From bcd2245a3801eb8a8cd7a76b3fb9f8305c0cca9f Mon Sep 17 00:00:00 2001 From: "github-actions[bot]" Date: Wed, 25 Mar 2026 00:05:21 +0000 Subject: [PATCH] bot: update RSS feed --- feed.xml | 400 +++++++++++++++++++++++++++++-------------------------- 1 file changed, 214 insertions(+), 186 deletions(-) diff --git a/feed.xml b/feed.xml index dfe6519..5239f10 100644 --- a/feed.xml +++ b/feed.xml @@ -7,265 +7,293 @@ http://www.rssboard.org/rss-specification python-feedgen en - Tue, 24 Mar 2026 00:04:40 +0000 + Wed, 25 Mar 2026 00:05:21 +0000 - Reasoning as Compression: Unifying Budget Forcing via the Conditional Information Bottleneck - https://arxiv.org/abs/2603.08462 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.08462.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Fabio Valerio Massoli, Andrey Kuzmin, Arash Behboodi</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Chain-of-Thought (CoT) prompting improves LLM accuracy on complex tasks but often increases token usage and inference cost. Existing "Budget Forcing" methods reducing cost via fine-tuning with heuristic length penalties, suppress both essential reasoning and redundant filler. We recast efficient reasoning as a lossy compression problem under the Information Bottleneck (IB) principle, and identify a key theoretical gap when applying naive IB to transformers: attention violates the Markov property between prompt, reasoning trace, and response. To resolve this issue, we model CoT generation under the Conditional Information Bottleneck (CIB) principle, where the reasoning trace Z acts as a computational bridge that contains only the information about the response Y that is not directly accessible from the prompt X. This yields a general Reinforcement Learning objective: maximize task reward while compressing completions under a prior over reasoning traces, subsuming common heuristics (e.g., length penalties) as special cases (e.g., uniform priors). In contrast to naive token-counting-based approaches, we introduce a semantic prior that measures token cost by surprisal under a language model prior. Empirically, our CIB objective prunes cognitive bloat while preserving fluency and logic, improving accuracy at moderate compression and enabling aggressive compression with minimal accuracy drop.</p> - https://arxiv.org/abs/2603.08462 - Mon, 09 Mar 2026 14:56:57 +0000 + ToolRosetta: Bridging Open-Source Repositories and Large Language Model Agents through Automated Tool Standardization + https://arxiv.org/abs/2603.09290 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.09290.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shimin Di, Xujie Yuan, Hanghui Guo, Chaoqian Ouyang, Zhangze Chen, Ling Yue, Libin Zheng, Jia Zhu, Shaowu Pan, Jian Yin, Min-Ling Zhang, Yong Rui</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Reusing and invoking existing code remains costly and unreliable, as most practical tools are embedded in heterogeneous code repositories and lack standardized, executable interfaces. Although large language models (LLMs) and Model Context Protocol (MCP)-based tool invocation frameworks enable natural language task execution, current approaches rely heavily on manual tool curation and standardization, which fundamentally limits scalability. In this paper, we propose ToolRosetta, a unified framework that automatically translates open-source code repositories and APIs into MCP-compatible tools that can be reliably invoked by LLMs. Given a user task, ToolRosetta autonomously plans toolchains, identifies relevant codebases, and converts them into executable MCP services, enabling end-to-end task completion with minimal human intervention. In addition, ToolRosetta incorporates a security inspection layer to mitigate risks inherent in executing arbitrary code. Extensive experiments across diverse scientific domains demonstrate that ToolRosetta can automatically standardize a large number of open-source tools and reduce the human effort required for code reproduction and deployment. Notably, by seamlessly leveraging specialized open-source tools, ToolRosetta-powered agents consistently improve task completion performance compared to commercial LLMs and existing agent systems.</p> + https://arxiv.org/abs/2603.09290 + Tue, 10 Mar 2026 07:19:43 +0000 - Deep Tabular Research via Continual Experience-Driven Execution - https://arxiv.org/abs/2603.09151 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.09151.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junnan Dong, Chuang Zhou, Zheng Yuan, Yifei Yu, Qiufeng Wang, Yinghui Li, Siyu An, Di Yin, Xing Sun, Feiyue Huang</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Large language models often struggle with complex long-horizon analytical tasks over unstructured tables, which typically feature hierarchical and bidirectional headers and non-canonical layouts. We formalize this challenge as Deep Tabular Research (DTR), requiring multi-step reasoning over interdependent table regions. To address DTR, we propose a novel agentic framework that treats tabular reasoning as a closed-loop decision-making process. We carefully design a coupled query and table comprehension for path decision making and operational execution. Specifically, (i) DTR first constructs a hierarchical meta graph to capture bidirectional semantics, mapping natural language queries into an operation-level search space; (ii) To navigate this space, we introduce an expectation-aware selection policy that prioritizes high-utility execution paths; (iii) Crucially, historical execution outcomes are synthesized into a siamese structured memory, i.e., parameterized updates and abstracted texts, enabling continual refinement. Extensive experiments on challenging unstructured tabular benchmarks verify the effectiveness and highlight the necessity of separating strategic planning from low-level execution for long-horizon tabular reasoning.</p> - https://arxiv.org/abs/2603.09151 - Tue, 10 Mar 2026 03:42:54 +0000 + Look Where It Matters: High-Resolution Crops Retrieval for Efficient VLMs + https://arxiv.org/abs/2603.16932 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.16932.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Nimrod Shabtay, Moshe Kimhi, Artem Spector, Sivan Haray, Ehud Rivlin, Chaim Baskin, Raja Giryes, Eli Schwartz</p><p><b>Upvotes:</b> 56</p><p><b>Summary:</b> Vision-language models (VLMs) typically process images at a native high-resolution, forcing a trade-off between accuracy and computational efficiency: high-resolution inputs capture fine details but incur significant computational costs, while low-resolution inputs advocate for efficiency, they potentially miss critical visual information, like small text. We present AwaRes, a spatial-on-demand framework that resolves this accuracy-efficiency trade-off by operating on a low-resolution global view and using tool-calling to retrieve only high-resolution segments needed for a given query. We construct supervised data automatically: a judge compares low- vs.\ high-resolution answers to label whether cropping is needed, and an oracle grounding model localizes the evidence for the correct answer, which we map to a discrete crop set to form multi-turn tool-use trajectories. We train our framework with cold-start SFT followed by multi-turn GRPO with a composite reward that combines semantic answer correctness with explicit crop-cost penalties. Project page: https://nimrodshabtay.github.io/AwaRes</p> + https://arxiv.org/abs/2603.16932 + Sat, 14 Mar 2026 10:11:32 +0000 - s2n-bignum-bench: A practical benchmark for evaluating low-level code reasoning of LLMs - https://arxiv.org/abs/2603.14628 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.14628.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Balaji Rao, John Harrison, Soonho Kong, Juneyoung Lee, Carlo Lipizzi</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Neurosymbolic approaches leveraging Large Language Models (LLMs) with formal methods have recently achieved strong results on mathematics-oriented theorem-proving benchmarks. However, success on competition-style mathematics does not by itself demonstrate the ability to construct proofs about real-world implementations. We address this gap with a benchmark derived from an industrial cryptographic library whose assembly routines are already verified in HOL Light. s2n-bignum is a library used at AWS for providing fast assembly routines for cryptography, and its correctness is established by formal verification. The task of formally verifying this library has been a significant achievement for the Automated Reasoning Group. It involved two tasks: (1) precisely specifying the correct behavior of a program as a mathematical proposition, and (2) proving that the proposition is correct. In the case of s2n-bignum, both tasks were carried out by human experts. In s2n-bignum-bench, we provide the formal specification and ask the LLM to generate a proof script that is accepted by HOL Light within a fixed proof-check timeout. To our knowledge, s2n-bignum-bench is the first public benchmark focused on machine-checkable proof synthesis for industrial low-level cryptographic assembly routines in HOL Light. This benchmark provides a challenging and practically relevant testbed for evaluating LLM-based theorem proving beyond competition mathematics. The code to set up and use the benchmark is available here: https://github.com/kings-crown/s2n-bignum-bench{s2n-bignum-bench}.</p> - https://arxiv.org/abs/2603.14628 - Sun, 15 Mar 2026 21:55:59 +0000 + Aperiodic Structures Never Collapse: Fibonacci Hierarchies for Lossless Compression + https://arxiv.org/abs/2603.14999 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.14999.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Roberto Tacconelli</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> We study whether an aperiodic hierarchy can provide a structural advantage for lossless compression over periodic alternatives. We show that Fibonacci quasicrystal tilings avoid the finite-depth collapse that affects periodic hierarchies: usable n-gram lookup positions remain non-zero at every level, while periodic tilings collapse after O(log p) levels for period p. This yields an aperiodic hierarchy advantage: dictionary reuse remains available across all scales instead of vanishing beyond a finite depth. Our analysis gives four main consequences. First, the Golden Compensation property shows that the exponential decay in the number of positions is exactly balanced by the exponential growth in phrase length, so potential coverage remains scale-invariant with asymptotic value Wvarphi/5. Second, using the Sturmian complexity law p(n)=n+1, we show that Fibonacci/Sturmian hierarchies maximize codebook coverage efficiency among binary aperiodic tilings. Third, under long-range dependence, the resulting hierarchy achieves lower coding entropy than comparable periodic hierarchies. Fourth, redundancy decays super-exponentially with depth, whereas periodic systems remain locked at the depth where collapse occurs. We validate these results with Quasicryth, a lossless text compressor built on a ten-level Fibonacci hierarchy with phrase lengths {2,3,5,8,13,21,34,55,89,144}. In controlled A/B experiments with identical codebooks, the aperiodic advantage over a Period-5 baseline grows from 36{,}243 B at 3 MB to 11{,}089{,}469 B at 1 GB, explained by the activation of deeper hierarchy levels. On enwik9, Quasicryth achieves 225{,}918{,}349 B (22.59%), with 20{,}735{,}733 B saved by the Fibonacci tiling relative to no tiling.</p> + https://arxiv.org/abs/2603.14999 + Mon, 16 Mar 2026 09:02:59 +0000 - Human-AI Synergy in Agentic Code Review - https://arxiv.org/abs/2603.15911 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15911.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Suzhen Zhong, Shayan Noei, Ying Zou, Bram Adams</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Code review is a critical software engineering practice where developers review code changes before integration to ensure code quality, detect defects, and improve maintainability. In recent years, AI agents that can understand code context, plan review actions, and interact with development environments have been increasingly integrated into the code review process. However, there is limited empirical evidence to compare the effectiveness of AI agents and human reviewers in collaborative workflows. To address this gap, we conduct a large-scale empirical analysis of 278,790 code review conversations across 300 open-source GitHub projects. In our study, we aim to compare the feedback differences provided by human reviewers and AI agents. We investigate human-AI collaboration patterns in review conversations to understand how interaction shapes review outcomes. Moreover, we analyze the adoption of code suggestions provided by human reviewers and AI agents into the codebase and how adopted suggestions change code quality. We find that human reviewers provide additional feedback than AI agents, including understanding, testing, and knowledge transfer. Human reviewers exchange 11.8% more rounds when reviewing AI-generated code than human-written code. Moreover, code suggestions made by AI agents are adopted into the codebase at a significantly lower rate than suggestions proposed by human reviewers. Over half of unadopted suggestions from AI agents are either incorrect or addressed through alternative fixes by developers. When adopted, suggestions provided by AI agents produce significantly larger increases in code complexity and code size than suggestions provided by human reviewers. Our findings suggest that while AI agents can scale defect screening, human oversight remains critical for ensuring suggestion quality and providing contextual feedback that AI agents lack.</p> - https://arxiv.org/abs/2603.15911 - Mon, 16 Mar 2026 20:56:18 +0000 + Safe Flow Q-Learning: Offline Safe Reinforcement Learning with Reachability-Based Flow Policies + https://arxiv.org/abs/2603.15136 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15136.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mumuksh Tayal, Manan Tayal, Ravi Prakash</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Offline safe reinforcement learning (RL) seeks reward-maximizing policies from static datasets under strict safety constraints. Existing methods often rely on soft expected-cost objectives or iterative generative inference, which can be insufficient for safety-critical real-time control. We propose Safe Flow Q-Learning (SafeFQL), which extends FQL to safe offline RL by combining a Hamilton--Jacobi reachability-inspired safety value function with an efficient one-step flow policy. SafeFQL learns the safety value via a self-consistency Bellman recursion, trains a flow policy by behavioral cloning, and distills it into a one-step actor for reward-maximizing safe action selection without rejection sampling at deployment. To account for finite-data approximation error in the learned safety boundary, we add a conformal prediction calibration step that adjusts the safety threshold and provides finite-sample probabilistic safety coverage. Empirically, SafeFQL trades modestly higher offline training cost for substantially lower inference latency than diffusion-style safe generative baselines, which is advantageous for real-time safety-critical deployment. Across boat navigation, and Safety Gymnasium MuJoCo tasks, SafeFQL matches or exceeds prior offline safe RL performance while substantially reducing constraint violations.</p> + https://arxiv.org/abs/2603.15136 + Mon, 16 Mar 2026 11:28:47 +0000 - Probing Cultural Signals in Large Language Models through Author Profiling - https://arxiv.org/abs/2603.16749 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.16749.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Valentin Lafargue, Ariel Guerra-Adames, Emmanuelle Claeys, Elouan Vuichard, Jean-Michel Loubes</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Large language models (LLMs) are increasingly deployed in applications with societal impact, raising concerns about the cultural biases they encode. We probe these representations by evaluating whether LLMs can perform author profiling from song lyrics in a zero-shot setting, inferring singers' gender and ethnicity without task-specific fine-tuning. Across several open-source models evaluated on more than 10,000 lyrics, we find that LLMs achieve non-trivial profiling performance but demonstrate systematic cultural alignment: most models default toward North American ethnicity, while DeepSeek-1.5B aligns more strongly with Asian ethnicity. This finding emerges from both the models' prediction distributions and an analysis of their generated rationales. To quantify these disparities, we introduce two fairness metrics, Modality Accuracy Divergence (MAD) and Recall Divergence (RD), and show that Ministral-8B displays the strongest ethnicity bias among the evaluated models, whereas Gemma-12B shows the most balanced behavior. Our code is available on GitHub (https://github.com/ValentinLafargue/CulturalProbingLLM).</p> - https://arxiv.org/abs/2603.16749 - Tue, 17 Mar 2026 16:27:47 +0000 + OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis + https://arxiv.org/abs/2603.20278 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.20278.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhuofeng Li, Dongfu Jiang, Xueguang Ma, Haoxiang Zhang, Ping Nie, Yuyu Zhang, Kai Zou, Jianwen Xie, Yu Zhang, Wenhu Chen</p><p><b>Upvotes:</b> 50</p><p><b>Summary:</b> Training deep research agents requires long-horizon trajectories that interleave search, evidence aggregation, and multi-step reasoning. However, existing data collection pipelines typically rely on proprietary web APIs, making large-scale trajectory synthesis costly, unstable, and difficult to reproduce. We present OpenResearcher, a reproducible pipeline that decouples one-time corpus bootstrapping from multi-turn trajectory synthesis and executes the search-and-browse loop entirely offline using three explicit browser primitives: search, open, and find, over a 15M-document corpus. Using GPT-OSS-120B as the teacher model, we synthesize over 97K trajectories, including a substantial long-horizon tail with 100+ tool calls. Supervised fine-tuning a 30B-A3B backbone on these trajectories achieves 54.8\% accuracy on BrowseComp-Plus, a +34.0 point improvement over the base model, while remaining competitive on BrowseComp, GAIA, and xbench-DeepSearch. Because the environment is offline and fully instrumented, it also enables controlled analysis, where our study reveals practical insights into deep research pipeline design, including data filtering strategies, agent configuration choices, and how retrieval success relates to final answer accuracy. We release the pipeline, synthesized trajectories, model checkpoints, and the offline search environment at https://github.com/TIGER-AI-Lab/OpenResearcher.</p> + https://arxiv.org/abs/2603.20278 + Tue, 17 Mar 2026 20:10:12 +0000 - HopChain: Multi-Hop Data Synthesis for Generalizable Vision-Language Reasoning - https://arxiv.org/abs/2603.17024 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.17024.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shenzhi Wang, Shixuan Liu, Jing Zhou, Chang Gao, Xiong-Hui Chen, Binghai Wang, An Yang, Shiji Song, Bowen Yu, Gao Huang, Junyang Lin</p><p><b>Upvotes:</b> 94</p><p><b>Summary:</b> VLMs show strong multimodal capabilities, but they still struggle with fine-grained vision-language reasoning. We find that long CoT reasoning exposes diverse failure modes, including perception, reasoning, knowledge, and hallucination errors, which can compound across intermediate steps. However, most existing vision-language data used for RLVR does not involve complex reasoning chains that rely on visual evidence throughout, leaving these weaknesses largely unexposed. We therefore propose HopChain, a scalable framework for synthesizing multi-hop vision-language reasoning data specifically for RLVR training of VLMs. Each synthesized multi-hop query forms a logically dependent chain of instance-grounded hops, where earlier hops establish the instances, sets, or conditions needed for later hops, while the final answer remains a specific, unambiguous number suitable for verifiable rewards. We add the multi-hop data synthesized by HopChain to the original RLVR data used to train Qwen3.5-35B-A3B and Qwen3.5-397B-A17B, and compare against RLVR on the original RLVR data alone across 24 benchmarks spanning STEM and Puzzle, General VQA, Text Recognition and Document Understanding, and Video Understanding. Although this multi-hop data is not synthesized to target any specific benchmark, adding it improves 20 out of 24 benchmarks on both models, indicating broad and generalizable gains. To demonstrate that full chained queries are important, we replace them with half-multi-hop or single-hop variants, reducing the 24-benchmark average accuracy by 5.3 and 7.0 points, respectively. Multi-hop training also strengthens long-CoT vision-language reasoning, with gains peaking at more than 50 accuracy points in the ultra-long-CoT regime. These experiments establish HopChain as an effective, scalable framework for synthesizing multi-hop data that improves generalizable vision-language reasoning.</p> - https://arxiv.org/abs/2603.17024 - Tue, 17 Mar 2026 18:04:58 +0000 + Insight-V++: Towards Advanced Long-Chain Visual Reasoning with Multimodal Large Language Models + https://arxiv.org/abs/2603.18118 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.18118.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuhao Dong, Zuyan Liu, Shulin Tian, Yongming Rao, Ziwei Liu</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Large Language Models (LLMs) have achieved remarkable reliability and advanced capabilities through extended test-time reasoning. However, extending these capabilities to Multi-modal Large Language Models (MLLMs) remains a significant challenge due to a critical scarcity of high-quality, long-chain reasoning data and optimized training pipelines. To bridge this gap, we present a unified multi-agent visual reasoning framework that systematically evolves from our foundational image-centric model, Insight-V, into a generalized spatial-temporal architecture, Insight-V++. We first propose a scalable data generation pipeline equipped with multi-granularity assessment that autonomously synthesizes structured, complex reasoning trajectories across image and video domains without human intervention. Recognizing that directly supervising MLLMs with such intricate data yields sub-optimal results, we design a dual-agent architecture comprising a reasoning agent to execute extensive analytical chains, and a summary agent to critically evaluate and distill final outcomes. While our initial framework utilized Direct Preference Optimization (DPO), its off-policy nature fundamentally constrained reinforcement learning potential. To overcome these limitations, particularly for long-horizon video understanding, Insight-V++ introduces two novel algorithms, ST-GRPO and J-GRPO, which enhance spatial-temporal reasoning and improve evaluative robustness. Crucially, by leveraging reliable feedback from the summary agent, we guide an iterative reasoning path generation process, retraining the entire multi-agent system in a continuous, self-improving loop. Extensive experiments on base models like LLaVA-NeXT and Qwen2.5-VL demonstrate significant performance gains across challenging image and video reasoning benchmarks while preserving strong capabilities on traditional perception-focused tasks.</p> + https://arxiv.org/abs/2603.18118 + Wed, 18 Mar 2026 15:28:07 +0000 - Astrolabe: Steering Forward-Process Reinforcement Learning for Distilled Autoregressive Video Models - https://arxiv.org/abs/2603.17051 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.17051.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Songchun Zhang, Zeyue Xue, Siming Fu, Jie Huang, Xianghao Kong, Y Ma, Haoyang Huang, Nan Duan, Anyi Rao</p><p><b>Upvotes:</b> 83</p><p><b>Summary:</b> Distilled autoregressive (AR) video models enable efficient streaming generation but frequently misalign with human visual preferences. Existing reinforcement learning (RL) frameworks are not naturally suited to these architectures, typically requiring either expensive re-distillation or solver-coupled reverse-process optimization that introduces considerable memory and computational overhead. We present Astrolabe, an efficient online RL framework tailored for distilled AR models. To overcome existing bottlenecks, we introduce a forward-process RL formulation based on negative-aware fine-tuning. By contrasting positive and negative samples directly at inference endpoints, this approach establishes an implicit policy improvement direction without requiring reverse-process unrolling. To scale this alignment to long videos, we propose a streaming training scheme that generates sequences progressively via a rolling KV-cache, applying RL updates exclusively to local clip windows while conditioning on prior context to ensure long-range coherence. Finally, to mitigate reward hacking, we integrate a multi-reward objective stabilized by uncertainty-aware selective regularization and dynamic reference updates. Extensive experiments demonstrate that our method consistently enhances generation quality across multiple distilled AR video models, serving as a robust and scalable alignment solution.</p> - https://arxiv.org/abs/2603.17051 - Tue, 17 Mar 2026 18:32:18 +0000 + Perceptio: Perception Enhanced Vision Language Models via Spatial Token Generation + https://arxiv.org/abs/2603.18795 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.18795.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuchen Li, Amanmeet Garg, Shalini Chaudhuri, Rui Zhao, Garin Kessler</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Large Vision Language Models (LVLMs) excel at semantic understanding but struggle with fine grained spatial grounding, as the model must implicitly infer complex geometry without ever producing a spatial interpretation. We present Perceptio, a perception enhanced LVLM with 2D and 3D spatial reasoning abilities, enabled via explicit semantic segmentation tokens and depth tokens generated directly within the autoregressive sequence. Concretely, we (i) distill a VQVAE depth codebook from a strong monocular teacher to tokenize dense depth into compact sequences, and (ii) integrate SAM2 based semantic segmentation tokens and VQ-VAE depth tokens inside the LLM so the model first emits spatial tokens and then answers. To stabilize depth token generation, we introduce novel composite depth-token objectives (marker, token, and count losses) and a soft-merging technique for differentiable reconstruction. We adopt a multi-task co-training strategy across diverse datasets, letting the model learn perception tokens to tackle multiple downstream tasks. Building on InternVL, Perceptio achieves state-of-the-art performance across benchmarks: improving referring expression segmentation by +0.8/+1.4/+1.1 cIoU on RefCOCO/+/g HardBLINK spatial understanding accuracy by 10.3%, and MMBench accuracy by 1.0%, demonstrating that explicit spatial chain-of-thought materially strengthens spatial grounding in LVLMs.</p> + https://arxiv.org/abs/2603.18795 + Thu, 19 Mar 2026 11:46:01 +0000 - ReLMXEL: Adaptive RL-Based Memory Controller with Explainable Energy and Latency Optimization - https://arxiv.org/abs/2603.17309 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.17309.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Panuganti Chirag Sai, Gandholi Sarat, R. Raghunatha Sarma, Venkata Kalyan Tavva, Naveen M</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Reducing latency and energy consumption is critical to improving the efficiency of memory systems in modern computing. This work introduces ReLMXEL (Reinforcement Learning for Memory Controller with Explainable Energy and Latency Optimization), a explainable multi-agent online reinforcement learning framework that dynamically optimizes memory controller parameters using reward decomposition. ReLMXEL operates within the memory controller, leveraging detailed memory behavior metrics to guide decision-making. Experimental evaluations across diverse workloads demonstrate consistent performance gains over baseline configurations, with refinements driven by workload-specific memory access behaviour. By incorporating explainability into the learning process, ReLMXEL not only enhances performance but also increases the transparency of control decisions, paving the way for more accountable and adaptive memory system designs.</p> - https://arxiv.org/abs/2603.17309 - Wed, 18 Mar 2026 03:07:54 +0000 + Progressive Training for Explainable Citation-Grounded Dialogue: Reducing Hallucination to Zero in English-Hindi LLMs + https://arxiv.org/abs/2603.18911 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.18911.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Vedant Pandya</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Knowledge-grounded dialogue systems aim to generate informative, contextually relevant responses by conditioning on external knowledge sources. However, most existing approaches focus exclusively on English, lack explicit citation mechanisms for verifying factual claims, and offer limited transparency into model decision-making. We present XKD-Dial, a progressive four-stage training pipeline for explainable, knowledge-grounded dialogue generation in a bilingual (English-Hindi) setting, comprising: (1) multilingual adaptation, (2) English dialogue SFT with citation grounding, (3) bilingual dialogue SFT, and (4) GRPO alignment with citation-aware rewards. We evaluate six models spanning encoder-decoder (250M-3B) and decoder-only (1B-7B) architectures at every pipeline stage. Our key contributions are: (i) three post-hoc explainability analyses - cross-attention alignment, Integrated Gradients attribution, and occlusion-based causal grounding - applied systematically across the training trajectory to reveal how citation behaviour is learned, not only whether it is learned; (ii) citation-grounded SFT reduces hallucination to 0.0% for encoder-decoder models from Stage 2 onward; (iii) the progressive pipeline prevents catastrophic forgetting while improving Hindi capabilities; (iv) smaller models match larger models on English after SFT; and (v) GRPO provides marginal improvement over well-designed SFT for structured citation tasks. We evaluate across six automatic metrics (BLEU, ROUGE, BERTScore, FactScore, Citation-F1, and hallucination rate).</p> + https://arxiv.org/abs/2603.18911 + Thu, 19 Mar 2026 13:48:19 +0000 - Language on Demand, Knowledge at Core: Composing LLMs with Encoder-Decoder Translation Models for Extensible Multilinguality - https://arxiv.org/abs/2603.17512 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.17512.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mengyu Bu, Yang Feng</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Large language models (LLMs) exhibit strong general intelligence, yet their multilingual performance remains highly imbalanced. Although LLMs encode substantial cross-lingual knowledge in a unified semantic space, they often struggle to reliably interface this knowledge with low-resource or unseen languages. Fortunately, pretrained encoder-decoder translation models already possess balanced multilingual capability, suggesting a natural complement to LLMs. In this work, we propose XBridge, a compositional encoder-LLM-decoder architecture that offloads multilingual understanding and generation to external pretrained translation models, while preserving the LLM as an English-centric core for general knowledge processing. To address the resulting representation misalignment across models, we introduce lightweight cross-model mapping layers and an optimal transport-based alignment objective, enabling fine-grained semantic consistency for multilingual generation. Experiments on four LLMs across multilingual understanding, reasoning, summarization, and generation indicate that XBridge outperforms strong baselines, especially on low-resource and previously unseen languages, without retraining the LLM.</p> - https://arxiv.org/abs/2603.17512 - Wed, 18 Mar 2026 09:19:08 +0000 + SEM: Sparse Embedding Modulation for Post-Hoc Debiasing of Vision-Language Models + https://arxiv.org/abs/2603.19028 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19028.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Quentin Guimard, Federico Bartsch, Simone Caldarella, Rahaf Aljundi, Elisa Ricci, Massimiliano Mancini</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Models that bridge vision and language, such as CLIP, are key components of multimodal AI, yet their large-scale, uncurated training data introduce severe social and spurious biases. Existing post-hoc debiasing methods often operate directly in the dense CLIP embedding space, where bias and task-relevant information are highly entangled. This entanglement limits their ability to remove bias without degrading semantic fidelity. In this work, we propose Sparse Embedding Modulation (SEM), a post-hoc, zero-shot debiasing framework that operates in a Sparse Autoencoder (SAE) latent space. By decomposing CLIP text embeddings into disentangled features, SEM identifies and modulates bias-relevant neurons while preserving query-relevant ones. This enables more precise, non-linear interventions. Across four benchmark datasets and two CLIP backbones, SEM achieves substantial fairness gains in retrieval and zero-shot classification. Our results demonstrate that sparse latent representations provide an effective foundation for post-hoc debiasing of vision-language models.</p> + https://arxiv.org/abs/2603.19028 + Thu, 19 Mar 2026 15:28:08 +0000 - TAPESTRY: From Geometry to Appearance via Consistent Turntable Videos - https://arxiv.org/abs/2603.17735 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.17735.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yan Zeng, Haoran Jiang, Kaixin Yao, Qixuan Zhang, Longwen Zhang, Lan Xu, Jingyi Yu</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Automatically generating photorealistic and self-consistent appearances for untextured 3D models is a critical challenge in digital content creation. The advancement of large-scale video generation models offers a natural approach: directly synthesizing 360-degree turntable videos (TTVs), which can serve not only as high-quality dynamic previews but also as an intermediate representation to drive texture synthesis and neural rendering. However, existing general-purpose video diffusion models struggle to maintain strict geometric consistency and appearance stability across the full range of views, making their outputs ill-suited for high-quality 3D reconstruction. To this end, we introduce TAPESTRY, a framework for generating high-fidelity TTVs conditioned on explicit 3D geometry. We reframe the 3D appearance generation task as a geometry-conditioned video diffusion problem: given a 3D mesh, we first render and encode multi-modal geometric features to constrain the video generation process with pixel-level precision, thereby enabling the creation of high-quality and consistent TTVs. Building upon this, we also design a method for downstream reconstruction tasks from the TTV input, featuring a multi-stage pipeline with 3D-Aware Inpainting. By rotating the model and performing a context-aware secondary generation, this pipeline effectively completes self-occluded regions to achieve full surface coverage. The videos generated by TAPESTRY are not only high-quality dynamic previews but also serve as a reliable, 3D-aware intermediate representation that can be seamlessly back-projected into UV textures or used to supervise neural rendering methods like 3DGS. This enables the automated creation of production-ready, complete 3D assets from untextured meshes. Experimental results demonstrate that our method outperforms existing approaches in both video consistency and final reconstruction quality.</p> - https://arxiv.org/abs/2603.17735 - Wed, 18 Mar 2026 14:02:09 +0000 + BubbleRAG: Evidence-Driven Retrieval-Augmented Generation for Black-Box Knowledge Graphs + https://arxiv.org/abs/2603.20309 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.20309.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Duyi Pan, Tianao Lou, Xin Li, Haoze Song, Yiwen Wu, Mengyi Deng, Mingyu Yang, Wei Wang</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> Large Language Models (LLMs) exhibit hallucinations in knowledge-intensive tasks. Graph-based retrieval augmented generation (RAG) has emerged as a promising solution, yet existing approaches suffer from fundamental recall and precision limitations when operating over black-box knowledge graphs -- graphs whose schema and structure are unknown in advance. We identify three core challenges that cause recall loss (semantic instantiation uncertainty and structural path uncertainty) and precision loss (evidential comparison uncertainty). To address these challenges, we formalize the retrieval task as the Optimal Informative Subgraph Retrieval (OISR) problem -- a variant of Group Steiner Tree -- and prove it to be NP-hard and APX-hard. We propose BubbleRAG, a training-free pipeline that systematically optimizes for both recall and precision through semantic anchor grouping, heuristic bubble expansion to discover candidate evidence graphs (CEGs), composite ranking, and reasoning-aware expansion. Experiments on multi-hop QA benchmarks demonstrate that BubbleRAG achieves state-of-the-art results, outperforming strong baselines in both F1 and accuracy while remaining plug-and-play.</p> + https://arxiv.org/abs/2603.20309 + Thu, 19 Mar 2026 16:00:36 +0000 - Versatile Editing of Video Content, Actions, and Dynamics without Training - https://arxiv.org/abs/2603.17989 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.17989.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Vladimir Kulikov, Roni Paiss, Andrey Voynov, Inbar Mosseri, Tali Dekel, Tomer Michaeli</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Controlled video generation has seen drastic improvements in recent years. However, editing actions and dynamic events, or inserting contents that should affect the behaviors of other objects in real-world videos, remains a major challenge. Existing trained models struggle with complex edits, likely due to the difficulty of collecting relevant training data. Similarly, existing training-free methods are inherently restricted to structure- and motion-preserving edits and do not support modification of motion or interactions. Here, we introduce DynaEdit, a training-free editing method that unlocks versatile video editing capabilities with pretrained text-to-video flow models. Our method relies on the recently introduced inversion-free approach, which does not intervene in the model internals, and is thus model-agnostic. We show that naively attempting to adapt this approach to general unconstrained editing results in severe low-frequency misalignment and high-frequency jitter. We explain the sources for these phenomena and introduce novel mechanisms for overcoming them. Through extensive experiments, we show that DynaEdit achieves state-of-the-art results on complex text-based video editing tasks, including modifying actions, inserting objects that interact with the scene, and introducing global effects.</p> - https://arxiv.org/abs/2603.17989 - Wed, 18 Mar 2026 17:50:56 +0000 + Scalable Prompt Routing via Fine-Grained Latent Task Discovery + https://arxiv.org/abs/2603.19415 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19415.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yunyi Zhang, Soji Adeshina, Patrick Guan, Ashwin Ganesh, Zhen Han, Vassilis N. Ioannidis, Huzefa Rangwala, George Karypis</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Prompt routing dynamically selects the most appropriate large language model from a pool of candidates for each query, optimizing performance while managing costs. As model pools scale to include dozens of frontier models with narrow performance gaps, existing approaches face significant challenges: manually defined task taxonomies cannot capture fine-grained capability distinctions, while monolithic routers struggle to differentiate subtle differences across diverse tasks. We propose a two-stage routing architecture that addresses these limitations through automated fine-grained task discovery and task-aware quality estimation. Our first stage employs graph-based clustering to discover latent task types and trains a classifier to assign prompts to discovered tasks. The second stage uses a mixture-of-experts architecture with task-specific prediction heads for specialized quality estimates. At inference, we aggregate predictions from both stages to balance task-level stability with prompt-specific adaptability. Evaluated on 10 benchmarks with 11 frontier models, our method consistently outperforms existing baselines and surpasses the strongest individual model while incurring less than half its cost.</p> + https://arxiv.org/abs/2603.19415 + Thu, 19 Mar 2026 19:15:51 +0000 - HiMu: Hierarchical Multimodal Frame Selection for Long Video Question Answering - https://arxiv.org/abs/2603.18558 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.18558.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dan Ben-Ami, Gabriele Serussi, Kobi Cohen, Chaim Baskin</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Long-form video question answering requires reasoning over extended temporal contexts, making frame selection critical for large vision-language models (LVLMs) bound by finite context windows. Existing methods face a sharp trade-off: similarity-based selectors are fast but collapse compositional queries into a single dense vector, losing sub-event ordering and cross-modal bindings; agent-based methods recover this structure through iterative LVLM inference, but at prohibitive cost. We introduce HiMu, a training-free framework that bridges this gap. A single text-only LLM call decomposes the query into a hierarchical logic tree whose leaves are atomic predicates, each routed to a lightweight expert spanning vision (CLIP, open-vocabulary detection, OCR) and audio (ASR, CLAP). The resulting signals are normalized, temporally smoothed to align different modalities, and composed bottom-up through fuzzy-logic operators that enforce temporal sequencing and adjacency, producing a continuous satisfaction curve. Evaluations on Video-MME, LongVideoBench and HERBench-Lite show that HiMu advances the efficiency-accuracy Pareto front: at 16 frames with Qwen3-VL 8B it outperforms all competing selectors, and with GPT-4o it surpasses agentic systems operating at 32-512 frames while requiring roughly 10x fewer FLOPs.</p> - https://arxiv.org/abs/2603.18558 - Thu, 19 Mar 2026 07:11:53 +0000 + In-the-Wild Camouflage Attack on Vehicle Detectors through Controllable Image Editing + https://arxiv.org/abs/2603.19456 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19456.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiao Fang, Yiming Gong, Stanislav Panev, Celso de Melo, Shuowen Hu, Shayok Chakraborty, Fernando De la Torre</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Deep neural networks (DNNs) have achieved remarkable success in computer vision but remain highly vulnerable to adversarial attacks. Among them, camouflage attacks manipulate an object's visible appearance to deceive detectors while remaining stealthy to humans. In this paper, we propose a new framework that formulates vehicle camouflage attacks as a conditional image-editing problem. Specifically, we explore both image-level and scene-level camouflage generation strategies, and fine-tune a ControlNet to synthesize camouflaged vehicles directly on real images. We design a unified objective that jointly enforces vehicle structural fidelity, style consistency, and adversarial effectiveness. Extensive experiments on the COCO and LINZ datasets show that our method achieves significantly stronger attack effectiveness, leading to more than 38% AP50 decrease, while better preserving vehicle structure and improving human-perceived stealthiness compared to existing approaches. Furthermore, our framework generalizes effectively to unseen black-box detectors and exhibits promising transferability to the physical world. Project page is available at https://humansensinglab.github.io/CtrlCamo</p> + https://arxiv.org/abs/2603.19456 + Thu, 19 Mar 2026 20:30:03 +0000 - Multiscale Switch for Semi-Supervised and Contrastive Learning in Medical Ultrasound Image Segmentation - https://arxiv.org/abs/2603.18655 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.18655.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jingguo Qu, Xinyang Han, Yao Pu, Man-Lik Chui, Simon Takadiyi Gunda, Ziman Chen, Jing Qin, Ann Dorothy King, Winnie Chiu-Wing Chu, Jing Cai, Michael Tin-Cheung Ying</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Medical ultrasound image segmentation faces significant challenges due to limited labeled data and characteristic imaging artifacts including speckle noise and low-contrast boundaries. While semi-supervised learning (SSL) approaches have emerged to address data scarcity, existing methods suffer from suboptimal unlabeled data utilization and lack robust feature representation mechanisms. In this paper, we propose Switch, a novel SSL framework with two key innovations: (1) Multiscale Switch (MSS) strategy that employs hierarchical patch mixing to achieve uniform spatial coverage; (2) Frequency Domain Switch (FDS) with contrastive learning that performs amplitude switching in Fourier space for robust feature representations. Our framework integrates these components within a teacher-student architecture to effectively leverage both labeled and unlabeled data. Comprehensive evaluation across six diverse ultrasound datasets (lymph nodes, breast lesions, thyroid nodules, and prostate) demonstrates consistent superiority over state-of-the-art methods. At 5\% labeling ratio, Switch achieves remarkable improvements: 80.04\% Dice on LN-INT, 85.52\% Dice on DDTI, and 83.48\% Dice on Prostate datasets, with our semi-supervised approach even exceeding fully supervised baselines. The method maintains parameter efficiency (1.8M parameters) while delivering superior performance, validating its effectiveness for resource-constrained medical imaging applications. The source code is publicly available at https://github.com/jinggqu/Switch</p> - https://arxiv.org/abs/2603.18655 - Thu, 19 Mar 2026 09:20:37 +0000 + Semantic Audio-Visual Navigation in Continuous Environments + https://arxiv.org/abs/2603.19660 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19660.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yichen Zeng, Hebaixu Wang, Meng Liu, Yu Zhou, Chen Gao, Kehan Chen, Gongping Huang</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Audio-visual navigation enables embodied agents to navigate toward sound-emitting targets by leveraging both auditory and visual cues. However, most existing approaches rely on precomputed room impulse responses (RIRs) for binaural audio rendering, restricting agents to discrete grid positions and leading to spatially discontinuous observations. To establish a more realistic setting, we introduce Semantic Audio-Visual Navigation in Continuous Environments (SAVN-CE), where agents can move freely in 3D spaces and perceive temporally and spatially coherent audio-visual streams. In this setting, targets may intermittently become silent or stop emitting sound entirely, causing agents to lose goal information. To tackle this challenge, we propose MAGNet, a multimodal transformer-based model that jointly encodes spatial and semantic goal representations and integrates historical context with self-motion cues to enable memory-augmented goal reasoning. Comprehensive experiments demonstrate that MAGNet significantly outperforms state-of-the-art methods, achieving up to a 12.1\% absolute improvement in success rate. These results also highlight its robustness to short-duration sounds and long-distance navigation scenarios. The code is available at https://github.com/yichenzeng24/SAVN-CE.</p> + https://arxiv.org/abs/2603.19660 + Fri, 20 Mar 2026 05:49:50 +0000 - Automatic detection of Gen-AI texts: A comparative framework of neural models - https://arxiv.org/abs/2603.18750 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.18750.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Cristian Buttaro, Irene Amerini</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> The rapid proliferation of Large Language Models has significantly increased the difficulty of distinguishing between human-written and AI generated texts, raising critical issues across academic, editorial, and social domains. This paper investigates the problem of AI generated text detection through the design, implementation, and comparative evaluation of multiple machine learning based detectors. Four neural architectures are developed and analyzed: a Multilayer Perceptron, a one-dimensional Convolutional Neural Network, a MobileNet-based CNN, and a Transformer model. The proposed models are benchmarked against widely used online detectors, including ZeroGPT, GPTZero, QuillBot, Originality.AI, Sapling, IsGen, Rephrase, and Writer. Experiments are conducted on the COLING Multilingual Dataset, considering both English and Italian configurations, as well as on an original thematic dataset focused on Art and Mental Health. Results show that supervised detectors achieve more stable and robust performance than commercial tools across different languages and domains, highlighting key strengths and limitations of current detection strategies.</p> - https://arxiv.org/abs/2603.18750 - Thu, 19 Mar 2026 10:55:07 +0000 + Understanding Behavior Cloning with Action Quantization + https://arxiv.org/abs/2603.20538 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.20538.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haoqun Cao, Tengyang Xie</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Behavior cloning is a fundamental paradigm in machine learning, enabling policy learning from expert demonstrations across robotics, autonomous driving, and generative models. Autoregressive models like transformer have proven remarkably effective, from large language models (LLMs) to vision-language-action systems (VLAs). However, applying autoregressive models to continuous control requires discretizing actions through quantization, a practice widely adopted yet poorly understood theoretically. This paper provides theoretical foundations for this practice. We analyze how quantization error propagates along the horizon and interacts with statistical sample complexity. We show that behavior cloning with quantized actions and log-loss achieves optimal sample complexity, matching existing lower bounds, and incurs only polynomial horizon dependence on quantization error, provided the dynamics are stable and the policy satisfies a probabilistic smoothness condition. We further characterize when different quantization schemes satisfy or violate these requirements, and propose a model-based augmentation that provably improves the error bound without requiring policy smoothness. Finally, we establish fundamental limits that jointly capture the effects of quantization error and statistical complexity.</p> + https://arxiv.org/abs/2603.20538 + Fri, 20 Mar 2026 22:22:43 +0000 - AgentDS Technical Report: Benchmarking the Future of Human-AI Collaboration in Domain-Specific Data Science - https://arxiv.org/abs/2603.19005 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19005.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> An Luo, Jin Du, Xun Xian, Robert Specht, Fangqiao Tian, Ganghua Wang, Xuan Bi, Charles Fleming, Ashish Kundu, Jayanth Srinivasa, Mingyi Hong, Rui Zhang, Tianxi Li, Galin Jones, Jie Ding</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Data science plays a critical role in transforming complex data into actionable insights across numerous domains. Recent developments in large language models (LLMs) and artificial intelligence (AI) agents have significantly automated data science workflow. However, it remains unclear to what extent AI agents can match the performance of human experts on domain-specific data science tasks, and in which aspects human expertise continues to provide advantages. We introduce AgentDS, a benchmark and competition designed to evaluate both AI agents and human-AI collaboration performance in domain-specific data science. AgentDS consists of 17 challenges across six industries: commerce, food production, healthcare, insurance, manufacturing, and retail banking. We conducted an open competition involving 29 teams and 80 participants, enabling systematic comparison between human-AI collaborative approaches and AI-only baselines. Our results show that current AI agents struggle with domain-specific reasoning. AI-only baselines perform near or below the median of competition participants, while the strongest solutions arise from human-AI collaboration. These findings challenge the narrative of complete automation by AI and underscore the enduring importance of human expertise in data science, while illuminating directions for the next generation of AI. Visit the AgentDS website here: https://agentds.org/ and open source datasets here: https://huggingface.co/datasets/lainmn/AgentDS .</p> - https://arxiv.org/abs/2603.19005 - Thu, 19 Mar 2026 15:11:13 +0000 + Agentic AI and the next intelligence explosion + https://arxiv.org/abs/2603.20639 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.20639.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> James Evans, Benjamin Bratton, Blaise Agüera y Arcas</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> The "AI singularity" is often miscast as a monolithic, godlike mind. Evolution suggests a different path: intelligence is fundamentally plural, social, and relational. Recent advances in agentic AI reveal that frontier reasoning models, such as DeepSeek-R1, do not improve simply by "thinking longer". Instead, they simulate internal "societies of thought," spontaneous cognitive debates that argue, verify, and reconcile to solve complex tasks. Moreover, we are entering an era of human-AI centaurs: hybrid actors where collective agency transcends individual control. Scaling this intelligence requires shifting from dyadic alignment (RLHF) toward institutional alignment. By designing digital protocols, modeled on organizations and markets, we can build a social infrastructure of checks and balances. The next intelligence explosion will not be a single silicon brain, but a complex, combinatorial society specializing and sprawling like a city. No mind is an island.</p> + https://arxiv.org/abs/2603.20639 + Sat, 21 Mar 2026 04:23:11 +0000 - TerraScope: Pixel-Grounded Visual Reasoning for Earth Observation - https://arxiv.org/abs/2603.19039 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19039.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yan Shu, Bin Ren, Zhitong Xiong, Xiao Xiang Zhu, Begüm Demir, Nicu Sebe, Paolo Rota</p><p><b>Upvotes:</b> 42</p><p><b>Summary:</b> Vision-language models (VLMs) have shown promise in earth observation (EO), yet they struggle with tasks that require grounding complex spatial reasoning in precise pixel-level visual representations. To address this problem, we introduce TerraScope, a unified VLM that delivers pixel-grounded geospatial reasoning with two key capabilities: (1) modality-flexible reasoning: it handles single-modality inputs (optical or SAR) and adaptively fuses different modalities into the reasoning process when both are available; (2) multi-temporal reasoning: it integrates temporal sequences for change analysis across multiple time points. In addition, we curate Terra-CoT, a large-scale dataset containing 1 million samples with pixel-level masks embedded in reasoning chains across multiple sources. We also propose TerraScope-Bench, the first benchmark for pixel-grounded geospatial reasoning with six sub-tasks that evaluates both answer accuracy and mask quality to ensure authentic pixel-grounded reasoning. Experiments show that TerraScope significantly outperforms existing VLMs on pixel-grounded geospatial reasoning while providing interpretable visual evidence.</p> - https://arxiv.org/abs/2603.19039 - Thu, 19 Mar 2026 15:38:02 +0000 + REVERE: Reflective Evolving Research Engineer for Scientific Workflows + https://arxiv.org/abs/2603.20667 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.20667.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Balaji Dinesh Gangireddi, Aniketh Garikaparthi, Manasi Patwardhan, Arman Cohan</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Existing prompt-optimization techniques rely on local signals to update behavior, often neglecting broader and recurring patterns across tasks, leading to poor generalization; they further rely on full-prompt rewrites or unstructured merges, resulting in knowledge loss. These limitations are magnified in research-coding workflows, which involve heterogeneous repositories, underspecified environments, and weak feedback, where reproducing results from public codebases is an established evaluation regime. We introduce Reflective Evolving Research Engineer (REVERE), a framework that continuously learns from Global Training Context, recognizes recurring failure modes in cross-repository execution trajectories, distills them into reusable heuristics, and performs targeted edits across three configurable fields: the system prompt, a task-prompt template, and a cumulative cheatsheet. REVERE, via this reflective optimization framework, improves performance over prior state-of-the-art expert-crafted instructions on research coding tasks by 4.50% on SUPER, 3.51% on ResearchCodeBench, and 4.89% on ScienceAgentBench across their respective metrics. These results demonstrate that agents equipped with mechanisms for continual learning and global memory consolidation can meaningfully evolve their capabilities over time.</p> + https://arxiv.org/abs/2603.20667 + Sat, 21 Mar 2026 05:58:30 +0000 - DROID-SLAM in the Wild - https://arxiv.org/abs/2603.19076 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19076.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Moyang Li, Zihan Zhu, Marc Pollefeys, Daniel Barath</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> We present a robust, real-time RGB SLAM system that handles dynamic environments by leveraging differentiable Uncertainty-aware Bundle Adjustment. Traditional SLAM methods typically assume static scenes, leading to tracking failures in the presence of motion. Recent dynamic SLAM approaches attempt to address this challenge using predefined dynamic priors or uncertainty-aware mapping, but they remain limited when confronted with unknown dynamic objects or highly cluttered scenes where geometric mapping becomes unreliable. In contrast, our method estimates per-pixel uncertainty by exploiting multi-view visual feature inconsistency, enabling robust tracking and reconstruction even in real-world environments. The proposed system achieves state-of-the-art camera poses and scene geometry in cluttered dynamic scenarios while running in real time at around 10 FPS. Code and datasets are available at https://github.com/MoyangLi00/DROID-W.git.</p> - https://arxiv.org/abs/2603.19076 - Thu, 19 Mar 2026 16:02:12 +0000 + SNAP: Speaker Nulling for Artifact Projection in Speech Deepfake Detection + https://arxiv.org/abs/2603.20686 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.20686.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kyudan Jung, Jihwan Kim, Minwoo Lee, Soyoon Kim, Jeonghoon Kim, Jaegul Choo, Cheonbok Park</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Recent advancements in text-to-speech technologies enable generating high-fidelity synthetic speech nearly indistinguishable from real human voices. While recent studies show the efficacy of self-supervised learning-based speech encoders for deepfake detection, these models struggle to generalize across unseen speakers. Our quantitative analysis suggests these encoder representations are substantially influenced by speaker information, causing detectors to exploit speaker-specific correlations rather than artifact-related cues. We call this phenomenon speaker entanglement. To mitigate this reliance, we introduce SNAP, a speaker-nulling framework. We estimate a speaker subspace and apply orthogonal projection to suppress speaker-dependent components, isolating synthesis artifacts within the residual features. By reducing speaker entanglement, SNAP encourages detectors to focus on artifact-related patterns, leading to state-of-the-art performance.</p> + https://arxiv.org/abs/2603.20686 + Sat, 21 Mar 2026 07:05:30 +0000 - Do VLMs Need Vision Transformers? Evaluating State Space Models as Vision Encoders - https://arxiv.org/abs/2603.19209 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19209.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shang-Jui Ray Kuo, Paola Cascante-Bonilla</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Large vision--language models (VLMs) often use a frozen vision backbone, whose image features are mapped into a large language model through a lightweight connector. While transformer-based encoders are the standard visual backbone, we ask whether state space model (SSM) vision backbones can be a strong alternative. We systematically evaluate SSM vision backbones for VLMs in a controlled setting. Under matched ImageNet-1K initialization, the SSM backbone achieves the strongest overall performance across both VQA and grounding/localization. We further adapt both SSM and ViT-family backbones with detection or segmentation training and find that dense-task tuning generally improves performance across families; after this adaptation, the SSM backbone remains competitive while operating at a substantially smaller model scale. We further observe that (i) higher ImageNet accuracy or larger backbones do not reliably translate into better VLM performance, and (ii) some visual backbones are unstable in localization. Based on these findings, we propose stabilization strategies that improve robustness for both backbone families and highlight SSM backbones as a strong alternative to transformer-based vision encoders in VLMs.</p> - https://arxiv.org/abs/2603.19209 - Thu, 19 Mar 2026 17:56:32 +0000 + LongCat-Flash-Prover: Advancing Native Formal Reasoning via Agentic Tool-Integrated Reinforcement Learning + https://arxiv.org/abs/2603.21065 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.21065.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jianing Wang, Jianfei Zhang, Qi Guo, Linsen Guo, Rumei Li, Chao Zhang, Chong Peng, Cunguang Wang, Dengchang Zhao, Jiarong Shi, Jingang Wang, Liulin Feng, Mengxia Shen, Qi Li, Shengnan An, Shun Wang, Wei Shi, Xiangyu Xi, Xiaoyu Li, Xuezhi Cao, Yi Lu, Yunke Zhao, Zhengyu Chen, Zhimin Lin, Wei Wang, Peng Pei, Xunliang Cai</p><p><b>Upvotes:</b> 62</p><p><b>Summary:</b> We introduce LongCat-Flash-Prover, a flagship 560-billion-parameter open-source Mixture-of- Experts (MoE) model that advances Native Formal Reasoning in Lean4 through agentic tool-integrated reasoning (TIR). We decompose the native formal reasoning task into three independent formal capabilities, i.e., auto-formalization, sketching, and proving. To facilitate these capabilities, we propose a Hybrid-Experts Iteration Framework to expand high-quality task trajectories, including generating a formal statement based on a given informal problem, producing a whole-proof directly from the statement, or a lemma-style sketch. During agentic RL, we present a Hierarchical Importance Sampling Policy Optimization (HisPO) algorithm, which aims to stabilize the MoE model training on such long-horizon tasks. It employs a gradient masking strategy that accounts for the policy staleness and the inherent train-inference engine discrepancies at both sequence and token levels. Additionally, we also incorporate theorem consistency and legality detection mechanisms to eliminate reward hacking issues. Extensive evaluations show that our LongCat-Flash-Prover sets a new state-of-the-art for open-weights models in both auto-formalization and theorem proving. Demonstrating remarkable sample efficiency, it achieves a 97.1% pass rate on MiniF2F-Test using only 72 inference budget per problem. On more challenging benchmarks, it solves 70.8% of ProverBench and 41.5% of PutnamBench with no more than 220 attempts per problem, significantly outperforming existing open-weights baselines.</p> + https://arxiv.org/abs/2603.21065 + Sun, 22 Mar 2026 05:16:09 +0000 - Cooperation and Exploitation in LLM Policy Synthesis for Sequential Social Dilemmas - https://arxiv.org/abs/2603.19453 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19453.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Víctor Gallego</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> We study LLM policy synthesis: using a large language model to iteratively generate programmatic agent policies for multi-agent environments. Rather than training neural policies via reinforcement learning, our framework prompts an LLM to produce Python policy functions, evaluates them in self-play, and refines them using performance feedback across iterations. We investigate feedback engineering (the design of what evaluation information is shown to the LLM during refinement) comparing sparse feedback (scalar reward only) against dense feedback (reward plus social metrics: efficiency, equality, sustainability, peace). Across two canonical Sequential Social Dilemmas (Gathering and Cleanup) and two frontier LLMs (Claude Sonnet 4.6, Gemini 3.1 Pro), dense feedback consistently matches or exceeds sparse feedback on all metrics. The advantage is largest in the Cleanup public goods game, where providing social metrics helps the LLM calibrate the costly cleaning-harvesting tradeoff. Rather than triggering over-optimization of fairness, social metrics serve as a coordination signal that guides the LLM toward more effective cooperative strategies, including territory partitioning, adaptive role assignment, and the avoidance of wasteful aggression. We further perform an adversarial experiment to determine whether LLMs can reward hack these environments. We characterize five attack classes and discuss mitigations, highlighting an inherent tension in LLM policy synthesis between expressiveness and safety. Code at https://github.com/vicgalle/llm-policies-social-dilemmas.</p> - https://arxiv.org/abs/2603.19453 - Thu, 19 Mar 2026 20:27:48 +0000 + F4Splat: Feed-Forward Predictive Densification for Feed-Forward 3D Gaussian Splatting + https://arxiv.org/abs/2603.21304 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.21304.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Injae Kim, Chaehyeon Kim, Minseong Bae, Minseok Joo, Hyunwoo J. Kim</p><p><b>Upvotes:</b> 30</p><p><b>Summary:</b> Feed-forward 3D Gaussian Splatting methods enable single-pass reconstruction and real-time rendering. However, they typically adopt rigid pixel-to-Gaussian or voxel-to-Gaussian pipelines that uniformly allocate Gaussians, leading to redundant Gaussians across views. Moreover, they lack an effective mechanism to control the total number of Gaussians while maintaining reconstruction fidelity. To address these limitations, we present F4Splat, which performs Feed-Forward predictive densification for Feed-Forward 3D Gaussian Splatting, introducing a densification-score-guided allocation strategy that adaptively distributes Gaussians according to spatial complexity and multi-view overlap. Our model predicts per-region densification scores to estimate the required Gaussian density and allows explicit control over the final Gaussian budget without retraining. This spatially adaptive allocation reduces redundancy in simple regions and minimizes duplicate Gaussians across overlapping views, producing compact yet high-quality 3D representations. Extensive experiments demonstrate that our model achieves superior novel-view synthesis performance compared to prior uncalibrated feed-forward methods, while using significantly fewer Gaussians.</p> + https://arxiv.org/abs/2603.21304 + Sun, 22 Mar 2026 16:03:56 +0000 - Hyperagents - https://arxiv.org/abs/2603.19461 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19461.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jenny Zhang, Bingchen Zhao, Wannan Yang, Jakob Foerster, Jeff Clune, Minqi Jiang, Sam Devlin, Tatiana Shavrina</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> Self-improving AI systems aim to reduce reliance on human engineering by learning to improve their own learning and problem-solving processes. Existing approaches to self-improvement rely on fixed, handcrafted meta-level mechanisms, fundamentally limiting how fast such systems can improve. The Darwin Gödel Machine (DGM) demonstrates open-ended self-improvement in coding by repeatedly generating and evaluating self-modified variants. Because both evaluation and self-modification are coding tasks, gains in coding ability can translate into gains in self-improvement ability. However, this alignment does not generally hold beyond coding domains. We introduce hyperagents, self-referential agents that integrate a task agent (which solves the target task) and a meta agent (which modifies itself and the task agent) into a single editable program. Crucially, the meta-level modification procedure is itself editable, enabling metacognitive self-modification, improving not only the task-solving behavior, but also the mechanism that generates future improvements. We instantiate this framework by extending DGM to create DGM-Hyperagents (DGM-H), eliminating the assumption of domain-specific alignment between task performance and self-modification skill to potentially support self-accelerating progress on any computable task. Across diverse domains, the DGM-H improves performance over time and outperforms baselines without self-improvement or open-ended exploration, as well as prior self-improving systems. Furthermore, the DGM-H improves the process by which it generates new agents (e.g., persistent memory, performance tracking), and these meta-level improvements transfer across domains and accumulate across runs. DGM-Hyperagents offer a glimpse of open-ended AI systems that do not merely search for better solutions, but continually improve their search for how to improve.</p> - https://arxiv.org/abs/2603.19461 - Thu, 19 Mar 2026 20:50:08 +0000 + FluidWorld: Reaction-Diffusion Dynamics as a Predictive Substrate for World Models + https://arxiv.org/abs/2603.21315 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.21315.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Fabien Polly</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> World models learn to predict future states of an environment, enabling planning and mental simulation. Current approaches default to Transformer-based predictors operating in learned latent spaces. This comes at a cost: O(N^2) computation and no explicit spatial inductive bias. This paper asks a foundational question: is self-attention necessary for predictive world modeling, or can alternative computational substrates achieve comparable or superior results? I introduce FluidWorld, a proof-of-concept world model whose predictive dynamics are governed by partial differential equations (PDEs) of reaction-diffusion type. Instead of using a separate neural network predictor, the PDE integration itself produces the future state prediction. In a strictly parameter-matched three-way ablation on unconditional UCF-101 video prediction (64x64, ~800K parameters, identical encoder, decoder, losses, and data), FluidWorld is compared against both a Transformer baseline (self-attention) and a ConvLSTM baseline (convolutional recurrence). While all three models converge to comparable single-step prediction loss, FluidWorld achieves 2x lower reconstruction error, produces representations with 10-15% higher spatial structure preservation and 18-25% more effective dimensionality, and critically maintains coherent multi-step rollouts where both baselines degrade rapidly. All experiments were conducted on a single consumer-grade PC (Intel Core i5, NVIDIA RTX 4070 Ti), without any large-scale compute. These results establish that PDE-based dynamics, which natively provide O(N) spatial complexity, adaptive computation, and global spatial coherence through diffusion, are a viable and parameter-efficient alternative to both attention and convolutional recurrence for world modeling.</p> + https://arxiv.org/abs/2603.21315 + Sun, 22 Mar 2026 16:49:43 +0000 - ProactiveBench: Benchmarking Proactiveness in Multimodal Large Language Models - https://arxiv.org/abs/2603.19466 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19466.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Thomas De Min, Subhankar Roy, Stéphane Lathuilière, Elisa Ricci, Massimiliano Mancini</p><p><b>Upvotes:</b> 26</p><p><b>Summary:</b> Effective collaboration begins with knowing when to ask for help. For example, when trying to identify an occluded object, a human would ask someone to remove the obstruction. Can MLLMs exhibit a similar "proactive" behavior by requesting simple user interventions? To investigate this, we introduce ProactiveBench, a benchmark built from seven repurposed datasets that tests proactiveness across different tasks such as recognizing occluded objects, enhancing image quality, and interpreting coarse sketches. We evaluate 22 MLLMs on ProactiveBench, showing that (i) they generally lack proactiveness; (ii) proactiveness does not correlate with model capacity; (iii) "hinting" at proactiveness yields only marginal gains. Surprisingly, we found that conversation histories and in-context learning introduce negative biases, hindering performance. Finally, we explore a simple fine-tuning strategy based on reinforcement learning: its results suggest that proactiveness can be learned, even generalizing to unseen scenarios. We publicly release ProactiveBench as a first step toward building proactive multimodal models.</p> - https://arxiv.org/abs/2603.19466 - Thu, 19 Mar 2026 20:58:03 +0000 + RoboAlign: Learning Test-Time Reasoning for Language-Action Alignment in Vision-Language-Action Models + https://arxiv.org/abs/2603.21341 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.21341.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dongyoung Kim, Sumin Park, Woomin Song, Seungku Kim, Taeyoung Kim, Huiwon Jang, Jinwoo Shin, Jaehyung Kim, Younggyo Seo</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> Improving embodied reasoning in multimodal-large-language models (MLLMs) is essential for building vision-language-action models (VLAs) on top of them to readily translate multimodal understanding into low-level actions. Accordingly, recent work has explored enhancing embodied reasoning in MLLMs through supervision of vision-question-answering type. However, these approaches have been reported to result in unstable VLA performance, often yielding only marginal or even negative gains. In this paper, we propose a more systematic MLLM training framework RoboAlign that reliably improves VLA performance. Our key idea is to sample action tokens via zero-shot natural language reasoning and refines this reasoning using reinforcement learning (RL) to improve action accuracy. As a result, RoboAlign bridges the modality gap between language and low-level actions in MLLMs, and facilitate knowledge transfer from MLLM to VLA. To validate the effectiveness of RoboAlign, we train VLAs by adding a diffusion-based action head on top of an MLLM backbone and evaluate them on major robotics benchmarks. Remarkably, by performing RL-based alignment after SFT using less than 1\% of the data, RoboAlign achieves performance improvements of 17.5\%, 18.9\%, and 106.6\% over SFT baselines on LIBERO, CALVIN, and real-world environments, respectively.</p> + https://arxiv.org/abs/2603.21341 + Sun, 22 Mar 2026 17:57:55 +0000 - Adaptive Layerwise Perturbation: Unifying Off-Policy Corrections for LLM RL - https://arxiv.org/abs/2603.19470 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19470.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chenlu Ye, Xuanchang Zhang, Yifan Hao, Zhou Yu, Ziji Zhang, Abhinav Gullapalli, Hao Chen, Jing Huang, Tong Zhang</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Off-policy problems such as policy staleness and training-inference mismatch, has become a major bottleneck for training stability and further exploration for LLM RL. To enhance inference efficiency, the distribution gap between the inference and updated policy grows, leading to heavy-tailed importance ratios. Heavy-tailed ratios arise when the policy is locally sharp, which further inflates sharp gradients and can push updates outside the trust region. To address this, we propose Adaptive Layerwise Perturbation(ALP) by injecting small learnable perturbations into input hidden states of each layer during updates, which is used as the numerator of the importance ratio against the unchanged inference policy in the objective. Intuitively, by adding controlled noise to intermediate representations, ALP prevents the updated policy from deviating too sharply from the inference policy, and enlarges the policy family to cover the inference policy family with mismatch noises. Hence, the flattened distribution can naturally tighten the updated and inference policy gap and reduce the tail of importance ratios, thus maintaining training stability. This is further validated empirically. Experiments on single-turn math and multi-turn tool-integrated reasoning tasks show that ALP not only improves final performance, but also avoid blow up of importance ratio tail and KL spikes during iterative training, along with boosted exploration. Ablations show that representation-level perturbations across all layers are most effective, substantially outperforming partial-layer and logits-only variants.</p> - https://arxiv.org/abs/2603.19470 - Thu, 19 Mar 2026 21:04:17 +0000 + Generalized Discrete Diffusion from Snapshots + https://arxiv.org/abs/2603.21342 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.21342.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Oussama Zekri, Théo Uscidda, Nicolas Boullé, Anna Korba</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> We introduce Generalized Discrete Diffusion from Snapshots (GDDS), a unified framework for discrete diffusion modeling that supports arbitrary noising processes over large discrete state spaces. Our formulation encompasses all existing discrete diffusion approaches, while allowing significantly greater flexibility in the choice of corruption dynamics. The forward noising process relies on uniformization and enables fast arbitrary corruption. For the reverse process, we derive a simple evidence lower bound (ELBO) based on snapshot latents, instead of the entire noising path, that allows efficient training of standard generative modeling architectures with clear probabilistic interpretation. Our experiments on large-vocabulary discrete generation tasks suggest that the proposed framework outperforms existing discrete diffusion methods in terms of training efficiency and generation quality, and beats autoregressive models for the first time at this scale. We provide the code along with a blog post on the project page : https://oussamazekri.fr/gdds{https://oussamazekri.fr/gdds}.</p> + https://arxiv.org/abs/2603.21342 + Sun, 22 Mar 2026 17:58:01 +0000 - Teaching an Agent to Sketch One Part at a Time - https://arxiv.org/abs/2603.19500 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19500.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiaodan Du, Ruize Xu, David Yunis, Yael Vinker, Greg Shakhnarovich</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> We develop a method for producing vector sketches one part at a time. To do this, we train a multi-modal language model-based agent using a novel multi-turn process-reward reinforcement learning following supervised fine-tuning. Our approach is enabled by a new dataset we call ControlSketch-Part, containing rich part-level annotations for sketches, obtained using a novel, generic automatic annotation pipeline that segments vector sketches into semantic parts and assigns paths to parts with a structured multi-stage labeling process. Our results indicate that incorporating structured part-level data and providing agent with the visual feedback through the process enables interpretable, controllable, and locally editable text-to-vector sketch generation.</p> - https://arxiv.org/abs/2603.19500 - Thu, 19 Mar 2026 22:08:53 +0000 + PivotRL: High Accuracy Agentic Post-Training at Low Compute Cost + https://arxiv.org/abs/2603.21383 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.21383.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junkeun Yi, Damon Mosk-Aoyama, Baihe Huang, Ritu Gala, Charles Wang, Sugam Dipak Devare, Khushi Bhardwaj, Abhibha Gupta, Oleksii Kuchaiev, Jiantao Jiao, Jian Zhang, Venkat Srinivasan</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Post-training for long-horizon agentic tasks has a tension between compute efficiency and generalization. While supervised fine-tuning (SFT) is compute efficient, it often suffers from out-of-domain (OOD) degradation. Conversely, end-to-end reinforcement learning (E2E RL) preserves OOD capabilities, but incurs high compute costs due to many turns of on-policy rollout. We introduce PivotRL, a novel framework that operates on existing SFT trajectories to combine the compute efficiency of SFT with the OOD accuracy of E2E RL. PivotRL relies on two key mechanisms: first, it executes local, on-policy rollouts and filters for pivots: informative intermediate turns where sampled actions exhibit high variance in outcomes; second, it utilizes rewards for functional-equivalent actions rather than demanding strict string matching with the SFT data demonstration. We theoretically show that these mechanisms incentivize strong learning signals with high natural gradient norm, while maximally preserving policy probability ordering on actions unrelated to training tasks. In comparison to standard SFT on identical data, we demonstrate that PivotRL achieves +4.17% higher in-domain accuracy on average across four agentic domains, and +10.04% higher OOD accuracy in non-agentic tasks. Notably, on agentic coding tasks, PivotRL achieves competitive accuracy with E2E RL with 4x fewer rollout turns. PivotRL is adopted by NVIDIA's Nemotron-3-Super-120B-A12B, acting as the workhorse in production-scale agentic post-training.</p> + https://arxiv.org/abs/2603.21383 + Sun, 22 Mar 2026 19:59:48 +0000 - CurveStream: Boosting Streaming Video Understanding in MLLMs via Curvature-Aware Hierarchical Visual Memory Management - https://arxiv.org/abs/2603.19571 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19571.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chao Wang, Xudong Tan, Jianjian Cao, Kangcong Li, Tao Chen</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Multimodal Large Language Models have achieved significant success in offline video understanding, yet their application to streaming videos is severely limited by the linear explosion of visual tokens, which often leads to Out-of-Memory (OOM) errors or catastrophic forgetting. Existing visual retention and memory management methods typically rely on uniform sampling, low-level physical metrics, or passive cache eviction. However, these strategies often lack intrinsic semantic awareness, potentially disrupting contextual coherence and blurring transient yet critical semantic transitions. To address these limitations, we propose CurveStream, a training-free, curvature-aware hierarchical visual memory management framework. Our approach is motivated by the key observation that high-curvature regions along continuous feature trajectories closely align with critical global semantic transitions. Based on this geometric insight, CurveStream evaluates real-time semantic intensity via a Curvature Score and integrates an online K-Sigma dynamic threshold to adaptively route frames into clear and fuzzy memory states under a strict token budget. Evaluations across diverse temporal scales confirm that this lightweight framework, CurveStream, consistently yields absolute performance gains of over 10% (e.g., 10.69% on StreamingBench and 13.58% on OVOBench) over respective baselines, establishing new state-of-the-art results for streaming video perception.The code will be released at https://github.com/streamingvideos/CurveStream.</p> - https://arxiv.org/abs/2603.19571 - Fri, 20 Mar 2026 02:28:57 +0000 + Effective Strategies for Asynchronous Software Engineering Agents + https://arxiv.org/abs/2603.21489 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.21489.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiayi Geng, Graham Neubig</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> AI agents have become increasingly capable at isolated software engineering (SWE) tasks such as resolving issues on Github. Yet long-horizon tasks involving multiple interdependent subtasks still pose challenges both with respect to accuracy, and with respect to timely completion. A natural approach to solving these long-horizon tasks in a timely manner is asynchronous multi-agent collaboration, where multiple agents work on different parts of the task at the same time. But effective application of multi-agent systems has proven surprisingly difficult: concurrent edits by multiple agents interfere with each other, dependencies are difficult to synchronize, and combining partial progress into a coherent whole is challenging. On the other hand, human developers have long relied on mature collaboration infrastructure to manage these challenges in large software projects. Inspired by these collaboration primitives, we introduce Centralized Asynchronous Isolated Delegation (CAID), a structured multi-agent coordination paradigm grounded in three core SWE primitives: centralized task delegation, asynchronous execution, and isolated workspaces. CAID constructs dependency-aware task plans through a central manager, executes subtasks concurrently in isolated workspaces, and consolidates progress via structured integration with executable test-based verification. In empirical evaluation, we find that CAID improves accuracy over single-agent baselines by 26.7% absolute on paper reproduction tasks (PaperBench) and 14.3% on Python library development tasks (Commit0). Through systematic analysis, we find that branch-and-merge is a central coordination mechanism for multi-agent collaboration, and that SWE primitives such as git worktree, git commit, and git merge enable it to be realized in a reliable and executable manner.</p> + https://arxiv.org/abs/2603.21489 + Mon, 23 Mar 2026 02:26:35 +0000 - FlowScene: Style-Consistent Indoor Scene Generation with Multimodal Graph Rectified Flow - https://arxiv.org/abs/2603.19598 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19598.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhifei Yang, Guangyao Zhai, Keyang Lu, YuYang Yin, Chao Zhang, Zhen Xiao, Jieyi Long, Nassir Navab, Yikai Wang</p><p><b>Upvotes:</b> 24</p><p><b>Summary:</b> Scene generation has extensive industrial applications, demanding both high realism and precise control over geometry and appearance. Language-driven retrieval methods compose plausible scenes from a large object database, but overlook object-level control and often fail to enforce scene-level style coherence. Graph-based formulations offer higher controllability over objects and inform holistic consistency by explicitly modeling relations, yet existing methods struggle to produce high-fidelity textured results, thereby limiting their practical utility. We present FlowScene, a tri-branch scene generative model conditioned on multimodal graphs that collaboratively generates scene layouts, object shapes, and object textures. At its core lies a tight-coupled rectified flow model that exchanges object information during generation, enabling collaborative reasoning across the graph. This enables fine-grained control of objects' shapes, textures, and relations while enforcing scene-level style coherence across structure and appearance. Extensive experiments show that FlowScene outperforms both language-conditioned and graph-conditioned baselines in terms of generation realism, style consistency, and alignment with human preferences.</p> - https://arxiv.org/abs/2603.19598 - Fri, 20 Mar 2026 03:15:42 +0000 + mSFT: Addressing Dataset Mixtures Overfiting Heterogeneously in Multi-task SFT + https://arxiv.org/abs/2603.21606 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.21606.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Woosung Koh, Jeyoung Jeon, Youngjin Song, Yujin Cheon, Soowon Oh, Jaehyeong Choi, Se-Young Yun</p><p><b>Upvotes:</b> 26</p><p><b>Summary:</b> Current language model training commonly applies multi-task Supervised Fine-Tuning (SFT) using a homogeneous compute budget across all sub-datasets. This approach is fundamentally sub-optimal: heterogeneous learning dynamics cause faster-learning tasks to overfit early while slower ones remain under-fitted. To address this, we introduce mSFT, an iterative, overfitting-aware search algorithm for multi-task data mixtures. mSFT trains the model on an active mixture, identifies and excludes the earliest overfitting sub-dataset, and reverts to that specific optimal checkpoint before continuing. Extensive evaluations demonstrate that mSFT consistently outperforms 4 baselines across 10 benchmarks and 6 base models. Further analysis confirms mSFT maintains robust gains across diverse dataset sizes, task granularities, and is insensitive to its single new hyperparameter (compute budget). Notably, at low compute budget, mSFT can improve performance while lowering training FLOPs. Ultimately, mSFT establishes a practical overfitting-aware algorithm for multi-task SFT that maximizes the potential of models across diverse data mixtures.</p> + https://arxiv.org/abs/2603.21606 + Mon, 23 Mar 2026 06:01:51 +0000 - BEAVER: A Training-Free Hierarchical Prompt Compression Method via Structure-Aware Page Selection - https://arxiv.org/abs/2603.19635 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19635.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhengpei Hu, Kai Li, Dapeng Fu, Chang Zeng, Yue Li, Yuanhao Tang, Jianqiang Huang</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> The exponential expansion of context windows in LLMs has unlocked capabilities for long-document understanding but introduced severe bottlenecks in inference latency and information utilization. Existing compression methods often suffer from high training costs or semantic fragmentation due to aggressive token pruning. In this paper, we propose BEAVER, a novel training-free framework that shifts compression from linear token removal to structure-aware hierarchical selection. BEAVER maximizes hardware parallelism by mapping variable-length contexts into dense page-level tensors via dual-path pooling, and preserves discourse integrity through a hybrid planner combining semantic and lexical dual-branch selection with sentence smoothing. Extensive evaluations on four long-context benchmarks demonstrate that BEAVER achieves comparable performance to state-of-the-art (SOTA) methods like LongLLMLingua. Notably, on the RULER benchmark, BEAVER maintains high fidelity in multi-needle retrieval where baselines deteriorate. Regarding efficiency, BEAVER reduces latency by 26.4x on 128k contexts, offering a scalable solution for high-throughput applications. Our code is available at https://cslikai.cn/BEAVER/.</p> - https://arxiv.org/abs/2603.19635 - Fri, 20 Mar 2026 04:35:04 +0000 + The Universal Normal Embedding + https://arxiv.org/abs/2603.21786 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.21786.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chen Tasker, Roy Betser, Eyal Gofer, Meir Yossef Levi, Guy Gilboa</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Generative models and vision encoders have largely advanced on separate tracks, optimized for different goals and grounded in different mathematical principles. Yet, they share a fundamental property: latent space Gaussianity. Generative models map Gaussian noise to images, while encoders map images to semantic embeddings whose coordinates empirically behave as Gaussian. We hypothesize that both are views of a shared latent source, the Universal Normal Embedding (UNE): an approximately Gaussian latent space from which encoder embeddings and DDIM-inverted noise arise as noisy linear projections. To test our hypothesis, we introduce NoiseZoo, a dataset of per-image latents comprising DDIM-inverted diffusion noise and matching encoder representations (CLIP, DINO). On CelebA, linear probes in both spaces yield strong, aligned attribute predictions, indicating that generative noise encodes meaningful semantics along linear directions. These directions further enable faithful, controllable edits (e.g., smile, gender, age) without architectural changes, where simple orthogonalization mitigates spurious entanglements. Taken together, our results provide empirical support for the UNE hypothesis and reveal a shared Gaussian-like latent geometry that concretely links encoding and generation. Code and data are available https://rbetser.github.io/UNE/</p> + https://arxiv.org/abs/2603.21786 + Mon, 23 Mar 2026 10:28:14 +0000 - A Subgoal-driven Framework for Improving Long-Horizon LLM Agents - https://arxiv.org/abs/2603.19685 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19685.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Taiyi Wang, Sian Gooding, Florian Hartmann, Oriana Riva, Edward Grefenstette</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Large language model (LLM)-based agents have emerged as powerful autonomous controllers for digital environments, including mobile interfaces, operating systems, and web browsers. Web navigation, for example, requires handling dynamic content and long sequences of actions, making it particularly challenging. Existing LLM-based agents struggle with long-horizon planning in two main ways. During online execution, they often lose track as new information arrives, lacking a clear and adaptive path toward the final goal. This issue is further exacerbated during reinforcement learning (RL) fine-tuning, where sparse and delayed rewards make it difficult for agents to identify which actions lead to success, preventing them from maintaining coherent reasoning over extended tasks. To address these challenges, we propose two contributions. First, we introduce an agent framework that leverages proprietary models for online planning through subgoal decomposition. Second, we present MiRA (Milestoning your Reinforcement Learning Enhanced Agent), an RL training framework that uses dense, milestone-based reward signals. The real-time planning mechanism improves proprietary models such as Gemini by approximately a 10% absolute increase in success rate (SR) on the WebArena-Lite benchmark. Meanwhile, applying MiRA to the open Gemma3-12B model increases its success rate from 6.4% to 43.0%. This performance surpasses proprietary systems such as GPT-4-Turbo (17.6%) and GPT-4o (13.9%), as well as the previous open-model state of the art, WebRL (38.4%). Overall, our findings demonstrate that combining explicit inference-time planning with milestone-based rewards significantly improves an agent's long-horizon capabilities, paving the way for more robust and general-purpose autonomous systems.</p> - https://arxiv.org/abs/2603.19685 - Fri, 20 Mar 2026 06:32:16 +0000 + Manifold-Aware Exploration for Reinforcement Learning in Video Generation + https://arxiv.org/abs/2603.21872 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.21872.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mingzhe Zheng, Weijie Kong, Yue Wu, Dengyang Jiang, Yue Ma, Xuanhua He, Bin Lin, Kaixiong Gong, Zhao Zhong, Liefeng Bo, Qifeng Chen, Harry Yang</p><p><b>Upvotes:</b> 30</p><p><b>Summary:</b> Group Relative Policy Optimization (GRPO) methods for video generation like FlowGRPO remain far less reliable than their counterparts for language models and images. This gap arises because video generation has a complex solution space, and the ODE-to-SDE conversion used for exploration can inject excess noise, lowering rollout quality and making reward estimates less reliable, which destabilizes post-training alignment. To address this problem, we view the pre-trained model as defining a valid video data manifold and formulate the core problem as constraining exploration within the vicinity of this manifold, ensuring that rollout quality is preserved and reward estimates remain reliable. We propose SAGE-GRPO (Stable Alignment via Exploration), which applies constraints at both micro and macro levels. At the micro level, we derive a precise manifold-aware SDE with a logarithmic curvature correction and introduce a gradient norm equalizer to stabilize sampling and updates across timesteps. At the macro level, we use a dual trust region with a periodic moving anchor and stepwise constraints so that the trust region tracks checkpoints that are closer to the manifold and limits long-horizon drift. We evaluate SAGE-GRPO on HunyuanVideo1.5 using the original VideoAlign as the reward model and observe consistent gains over previous methods in VQ, MQ, TA, and visual metrics (CLIPScore, PickScore), demonstrating superior performance in both reward maximization and overall video quality. The code and visual gallery are available at https://dungeonmassster.github.io/SAGE-GRPO-Page/.</p> + https://arxiv.org/abs/2603.21872 + Mon, 23 Mar 2026 12:04:38 +0000 - WorldAgents: Can Foundation Image Models be Agents for 3D World Models? - https://arxiv.org/abs/2603.19708 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19708.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ziya Erkoç, Angela Dai, Matthias Nießner</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Given the remarkable ability of 2D foundation image models to generate high-fidelity outputs, we investigate a fundamental question: do 2D foundation image models inherently possess 3D world model capabilities? To answer this, we systematically evaluate multiple state-of-the-art image generation models and Vision-Language Models (VLMs) on the task of 3D world synthesis. To harness and benchmark their potential implicit 3D capability, we propose an agentic framing to facilitate 3D world generation. Our approach employs a multi-agent architecture: a VLM-based director that formulates prompts to guide image synthesis, a generator that synthesizes new image views, and a VLM-backed two-step verifier that evaluates and selectively curates generated frames from both 2D image and 3D reconstruction space. Crucially, we demonstrate that our agentic approach provides coherent and robust 3D reconstruction, producing output scenes that can be explored by rendering novel views. Through extensive experiments across various foundation models, we demonstrate that 2D models do indeed encapsulate a grasp of 3D worlds. By exploiting this understanding, our method successfully synthesizes expansive, realistic, and 3D-consistent worlds.</p> - https://arxiv.org/abs/2603.19708 - Fri, 20 Mar 2026 07:22:41 +0000 + Not All Layers Are Created Equal: Adaptive LoRA Ranks for Personalized Image Generation + https://arxiv.org/abs/2603.21884 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.21884.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Donald Shenaj, Federico Errica, Antonio Carta</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Low Rank Adaptation (LoRA) is the de facto fine-tuning strategy to generate personalized images from pre-trained diffusion models. Choosing a good rank is extremely critical, since it trades off performance and memory consumption, but today the decision is often left to the community's consensus, regardless of the personalized subject's complexity. The reason is evident: the cost of selecting a good rank for each LoRA component is combinatorial, so we opt for practical shortcuts such as fixing the same rank for all components. In this paper, we take a first step to overcome this challenge. Inspired by variational methods that learn an adaptive width of neural networks, we let the ranks of each layer freely adapt during fine-tuning on a subject. We achieve it by imposing an ordering of importance on the rank's positions, effectively encouraging the creation of higher ranks when strictly needed. Qualitatively and quantitatively, our approach, LoRA^2, achieves a competitive trade-off between DINO, CLIP-I, and CLIP-T across 29 subjects while requiring much less memory and lower rank than high rank LoRA versions. Code: https://github.com/donaldssh/NotAllLayersAreCreatedEqual.</p> + https://arxiv.org/abs/2603.21884 + Mon, 23 Mar 2026 12:13:47 +0000 - LoopRPT: Reinforcement Pre-Training for Looped Language Models - https://arxiv.org/abs/2603.19714 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19714.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Guo Tang, Shixin Jiang, Heng Chang, Nuo Chen, Yuhan Li, Huiming Fan, Jia Li, Ming Liu, Bing Qin</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Looped language models (LoopLMs) perform iterative latent computation to refine internal representations, offering a promising alternative to explicit chain-of-thought (CoT) reasoning. However, existing reinforcement learning (RL) paradigms primarily target output tokens, creating a structural mismatch with looped architectures whose reasoning unfolds implicitly. In this work, we propose LoopRPT, a reinforcement pre-training framework tailored for LoopLMs. By reframing next-token prediction as a next-token reasoning task, LoopRPT assigns reinforcement signals directly to latent steps using an EMA teacher reference and noisy latent rollouts. This formulation enables RL to directly shape intermediate representations, compressing effective reasoning into fewer iterations. We instantiate LoopRPT on the Ouro architecture across multiple model scales. Results demonstrate that LoopRPT consistently improves per-step representation quality, achieving Pareto dominance in accuracy-computation trade-offs. Notably, significant gains on hard tokens indicate that LoopRPT enhances early-stage reasoning rather than merely encouraging premature exits. Our findings highlight reinforcement pre-training as a principled paradigm for learning efficient latent reasoning in LoopLMs.</p> - https://arxiv.org/abs/2603.19714 - Fri, 20 Mar 2026 07:35:38 +0000 + Group3D: MLLM-Driven Semantic Grouping for Open-Vocabulary 3D Object Detection + https://arxiv.org/abs/2603.21944 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.21944.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Youbin Kim, Jinho Park, Hogun Park, Eunbyung Park</p><p><b>Upvotes:</b> 24</p><p><b>Summary:</b> Open-vocabulary 3D object detection aims to localize and recognize objects beyond a fixed training taxonomy. In multi-view RGB settings, recent approaches often decouple geometry-based instance construction from semantic labeling, generating class-agnostic fragments and assigning open-vocabulary categories post hoc. While flexible, such decoupling leaves instance construction governed primarily by geometric consistency, without semantic constraints during merging. When geometric evidence is view-dependent and incomplete, this geometry-only merging can lead to irreversible association errors, including over-merging of distinct objects or fragmentation of a single instance. We propose Group3D, a multi-view open-vocabulary 3D detection framework that integrates semantic constraints directly into the instance construction process. Group3D maintains a scene-adaptive vocabulary derived from a multimodal large language model (MLLM) and organizes it into semantic compatibility groups that encode plausible cross-view category equivalence. These groups act as merge-time constraints: 3D fragments are associated only when they satisfy both semantic compatibility and geometric consistency. This semantically gated merging mitigates geometry-driven over-merging while absorbing multi-view category variability. Group3D supports both pose-known and pose-free settings, relying only on RGB observations. Experiments on ScanNet and ARKitScenes demonstrate that Group3D achieves state-of-the-art performance in multi-view open-vocabulary 3D detection, while exhibiting strong generalization in zero-shot scenarios. The project page is available at https://ubin108.github.io/Group3D/.</p> + https://arxiv.org/abs/2603.21944 + Mon, 23 Mar 2026 13:01:14 +0000 - ReLi3D: Relightable Multi-view 3D Reconstruction with Disentangled Illumination - https://arxiv.org/abs/2603.19753 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19753.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jan-Niklas Dihlmann, Mark Boss, Simon Donne, Andreas Engelhardt, Hendrik P. A. Lensch, Varun Jampani</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Reconstructing 3D assets from images has long required separate pipelines for geometry reconstruction, material estimation, and illumination recovery, each with distinct limitations and computational overhead. We present ReLi3D, the first unified end-to-end pipeline that simultaneously reconstructs complete 3D geometry, spatially-varying physically-based materials, and environment illumination from sparse multi-view images in under one second. Our key insight is that multi-view constraints can dramatically improve material and illumination disentanglement, a problem that remains fundamentally ill-posed for single-image methods. Key to our approach is the fusion of the multi-view input via a transformer cross-conditioning architecture, followed by a novel unified two-path prediction strategy. The first path predicts the object's structure and appearance, while the second path predicts the environment illumination from image background or object reflections. This, combined with a differentiable Monte Carlo multiple importance sampling renderer, creates an optimal illumination disentanglement training pipeline. In addition, with our mixed domain training protocol, which combines synthetic PBR datasets with real-world RGB captures, we establish generalizable results in geometry, material accuracy, and illumination quality. By unifying previously separate reconstruction tasks into a single feed-forward pass, we enable near-instantaneous generation of complete, relightable 3D assets. Project Page: https://reli3d.jdihlmann.com/</p> - https://arxiv.org/abs/2603.19753 - Fri, 20 Mar 2026 08:37:39 +0000 + Demystifying Reinforcement Learning for Long-Horizon Tool-Using Agents: A Comprehensive Recipe + https://arxiv.org/abs/2603.21972 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.21972.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xixi Wu, Qianguo Sun, Ruiyang Zhang, Chao Song, Junlong Wu, Yiyan Qi, Hong Cheng</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Reinforcement Learning (RL) is essential for evolving Large Language Models (LLMs) into autonomous agents capable of long-horizon planning, yet a practical recipe for scaling RL in complex, multi-turn environments remains elusive. This paper presents a systematic empirical study using TravelPlanner, a challenging testbed requiring tool orchestration to satisfy multifaceted constraints. We decompose the agentic RL design space along 5 axes: reward shaping, model scaling, data composition, algorithm selection, and environmental stability. Our controlled experiments yield 7 key takeaways, e.g., (1) reward and algorithm choices are scale-dependent as smaller models benefit from staged rewards and enhanced exploration, whereas larger models converge efficiently with simpler dense rewards, (2) ~ 1K training samples with a balanced difficulty mixture mark a sweet spot for both in-domain and out-of-domain performance, and (3) environmental stability is critical to prevent policy degradation. Based on our distilled recipe, our RL-trained models achieve state-of-the-art performance on TravelPlanner, significantly outperforming leading LLMs.</p> + https://arxiv.org/abs/2603.21972 + Mon, 23 Mar 2026 13:40:08 +0000 - How Well Does Generative Recommendation Generalize? - https://arxiv.org/abs/2603.19809 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19809.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yijie Ding, Zitian Guo, Jiacheng Li, Letian Peng, Shuai Shao, Wei Shao, Xiaoqiang Luo, Luke Simon, Jingbo Shang, Julian McAuley, Yupeng Hou</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> A widely held hypothesis for why generative recommendation (GR) models outperform conventional item ID-based models is that they generalize better. However, there is few systematic way to verify this hypothesis beyond a superficial comparison of overall performance. To address this gap, we categorize each data instance based on the specific capability required for a correct prediction: either memorization (reusing item transition patterns observed during training) or generalization (composing known patterns to predict unseen item transitions). Extensive experiments show that GR models perform better on instances that require generalization, whereas item ID-based models perform better when memorization is more important. To explain this divergence, we shift the analysis from the item level to the token level and show that what appears to be item-level generalization often reduces to token-level memorization for GR models. Finally, we show that the two paradigms are complementary. We propose a simple memorization-aware indicator that adaptively combines them on a per-instance basis, leading to improved overall recommendation performance.</p> - https://arxiv.org/abs/2603.19809 - Fri, 20 Mar 2026 09:48:57 +0000 + Speed by Simplicity: A Single-Stream Architecture for Fast Audio-Video Generative Foundation Model + https://arxiv.org/abs/2603.21986 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.21986.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> SII-GAIR, Sand. ai, Ethan Chern, Hansi Teng, Hanwen Sun, Hao Wang, Hong Pan, Hongyu Jia, Jiadi Su, Jin Li, Junjie Yu, Lijie Liu, Lingzhi Li, Lyumanshan Ye, Min Hu, Qiangang Wang, Quanwei Qi, Steffi Chern, Tao Bu, Taoran Wang, Teren Xu, Tianning Zhang, Tiantian Mi, Weixian Xu, Wenqiang Zhang, Wentai Zhang, Xianping Yi, Xiaojie Cai, Xiaoyang Kang, Yan Ma, Yixiu Liu, Yunbo Zhang, Yunpeng Huang, Yutong Lin, Zewei Tao, Zhaoliang Liu, Zheng Zhang, Zhiyao Cen, Zhixuan Yu, Zhongshu Wang, Zhulin Hu, Zijin Zhou, Zinan Guo, Yue Cao, Pengfei Liu</p><p><b>Upvotes:</b> 88</p><p><b>Summary:</b> We present daVinci-MagiHuman, an open-source audio-video generative foundation model for human-centric generation. daVinci-MagiHuman jointly generates synchronized video and audio using a single-stream Transformer that processes text, video, and audio within a unified token sequence via self-attention only. This single-stream design avoids the complexity of multi-stream or cross-attention architectures while remaining easy to optimize with standard training and inference infrastructure. The model is particularly strong in human-centric scenarios, producing expressive facial performance, natural speech-expression coordination, realistic body motion, and precise audio-video synchronization. It supports multilingual spoken generation across Chinese (Mandarin and Cantonese), English, Japanese, Korean, German, and French. For efficient inference, we combine the single-stream backbone with model distillation, latent-space super-resolution, and a Turbo VAE decoder, enabling generation of a 5-second 256p video in 2 seconds on a single H100 GPU. In automatic evaluation, daVinci-MagiHuman achieves the highest visual quality and text alignment among leading open models, along with the lowest word error rate (14.60%) for speech intelligibility. In pairwise human evaluation, it achieves win rates of 80.0% against Ovi 1.1 and 60.9% against LTX 2.3 over 2000 comparisons. We open-source the complete model stack, including the base model, the distilled model, the super-resolution model, and the inference codebase.</p> + https://arxiv.org/abs/2603.21986 + Mon, 23 Mar 2026 13:49:06 +0000 - Breaking the Capability Ceiling of LLM Post-Training by Reintroducing Markov States - https://arxiv.org/abs/2603.19987 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19987.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yurun Yuan, Tengyang Xie</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Reinforcement learning (RL) has become a standard paradigm for post-training and aligning Large Language Models (LLMs), yet recent evidence suggests it faces a persistent "capability ceiling": unlike classical RL systems that discover novel strategies, RL for LLMs often acts as a mere refiner of patterns already latent in pre-trained weights. In this work, we identify a fundamental structural bottleneck: while classical RL relies on compact, informative Markov states, current LLM post-training formulations are tethered to an ever-expanding history of actions. We revisit a classical principle long central to RL yet absent from LLM post-training: explicit Markov states. Theoretically, we provide rigorous guarantees demonstrating that leveraging estimated Markov states can significantly reduce sample complexity. Empirically, we show that introducing Markov states consistently breaks the performance boundaries of standard RL post-training across a suite of complex logic puzzles. Our findings suggest that moving beyond "history-as-state" modeling in favor of structured Markovian representations is essential for unlocking open-ended discovery and genuinely new reasoning capabilities in Generative AI.</p> - https://arxiv.org/abs/2603.19987 - Fri, 20 Mar 2026 14:35:49 +0000 + AdditiveLLM2: A Multi-modal Large Language Model for Additive Manufacturing + https://arxiv.org/abs/2603.22017 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.22017.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Peter Pak, Amir Barati Farimani</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> This work presents AdditiveLLM2 a multi-modal, domain adapted large language model built upon the instruction tuned variant of the Gemma 3 model using a relatively small dataset of around 50 million tokens. The dataset (AdditiveLLM2-OA) consists of open-access additive manufacturing journal articles with data extracted for the domain adaptive pretraining and visual instruction tuning processes. Various stages of the developed model are evaluated with the Additive-Manufacturing-Benchmark which consists of additive manufacturing domain specific tasks compiled published resources. AdditiveLLM2 exhibits proficiency in both language and vision based tasks, achieving accuracies upwards of 90% in general additive manufacturing knowledge. This domain adaptive pretraining and instruction tuning strategy outline an accessible specialization method for large language models to a domain such as additive manufacturing.</p> + https://arxiv.org/abs/2603.22017 + Mon, 23 Mar 2026 14:28:10 +0000 - The Y-Combinator for LLMs: Solving Long-Context Rot with λ-Calculus - https://arxiv.org/abs/2603.20105 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.20105.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Amartya Roy, Rasul Tutunov, Xiaotong Ji, Matthieu Zimmer, Haitham Bou-Ammar</p><p><b>Upvotes:</b> 23</p><p><b>Summary:</b> LLMs are increasingly used as general-purpose reasoners, but long inputs remain bottlenecked by a fixed context window. Recursive Language Models (RLMs) address this by externalising the prompt and recursively solving subproblems. Yet existing RLMs depend on an open-ended read-eval-print loop (REPL) in which the model generates arbitrary control code, making execution difficult to verify, predict, and analyse. We introduce λ-RLM, a framework for long-context reasoning that replaces free-form recursive code generation with a typed functional runtime grounded in λ-calculus. It executes a compact library of pre-verified combinators and uses neural inference only on bounded leaf subproblems, turning recursive reasoning into a structured functional program with explicit control flow. We show that λ-RLM admits formal guarantees absent from standard RLMs, including termination, closed-form cost bounds, controlled accuracy scaling with recursion depth, and an optimal partition rule under a simple cost model. Empirically, across four long-context reasoning tasks and nine base models, λ-RLM outperforms standard RLM in 29 of 36 model-task comparisons, improves average accuracy by up to +21.9 points across model tiers, and reduces latency by up to 4.1x. These results show that typed symbolic control yields a more reliable and efficient foundation for long-context reasoning than open-ended recursive code generation. The complete implementation of λ-RLM, is open-sourced for the community at: https://github.com/lambda-calculus-LLM/lambda-RLM.</p> - https://arxiv.org/abs/2603.20105 - Fri, 20 Mar 2026 16:29:51 +0000 + AnimalCLAP: Taxonomy-Aware Language-Audio Pretraining for Species Recognition and Trait Inference + https://arxiv.org/abs/2603.22053 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.22053.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Risa Shinoda, Kaede Shiohara, Nakamasa Inoue, Hiroaki Santo, Fumio Okura</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Animal vocalizations provide crucial insights for wildlife assessment, particularly in complex environments such as forests, aiding species identification and ecological monitoring. Recent advances in deep learning have enabled automatic species classification from their vocalizations. However, classifying species unseen during training remains challenging. To address this limitation, we introduce AnimalCLAP, a taxonomy-aware language-audio framework comprising a new dataset and model that incorporate hierarchical biological information. Specifically, our vocalization dataset consists of 4,225 hours of recordings covering 6,823 species, annotated with 22 ecological traits. The AnimalCLAP model is trained on this dataset to align audio and textual representations using taxonomic structures, improving the recognition of unseen species. We demonstrate that our proposed model effectively infers ecological and biological attributes of species directly from their vocalizations, achieving superior performance compared to CLAP. Our dataset, code, and models will be publicly available at https://dahlian00.github.io/AnimalCLAP_Page/.</p> + https://arxiv.org/abs/2603.22053 + Mon, 23 Mar 2026 14:53:02 +0000 - Beyond Single Tokens: Distilling Discrete Diffusion Models via Discrete MMD - https://arxiv.org/abs/2603.20155 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.20155.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Emiel Hoogeboom, David Ruhe, Jonathan Heek, Thomas Mensink, Tim Salimans</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> It is currently difficult to distill discrete diffusion models. In contrast, continuous diffusion literature has many distillation approaches methods that can reduce sampling steps to a handful. Our method, Discrete Moment Matching Distillation (D-MMD), leverages ideas that have been highly successful in the continuous domain. Whereas previous discrete distillation methods collapse, D-MMD maintains high quality and diversity (given sufficient sampling steps). This is demonstrated on both text and image datasets. Moreover, the newly distilled generators can outperform their teachers.</p> - https://arxiv.org/abs/2603.20155 - Fri, 20 Mar 2026 17:29:12 +0000 + SpatialBoost: Enhancing Visual Representation through Language-Guided Reasoning + https://arxiv.org/abs/2603.22057 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.22057.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Byungwoo Jeon, Dongyoung Kim, Huiwon Jang, Insoo Kim, Jinwoo Shin</p><p><b>Upvotes:</b> 38</p><p><b>Summary:</b> Despite the remarkable success of large-scale pre-trained image representation models (i.e., vision encoders) across various vision tasks, they are predominantly trained on 2D image data and therefore often fail to capture 3D spatial relationships between objects and backgrounds in the real world, constraining their effectiveness in many downstream applications. To address this, we propose SpatialBoost, a scalable framework that enhances the spatial awareness of existing pre-trained vision encoders by injecting 3D spatial knowledge expressed in linguistic descriptions. The core idea involves converting dense 3D spatial information from 2D images into linguistic expressions, which is then used to inject such spatial knowledge into vision encoders through a Large Language Model (LLM). To this end, we adopt a multi-turn Chain-of-Thought (CoT) reasoning process that progressively incorporates dense spatial knowledge and builds hierarchical spatial understanding. To validate effectiveness, we adapt SpatialBoost to state-of-the-art vision encoders such as DINOv3, and evaluate its performance gains on a wide range of benchmarks requiring both 3D perception and general vision abilities. For instance, SpatialBoost improves DINOv3 performance from 55.9 to 59.7 mIoU on ADE20K, achieving state-of-the-art performance with 3.8% gain over the pre-trained DINOv3.</p> + https://arxiv.org/abs/2603.22057 + Mon, 23 Mar 2026 14:54:34 +0000 - EgoForge: Goal-Directed Egocentric World Simulator - https://arxiv.org/abs/2603.20169 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.20169.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yifan Shen, Jiateng Liu, Xinzhuo Li, Yuanzhe Liu, Bingxuan Li, Houze Yang, Wenqi Jia, Yijiang Li, Tianjiao Yu, James Matthew Rehg, Xu Cao, Ismini Lourentzou</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Generative world models have shown promise for simulating dynamic environments, yet egocentric video remains challenging due to rapid viewpoint changes, frequent hand-object interactions, and goal-directed procedures whose evolution depends on latent human intent. Existing approaches either focus on hand-centric instructional synthesis with limited scene evolution, perform static view translation without modeling action dynamics, or rely on dense supervision, such as camera trajectories, long video prefixes, synchronized multicamera capture, etc. In this work, we introduce EgoForge, an egocentric goal-directed world simulator that generates coherent, first-person video rollouts from minimal static inputs: a single egocentric image, a high-level instruction, and an optional auxiliary exocentric view. To improve intent alignment and temporal consistency, we propose VideoDiffusionNFT, a trajectory-level reward-guided refinement that optimizes goal completion, temporal causality, scene consistency, and perceptual fidelity during diffusion sampling. Extensive experiments show EgoForge achieves consistent gains in semantic alignment, geometric stability, and motion fidelity over strong baselines, and robust performance in real-world smart-glasses experiments.</p> - https://arxiv.org/abs/2603.20169 - Fri, 20 Mar 2026 17:46:55 +0000 + On the Direction of RLVR Updates for LLM Reasoning: Identification and Exploitation + https://arxiv.org/abs/2603.22117 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.22117.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kexin Huang, Haoming Meng, Junkang Wu, Jinda Lu, Chiyu Ma, Ziqian Chen, Xue Wang, Bolin Ding, Jiancan Wu, Xiang Wang, Xiangnan He, Guoyin Wang, Jingren Zhou</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Reinforcement learning with verifiable rewards (RLVR) has substantially improved the reasoning capabilities of large language models. While existing analyses identify that RLVR-induced changes are sparse, they primarily focus on the magnitude of these updates, largely overlooking their direction. In this work, we argue that the direction of updates is a more critical lens for understanding RLVR's effects, which can be captured by the signed, token-level log probability difference Δlog p between the base and final RLVR models. Through statistical analysis and token-replacement interventions, we demonstrate that Δlog p more effectively identifies sparse, yet reasoning-critical updates than magnitude-based metrics (\eg divergence or entropy). Building on this insight, we propose two practical applications: (1) a test-time extrapolation method that amplifies the policy along the learned Δlog p direction to improve reasoning accuracy without further training; (2) a training-time reweighting method that focuses learning on low-probability (corresponding to higher Δlog p) tokens, which improves reasoning performance across models and benchmarks. Our work establishes the direction of change as a key principle for analyzing and improving RLVR.</p> + https://arxiv.org/abs/2603.22117 + Mon, 23 Mar 2026 15:42:24 +0000 - LumosX: Relate Any Identities with Their Attributes for Personalized Video Generation - https://arxiv.org/abs/2603.20192 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.20192.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiazheng Xing, Fei Du, Hangjie Yuan, Pengwei Liu, Hongbin Xu, Hai Ci, Ruigang Niu, Weihua Chen, Fan Wang, Yong Liu</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> Recent advances in diffusion models have significantly improved text-to-video generation, enabling personalized content creation with fine-grained control over both foreground and background elements. However, precise face-attribute alignment across subjects remains challenging, as existing methods lack explicit mechanisms to ensure intra-group consistency. Addressing this gap requires both explicit modeling strategies and face-attribute-aware data resources. We therefore propose LumosX, a framework that advances both data and model design. On the data side, a tailored collection pipeline orchestrates captions and visual cues from independent videos, while multimodal large language models (MLLMs) infer and assign subject-specific dependencies. These extracted relational priors impose a finer-grained structure that amplifies the expressive control of personalized video generation and enables the construction of a comprehensive benchmark. On the modeling side, Relational Self-Attention and Relational Cross-Attention intertwine position-aware embeddings with refined attention dynamics to inscribe explicit subject-attribute dependencies, enforcing disciplined intra-group cohesion and amplifying the separation between distinct subject clusters. Comprehensive evaluations on our benchmark demonstrate that LumosX achieves state-of-the-art performance in fine-grained, identity-consistent, and semantically aligned personalized multi-subject video generation. Code and models are available at https://jiazheng-xing.github.io/lumosx-home/.</p> - https://arxiv.org/abs/2603.20192 - Fri, 20 Mar 2026 17:59:46 +0000 + Omni-WorldBench: Towards a Comprehensive Interaction-Centric Evaluation for World Models + https://arxiv.org/abs/2603.22212 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.22212.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Meiqi Wu, Zhixin Cai, Fufangchen Zhao, Xiaokun Feng, Rujing Dang, Bingze Song, Ruitian Tian, Jiashu Zhu, Jiachen Lei, Hao Dou, Jing Tang, Lei Sun, Jiahong Wu, Xiangxiang Chu, Zeming Liu, Kaiqi Huang</p><p><b>Upvotes:</b> 107</p><p><b>Summary:</b> Video--based world models have emerged along two dominant paradigms: video generation and 3D reconstruction. However, existing evaluation benchmarks either focus narrowly on visual fidelity and text--video alignment for generative models, or rely on static 3D reconstruction metrics that fundamentally neglect temporal dynamics. We argue that the future of world modeling lies in 4D generation, which jointly models spatial structure and temporal evolution. In this paradigm, the core capability is interactive response: the ability to faithfully reflect how interaction actions drive state transitions across space and time. Yet no existing benchmark systematically evaluates this critical dimension. To address this gap, we propose Omni--WorldBench, a comprehensive benchmark specifically designed to evaluate the interactive response capabilities of world models in 4D settings. Omni--WorldBench comprises two key components: Omni--WorldSuite, a systematic prompt suite spanning diverse interaction levels and scene types; and Omni--Metrics, an agent-based evaluation framework that quantifies world modeling capabilities by measuring the causal impact of interaction actions on both final outcomes and intermediate state evolution trajectories. We conduct extensive evaluations of 18 representative world models across multiple paradigms. Our analysis reveals critical limitations of current world models in interactive response, providing actionable insights for future research. Omni-WorldBench will be publicly released to foster progress in interactive 4D world modeling.</p> + https://arxiv.org/abs/2603.22212 + Mon, 23 Mar 2026 17:10:29 +0000 - From Masks to Pixels and Meaning: A New Taxonomy, Benchmark, and Metrics for VLM Image Tampering - https://arxiv.org/abs/2603.20193 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.20193.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xinyi Shang, Yi Tang, Jiacheng Cui, Ahmed Elhagry, Salwa K. Al Khatib, Sondos Mahmoud Bsharat, Jiacheng Liu, Xiaohan Zhao, Jing-Hao Xue, Hao Li, Salman Khan, Zhiqiang Shen</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Existing tampering detection benchmarks largely rely on object masks, which severely misalign with the true edit signal: many pixels inside a mask are untouched or only trivially modified, while subtle yet consequential edits outside the mask are treated as natural. We reformulate VLM image tampering from coarse region labels to a pixel-grounded, meaning and language-aware task. First, we introduce a taxonomy spanning edit primitives (replace/remove/splice/inpaint/attribute/colorization, etc.) and their semantic class of tampered object, linking low-level changes to high-level understanding. Second, we release a new benchmark with per-pixel tamper maps and paired category supervision to evaluate detection and classification within a unified protocol. Third, we propose a training framework and evaluation metrics that quantify pixel-level correctness with localization to assess confidence or prediction on true edit intensity, and further measure tamper meaning understanding via semantics-aware classification and natural language descriptions for the predicted regions. We also re-evaluate the existing strong segmentation/localization baselines on recent strong tamper detectors and reveal substantial over- and under-scoring using mask-only metrics, and expose failure modes on micro-edits and off-mask changes. Our framework advances the field from masks to pixels, meanings and language descriptions, establishing a rigorous standard for tamper localization, semantic classification and description. Code and benchmark data are available at https://github.com/VILA-Lab/PIXAR.</p> - https://arxiv.org/abs/2603.20193 - Fri, 20 Mar 2026 17:59:54 +0000 + MemDLM: Memory-Enhanced DLM Training + https://arxiv.org/abs/2603.22241 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.22241.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zehua Pei, Hui-Ling Zhen, Weizhe Lin, Sinno Jialin Pan, Yunhe Wang, Mingxuan Yuan, Bei Yu</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Diffusion Language Models (DLMs) offer attractive advantages over Auto-Regressive (AR) models, such as full-attention parallel decoding and flexible generation. However, they suffer from a notable train-inference mismatch: DLMs are trained with a static, single-step masked prediction objective, but deployed through a multi-step progressive denoising trajectory. We propose MemDLM (Memory-Enhanced DLM), which narrows this gap by embedding a simulated denoising process into training via Bi-level Optimization. An inner loop updates a set of fast weights, forming a Parametric Memory that captures the local trajectory experience of each sample, while an outer loop updates the base model conditioned on this memory. By offloading memorization pressure from token representations to parameters, MemDLM yields faster convergence and lower training loss. Moreover, the inner loop can be re-enabled at inference time as an adaptation step, yielding additional gains on long-context understanding. We find that, when activated at inference time, this Parametric Memory acts as an emergent in-weight retrieval mechanism, helping MemDLM further reduce token-level attention bottlenecks on challenging Needle-in-a-Haystack retrieval tasks. Code: https://github.com/JarvisPei/MemDLM.</p> + https://arxiv.org/abs/2603.22241 + Mon, 23 Mar 2026 17:39:56 +0000 + + + Repurposing Geometric Foundation Models for Multi-view Diffusion + https://arxiv.org/abs/2603.22275 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.22275.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wooseok Jang, Seonghu Jeon, Jisang Han, Jinhyeok Choi, Minkyung Kwon, Seungryong Kim, Saining Xie, Sainan Liu</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> While recent advances in generative latent spaces have driven substantial progress in single-image generation, the optimal latent space for novel view synthesis (NVS) remains largely unexplored. In particular, NVS requires geometrically consistent generation across viewpoints, but existing approaches typically operate in a view-independent VAE latent space. In this paper, we propose Geometric Latent Diffusion (GLD), a framework that repurposes the geometrically consistent feature space of geometric foundation models as the latent space for multi-view diffusion. We show that these features not only support high-fidelity RGB reconstruction but also encode strong cross-view geometric correspondences, providing a well-suited latent space for NVS. Our experiments demonstrate that GLD outperforms both VAE and RAE on 2D image quality and 3D consistency metrics, while accelerating training by more than 4.4x compared to the VAE latent space. Notably, GLD remains competitive with state-of-the-art methods that leverage large-scale text-to-image pretraining, despite training its diffusion model from scratch without such generative pretraining.</p> + https://arxiv.org/abs/2603.22275 + Mon, 23 Mar 2026 17:57:05 +0000 + + + Scaling DoRA: High-Rank Adaptation via Factored Norms and Fused Kernels + https://arxiv.org/abs/2603.22276 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.22276.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Alexandra Zelenin, Alexandra Zhuravlyova</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Weight-Decomposed Low-Rank Adaptation (DoRA) extends LoRA by decoupling weight magnitude from direction, but its forward pass requires the row-wise norm of W + sBA, a computation that every major framework we surveyed implements by materializing the dense [d_out, d_in] product BA. At d_in = 8192 and rank r = 384, a single module's norm requires about 512 MB of transient working memory in bf16, making high-rank DoRA costly and often infeasible on common single-GPU setups once hundreds of adapted modules and checkpointing are involved. We present two systems contributions. A factored norm decomposes the squared norm into base, cross, and Gram terms computable through O(d_out r + r^2) intermediates, eliminating the dense product. Fused Triton kernels collapse the four-kernel DoRA composition into a single pass, reducing memory traffic by about 4x and using a numerically stable form that avoids catastrophic cancellation in the near-unity rescaling regime where magnitude scales concentrate in practice. Across six 8-32B vision-language models (VLMs) on three NVIDIA GPUs (RTX 6000 PRO, H200, B200) at r = 384 in bf16, the fused implementation is 1.5-2.0x faster than Hugging Face PEFT's DoRA implementation for inference and 1.5-1.9x faster for gradient computation (optimizer step excluded), with up to 7 GB lower peak VRAM. Microbenchmarks on six GPUs spanning four architecture generations (L40S, A100, RTX 6000 PRO, H200, B200, B300) confirm 1.5-2.7x compose-kernel speedup. Final-logit cosine similarity exceeds 0.9999 across all model/GPU pairs, and multi-seed training curves match within 7.1 x 10^-4 mean per-step loss delta over 2000 steps.</p> + https://arxiv.org/abs/2603.22276 + Mon, 23 Mar 2026 17:57:24 +0000 + + + VideoDetective: Clue Hunting via both Extrinsic Query and Intrinsic Relevance for Long Video Understanding + https://arxiv.org/abs/2603.22285 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.22285.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ruoliu Yang, Chu Wu, Caifeng Shan, Ran He, Chaoyou Fu</p><p><b>Upvotes:</b> 45</p><p><b>Summary:</b> Long video understanding remains challenging for multimodal large language models (MLLMs) due to limited context windows, which necessitate identifying sparse query-relevant video segments. However, existing methods predominantly localize clues based solely on the query, overlooking the video's intrinsic structure and varying relevance across segments. To address this, we propose VideoDetective, a framework that integrates query-to-segment relevance and inter-segment affinity for effective clue hunting in long-video question answering. Specifically, we divide a video into various segments and represent them as a visual-temporal affinity graph built from visual similarity and temporal proximity. We then perform a Hypothesis-Verification-Refinement loop to estimate relevance scores of observed segments to the query and propagate them to unseen segments, yielding a global relevance distribution that guides the localization of the most critical segments for final answering with sparse observation. Experiments show our method consistently achieves substantial gains across a wide range of mainstream MLLMs on representative benchmarks, with accuracy improvements of up to 7.5% on VideoMME-long. Our code is available at https://videodetective.github.io/</p> + https://arxiv.org/abs/2603.22285 + Mon, 23 Mar 2026 17:59:51 +0000 + + + WorldCache: Content-Aware Caching for Accelerated Video World Models + https://arxiv.org/abs/2603.22286 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.22286.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Umair Nawaz, Ahmed Heakl, Ufaq Khan, Abdelrahman Shaker, Salman Khan, Fahad Shahbaz Khan</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Diffusion Transformers (DiTs) power high-fidelity video world models but remain computationally expensive due to sequential denoising and costly spatio-temporal attention. Training-free feature caching accelerates inference by reusing intermediate activations across denoising steps; however, existing methods largely rely on a Zero-Order Hold assumption i.e., reusing cached features as static snapshots when global drift is small. This often leads to ghosting artifacts, blur, and motion inconsistencies in dynamic scenes. We propose WorldCache, a Perception-Constrained Dynamical Caching framework that improves both when and how to reuse features. WorldCache introduces motion-adaptive thresholds, saliency-weighted drift estimation, optimal approximation via blending and warping, and phase-aware threshold scheduling across diffusion steps. Our cohesive approach enables adaptive, motion-consistent feature reuse without retraining. On Cosmos-Predict2.5-2B evaluated on PAI-Bench, WorldCache achieves 2.3times inference speedup while preserving 99.4\% of baseline quality, substantially outperforming prior training-free caching approaches. Our code can be accessed on https://umair1221.github.io/World-Cache/{World-Cache}.</p> + https://arxiv.org/abs/2603.22286 + Mon, 23 Mar 2026 17:59:54 +0000