tasks such as retrieval, classification, and segmentation. However, such representations tend to focus on the most salient visual cues in the image, with no way to direct them toward less prominent concepts of interest. In contrast, Multimodal LLMs can be guided with textual prompts, but the resulting representations tend to be language-centric and lose their effectiveness for generic visual tasks. To address this, we introduce Steerable Visual Representations, a new class of visual representations, whose global and local features can be steered with natural language. While most vision-language models (e.g., CLIP) fuse text with visual features after encoding (late fusion), we inject text directly into the layers of the visual encoder (early fusion) via lightweight cross-attention. We introduce benchmarks for measuring representational steerability, and demonstrate that our steerable visual features can focus on any desired objects in an image while preserving the underlying representation quality. Our method also matches or outperforms dedicated approaches on anomaly detection and personalized object discrimination, exhibiting zero-shot generalization to out-of-distribution tasks.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.02327</guid>
|
||||||
|
<pubDate>Thu, 02 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization</title>
|
||||||
|
<link>https://arxiv.org/abs/2604.02268</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.02268.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhengxi Lu, Zhiyuan Yao, Jinyang Wu, Chengcheng Han, Qi Gu, Xunliang Cai, Weiming Lu, Jun Xiao, Yueting Zhuang, Yongliang Shen</p><p><b>Upvotes:</b> 72</p><p><b>Summary:</b> Agent skills, structured packages of procedural knowledge and executable resources that agents dynamically load at inference time, have become a reliable mechanism for augmenting LLM agents. Yet inference-time skill augmentation is fundamentally limited: retrieval noise introduces irrelevant guidance, injected skill content imposes substantial token overhead, and the model never truly acquires the knowledge it merely follows. We ask whether skills can instead be internalized into model parameters, enabling zero-shot autonomous behavior without any runtime skill retrieval. We introduce SKILL0, an in-context reinforcement learning framework designed for skill internalization. SKILL0 introduces a training-time curriculum that begins with full skill context and progressively withdraws it. Skills are grouped offline by category and rendered with interaction history into a compact visual context, teaching he model tool invocation and multi-turn task completion. A Dynamic Curriculum then evaluates each skill file's on-policy helpfulness, retaining only those from which the current policy still benefits within a linearly decaying budget, until the agent operates in a fully zero-shot setting. Extensive agentic experiments demonstrate that SKILL0 achieves substantial improvements over the standard RL baseline (+9.7\% for ALFWorld and +6.6\% for Search-QA), while maintaining a highly efficient context of fewer than 0.5k tokens per step. Our code is available at https://github.com/ZJU-REAL/SkillZero.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.02268</guid>
|
||||||
|
<pubDate>Thu, 02 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Generative World Renderer</title>
|
||||||
|
<link>https://arxiv.org/abs/2604.02329</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.02329.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zheng-Hui Huang, Zhixiang Wang, Jiaming Tan, Ruihan Yu, Yidan Zhang, Bo Zheng, Yu-Lun Liu, Yung-Yu Chuang, Kaipeng Zhang</p><p><b>Upvotes:</b> 74</p><p><b>Summary:</b> Scaling generative inverse and forward rendering to real-world scenarios is bottlenecked by the limited realism and temporal coherence of existing synthetic datasets. To bridge this persistent domain gap, we introduce a large-scale, dynamic dataset curated from visually complex AAA games. Using a novel dual-screen stitched capture method, we extracted 4M continuous frames (720p/30 FPS) of synchronized RGB and five G-buffer channels across diverse scenes, visual effects, and environments, including adverse weather and motion-blur variants. This dataset uniquely advances bidirectional rendering: enabling robust in-the-wild geometry and material decomposition, and facilitating high-fidelity G-buffer-guided video generation. Furthermore, to evaluate the real-world performance of inverse rendering without ground truth, we propose a novel VLM-based assessment protocol measuring semantic, spatial, and temporal consistency. Experiments demonstrate that inverse renderers fine-tuned on our data achieve superior cross-dataset generalization and controllable generation, while our VLM evaluation strongly correlates with human judgment. Combined with our toolkit, our forward renderer enables users to edit styles of AAA games from G-buffers using text prompts.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.02329</guid>
|
||||||
|
<pubDate>Thu, 02 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook</title>
|
||||||
|
<link>https://arxiv.org/abs/2604.02029</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.02029.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xinlei Yu, Zhangquan Chen, Yongbo He, Tianyu Fu, Cheng Yang, Chengming Xu, Yue Ma, Xiaobin Hu, Zhe Cao, Jie Xu, Guibin Zhang, Jiale Tao, Jiayi Zhang, Siyuan Ma, Kaituo Feng, Haojie Huang, Youxing Li, Ronghao Chen, Huacan Wang, Chenglin Wu, Zikun Su, Xiaogang Xu, Kelu Yao, Kun Wang, Chen Gao, Yue Liao, Ruqi Huang, Tao Jin, Cheng Tan, Jiangning Zhang, Wenqi Ren, Yanwei Fu, Yong Liu, Yu Wang, Xiangyu Yue, Yu-Gang Jiang, Shuicheng Yan</p><p><b>Upvotes:</b> 98</p><p><b>Summary:</b> Latent space is rapidly emerging as a native substrate for language-based models. While modern systems are still commonly understood through explicit token-level generation, an increasing body of work shows that many critical internal processes are more naturally carried out in continuous latent space than in human-readable verbal traces. This shift is driven by the structural limitations of explicit-space computation, including linguistic redundancy, discretization bottlenecks, sequential inefficiency, and semantic loss. This survey aims to provide a unified and up-to-date landscape of latent space in language-based models. We organize the survey into five sequential perspectives: Foundation, Evolution, Mechanism, Ability, and Outlook. We begin by delineating the scope of latent space, distinguishing it from explicit or verbal space and from the latent spaces commonly studied in generative visual models. We then trace the field's evolution from early exploratory efforts to the current large-scale expansion. To organize the technical landscape, we examine existing work through the complementary lenses of mechanism and ability. From the perspective of Mechanism, we identify four major lines of development: Architecture, Representation, Computation, and Optimization. From the perspective of Ability, we show how latent space supports a broad capability spectrum spanning Reasoning, Planning, Modeling, Perception, Memory, Collaboration, and Embodiment. Beyond consolidation, we discuss the key open challenges, and outline promising directions for future research. We hope this survey serves not only as a reference for existing work, but also as a foundation for understanding latent space as a general computational and systems paradigm for next-generation intelligence.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.02029</guid>
|
||||||
|
<pubDate>Thu, 02 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
</channel>
|
</channel>
|
||||||
</rss>
|
</rss>
|
||||||
|
|||||||
Reference in New Issue
Block a user