diff --git a/feed.xml b/feed.xml index c466e52..8e557fe 100644 --- a/feed.xml +++ b/feed.xml @@ -7,216 +7,202 @@ http://www.rssboard.org/rss-specification python-feedgen en - Thu, 09 Apr 2026 00:06:35 +0000 + Fri, 10 Apr 2026 00:09:11 +0000 - Learning to Retrieve from Agent Trajectories - https://arxiv.org/abs/2604.04949 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.04949.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuqi Zhou, Sunhao Dai, Changle Qu, Liang Pang, Jun Xu, Ji-Rong Wen</p><p><b>Upvotes:</b> 55</p><p><b>Summary:</b> Information retrieval (IR) systems have traditionally been designed and trained for human users, with learning-to-rank methods relying heavily on large-scale human interaction logs such as clicks and dwell time. With the rapid emergence of large language model (LLM) powered search agents, however, retrieval is increasingly consumed by agents rather than human beings, and is embedded as a core component within multi-turn reasoning and action loops. In this setting, retrieval models trained under human-centric assumptions exhibit a fundamental mismatch with the way agents issue queries and consume results. In this work, we argue that retrieval models for agentic search should be trained directly from agent interaction data. We introduce learning to retrieve from agent trajectories as a new training paradigm, where supervision is derived from multi-step agent interactions. Through a systematic analysis of search agent trajectories, we identify key behavioral signals that reveal document utility, including browsing actions, unbrowsed rejections, and post-browse reasoning traces. Guided by these insights, we propose LRAT, a simple yet effective framework that mines high-quality retrieval supervision from agent trajectories and incorporates relevance intensity through weighted optimization. Extensive experiments on both in-domain and out-of-domain deep research benchmarks demonstrate that retrievers trained with LRAT consistently improve evidence recall, end-to-end task success, and execution efficiency across diverse agent architectures and scales. Our results highlight agent trajectories as a practical and scalable supervision source, pointing to a promising direction for retrieval in the era of agentic search.</p> - https://arxiv.org/abs/2604.04949 - Mon, 30 Mar 2026 00:00:00 +0000 + VenusBench-Mobile: A Challenging and User-Centric Benchmark for Mobile GUI Agents with Capability Diagnostics + https://arxiv.org/abs/2604.06182 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.06182.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yichen Gong, Zhuohan Cai, Sunhao Dai, Yuqi Zhou, Zhangxuan Gu, Changhua Meng, Shuheng Shen</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Existing online benchmarks for mobile GUI agents remain largely app-centric and task-homogeneous, failing to reflect the diversity and instability of real-world mobile usage. To this end, we introduce VenusBench-Mobile, a challenging online benchmark for evaluating general-purpose mobile GUI agents under realistic, user-centric conditions. VenusBench-Mobile builds two core evaluation pillars: defining what to evaluate via user-intent-driven task design that reflects real mobile usage, and how to evaluate through a capability-oriented annotation scheme for fine-grained agent behavior analysis. Extensive evaluation of state-of-the-art mobile GUI agents reveals large performance gaps relative to prior benchmarks, indicating that VenusBench-Mobile poses substantially more challenging and realistic tasks and that current agents remain far from reliable real-world deployment. Diagnostic analysis further shows that failures are dominated by deficiencies in perception and memory, which are largely obscured by coarse-grained evaluations. Moreover, even the strongest agents exhibit near-zero success under environment variations, highlighting their brittleness in realistic settings. Based on these insights, we believe VenusBench-Mobile provides an important stepping stone toward robust real-world deployment of mobile GUI agents. Code and data are available at https://github.com/inclusionAI/UI-Venus/tree/VenusBench-Mobile.</p> + https://arxiv.org/abs/2604.06182 + Fri, 06 Feb 2026 00:00:00 +0000 - Expert-Choice Routing Enables Adaptive Computation in Diffusion Language Models - https://arxiv.org/abs/2604.01622 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.01622.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shuibai Zhang, Caspian Zhuang, Chihan Cui, Zhihan Yang, Fred Zhangzhi Peng, Yanxin Zhang, Haoyue Bai, Zack Jia, Yang Zhou, Guanhua Chen, Ming Liu</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Diffusion language models (DLMs) enable parallel, non-autoregressive text generation, yet existing DLM mixture-of-experts (MoE) models inherit token-choice (TC) routing from autoregressive systems, leading to load imbalance and rigid computation allocation. We show that expert-choice (EC) routing is a better fit for DLMs: it provides deterministic load balancing by design, yielding higher throughput and faster convergence than TC. Building on the property that EC capacity is externally controllable, we introduce timestep-dependent expert capacity, which varies expert allocation according to the denoising step. We find that allocating more capacity to low-mask-ratio steps consistently achieves the best performance under matched FLOPs, and provide a mechanistic explanation: tokens in low-mask-ratio contexts exhibit an order-of-magnitude higher learning efficiency, so concentrating compute on these steps yields the largest marginal return. Finally, we show that existing pretrained TC DLMs can be retrofitted to EC by replacing only the router, achieving faster convergence and improved accuracy across diverse downstream tasks. Together, these results establish EC routing as a superior paradigm for DLM MoE models and demonstrate that computation in DLMs can be treated as an adaptive policy rather than a fixed architectural constant. Code is available at https://github.com/zhangshuibai/EC-DLM.</p> - https://arxiv.org/abs/2604.01622 - Thu, 02 Apr 2026 00:00:00 +0000 + SEVerA: Verified Synthesis of Self-Evolving Agents + https://arxiv.org/abs/2603.25111 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.25111.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Debangshu Banerjee, Changming Xu, Gagandeep Singh</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> Recent advances have shown the effectiveness of self-evolving LLM agents on tasks such as program repair and scientific discovery. In this paradigm, a planner LLM synthesizes an agent program that invokes parametric models, including LLMs, which are then tuned per task to improve performance. However, existing self-evolving agent frameworks provide no formal guarantees of safety or correctness. Because such programs are often executed autonomously on unseen inputs, this lack of guarantees raises reliability and security concerns. We formulate agentic code generation as a constrained learning problem, combining hard formal specifications with soft objectives capturing task utility. We introduce Formally Guarded Generative Models (FGGM), which allow the planner LLM to specify a formal output contract for each generative model call using first-order logic. Each FGGM call wraps the underlying model in a rejection sampler with a verified fallback, ensuring every returned output satisfies the contract for any input and parameter setting. Building on FGGM, we present SEVerA (Self-Evolving Verified Agents), a three-stage framework: Search synthesizes candidate parametric programs containing FGGM calls; Verification proves correctness with respect to hard constraints for all parameter values, reducing the problem to unconstrained learning; and Learning applies scalable gradient-based optimization, including GRPO-style fine-tuning, to improve the soft objective while preserving correctness. We evaluate SEVerA on Dafny program verification, symbolic math synthesis, and policy-compliant agentic tool use (τ^2-bench). Across tasks, SEVerA achieves zero constraint violations while improving performance over unconstrained and SOTA baselines, showing that formal behavioral constraints not only guarantee correctness but also steer synthesis toward higher-quality agents.</p> + https://arxiv.org/abs/2603.25111 + Thu, 26 Mar 2026 00:00:00 +0000 - ThinkTwice: Jointly Optimizing Large Language Models for Reasoning and Self-Refinement - https://arxiv.org/abs/2604.01591 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.01591.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Difan Jiao, Qianfeng Wen, Blair Yang, Zhenwei Tang, Ashton Anderson</p><p><b>Upvotes:</b> 32</p><p><b>Summary:</b> We introduce ThinkTwice, a simple two-phase framework that jointly optimizes LLMs to solve reasoning problems and refine the answers, based on Group Relative Policy Optimization (GRPO). In each pair of training steps, ThinkTwice first optimizes the model on solving reasoning problems, then optimizes it on refining its own solutions to the same problems, using the same binary correctness reward in both phases without correctness signals or critique annotations. Across five mathematical reasoning benchmarks and two model families including Qwen3-4B and Olmo3-7B, ThinkTwice substantially improves both reasoning and refinement performance over competitive online policy optimization baselines. Specifically, on Qwen3-4B, ThinkTwice outperforms GRPO on AIME by 5 percentage points before refinement and by 11.5 points after one self-refinement step, measured by pass@4. Analysis of the training dynamics of ThinkTwice reveals an implicit rectify-then-fortify curriculum: refinement predominantly corrects errors early in training and naturally shifts toward preserving already-correct solutions as the model improves, yielding a more rectified reward signal. Our work establishes joint training of reasoning and self-refinement as a principled and effective methodology for RLVR.</p> - https://arxiv.org/abs/2604.01591 - Thu, 02 Apr 2026 00:00:00 +0000 + Tunable Soft Equivariance with Guarantees + https://arxiv.org/abs/2603.26657 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.26657.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Md Ashiqur Rahman, Lim Jun Hao, Jeremiah Jiang, Teck-Yian Lim, Raymond A. Yeh</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Equivariance is a fundamental property in computer vision models, yet strict equivariance is rarely satisfied in real-world data, which can limit a model's performance. Controlling the degree of equivariance is therefore desirable. We propose a general framework for constructing soft equivariant models by projecting the model weights into a designed subspace. The method applies to any pre-trained architecture and provides theoretical bounds on the induced equivariance error. Empirically, we demonstrate the effectiveness of our method on multiple pre-trained backbones, including ViT and ResNet, across image classification, semantic segmentation, and human-trajectory prediction tasks. Notably, our approach improves the performance while simultaneously reducing equivariance error on the competitive ImageNet benchmark.</p> + https://arxiv.org/abs/2603.26657 + Fri, 27 Mar 2026 17:56:25 +0000 - GBQA: A Game Benchmark for Evaluating LLMs as Quality Assurance Engineers - https://arxiv.org/abs/2604.02648 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.02648.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shufan Jiang, Chios Chen, Zhiyang Chen</p><p><b>Upvotes:</b> 37</p><p><b>Summary:</b> The autonomous discovery of bugs remains a significant challenge in modern software development. Compared to code generation, the complexity of dynamic runtime environments makes bug discovery considerably harder for large language models (LLMs). In this paper, we take game development as a representative domain and introduce the Game Benchmark for Quality Assurance (GBQA), a benchmark containing 30 games and 124 human-verified bugs across three difficulty levels, to evaluate whether LLMs can autonomously detect software bugs. The benchmark is constructed using a multi-agent system that develops games and injects bugs in a scalable manner, with human experts in the loop to ensure correctness. Moreover, we provide a baseline interactive agent equipped with a multi-round ReAct loop and a memory mechanism, enabling long-horizon exploration of game environments for bug detection across different LLMs. Extensive experiments on frontier LLMs demonstrate that autonomous bug discovery remains highly challenging: the best-performing model, Claude-4.6-Opus in thinking mode, identifies only 48.39% of the verified bugs. We believe GBQA provides an adequate testbed and evaluation criterion, and that further progress on it will help close the gap in autonomous software engineering.</p> - https://arxiv.org/abs/2604.02648 - Fri, 03 Apr 2026 00:00:00 +0000 + Learning to Hint for Reinforcement Learning + https://arxiv.org/abs/2604.00698 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.00698.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yu Xia, Canwen Xu, Zhewei Yao, Julian McAuley, Yuxiong He</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Group Relative Policy Optimization (GRPO) is widely used for reinforcement learning with verifiable rewards, but it often suffers from advantage collapse: when all rollouts in a group receive the same reward, the group yields zero relative advantage and thus no learning signal. For example, if a question is too hard for the reasoner, all sampled rollouts can be incorrect and receive zero reward. Recent work addresses this issue by adding hints or auxiliary scaffolds to such hard questions so that the reasoner produces mixed outcomes and recovers a non-zero update. However, existing hints are usually fixed rather than adapted to the current reasoner, and a hint that creates learning signal under the hinted input does not necessarily improve the no-hint policy used at test time. To this end, we propose Hint Learning for Reinforcement Learning (HiLL), a framework that jointly trains a hinter policy and a reasoner policy during RL. For each hard question, the hinter generates hints online conditioned on the current reasoner's incorrect rollout, allowing hint generation to adapt to the reasoner's evolving errors. We further introduce hint reliance, which measures how strongly correct hinted trajectories depend on the hint. We derive a transferability result showing that lower hint reliance implies stronger transfer from hinted success to no-hint success, and we use this result to define a transfer-weighted reward for training the hinter. Therefore, HiLL favors hints that not only recover informative GRPO groups, but also produce signals that are more likely to improve the original no-hint policy. Experiments across multiple benchmarks show that HiLL consistently outperforms GRPO and prior hint-based baselines, demonstrating the value of adaptive and transfer-aware hint learning for RL. The code is available at https://github.com/Andree-9/HiLL.</p> + https://arxiv.org/abs/2604.00698 + Wed, 01 Apr 2026 00:00:00 +0000 - Can Natural Image Autoencoders Compactly Tokenize fMRI Volumes for Long-Range Dynamics Modeling? - https://arxiv.org/abs/2604.03619 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.03619.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Peter Yongho Kim, Juhyeon Park, Jungwoo Park, Jubin Choi, Jungwoo Seo, Jiook Cha, Taesup Moon</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Modeling long-range spatiotemporal dynamics in functional Magnetic Resonance Imaging (fMRI) remains a key challenge due to the high dimensionality of the four-dimensional signals. Prior voxel-based models, although demonstrating excellent performance and interpretation capabilities, are constrained by prohibitive memory demands and thus can only capture limited temporal windows. To address this, we propose TABLeT (Two-dimensionally Autoencoded Brain Latent Transformer), a novel approach that tokenizes fMRI volumes using a pre-trained 2D natural image autoencoder. Each 3D fMRI volume is compressed into a compact set of continuous tokens, enabling long-sequence modeling with a simple Transformer encoder with limited VRAM. Across large-scale benchmarks including the UK-Biobank (UKB), Human Connectome Project (HCP), and ADHD-200 datasets, TABLeT outperforms existing models in multiple tasks, while demonstrating substantial gains in computational and memory efficiency over the state-of-the-art voxel-based method given the same input. Furthermore, we develop a self-supervised masked token modeling approach to pre-train TABLeT, which improves the model's performance for various downstream tasks. Our findings suggest a promising approach for scalable and interpretable spatiotemporal modeling of brain activity. Our code is available at https://github.com/beotborry/TABLeT.</p> - https://arxiv.org/abs/2604.03619 - Sat, 04 Apr 2026 00:00:00 +0000 - - - Squeez: Task-Conditioned Tool-Output Pruning for Coding Agents - https://arxiv.org/abs/2604.04979 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.04979.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ádám Kovács</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Coding agents repeatedly consume long tool observations even though only a small fraction of each observation matters for the next step. We study task-conditioned tool-output pruning: given a focused query and one tool output, return the smallest verbatim evidence block the agent should inspect next. We introduce a benchmark of 11,477 examples built from SWE-bench repository interactions and synthetic multi-ecosystem tool outputs, with a manually curated 618-example test set. We fine-tune Qwen 3.5 2B with LoRA and compare it against larger zero-shot models and heuristic pruning baselines. Our model reaches 0.86 recall and 0.80 F1 while removing 92% of input tokens, outperforming zero-shot Qwen 3.5 35B A3B by 11 recall points and all heuristic baselines by a wide margin.</p> - https://arxiv.org/abs/2604.04979 - Sat, 04 Apr 2026 00:00:00 +0000 - - - DARE: Diffusion Large Language Models Alignment and Reinforcement Executor - https://arxiv.org/abs/2604.04215 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.04215.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jingyi Yang, Yuxian Jiang, Xuhao Hu, Shuang Cheng, Biqing Qi, Jing Shao</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> Diffusion large language models (dLLMs) are emerging as a compelling alternative to dominant autoregressive models, replacing strictly sequential token generation with iterative denoising and parallel generation dynamics. However, their open-source ecosystem remains fragmented across model families and, in particular, across post-training pipelines, where reinforcement learning objectives, rollout implementations and evaluation scripts are often released as paper-specific codebases. This fragmentation slows research iteration, raises the engineering burden of reproduction, and makes fair comparison across algorithms difficult. We present DARE (dLLMs Alignment and Reinforcement Executor), an open framework for post-training and evaluating dLLMs. Built on top of verl~sheng2024hybridflow and OpenCompass~2023opencompass, DARE unifies supervised fine-tuning, parameter-efficient fine-tuning, preference optimization, and dLLM-specific reinforcement learning under a shared execution stack for both masked and block diffusion language models. Across representative model families including LLaDA, Dream, SDAR, and LLaDA2.x, DARE provides broad algorithmic coverage, reproducible benchmark evaluation, and practical acceleration. Extensive empirical results position that DARE serves as a reusable research substrate for developing, comparing, and deploying post-training methods for current and emerging dLLMs.</p> - https://arxiv.org/abs/2604.04215 + A Systematic Study of Cross-Modal Typographic Attacks on Audio-Visual Reasoning + https://arxiv.org/abs/2604.03995 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.03995.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tianle Chen, Deepti Ghadiyaram</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> As audio-visual multi-modal large language models (MLLMs) are increasingly deployed in safety-critical applications, understanding their vulnerabilities is crucial. To this end, we introduce Multi-Modal Typography, a systematic study examining how typographic attacks across multiple modalities adversely influence MLLMs. While prior work focuses narrowly on unimodal attacks, we expose the cross-modal fragility of MLLMs. We analyze the interactions between audio, visual, and text perturbations and reveal that coordinated multi-modal attack creates a significantly more potent threat than single-modality attacks (attack success rate = 83.43% vs 34.93%).Our findings across multiple frontier MLLMs, tasks, and common-sense reasoning and content moderation benchmarks establishes multi-modal typography as a critical and underexplored attack strategy in multi-modal reasoning. Code and data will be publicly available.</p> + https://arxiv.org/abs/2604.03995 Sun, 05 Apr 2026 00:00:00 +0000 - ACES: Who Tests the Tests? Leave-One-Out AUC Consistency for Code Generation - https://arxiv.org/abs/2604.03922 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.03922.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hui Sun, Yun-Ji Zhang, Zheng Xie, Ren-Biao Liu, Yali Du, Xin-Ye Li, Ming Li</p><p><b>Upvotes:</b> 46</p><p><b>Summary:</b> Selecting LLM-generated code candidates using LLM-generated tests is challenging because the tests themselves may be incorrect. Existing methods either treat all tests equally or rely on ad-hoc heuristics to filter unreliable tests. Yet determining test correctness requires knowing which codes are correct, creating a circular dependency. Our key insight is that we need not determine test correctness at all: test votes should rank, not merely count. What matters is not how many codes pass a test, but whether the test can distinguish correct from incorrect code. We break the circular dependency via leave-one-out evaluation: hold out one test, rank codes by their aggregate scores on all remaining tests, and measure whether the held-out test's pass/fail pattern agrees with this ranking. We formalize this agreement as the leave-one-out AUC~(LOO-AUC) and prove that the expected LOO-AUC is proportional to each test's ability to separate correct code from incorrect code. Building on this, we propose ACES~(AUC ConsistEncy Scoring) with two complementary variants: ACES-C provides closed-form weights that provably approximate the oracle in expectation under a mild assumption on average test quality; ACES-O drops this assumption and iteratively optimizes a differentiable LOO-AUC objective. Both operate solely on the binary pass matrix with negligible overhead, and achieve state-of-the-art Pass@k on multiple code generation benchmarks.</p> - https://arxiv.org/abs/2604.03922 + Combee: Scaling Prompt Learning for Self-Improving Language Model Agents + https://arxiv.org/abs/2604.04247 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.04247.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hanchen Li, Runyuan He, Qizheng Zhang, Changxiu Ji, Qiuyang Mang, Xiaokun Chen, Lakshya A Agrawal, Wei-Liang Liao, Eric Yang, Alvin Cheung, James Zou, Kunle Olukotun, Ion Stoica, Joseph E. Gonzalez</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> Recent advances in prompt learning allow large language model agents to acquire task-relevant knowledge from inference-time context without parameter changes. For example, existing methods (like ACE or GEPA) can learn system prompts to improve accuracy based on previous agent runs. However, these methods primarily focus on single-agent or low-parallelism settings. This fundamentally limits their ability to efficiently learn from a large set of collected agentic traces. It would be efficient and beneficial to run prompt learning in parallel to accommodate the growing trend of learning from many agentic traces or parallel agent executions. Yet without a principled strategy for scaling, current methods suffer from quality degradation with high parallelism. To improve both the efficiency and quality of prompt learning, we propose Combee, a novel framework to scale parallel prompt learning for self-improving agents. Combee speeds up learning and enables running many agents in parallel while learning from their aggregate traces without quality degradation. To achieve this, Combee leverages parallel scans and employs an augmented shuffle mechanism; Combee also introduces a dynamic batch size controller to balance quality and delay. Evaluations on AppWorld, Terminal-Bench, Formula, and FiNER demonstrate that Combee achieves up to 17x speedup over previous methods with comparable or better accuracy and equivalent cost.</p> + https://arxiv.org/abs/2604.04247 Sun, 05 Apr 2026 00:00:00 +0000 - REAM: Merging Improves Pruning of Experts in LLMs - https://arxiv.org/abs/2604.04356 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.04356.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Saurav Jha, Maryam Hashemzadeh, Ali Saheb Pasand, Ali Parviz, Min-Joong Lee, Boris Knyazev</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Mixture-of-Experts (MoE) large language models (LLMs) are among the top-performing architectures. The largest models, often with hundreds of billions of parameters, pose significant memory challenges for deployment. Traditional approaches to reduce memory requirements include weight pruning and quantization. Motivated by the Router-weighted Expert Activation Pruning (REAP) that prunes experts, we propose a novel method, Router-weighted Expert Activation Merging (REAM). Instead of removing experts, REAM groups them and merges their weights, better preserving original performance. We evaluate REAM against REAP and other baselines across multiple MoE LLMs on diverse multiple-choice (MC) question answering and generative (GEN) benchmarks. Our results reveal a trade-off between MC and GEN performance that depends on the mix of calibration data. By controlling the mix of general, math and coding data, we examine the Pareto frontier of this trade-off and show that REAM often outperforms the baselines and in many cases is comparable to the original uncompressed models.</p> - https://arxiv.org/abs/2604.04356 + R3PM-Net: Real-time, Robust, Real-world Point Matching Network + https://arxiv.org/abs/2604.05060 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.05060.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yasaman Kashefbahrami, Erkut Akdag, Panagiotis Meletis, Evgeniya Balmashnova, Dip Goswami, Egor Bondarau</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Accurate Point Cloud Registration (PCR) is an important task in 3D data processing, involving the estimation of a rigid transformation between two point clouds. While deep-learning methods have addressed key limitations of traditional non-learning approaches, such as sensitivity to noise, outliers, occlusion, and initialization, they are developed and evaluated on clean, dense, synthetic datasets (limiting their generalizability to real-world industrial scenarios). This paper introduces R3PM-Net, a lightweight, global-aware, object-level point matching network designed to bridge this gap by prioritizing both generalizability and real-time efficiency. To support this transition, two datasets, Sioux-Cranfield and Sioux-Scans, are proposed. They provide an evaluation ground for registering imperfect photogrammetric and event-camera scans to digital CAD models, and have been made publicly available. Extensive experiments demonstrate that R3PM-Net achieves competitive accuracy with unmatched speed. On ModelNet40, it reaches a perfect fitness score of 1 and inlier RMSE of 0.029 cm in only 0.007s, approximately 7 times faster than the state-of-the-art method RegTR. This performance carries over to the Sioux-Cranfield dataset, maintaining a fitness of 1 and inlier RMSE of 0.030 cm with similarly low latency. Furthermore, on the highly challenging Sioux-Scans dataset, R3PM-Net successfully resolves edge cases in under 50 ms. These results confirm that R3PM-Net offers a robust, high-speed solution for critical industrial applications, where precision and real-time performance are indispensable. The code and datasets are available at https://github.com/YasiiKB/R3PM-Net.</p> + https://arxiv.org/abs/2604.05060 Mon, 06 Apr 2026 00:00:00 +0000 - MedGemma 1.5 Technical Report - https://arxiv.org/abs/2604.05081 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.05081.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Andrew Sellergren, Chufan Gao, Fereshteh Mahvar, Timo Kohlberger, Fayaz Jamil, Madeleine Traverse, Alberto Tono, Bashir Sadjad, Lin Yang, Charles Lau, Liron Yatziv, Tiffany Chen, Bram Sterling, Kenneth Philbrick, Richa Tiwari, Yun Liu, Madhuram Jajoo, Chandrashekar Sankarapu, Swapnil Vispute, Harshad Purandare, Abhishek Bijay Mishra, Sam Schmidgall, Tao Tu, Anil Palepu, Chunjong Park, Tim Strother, Rahul Thapa, Yong Cheng, Preeti Singh, Kat Black, Yossi Matias, Katherine Chou, Avinatan Hassidim, Kavi Goel, Joelle Barral, Tris Warkentin, Shravya Shetty, Dale Webster, Sunny Virmani, David F. Steiner, Can Kirmizibayrak, Daniel Golden</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> We introduce MedGemma 1.5 4B, the latest model in the MedGemma collection. MedGemma 1.5 expands on MedGemma 1 by integrating additional capabilities: high-dimensional medical imaging (CT/MRI volumes and histopathology whole slide images), anatomical localization via bounding boxes, multi-timepoint chest X-ray analysis, and improved medical document understanding (lab reports, electronic health records). We detail the innovations required to enable these modalities within a single architecture, including new training data, long-context 3D volume slicing, and whole-slide pathology sampling. Compared to MedGemma 1 4B, MedGemma 1.5 4B demonstrates significant gains in these new areas, improving 3D MRI condition classification accuracy by 11% and 3D CT condition classification by 3% (absolute improvements). In whole slide pathology imaging, MedGemma 1.5 4B achieves a 47% macro F1 gain. Additionally, it improves anatomical localization with a 35% increase in Intersection over Union on chest X-rays and achieves a 4% macro accuracy for longitudinal (multi-timepoint) chest x-ray analysis. Beyond its improved multimodal performance over MedGemma 1, MedGemma 1.5 improves on text-based clinical knowledge and reasoning, improving by 5% on MedQA accuracy and 22% on EHRQA accuracy. It also achieves an average of 18% macro F1 on 4 different lab report information extraction datasets (EHR Datasets 2, 3, 4, and Mendeley Clinical Laboratory Test Reports). Taken together, MedGemma 1.5 serves as a robust, open resource for the community, designed as an improved foundation on which developers can create the next generation of medical AI systems. Resources and tutorials for building upon MedGemma 1.5 can be found at https://goo.gle/MedGemma.</p> - https://arxiv.org/abs/2604.05081 + A Frame is Worth One Token: Efficient Generative World Modeling with Delta Tokens + https://arxiv.org/abs/2604.04913 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.04913.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tommie Kerssies, Gabriele Berton, Ju He, Qihang Yu, Wufei Ma, Daan de Geus, Gijs Dubbelman, Liang-Chieh Chen</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Anticipating diverse future states is a central challenge in video world modeling. Discriminative world models produce a deterministic prediction that implicitly averages over possible futures, while existing generative world models remain computationally expensive. Recent work demonstrates that predicting the future in the feature space of a vision foundation model (VFM), rather than a latent space optimized for pixel reconstruction, requires significantly fewer world model parameters. However, most such approaches remain discriminative. In this work, we introduce DeltaTok, a tokenizer that encodes the VFM feature difference between consecutive frames into a single continuous "delta" token, and DeltaWorld, a generative world model operating on these tokens to efficiently generate diverse plausible futures. Delta tokens reduce video from a three-dimensional spatio-temporal representation to a one-dimensional temporal sequence, for example yielding a 1,024x token reduction with 512x512 frames. This compact representation enables tractable multi-hypothesis training, where many futures are generated in parallel and only the best is supervised. At inference, this leads to diverse predictions in a single forward pass. Experiments on dense forecasting tasks demonstrate that DeltaWorld forecasts futures that more closely align with real-world outcomes, while having over 35x fewer parameters and using 2,000x fewer FLOPs than existing generative world models. Code and weights: https://deltatok.github.io.</p> + https://arxiv.org/abs/2604.04913 Mon, 06 Apr 2026 00:00:00 +0000 - Demystifying When Pruning Works via Representation Hierarchies - https://arxiv.org/abs/2603.24652 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.24652.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shwai He, Guoheng Sun, Haichao Zhang, Yun Fu, Ang Li</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> Network pruning, which removes less important parameters or architectures, is often expected to improve efficiency while preserving performance. However, this expectation does not consistently hold across language tasks: pruned models can perform well on non-generative tasks but frequently fail in generative settings. To understand this discrepancy, we analyze network pruning from a representation-hierarchy perspective, decomposing the internal computation of language models into three sequential spaces: embedding (hidden representations), logit (pre-softmax outputs), and probability (post-softmax distributions). We find that representations in the embedding and logit spaces are largely robust to pruning-induced perturbations. However, the nonlinear transformation from logits to probabilities amplifies these deviations, which accumulate across time steps and lead to substantial degradation during generation. In contrast, the stability of the categorical-token probability subspace, together with the robustness of the embedding space, supports the effectiveness of pruning for non-generative tasks such as retrieval and multiple-choice selection. Our analysis disentangles the effects of pruning across tasks and provides practical guidance for its application. Code is available at https://github.com/CASE-Lab-UMD/Pruning-on-Representations</p> - https://arxiv.org/abs/2603.24652 + DeonticBench: A Benchmark for Reasoning over Rules + https://arxiv.org/abs/2604.04443 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.04443.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Guangyao Dou, Luis Brena, Akhil Deo, William Jurayj, Jingyu Zhang, Nils Holzenberger, Benjamin Van Durme</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Reasoning with complex, context-specific rules remains challenging for large language models (LLMs). In legal and policy settings, this manifests as deontic reasoning: reasoning about obligations, permissions, and prohibitions under explicit rules. While many recent benchmarks emphasize short-context mathematical reasoning, fewer focus on long-context, high-stakes deontic reasoning. To address this gap, we introduce DEONTICBENCH, a benchmark of 6,232 tasks across U.S. federal taxes, airline baggage policies, U.S. immigration administration, and U.S. state housing law. These tasks can be approached in multiple ways, including direct reasoning in language or with the aid of symbolic computation. Besides free-form chain-of-thought reasoning, DEONTICBENCH enables an optional solver-based workflow in which models translate statutes and case facts into executable Prolog, leading to formal problem interpretations and an explicit program trace. We release reference Prolog programs for all instances. Across frontier LLMs and coding models, best hard-subset performance reaches only 44.4% on SARA Numeric and 46.6 macro-F1 on Housing. We further study training with supervised fine-tuning and reinforcement learning for symbolic program generation. Although training improves Prolog generation quality, current RL methods still fail to solve these tasks reliably. Overall, DEONTICBENCH provides a benchmark for studying context-grounded rule reasoning in real-world domains under both symbolic and non-symbolic settings.</p> + https://arxiv.org/abs/2604.04443 Mon, 06 Apr 2026 00:00:00 +0000 - ClawsBench: Evaluating Capability and Safety of LLM Productivity Agents in Simulated Workspaces - https://arxiv.org/abs/2604.05172 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.05172.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiangyi Li, Kyoung Whan Choe, Yimin Liu, Xiaokun Chen, Chujun Tao, Bingran You, Wenbo Chen, Zonglin Di, Jiankai Sun, Shenghan Zheng, Jiajun Bao, Yuanli Wang, Weixiang Yan, Yiyuan Li, Han-chung Lee</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Large language model (LLM) agents are increasingly deployed to automate productivity tasks (e.g., email, scheduling, document management), but evaluating them on live services is risky due to potentially irreversible changes. Existing benchmarks rely on simplified environments and fail to capture realistic, stateful, multi-service workflows. We introduce ClawsBench, a benchmark for evaluating and improving LLM agents in realistic productivity settings. It includes five high-fidelity mock services (Gmail, Slack, Google Calendar, Google Docs, Google Drive) with full state management and deterministic snapshot/restore, along with 44 structured tasks covering single-service, cross-service, and safety-critical scenarios. We decompose agent scaffolding into two independent levers (domain skills that inject API knowledge via progressive disclosure, and a meta prompt that coordinates behavior across services) and vary both to measure their separate and combined effects. Experiments across 6 models, 4 agent harnesses, and 33 conditions show that with full scaffolding, agents achieve task success rates of 39-64% but exhibit unsafe action rates of 7-33%. On OpenClaw, the top five models fall within a 10 percentage-point band on task success (53-63%), with unsafe action rates from 7% to 23% and no consistent ordering between the two metrics. We identify eight recurring patterns of unsafe behavior, including multi-step sandbox escalation and silent contract modification.</p> - https://arxiv.org/abs/2604.05172 + Beyond Hard Negatives: The Importance of Score Distribution in Knowledge Distillation for Dense Retrieval + https://arxiv.org/abs/2604.04734 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.04734.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Youngjoon Jang, Seongtae Hong, Hyeonseok Moon, Heuiseok Lim</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Transferring knowledge from a cross-encoder teacher via Knowledge Distillation (KD) has become a standard paradigm for training retrieval models. While existing studies have largely focused on mining hard negatives to improve discrimination, the systematic composition of training data and the resulting teacher score distribution have received relatively less attention. In this work, we highlight that focusing solely on hard negatives prevents the student from learning the comprehensive preference structure of the teacher, potentially hampering generalization. To effectively emulate the teacher score distribution, we propose a Stratified Sampling strategy that uniformly covers the entire score spectrum. Experiments on in-domain and out-of-domain benchmarks confirm that Stratified Sampling, which preserves the variance and entropy of teacher scores, serves as a robust baseline, significantly outperforming top-K and random sampling in diverse settings. These findings suggest that the essence of distillation lies in preserving the diverse range of relative scores perceived by the teacher.</p> + https://arxiv.org/abs/2604.04734 Mon, 06 Apr 2026 00:00:00 +0000 - General Multimodal Protein Design Enables DNA-Encoding of Chemistry - https://arxiv.org/abs/2604.05181 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.05181.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jarrid Rector-Brooks, Théophile Lambert, Marta Skreta, Daniel Roth, Yueming Long, Zi-Qi Li, Xi Zhang, Miruna Cretu, Francesca-Zhoufan Li, Tanvi Ganapathy, Emily Jin, Avishek Joey Bose, Jason Yang, Kirill Neklyudov, Yoshua Bengio, Alexander Tong, Frances H. Arnold, Cheng-Hao Liu</p><p><b>Upvotes:</b> 20</p><p><b>Summary:</b> Evolution is an extraordinary engine for enzymatic diversity, yet the chemistry it has explored remains a narrow slice of what DNA can encode. Deep generative models can design new proteins that bind ligands, but none have created enzymes without pre-specifying catalytic residues. We introduce DISCO (DIffusion for Sequence-structure CO-design), a multimodal model that co-designs protein sequence and 3D structure around arbitrary biomolecules, as well as inference-time scaling methods that optimize objectives across both modalities. Conditioned solely on reactive intermediates, DISCO designs diverse heme enzymes with novel active-site geometries. These enzymes catalyze new-to-nature carbene-transfer reactions, including alkene cyclopropanation, spirocyclopropanation, B-H, and C(sp^3)-H insertions, with high activities exceeding those of engineered enzymes. Random mutagenesis of a selected design further confirmed that enzyme activity can be improved through directed evolution. By providing a scalable route to evolvable enzymes, DISCO broadens the potential scope of genetically encodable transformations. Code is available at https://github.com/DISCO-design/DISCO.</p> - https://arxiv.org/abs/2604.05181 - Mon, 06 Apr 2026 00:00:00 +0000 - - - How Well Do Agentic Skills Work in the Wild: Benchmarking LLM Skill Usage in Realistic Settings - https://arxiv.org/abs/2604.04323 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.04323.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yujian Liu, Jiabao Ji, Li An, Tommi Jaakkola, Yang Zhang, Shiyu Chang</p><p><b>Upvotes:</b> 24</p><p><b>Summary:</b> Agent skills, which are reusable, domain-specific knowledge artifacts, have become a popular mechanism for extending LLM-based agents, yet formally benchmarking skill usage performance remains scarce. Existing skill benchmarking efforts focus on overly idealized conditions, where LLMs are directly provided with hand-crafted, narrowly-tailored task-specific skills for each task, whereas in many realistic settings, the LLM agent may have to search for and select relevant skills on its own, and even the closest matching skills may not be well-tailored for the task. In this paper, we conduct the first comprehensive study of skill utility under progressively challenging realistic settings, where agents must retrieve skills from a large collection of 34k real-world skills and may not have access to any hand-curated skills. Our findings reveal that the benefits of skills are fragile: performance gains degrade consistently as settings become more realistic, with pass rates approaching no-skill baselines in the most challenging scenarios. To narrow this gap, we study skill refinement strategies, including query-specific and query-agnostic approaches, and we show that query-specific refinement substantially recovers lost performance when the initial skills are of reasonable relevance and quality. We further demonstrate the generality of retrieval and refinement on Terminal-Bench 2.0, where they improve the pass rate of Claude Opus 4.6 from 57.7% to 65.5%. Our results, consistent across multiple models, highlight both the promise and the current limitations of skills for LLM-based agents. Our code is available at https://github.com/UCSB-NLP-Chang/Skill-Usage.</p> - https://arxiv.org/abs/2604.04323 - Mon, 06 Apr 2026 00:00:00 +0000 - - - MegaTrain: Full Precision Training of 100B+ Parameter Large Language Models on a Single GPU - https://arxiv.org/abs/2604.05091 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.05091.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhengqing Yuan, Hanchi Sun, Lichao Sun, Yanfang Ye</p><p><b>Upvotes:</b> 24</p><p><b>Summary:</b> We present MegaTrain, a memory-centric system that efficiently trains 100B+ parameter large language models at full precision on a single GPU. Unlike traditional GPU-centric systems, MegaTrain stores parameters and optimizer states in host memory (CPU memory) and treats GPUs as transient compute engines. For each layer, we stream parameters in and compute gradients out, minimizing persistent device state. To battle the CPU-GPU bandwidth bottleneck, we adopt two key optimizations. 1) We introduce a pipelined double-buffered execution engine that overlaps parameter prefetching, computation, and gradient offloading across multiple CUDA streams, enabling continuous GPU execution. 2) We replace persistent autograd graphs with stateless layer templates, binding weights dynamically as they stream in, eliminating persistent graph metadata while providing flexibility in scheduling. On a single H200 GPU with 1.5TB host memory, MegaTrain reliably trains models up to 120B parameters. It also achieves 1.84times the training throughput of DeepSpeed ZeRO-3 with CPU offloading when training 14B models. MegaTrain also enables 7B model training with 512k token context on a single GH200.</p> - https://arxiv.org/abs/2604.05091 - Mon, 06 Apr 2026 00:00:00 +0000 - - - Watch Before You Answer: Learning from Visually Grounded Post-Training - https://arxiv.org/abs/2604.05117 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.05117.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuxuan Zhang, EunJeong Hwang, Huaisong Zhang, Penghui Du, Yiming Jia, Dongfu Jiang, Xuan He, Shenhui Zhang, Ping Nie, Peter West, Kelsey R. Allen</p><p><b>Upvotes:</b> 24</p><p><b>Summary:</b> It is critical for vision-language models (VLMs) to comprehensively understand visual, temporal, and textual cues. However, despite rapid progress in multimodal modeling, video understanding performance still lags behind text-based reasoning. In this work, we find that progress is even worse than previously assumed: commonly reported long video understanding benchmarks contain 40-60% of questions that can be answered using text cues alone. Furthermore, we find that these issues are also pervasive in widely used post-training datasets, potentially undercutting the ability of post-training to improve VLM video understanding performance. Guided by this observation, we introduce VidGround as a simple yet effective solution: using only the actual visually grounded questions without any linguistic biases for post-training. When used in tandem with RL-based post-training algorithms, this simple technique improves performance by up to 6.2 points relative to using the full dataset, while using only 69.1% of the original post-training data. Moreover, we show that data curation with a simple post-training algorithm outperforms several more complex post-training techniques, highlighting that data quality is a major bottleneck for improving video understanding in VLMs. These results underscore the importance of curating post-training data and evaluation benchmarks that truly require visual grounding to advance the development of more capable VLMs. Project page: http://vidground.etuagi.com.</p> - https://arxiv.org/abs/2604.05117 - Mon, 06 Apr 2026 00:00:00 +0000 - - - Vanast: Virtual Try-On with Human Image Animation via Synthetic Triplet Supervision - https://arxiv.org/abs/2604.04934 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.04934.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hyunsoo Cha, Wonjung Woo, Byungjun Kim, Hanbyul Joo</p><p><b>Upvotes:</b> 29</p><p><b>Summary:</b> We present Vanast, a unified framework that generates garment-transferred human animation videos directly from a single human image, garment images, and a pose guidance video. Conventional two-stage pipelines treat image-based virtual try-on and pose-driven animation as separate processes, which often results in identity drift, garment distortion, and front-back inconsistency. Our model addresses these issues by performing the entire process in a single unified step to achieve coherent synthesis. To enable this setting, we construct large-scale triplet supervision. Our data generation pipeline includes generating identity-preserving human images in alternative outfits that differ from garment catalog images, capturing full upper and lower garment triplets to overcome the single-garment-posed video pair limitation, and assembling diverse in-the-wild triplets without requiring garment catalog images. We further introduce a Dual Module architecture for video diffusion transformers to stabilize training, preserve pretrained generative quality, and improve garment accuracy, pose adherence, and identity preservation while supporting zero-shot garment interpolation. Together, these contributions allow Vanast to produce high-fidelity, identity-consistent animation across a wide range of garment types.</p> - https://arxiv.org/abs/2604.04934 - Mon, 06 Apr 2026 00:00:00 +0000 - - - Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding - https://arxiv.org/abs/2604.05015 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.05015.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chaoyou Fu, Haozhi Yuan, Yuhao Dong, Yi-Fan Zhang, Yunhang Shen, Xiaoxing Hu, Xueying Li, Jinsen Su, Chengwu Long, Xiaoyao Xie, Yongkang Xie, Xiawu Zheng, Xue Yang, Haoyu Cao, Yunsheng Wu, Ziwei Liu, Xing Sun, Caifeng Shan, Ran He</p><p><b>Upvotes:</b> 197</p><p><b>Summary:</b> With the rapid advancement of video understanding, existing benchmarks are becoming increasingly saturated, exposing a critical discrepancy between inflated leaderboard scores and real-world model capabilities. To address this widening gap, we introduce Video-MME-v2, a comprehensive benchmark designed to rigorously evaluate the robustness and faithfulness of video understanding. To systematically evaluate model capabilities, we design a progressive tri-level hierarchy that incrementally increases the complexity of video comprehension, ranging from multi-point visual information aggregation, to temporal dynamics modeling, and ultimately to complex multimodal reasoning. Besides, in contrast to conventional per-question accuracy, we propose a group-based non-linear evaluation strategy that enforces both consistency across related queries and coherence in multi-step reasoning. It penalizes fragmented or guess-based correctness and assigns credit only to answers supported by valid reasoning. To guarantee data quality, Video-MME-v2 is constructed through a rigorously controlled human annotation pipeline, involving 12 annotators and 50 independent reviewers. Backed by 3,300 human-hours and up to 5 rounds of quality assurance, Video-MME-v2 aims to serve as one of the most authoritative video benchmarks. Extensive experiments reveal a substantial gap between current best model Gemini-3-Pro and human experts, and uncover a clear hierarchical bottleneck where errors in visual information aggregation and temporal modeling propagate to limit high-level reasoning. We further find that thinking-based reasoning is highly dependent on textual cues, improving performance with subtitles but sometimes degrading it in purely visual settings. By exposing these limitations, Video-MME-v2 establishes a demanding new testbed for the development of next-generation video MLLMs.</p> - https://arxiv.org/abs/2604.05015 - Mon, 06 Apr 2026 00:00:00 +0000 - - - CUE-R: Beyond the Final Answer in Retrieval-Augmented Generation - https://arxiv.org/abs/2604.05467 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.05467.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Siddharth Jain, Venkat Narayan Vedam</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> As language models shift from single-shot answer generation toward multi-step reasoning that retrieves and consumes evidence mid-inference, evaluating the role of individual retrieved items becomes more important. Existing RAG evaluation typically targets final-answer quality, citation faithfulness, or answer-level attribution, but none of these directly targets the intervention-based, per-evidence-item utility view we study here. We introduce CUE-R, a lightweight intervention-based framework for measuring per-evidence-item operational utility in single-shot RAG using shallow observable retrieval-use traces. CUE-R perturbs individual evidence items via REMOVE, REPLACE, and DUPLICATE operators, then measures changes along three utility axes (correctness, proxy-based grounding faithfulness, and confidence error) plus a trace-divergence signal. We also outline an operational evidence-role taxonomy for interpreting intervention outcomes. Experiments on HotpotQA and 2WikiMultihopQA with Qwen-3 8B and GPT-5.2 reveal a consistent pattern: REMOVE and REPLACE substantially harm correctness and grounding while producing large trace shifts, whereas DUPLICATE is often answer-redundant yet not fully behaviorally neutral. A zero-retrieval control confirms that these effects arise from degradation of meaningful retrieval. A two-support ablation further shows that multi-hop evidence items can interact non-additively: removing both supports harms performance far more than either single removal. Our results suggest that answer-only evaluation misses important evidence effects and that intervention-based utility analysis is a practical complement for RAG evaluation.</p> - https://arxiv.org/abs/2604.05467 + Qualixar OS: A Universal Operating System for AI Agent Orchestration + https://arxiv.org/abs/2604.06392 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.06392.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Varun Pratap Bhardwaj</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> We present Qualixar OS, the first application-layer operating system for universal AI agent orchestration. Unlike kernel-level approaches (AIOS) or single-framework tools (AutoGen, CrewAI), Qualixar OS provides a complete runtime for heterogeneous multi-agent systems spanning 10 LLM providers, 8+ agent frameworks, and 7 transports. We contribute: (1) execution semantics for 12 multi-agent topologies including grid, forest, mesh, and maker patterns; (2) Forge, an LLM-driven team design engine with historical strategy memory; (3) three-layer model routing combining Q-learning, five strategies, and Bayesian POMDP with dynamic multi-provider discovery; (4) a consensus-based judge pipeline with Goodhart detection, JSD drift monitoring, and alignment trilemma navigation; (5) four-layer content attribution with HMAC signing and steganographic watermarks; (6) universal compatibility via the Claw Bridge supporting MCP and A2A protocols with a 25-command Universal Command Protocol; (7) a 24-tab production dashboard with visual workflow builder and skill marketplace. Qualixar OS is validated by 2,821 test cases across 217 event types and 8 quality modules. On a custom 20-task evaluation suite, the system achieves 100% accuracy at a mean cost of $0.000039 per task. Source-available under the Elastic License 2.0.</p> + https://arxiv.org/abs/2604.06392 Tue, 07 Apr 2026 00:00:00 +0000 - Scientific Graphics Program Synthesis via Dual Self-Consistency Reinforcement Learning - https://arxiv.org/abs/2604.06079 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.06079.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Juekai Lin, Yun Zhu, Honglin Lin, Sijing Li, Tianwei Lin, Zheng Liu, Xiaoyang Wang, Wenqiao Zhang, Lijun Wu</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Graphics Program Synthesis is pivotal for interpreting and editing visual data, effectively facilitating the reverse-engineering of static visuals into editable TikZ code. While TikZ is the de facto standard for scientific schematics due to its programmatic flexibility, its requirement for rigorous spatial precision presents a significant challenge for Multimodal Large Language Models. Progress is currently stifled by two primary gaps: (1) Data Quality Gap: existing image-TikZ corpora often lack strict executability and reliable visual alignment; (2) Evaluation Gap: a lack of benchmarks for both structural and visual fidelity. To address these, we present a closed-loop framework featuring: SciTikZ-230K, a large-scale, high-quality dataset from our Execution-Centric Data Engine covering 11 diverse scientific disciplines; SciTikZ-Bench, a multifaceted benchmark spanning from basic geometric constructs to intricate hierarchical schematics to evaluate both visual fidelity and structural logic. To further broaden the scope of visual-code optimization methodology, we introduce a novel Dual Self-Consistency Reinforcement Learning optimization paradigm, which utilizes Round-Trip Verification to penalize degenerate code and boost overall self-consistency. Empowered by these, our trained model SciTikZer-8B achieves state-of-the-art performance, consistently outperforming proprietary giants like Gemini-2.5-Pro and massive models like Qwen3-VL-235B-A22B-Instruct.</p> - https://arxiv.org/abs/2604.06079 + AgentGL: Towards Agentic Graph Learning with LLMs via Reinforcement Learning + https://arxiv.org/abs/2604.05846 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.05846.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuanfu Sun, Kang Li, Dongzhe Fan, Jiajin Liu, Qiaoyu Tan</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Large Language Models (LLMs) increasingly rely on agentic capabilities-iterative retrieval, tool use, and decision-making-to overcome the limits of static, parametric knowledge. Yet existing agentic frameworks treat external information as unstructured text and fail to leverage the topological dependencies inherent in real-world data. To bridge this gap, we introduce Agentic Graph Learning (AGL), a paradigm that reframes graph learning as an interleaved process of topology-aware navigation and LLM-based inference. Specifically, we propose AgentGL, the first reinforcement learning (RL)-driven framework for AGL. AgentGL equips an LLM agent with graph-native tools for multi-scale exploration, regulates tool usage via search-constrained thinking to balance accuracy and efficiency, and employs a graph-conditioned curriculum RL strategy to stabilize long-horizon policy learning without step-wise supervision. Across diverse Text-Attributed Graph (TAG) benchmarks and multiple LLM backbones, AgentGL substantially outperforms strong GraphLLMs and GraphRAG baselines, achieving absolute improvements of up to 17.5% in node classification and 28.4% in link prediction. These results demonstrate that AGL is a promising frontier for enabling LLMs to autonomously navigate and reason over complex relational environments. The code is publicly available at https://github.com/sunyuanfu/AgentGL.</p> + https://arxiv.org/abs/2604.05846 Tue, 07 Apr 2026 00:00:00 +0000 - QiMeng-PRepair: Precise Code Repair via Edit-Aware Reward Optimization - https://arxiv.org/abs/2604.05963 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.05963.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Changxin Ke, Rui Zhang, Jiaming Guo, Yuanbo Wen, Li Ding, Shuo Wang, Xuyuan Zhu, Xiong Peng, Di Huang, Zidong Du, Xing Hu, Qi Guo, Yunji Chen</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Large Language Models (LLMs) achieve strong program repair performance but often suffer from over-editing, where excessive modifications overwrite correct code and hinder bug localization. We systematically quantify its impact and introduce precise repair task, which maximizes reuse of correct code while fixing only buggy parts. Building on this insight, we propose PRepair, a framework that mitigates over-editing and improves repair accuracy. PRepair has two components: Self-Breaking, which generates diverse buggy programs via controlled bug injection and min-max sampling, and Self-Repairing, which trains models with Edit-Aware Group Relative Policy Optimization (EA-GRPO) using an edit-aware reward to encourage minimal yet correct edits. Experiments show that PRepair improves repair precision by up to 31.4% under fix_1@1, a metric that jointly considers repair correctness and extent, and significantly increases decoding throughput when combined with speculative editing, demonstrating its potential for precise and practical code repair.</p> - https://arxiv.org/abs/2604.05963 + Improving Semantic Proximity in Information Retrieval through Cross-Lingual Alignment + https://arxiv.org/abs/2604.05684 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.05684.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Seongtae Hong, Youngjoon Jang, Jungseob Lee, Hyeonseok Moon, Heuiseok Lim</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> With the increasing accessibility and utilization of multilingual documents, Cross-Lingual Information Retrieval (CLIR) has emerged as an important research area. Conventionally, CLIR tasks have been conducted under settings where the language of documents differs from that of queries, and typically, the documents are composed in a single coherent language. In this paper, we highlight that in such a setting, the cross-lingual alignment capability may not be evaluated adequately. Specifically, we observe that, in a document pool where English documents coexist with another language, most multilingual retrievers tend to prioritize unrelated English documents over the related document written in the same language as the query. To rigorously analyze and quantify this phenomenon, we introduce various scenarios and metrics designed to evaluate the cross-lingual alignment performance of multilingual retrieval models. Furthermore, to improve cross-lingual performance under these challenging conditions, we propose a novel training strategy aimed at enhancing cross-lingual alignment. Using only a small dataset consisting of 2.8k samples, our method significantly improves the cross-lingual retrieval performance while simultaneously mitigating the English inclination problem. Extensive analyses demonstrate that the proposed method substantially enhances the cross-lingual alignment capabilities of most multilingual embedding models.</p> + https://arxiv.org/abs/2604.05684 Tue, 07 Apr 2026 00:00:00 +0000 - Context-Value-Action Architecture for Value-Driven Large Language Model Agents - https://arxiv.org/abs/2604.05939 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.05939.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> TianZe Zhang, Sirui Sun, Yuhang Xie, Xin Zhang, Zhiqiang Wu, Guojie Song</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Large Language Models (LLMs) have shown promise in simulating human behavior, yet existing agents often exhibit behavioral rigidity, a flaw frequently masked by the self-referential bias of current "LLM-as-a-judge" evaluations. By evaluating against empirical ground truth, we reveal a counter-intuitive phenomenon: increasing the intensity of prompt-driven reasoning does not enhance fidelity but rather exacerbates value polarization, collapsing population diversity. To address this, we propose the Context-Value-Action (CVA) architecture, grounded in the Stimulus-Organism-Response (S-O-R) model and Schwartz's Theory of Basic Human Values. Unlike methods relying on self-verification, CVA decouples action generation from cognitive reasoning via a novel Value Verifier trained on authentic human data to explicitly model dynamic value activation. Experiments on CVABench, which comprises over 1.1 million real-world interaction traces, demonstrate that CVA significantly outperforms baselines. Our approach effectively mitigates polarization while offering superior behavioral fidelity and interpretability.</p> - https://arxiv.org/abs/2604.05939 + The Depth Ceiling: On the Limits of Large Language Models in Discovering Latent Planning + https://arxiv.org/abs/2604.06427 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.06427.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yi Xu, Philipp Jettkant, Laura Ruis</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> The viability of chain-of-thought (CoT) monitoring hinges on models being unable to reason effectively in their latent representations. Yet little is known about the limits of such latent reasoning in LLMs. We test these limits by studying whether models can discover multi-step planning strategies without supervision on intermediate steps and execute them latently, within a single forward pass. Using graph path-finding tasks that precisely control the number of required latent planning steps, we uncover a striking limitation unresolved by massive scaling: tiny transformers trained from scratch discover strategies requiring up to three latent steps, fine-tuned GPT-4o and Qwen3-32B reach five, and GPT-5.4 attains seven under few-shot prompting. Although the maximum latent planning depth models can learn during training is five, the discovered strategy generalizes up to eight latent steps at test-time. This reveals a dissociation between the ability to discover a latent strategy under final-answer supervision alone and the ability to execute it once discovered. If similar limits hold more broadly, strategies requiring multiple coordinated latent planning steps may need to be explicitly taught or externalized, lending credence to CoT monitoring.</p> + https://arxiv.org/abs/2604.06427 Tue, 07 Apr 2026 00:00:00 +0000 - FactReview: Evidence-Grounded Reviews with Literature Positioning and Execution-Based Claim Verification - https://arxiv.org/abs/2604.04074 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.04074.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hang Xu, Ling Yue, Chaoqian Ouyang, Yuchen Liu, Libin Zheng, Shaowu Pan, Shimin Di, Min-Ling Zhang</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Peer review in machine learning is under growing pressure from rising submission volume and limited reviewer time. Most LLM-based reviewing systems read only the manuscript and generate comments from the paper's own narrative. This makes their outputs sensitive to presentation quality and leaves them weak when the evidence needed for review lies in related work or released code. We present FactReview, an evidence-grounded reviewing system that combines claim extraction, literature positioning, and execution-based claim verification. Given a submission, FactReview identifies major claims and reported results, retrieves nearby work to clarify the paper's technical position, and, when code is available, executes the released repository under bounded budgets to test central empirical claims. It then produces a concise review and an evidence report that assigns each major claim one of five labels: Supported, Supported by the paper, Partially supported, In conflict, or Inconclusive. In a case study on CompGCN, FactReview reproduces results that closely match those reported for link prediction and node classification, yet also shows that the paper's broader performance claim across tasks is not fully sustained: on MUTAG graph classification, the reproduced result is 88.4%, whereas the strongest baseline reported in the paper remains 92.6%. The claim is therefore only partially supported. More broadly, this case suggests that AI is most useful in peer review not as a final decision-maker, but as a tool for gathering evidence and helping reviewers produce more evidence-grounded assessments. The code is public at https://github.com/DEFENSE-SEU/Review-Assistant.</p> - https://arxiv.org/abs/2604.04074 + Graph-Based Chain-of-Thought Pruning for Reducing Redundant Reflections in Reasoning LLMs + https://arxiv.org/abs/2604.05643 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.05643.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hongyuan Yuan, Xinran He, Run Shao, Bolei He, Xianwei Xue, Mengke Chen, Qiutong Pan, Haiwei Wang, Haifeng Li</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Extending CoT through RL has been widely used to enhance the reasoning capabilities of LLMs. However, due to the sparsity of reward signals, it can also induce undesirable thinking patterns such as overthinking, i.e., generating redundant intermediate reasoning content. In this work, we argue that a major source of such redundancy is inefficient reflection, which often manifests in two problematic patterns: Indiscriminate Reflection, where the model performs broad, low-impact checks throughout reasoning, and Repetitive Reflection, where it repeatedly re-verifies an already established conclusion. To address this, we introduce a graph-based CoT optimization framework. Specifically, we convert each linear CoT into a directed acyclic graph (DAG) with explicit dependency edges, and design a dual pruning strategy: branch-level pruning removes weakly contributing reflection branches, while depth-level pruning eliminates late-stage re-verification. We distill this behavior via a three-stage pipeline: (1) SFT to initialize the policy on pruned concise traces, (2) DPO to prefer correct but less redundant trajectories, and (3) GRPO with length penalty to jointly optimize answer correctness and efficiency. Experiments show that our approach reduces the average reasoning tokens by 42\% while maintaining or improving accuracy.</p> + https://arxiv.org/abs/2604.05643 Tue, 07 Apr 2026 00:00:00 +0000 - Experience Transfer for Multimodal LLM Agents in Minecraft Game - https://arxiv.org/abs/2604.05533 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.05533.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chenghao Li, Jun Liu, Songbo Zhang, Huadong Jian, Hao Ni, Lik-Hang Lee, Sung-Ho Bae, Guoqing Wang, Yang Yang, Chaoning Zhang</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Multimodal LLM agents operating in complex game environments must continually reuse past experience to solve new tasks efficiently. In this work, we propose Echo, a transfer-oriented memory framework that enables agents to derive actionable knowledge from prior interactions rather than treating memory as a passive repository of static records. To make transfer explicit, Echo decomposes reusable knowledge into five dimensions: structure, attribute, process, function, and interaction. This formulation allows the agent to identify recurring patterns shared across different tasks and infer what prior experience remains applicable in new situations. Building on this formulation, Echo leverages In-Context Analogy Learning (ICAL) to retrieve relevant experiences and adapt them to unseen tasks through contextual examples. Experiments in Minecraft show that, under a from-scratch learning setting, Echo achieves a 1.3x to 1.7x speed-up on object-unlocking tasks. Moreover, Echo exhibits a burst-like chain-unlocking phenomenon, rapidly unlocking multiple similar items within a short time interval after acquiring transferable experience. These results suggest that experience transfer is a promising direction for improving the efficiency and adaptability of multimodal LLM agents in complex interactive environments.</p> - https://arxiv.org/abs/2604.05533 + Neural Computers + https://arxiv.org/abs/2604.06425 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.06425.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mingchen Zhuge, Changsheng Zhao, Haozhe Liu, Zijian Zhou, Shuming Liu, Wenyi Wang, Ernie Chang, Gael Le Lan, Junjie Fei, Wenxuan Zhang, Yasheng Sun, Zhipeng Cai, Zechun Liu, Yunyang Xiong, Yining Yang, Yuandong Tian, Yangyang Shi, Vikas Chandra, Jürgen Schmidhuber</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> We propose a new frontier: Neural Computers (NCs) -- an emerging machine form that unifies computation, memory, and I/O in a learned runtime state. Unlike conventional computers, which execute explicit programs, agents, which act over external execution environments, and world models, which learn environment dynamics, NCs aim to make the model itself the running computer. Our long-term goal is the Completely Neural Computer (CNC): the mature, general-purpose realization of this emerging machine form, with stable execution, explicit reprogramming, and durable capability reuse. As an initial step, we study whether early NC primitives can be learned solely from collected I/O traces, without instrumented program state. Concretely, we instantiate NCs as video models that roll out screen frames from instructions, pixels, and user actions (when available) in CLI and GUI settings. These implementations show that learned runtimes can acquire early interface primitives, especially I/O alignment and short-horizon control, while routine reuse, controlled updates, and symbolic stability remain open. We outline a roadmap toward CNCs around these challenges. If overcome, CNCs could establish a new computing paradigm beyond today's agents, world models, and conventional computers.</p> + https://arxiv.org/abs/2604.06425 Tue, 07 Apr 2026 00:00:00 +0000 - MMEmb-R1: Reasoning-Enhanced Multimodal Embedding with Pair-Aware Selection and Adaptive Control - https://arxiv.org/abs/2604.06156 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.06156.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuchi Wang, Haiyang Yu, Weikang Bian, Jiefeng Long, Xiao Liang, Chao Feng, Hongsheng Li</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> MLLMs have been successfully applied to multimodal embedding tasks, yet their generative reasoning capabilities remain underutilized. Directly incorporating chain-of-thought reasoning into embedding learning introduces two fundamental challenges. First, structural misalignment between instance-level reasoning and pairwise contrastive supervision may lead to shortcut behavior, where the model merely learns the superficial format of reasoning. Second, reasoning is not universally beneficial for embedding tasks. Enforcing reasoning for all inputs may introduce unnecessary computation and latency, and can even obscure salient semantic signals for simple cases. To address these issues, we propose MMEmb-R1, an adaptive reasoning-based multimodal embedding framework. We formulate reasoning as a latent variable and introduce pair-aware reasoning selection that employs counterfactual intervention to identify reasoning paths beneficial for query-target alignment. Furthermore, we adopt reinforcement learning to selectively invoke reasoning only when necessary. Experiments on the MMEB-V2 benchmark demonstrate that our model achieves a score of 71.2 with only 4B parameters, establishing a new state-of-the-art while significantly reducing reasoning overhead and inference latency.</p> - https://arxiv.org/abs/2604.06156 + RAGEN-2: Reasoning Collapse in Agentic RL + https://arxiv.org/abs/2604.06268 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.06268.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zihan Wang, Chi Gui, Xing Jin, Qineng Wang, Licheng Liu, Kangrui Wang, Shiqi Chen, Linjie Li, Zhengyuan Yang, Pingyue Zhang, Yiping Lu, Jiajun Wu, Li Fei-Fei, Lijuan Wang, Yejin Choi, Manling Li</p><p><b>Upvotes:</b> 42</p><p><b>Summary:</b> RL training of multi-turn LLM agents is inherently unstable, and reasoning quality directly determines task performance. Entropy is widely used to track reasoning stability. However, entropy only measures diversity within the same input, and cannot tell whether reasoning actually responds to different inputs. In RAGEN-2, we find that even with stable entropy, models can rely on fixed templates that look diverse but are input-agnostic. We call this template collapse, a failure mode invisible to entropy and all existing metrics. To diagnose this failure, we decompose reasoning quality into within-input diversity (Entropy) and cross-input distinguishability (Mutual Information, MI), and introduce a family of mutual information proxies for online diagnosis. Across diverse tasks, mutual information correlates with final performance much more strongly than entropy, making it a more reliable proxy for reasoning quality. We further explain template collapse with a signal-to-noise ratio (SNR) mechanism. Low reward variance weakens task gradients, letting regularization terms dominate and erase cross-input reasoning differences. To address this, we propose SNR-Aware Filtering to select high-signal prompts per iteration using reward variance as a lightweight proxy. Across planning, math reasoning, web navigation, and code execution, the method consistently improves both input dependence and task performance.</p> + https://arxiv.org/abs/2604.06268 Tue, 07 Apr 2026 00:00:00 +0000 - Action Images: End-to-End Policy Learning via Multiview Video Generation - https://arxiv.org/abs/2604.06168 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.06168.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haoyu Zhen, Zixian Gao, Qiao Sun, Yilin Zhao, Yuncong Yang, Yilun Du, Tsun-Hsuan Wang, Yi-Ling Qiao, Chuang Gan</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> World action models (WAMs) have emerged as a promising direction for robot policy learning, as they can leverage powerful video backbones to model the future states. However, existing approaches often rely on separate action modules, or use action representations that are not pixel-grounded, making it difficult to fully exploit the pretrained knowledge of video models and limiting transfer across viewpoints and environments. In this work, we present Action Images, a unified world action model that formulates policy learning as multiview video generation. Instead of encoding control as low-dimensional tokens, we translate 7-DoF robot actions into interpretable action images: multi-view action videos that are grounded in 2D pixels and explicitly track robot-arm motion. This pixel-grounded action representation allows the video backbone itself to act as a zero-shot policy, without a separate policy head or action module. Beyond control, the same unified model supports video-action joint generation, action-conditioned video generation, and action labeling under a shared representation. On RLBench and real-world evaluations, our model achieves the strongest zero-shot success rates and improves video-action joint generation quality over prior video-space world models, suggesting that interpretable action images are a promising route to policy learning.</p> - https://arxiv.org/abs/2604.06168 - Tue, 07 Apr 2026 00:00:00 +0000 + GenLCA: 3D Diffusion for Full-Body Avatars from In-the-Wild Videos + https://arxiv.org/abs/2604.07273 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.07273.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yiqian Wu, Rawal Khirodkar, Egor Zakharov, Timur Bagautdinov, Lei Xiao, Zhaoen Su, Shunsuke Saito, Xiaogang Jin, Junxuan Li</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> We present GenLCA, a diffusion-based generative model for generating and editing photorealistic full-body avatars from text and image inputs. The generated avatars are faithful to the inputs, while supporting high-fidelity facial and full-body animations. The core idea is a novel paradigm that enables training a full-body 3D diffusion model from partially observable 2D data, allowing the training dataset to scale to millions of real-world videos. This scalability contributes to the superior photorealism and generalizability of GenLCA. Specifically, we scale up the dataset by repurposing a pretrained feed-forward avatar reconstruction model as an animatable 3D tokenizer, which encodes unstructured video frames into structured 3D tokens. However, most real-world videos only provide partial observations of body parts, resulting in excessive blurring or transparency artifacts in the 3D tokens. To address this, we propose a novel visibility-aware diffusion training strategy that replaces invalid regions with learnable tokens and computes losses only over valid regions. We then train a flow-based diffusion model on the token dataset, inherently maintaining the photorealism and animatability provided by the pretrained avatar reconstruction model. Our approach effectively enables the use of large-scale real-world video data to train a diffusion model natively in 3D. We demonstrate the efficacy of our method through diverse and high-fidelity generation and editing results, outperforming existing solutions by a large margin. The project page is available at https://onethousandwu.com/GenLCA-Page.</p> + https://arxiv.org/abs/2604.07273 + Wed, 08 Apr 2026 00:00:00 +0000 - In-Place Test-Time Training - https://arxiv.org/abs/2604.06169 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.06169.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Guhao Feng, Shengjie Luo, Kai Hua, Ge Zhang, Di He, Wenhao Huang, Tianle Cai</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> The static ``train then deploy" paradigm fundamentally limits Large Language Models (LLMs) from dynamically adapting their weights in response to continuous streams of new information inherent in real-world tasks. Test-Time Training (TTT) offers a compelling alternative by updating a subset of model parameters (fast weights) at inference time, yet its potential in the current LLM ecosystem is hindered by critical barriers including architectural incompatibility, computational inefficiency and misaligned fast weight objectives for language modeling. In this work, we introduce In-Place Test-Time Training (In-Place TTT), a framework that seamlessly endows LLMs with Test-Time Training ability. In-Place TTT treats the final projection matrix of the ubiquitous MLP blocks as its adaptable fast weights, enabling a ``drop-in" enhancement for LLMs without costly retraining from scratch. Furthermore, we replace TTT's generic reconstruction objective with a tailored, theoretically-grounded objective explicitly aligned with the Next-Token-Prediction task governing autoregressive language modeling. This principled objective, combined with an efficient chunk-wise update mechanism, results in a highly scalable algorithm compatible with context parallelism. Extensive experiments validate our framework's effectiveness: as an in-place enhancement, it enables a 4B-parameter model to achieve superior performance on tasks with contexts up to 128k, and when pretrained from scratch, it consistently outperforms competitive TTT-related approaches. Ablation study results further provide deeper insights on our design choices. Collectively, our results establish In-Place TTT as a promising step towards a paradigm of continual learning in LLMs.</p> - https://arxiv.org/abs/2604.06169 - Tue, 07 Apr 2026 00:00:00 +0000 + Q-Zoom: Query-Aware Adaptive Perception for Efficient Multimodal Large Language Models + https://arxiv.org/abs/2604.06912 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.06912.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuheng Shi, Xiaohuan Pei, Linfeng Wen, Minjing Dong, Chang Xu</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> MLLMs require high-resolution visual inputs for fine-grained tasks like document understanding and dense scene perception. However, current global resolution scaling paradigms indiscriminately flood the quadratic self-attention mechanism with visually redundant tokens, severely bottlenecking inference throughput while ignoring spatial sparsity and query intent. To overcome this, we propose Q-Zoom, a query-aware adaptive high-resolution perception framework that operates in an efficient coarse-to-fine manner. First, a lightweight Dynamic Gating Network safely bypasses high-resolution processing when coarse global features suffice. Second, for queries demanding fine-grained perception, a Self-Distilled Region Proposal Network (SD-RPN) precisely localizes the task-relevant Region-of-Interest (RoI) directly from intermediate feature spaces. To optimize these modules efficiently, the gating network uses a consistency-aware generation strategy to derive deterministic routing labels, while the SD-RPN employs a fully self-supervised distillation paradigm. A continuous spatio-temporal alignment scheme and targeted fine-tuning then seamlessly fuse the dense local RoI with the coarse global layout. Extensive experiments demonstrate that Q-Zoom establishes a dominant Pareto frontier. Using Qwen2.5-VL-7B as a primary testbed, Q-Zoom accelerates inference by 2.52 times on Document & OCR benchmarks and 4.39 times in High-Resolution scenarios while matching the baseline's peak accuracy. Furthermore, when configured for maximum perceptual fidelity, Q-Zoom surpasses the baseline's peak performance by 1.1% and 8.1% on these respective benchmarks. These robust improvements transfer seamlessly to Qwen3-VL, LLaVA, and emerging RL-based thinking-with-image models. Project page is available at https://yuhengsss.github.io/Q-Zoom/.</p> + https://arxiv.org/abs/2604.06912 + Wed, 08 Apr 2026 00:00:00 +0000 - Paper Circle: An Open-source Multi-agent Research Discovery and Analysis Framework - https://arxiv.org/abs/2604.06170 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.06170.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Komal Kumar, Aman Chadha, Salman Khan, Fahad Shahbaz Khan, Hisham Cholakkal</p><p><b>Upvotes:</b> 20</p><p><b>Summary:</b> The rapid growth of scientific literature has made it increasingly difficult for researchers to efficiently discover, evaluate, and synthesize relevant work. Recent advances in multi-agent large language models (LLMs) have demonstrated strong potential for understanding user intent and are being trained to utilize various tools. In this paper, we introduce Paper Circle, a multi-agent research discovery and analysis system designed to reduce the effort required to find, assess, organize, and understand academic literature. The system comprises two complementary pipelines: (1) a Discovery Pipeline that integrates offline and online retrieval from multiple sources, multi-criteria scoring, diversity-aware ranking, and structured outputs; and (2) an Analysis Pipeline that transforms individual papers into structured knowledge graphs with typed nodes such as concepts, methods, experiments, and figures, enabling graph-aware question answering and coverage verification. Both pipelines are implemented within a coder LLM-based multi-agent orchestration framework and produce fully reproducible, synchronized outputs including JSON, CSV, BibTeX, Markdown, and HTML at each agent step. This paper describes the system architecture, agent roles, retrieval and scoring methods, knowledge graph schema, and evaluation interfaces that together form the Paper Circle research workflow. We benchmark Paper Circle on both paper retrieval and paper review generation, reporting hit rate, MRR, and Recall at K. Results show consistent improvements with stronger agent models. We have publicly released the website at https://papercircle.vercel.app/ and the code at https://github.com/MAXNORM8650/papercircle.</p> - https://arxiv.org/abs/2604.06170 - Tue, 07 Apr 2026 00:00:00 +0000 + Personalized RewardBench: Evaluating Reward Models with Human Aligned Personalization + https://arxiv.org/abs/2604.07343 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.07343.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qiyao Ma, Dechen Gao, Rui Cai, Boqi Zhao, Hanchu Zhou, Junshan Zhang, Zhe Zhao</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Pluralistic alignment has emerged as a critical frontier in the development of Large Language Models (LLMs), with reward models (RMs) serving as a central mechanism for capturing diverse human values. While benchmarks for general response quality are prevalent, evaluating how well reward models account for individual user preferences remains an open challenge. To bridge this gap, we introduce Personalized RewardBench, a novel benchmark designed to rigorously assess reward models' capacity to model personalized preferences. We construct chosen and rejected response pairs based on strict adherence to (or violation of) user-specific rubrics, ensuring that preference distinctions are uniquely tailored to the individual. In particular, human evaluations confirm that the primary discriminative factor between pairs is strictly personal preference, with both responses maintaining high general quality (e.g., correctness, relevance and helpfulness). Extensive testing reveals that existing state-of-the-art reward models struggle significantly with personalization, peaking at an accuracy of just 75.94%. Crucially, because an effective reward model benchmark should predict a reward model's performance on downstream tasks, we conduct experiments demonstrating that our benchmark exhibits a significantly higher correlation with downstream performance in both Best-of-N (BoN) sampling and Proximal Policy Optimization (PPO) compared to existing baselines. These findings establish Personalized RewardBench as a robust and accurate proxy for evaluating reward models' performance in downstream applications.</p> + https://arxiv.org/abs/2604.07343 + Wed, 08 Apr 2026 00:00:00 +0000 - Beyond Accuracy: Unveiling Inefficiency Patterns in Tool-Integrated Reasoning - https://arxiv.org/abs/2604.05404 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.05404.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qisheng Su, Shiting Huang, Zhen Fang, Ziyan Chen, Zehui Chen, Feng Zhao</p><p><b>Upvotes:</b> 29</p><p><b>Summary:</b> In real-world Tool-Integrated Reasoning (TIR) scenarios, where LLMs interleave reasoning with external tool calls, a major source of inefficiency is that the toolcalls create pauses between LLM requests and cause KV-Cache eviction, forcing recomputation. Also, the long, unfiltered response returned by external tools inflates the KV-Cache, so each decode step spends more time loading the growing cache and thus becomes steadily slower as context length increases. However, existing efficiency metrics like token counts and toolcall counts fail to capture the real model inference latency. To address this, we introduce PTE (Prefill Token Equivalents), a hardware-aware TIR-efficiency metric that unifies internal reasoning and external tool-use costs while explicitly accounting for non-reusable KV-Cache and long-tool-response scenarios. Validation in a high-concurrency industrial setting indicates that PTE aligns significantly better with wall-clock latency than standard token counts, while maintaining consistent efficiency rankings across diverse hardware profiles. We conduct extensive experiments across five TIR benchmarks, quantify their PTE costs, and identify four inefficiency patterns that appear in TIR. We also discover that trajectories with higher PTE costs tend to have lower reasoning correctness, indicating that simply using more tools does not improve the quality of the answer.</p> - https://arxiv.org/abs/2604.05404 - Tue, 07 Apr 2026 00:00:00 +0000 + MoRight: Motion Control Done Right + https://arxiv.org/abs/2604.07348 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.07348.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shaowei Liu, Xuanchi Ren, Tianchang Shen, Huan Ling, Saurabh Gupta, Shenlong Wang, Sanja Fidler, Jun Gao</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Generating motion-controlled videos--where user-specified actions drive physically plausible scene dynamics under freely chosen viewpoints--demands two capabilities: (1) disentangled motion control, allowing users to separately control the object motion and adjust camera viewpoint; and (2) motion causality, ensuring that user-driven actions trigger coherent reactions from other objects rather than merely displacing pixels. Existing methods fall short on both fronts: they entangle camera and object motion into a single tracking signal and treat motion as kinematic displacement without modeling causal relationships between object motion. We introduce MoRight, a unified framework that addresses both limitations through disentangled motion modeling. Object motion is specified in a canonical static-view and transferred to an arbitrary target camera viewpoint via temporal cross-view attention, enabling disentangled camera and object control. We further decompose motion into active (user-driven) and passive (consequence) components, training the model to learn motion causality from data. At inference, users can either supply active motion and MoRight predicts consequences (forward reasoning), or specify desired passive outcomes and MoRight recovers plausible driving actions (inverse reasoning), all while freely adjusting the camera viewpoint. Experiments on three benchmarks demonstrate state-of-the-art performance in generation quality, motion controllability, and interaction awareness.</p> + https://arxiv.org/abs/2604.07348 + Wed, 08 Apr 2026 00:00:00 +0000 - Claw-Eval: Toward Trustworthy Evaluation of Autonomous Agents - https://arxiv.org/abs/2604.06132 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.06132.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bowen Ye, Rang Li, Qibin Yang, Yuanxin Liu, Linli Yao, Hanglong Lv, Zhihui Xie, Chenxin An, Lei Li, Lingpeng Kong, Qi Liu, Zhifang Sui, Tong Yang</p><p><b>Upvotes:</b> 95</p><p><b>Summary:</b> Large language models are increasingly deployed as autonomous agents executing multi-step workflows in real-world software environments. However, existing agent benchmarks suffer from three critical limitations: (1) trajectory-opaque grading that checks only final outputs, (2) underspecified safety and robustness evaluation, and (3) narrow modality coverage and interaction paradigms. We introduce Claw-Eval, an end-to-end evaluation suite addressing all three gaps. It comprises 300 human-verified tasks spanning 9 categories across three groups (general service orchestration, multimodal perception and generation, and multi-turn professional dialogue). Every agent action is recorded through three independent evidence channels (execution traces, audit logs, and environment snapshots), enabling trajectory-aware grading over 2,159 fine-grained rubric items. The scoring protocol evaluates Completion, Safety, and Robustness, reporting Average Score, Pass@k, and Pass^k across three trials to distinguish genuine capability from lucky outcomes. Experiments on 14 frontier models reveal that: (1) trajectory-opaque evaluation is systematically unreliable, missing 44% of safety violations and 13% of robustness failures that our hybrid pipeline catches; (2) controlled error injection primarily degrades consistency rather than peak capability, with Pass^3 dropping up to 24% while Pass@3 remains stable; (3) multimodal performance varies sharply, with most models performing poorer on video than on document or image, and no single model dominating across all modalities. Beyond benchmarking, Claw-Eval highlights actionable directions for agent development, shedding light on what it takes to build agents that are not only capable but reliably deployable.</p> - https://arxiv.org/abs/2604.06132 - Tue, 07 Apr 2026 00:00:00 +0000 + Fast Spatial Memory with Elastic Test-Time Training + https://arxiv.org/abs/2604.07350 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.07350.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ziqiao Ma, Xueyang Yu, Haoyu Zhen, Yuncong Yang, Joyce Chai, Chuang Gan</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Large Chunk Test-Time Training (LaCT) has shown strong performance on long-context 3D reconstruction, but its fully plastic inference-time updates remain vulnerable to catastrophic forgetting and overfitting. As a result, LaCT is typically instantiated with a single large chunk spanning the full input sequence, falling short of the broader goal of handling arbitrarily long sequences in a single pass. We propose Elastic Test-Time Training inspired by elastic weight consolidation, that stabilizes LaCT fast-weight updates with a Fisher-weighted elastic prior around a maintained anchor state. The anchor evolves as an exponential moving average of past fast weights to balance stability and plasticity. Based on this updated architecture, we introduce Fast Spatial Memory (FSM), an efficient and scalable model for 4D reconstruction that learns spatiotemporal representations from long observation sequences and renders novel view-time combinations. We pre-trained FSM on large-scale curated 3D/4D data to capture the dynamics and semantics of complex spatial environments. Extensive experiments show that FSM supports fast adaptation over long sequences and delivers high-quality 3D/4D reconstruction with smaller chunks and mitigating the camera-interpolation shortcut. Overall, we hope to advance LaCT beyond the bounded single-chunk setting toward robust multi-chunk adaptation, a necessary step for generalization to genuinely longer sequences, while substantially alleviating the activation-memory bottleneck.</p> + https://arxiv.org/abs/2604.07350 + Wed, 08 Apr 2026 00:00:00 +0000 + + + FlowInOne:Unifying Multimodal Generation as Image-in, Image-out Flow Matching + https://arxiv.org/abs/2604.06757 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.06757.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junchao Yi, Rui Zhao, Jiahao Tang, Weixian Lei, Linjie Li, Qisheng Su, Zhengyuan Yang, Lijuan Wang, Xiaofeng Zhu, Alex Jinpeng Wang</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Multimodal generation has long been dominated by text-driven pipelines where language dictates vision but cannot reason or create within it. We challenge this paradigm by asking whether all modalities, including textual descriptions, spatial layouts, and editing instructions, can be unified into a single visual representation. We present FlowInOne, a framework that reformulates multimodal generation as a purely visual flow, converting all inputs into visual prompts and enabling a clean image-in, image-out pipeline governed by a single flow matching model. This vision-centric formulation naturally eliminates cross-modal alignment bottlenecks, noise scheduling, and task-specific architectural branches, unifying text-to-image generation, layout-guided editing, and visual instruction following under one coherent paradigm. To support this, we introduce VisPrompt-5M, a large-scale dataset of 5 million visual prompt pairs spanning diverse tasks including physics-aware force dynamics and trajectory prediction, alongside VP-Bench, a rigorously curated benchmark assessing instruction faithfulness, spatial precision, visual realism, and content consistency. Extensive experiments demonstrate that FlowInOne achieves state-of-the-art performance across all unified generation tasks, surpassing both open-source models and competitive commercial systems, establishing a new foundation for fully vision-centric generative modeling where perception and creation coexist within a single continuous visual space.</p> + https://arxiv.org/abs/2604.06757 + Wed, 08 Apr 2026 00:00:00 +0000 + + + TC-AE: Unlocking Token Capacity for Deep Compression Autoencoders + https://arxiv.org/abs/2604.07340 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.07340.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Teng Li, Ziyuan Huang, Cong Chen, Yangfu Li, Yuanhuiyi Lyu, Dandan Zheng, Chunhua Shen, Jun Zhang</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> We propose TC-AE, a ViT-based architecture for deep compression autoencoders. Existing methods commonly increase the channel number of latent representations to maintain reconstruction quality under high compression ratios. However, this strategy often leads to latent representation collapse, which degrades generative performance. Instead of relying on increasingly complex architectures or multi-stage training schemes, TC-AE addresses this challenge from the perspective of the token space, the key bridge between pixels and image latents, through two complementary innovations: Firstly, we study token number scaling by adjusting the patch size in ViT under a fixed latent budget, and identify aggressive token-to-latent compression as the key factor that limits effective scaling. To address this issue, we decompose token-to-latent compression into two stages, reducing structural information loss and enabling effective token number scaling for generation. Secondly, to further mitigate latent representation collapse, we enhance the semantic structure of image tokens via joint self-supervised training, leading to more generative-friendly latents. With these designs, TC-AE achieves substantially improved reconstruction and generative performance under deep compression. We hope our research will advance ViT-based tokenizer for visual generation.</p> + https://arxiv.org/abs/2604.07340 + Wed, 08 Apr 2026 00:00:00 +0000 + + + FP4 Explore, BF16 Train: Diffusion Reinforcement Learning via Efficient Rollout Scaling + https://arxiv.org/abs/2604.06916 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.06916.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yitong Li, Junsong Chen, Shuchen Xue, Pengcuo Zeren, Siyuan Fu, Dinghao Yang, Yangyang Tang, Junjie Bai, Ping Luo, Song Han, Enze Xie</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Reinforcement-Learning-based post-training has recently emerged as a promising paradigm for aligning text-to-image diffusion models with human preferences. In recent studies, increasing the rollout group size yields pronounced performance improvements, indicating substantial room for further alignment gains. However, scaling rollouts on large-scale foundational diffusion models (e.g., FLUX.1-12B) imposes a heavy computational burden. To alleviate this bottleneck, we explore the integration of FP4 quantization into Diffusion RL rollouts. Yet, we identify that naive quantized pipelines inherently introduce risks of performance degradation. To overcome this dilemma between efficiency and training integrity, we propose Sol-RL (Speed-of-light RL), a novel FP4-empowered Two-stage Reinforcement Learning framework. First, we utilize high-throughput NVFP4 rollouts to generate a massive candidate pool and extract a highly contrastive subset. Second, we regenerate these selected samples in BF16 precision and optimize the policy exclusively on them. By decoupling candidate exploration from policy optimization, Sol-RL integrates the algorithmic mechanisms of rollout scaling with the system-level throughput gains of NVFP4. This synergistic algorithm-hardware design effectively accelerates the rollout phase while reserving high-fidelity samples for optimization. We empirically demonstrate that our framework maintains the training integrity of BF16 precision pipeline while fully exploiting the throughput gains enabled by FP4 arithmetic. Extensive experiments across SANA, FLUX.1, and SD3.5-L substantiate that our approach delivers superior alignment performance across multiple metrics while accelerating training convergence by up to 4.64times, unlocking the power of massive rollout scaling at a fraction of the cost.</p> + https://arxiv.org/abs/2604.06916 + Wed, 08 Apr 2026 00:00:00 +0000 + + + INSPATIO-WORLD: A Real-Time 4D World Simulator via Spatiotemporal Autoregressive Modeling + https://arxiv.org/abs/2604.07209 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.07209.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> InSpatio Team, Donghui Shen, Guofeng Zhang, Haomin Liu, Haoyu Ji, Hujun Bao, Hongjia Zhai, Jialin Liu, Jing Guo, Nan Wang, Siji Pan, Weihong Pan, Weijian Xie, Xianbin Liu, Xiaojun Xiang, Xiaoyu Zhang, Xinyu Chen, Yifu Wang, Yipeng Chen, Zhenzhou Fan, Zhewen Le, Zhichao Ye, Ziqiang Zhao</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Building world models with spatial consistency and real-time interactivity remains a fundamental challenge in computer vision. Current video generation paradigms often struggle with a lack of spatial persistence and insufficient visual realism, making it difficult to support seamless navigation in complex environments. To address these challenges, we propose INSPATIO-WORLD, a novel real-time framework capable of recovering and generating high-fidelity, dynamic interactive scenes from a single reference video. At the core of our approach is a Spatiotemporal Autoregressive (STAR) architecture, which enables consistent and controllable scene evolution through two tightly coupled components: Implicit Spatiotemporal Cache aggregates reference and historical observations into a latent world representation, ensuring global consistency during long-horizon navigation; Explicit Spatial Constraint Module enforces geometric structure and translates user interactions into precise and physically plausible camera trajectories. Furthermore, we introduce Joint Distribution Matching Distillation (JDMD). By using real-world data distributions as a regularizing guide, JDMD effectively overcomes the fidelity degradation typically caused by over-reliance on synthetic data. Extensive experiments demonstrate that INSPATIO-WORLD significantly outperforms existing state-of-the-art (SOTA) models in spatial consistency and interaction precision, ranking first among real-time interactive methods on the WorldScore-Dynamic benchmark, and establishing a practical pipeline for navigating 4D environments reconstructed from monocular videos.</p> + https://arxiv.org/abs/2604.07209 + Wed, 08 Apr 2026 00:00:00 +0000 + + + MARS: Enabling Autoregressive Models Multi-Token Generation + https://arxiv.org/abs/2604.07023 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.07023.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ziqi Jin, Lei Wang, Ziwei Luo, Aixin Sun</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> Autoregressive (AR) language models generate text one token at a time, even when consecutive tokens are highly predictable given earlier context. We introduce MARS (Mask AutoRegreSsion), a lightweight fine-tuning method that teaches an instruction-tuned AR model to predict multiple tokens per forward pass. MARS adds no architectural modifications, no extra parameters, and produces a single model that can still be called exactly like the original AR model with no performance degradation. Unlike speculative decoding, which maintains a separate draft model alongside the target, or multi-head approaches such as Medusa, which attach additional prediction heads, MARS requires only continued training on existing instruction data. When generating one token per forward pass, MARS matches or exceeds the AR baseline on six standard benchmarks. When allowed to accept multiple tokens per step, it maintains baseline-level accuracy while achieving 1.5-1.7x throughput. We further develop a block-level KV caching strategy for batch inference, achieving up to 1.71x wall-clock speedup over AR with KV cache on Qwen2.5-7B. Finally, MARS supports real-time speed adjustment via confidence thresholding: under high request load, the serving system can increase throughput on the fly without swapping models or restarting, providing a practical latency-quality knob for deployment.</p> + https://arxiv.org/abs/2604.07023 + Wed, 08 Apr 2026 00:00:00 +0000 + + + Think in Strokes, Not Pixels: Process-Driven Image Generation via Interleaved Reasoning + https://arxiv.org/abs/2604.04746 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.04746.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lei Zhang, Junjiao Tian, Zhipeng Fan, Kunpeng Li, Jialiang Wang, Weifeng Chen, Markos Georgopoulos, Felix Juefei-Xu, Yuxiang Bao, Julian McAuley, Manling Li, Zecheng He</p><p><b>Upvotes:</b> 45</p><p><b>Summary:</b> Humans paint images incrementally: they plan a global layout, sketch a coarse draft, inspect, and refine details, and most importantly, each step is grounded in the evolving visual states. However, can unified multimodal models trained on text-image interleaved datasets also imagine the chain of intermediate states? In this paper, we introduce process-driven image generation, a multi-step paradigm that decomposes synthesis into an interleaved reasoning trajectory of thoughts and actions. Rather than generating images in a single step, our approach unfolds across multiple iterations, each consisting of 4 stages: textual planning, visual drafting, textual reflection, and visual refinement. The textual reasoning explicitly conditions how the visual state should evolve, while the generated visual intermediate in turn constrains and grounds the next round of textual reasoning. A core challenge of process-driven generation stems from the ambiguity of intermediate states: how can models evaluate each partially-complete image? We address this through dense, step-wise supervision that maintains two complementary constraints: for the visual intermediate states, we enforce the spatial and semantic consistency; for the textual intermediate states, we preserve the prior visual knowledge while enabling the model to identify and correct prompt-violating elements. This makes the generation process explicit, interpretable, and directly supervisable. To validate proposed method, we conduct experiments under various text-to-image generation benchmarks.</p> + https://arxiv.org/abs/2604.04746 + Wed, 08 Apr 2026 00:00:00 +0000