论文广场 - AcademicHub

01.

arXiv (CS.CV) 2026-06-11 DOI: arXiv:2606.12295

Findings of the MAGMaR 2026 Shared Task

作者:

Alexander Martin ↗Dengjia Zhang ↗Joel Brogan ↗Francis Ferraro ↗Jeremy Gwinnup ↗Reno Kriz ↗Teng Long ↗Kenton Murray ↗Andrew Yates ↗Xiang Xiang ↗

This overview paper presents the results of the shared task for the second workshop on Multimodal Augmented Generation via Multimodal Retrieval (MAGMaR). In this shared task participants submitted systems focused on either (i) video retrieval or (ii) grounded generation of articles given retrieved videos. Teams could submit to either task. For the retrieval task, we had 2 participating teams that submitted a total of 17 systems – all of which beat a baseline derived from the winner of last year's shared task. On the generation side, we had 4 teams submit 16 systems. All teams had at least one generated report that was labeled the best by a human annotator.

阅读与讨论 → 访问原文 →

02.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2606.01139

SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision

作者:

Yuxuan Liu ↗Zhaochen Su ↗Lingyun Xie ↗Yuhao Zhang ↗Qing Zong ↗Jiahe Guo ↗Zhongwei Xie ↗Yiyan Ji ↗Yauwai Yim ↗Hongyu Luo ↗Xiyu Ren ↗Ruan Chenyu ↗…

arXiv:2606.01139v3 Announce Type: replace Abstract: Agent skills are procedural artifacts that enable LLM agents to execute workflows, verify constraints, and recover from failures. Existing self-evolving methods refine skills using accumulated trajectories. However, they struggle in cold-start settings, where only an initial, imperfect skill is available. Consequently, skill construction defaults to expert authoring or one-shot LLM generation. Expert-authored skills are costly and may not align with how LLM agents actually execute tasks, while one-shot generated skills can be syntactically well formed yet behaviorally weak. To bridge this gap, we propose SkillRevise, an execution-grounded framework designed to iteratively refine these initial skills. SkillRevise diagnoses skill defects from execution evidence, retrieves relevant repair principles from a general memory, and applies execution-anchored edits. By re-executing candidates, it retains the first verifier-passing skill within the revision budget and falls back to empirical utility only when no candidate succeeds. Evaluated across three benchmarks and five LLMs, SkillRevise substantially outperforms one-shot baselines, improving the base agent's success rate on SkillsBench from 36.05% to 61.63%. Furthermore, the revised skills transfer across both executors and task environments, suggesting that SkillRevise captures reusable procedural knowledge beyond any single executor.

阅读与讨论 → 访问原文 →

03.

arXiv (CS.CL) 2026-06-17 DOI: arXiv:2601.19792

LVLMs and Humans Ground Differently in Referential Communication

作者:

Peter Zeng ↗Weiling Li ↗Amie Paige ↗Zhengxiang Wang ↗Panagiotis Kaliosis ↗Dimitris Samaras ↗Gregory Zelinsky ↗Susan Brennan ↗Owen Rambow ↗

For generative AI agents to partner effectively with human users, the ability to accurately predict human intent is critical. But this ability to collaborate remains limited by a critical deficit: an inability to model common ground. We present a referential communication experiment with a factorial design involving director-matcher pairs (human-human, human-AI, AI-human, and AI-AI) that interact with multiple turns in repeated rounds to match pictures of objects not associated with any obvious lexicalized labels. We show that LVLMs cannot interactively generate and resolve referring expressions in a way that enables smooth communication, a crucial skill that underlies human language use. We release our corpus of 356 dialogues (89 pairs over 4 rounds each) along with the online pipeline for data collection and the tools for analyzing accuracy, efficiency, and lexical overlap.

阅读与讨论 → 访问原文 →

04.

arXiv (CS.CV) 2026-06-12 DOI: arXiv:2606.13032

GeoCFNet: Geometry-Aware Confidence Field Network for Robot-Assisted Endoscopic Submucosal Dissection

作者:

Rui Tang ↗Guankun Wang ↗Long Bai ↗Haochen Yin ↗Huxin Gao ↗Jiewen Lai ↗Jiazheng Wang ↗Hongliang Ren ↗

Advanced surgical robotics has made robot-assisted endoscopic submucosal dissection (ESD) a promising approach for the en-bloc resection of large lesions, with the potential to reduce recurrence and improve long-term outcomes. However, the technical complexity and risk of complications in ESD demand stable and precise visual guidance to maintain an accurate dissection corridor and a safe tissue margin. Dense confidence fields provide an effective representation for this purpose by describing both the preferred dissection region and its spatial transition to surrounding tissue. However, reliable confidence field estimation remains challenging in dynamic endoscopic scenes due to smoke, specular highlights, tissue deformation, weak texture, and the thin geometric structure of the target region. To address these challenges, we formulate dissection guidance as a geometry-aware confidence field estimation problem and propose GeoCFNet, a geometry-aware confidence field network built on a pretrained DINOv3 backbone. GeoCFNet integrates a Token-Differentiated Fusion module to aggregate class-token context with dense patch representations, a SegFormer decoder for confidence regression, and Geometry-Aware Spatial Regularization (GASR) to preserve spatial coherence and local geometric transitions. Experimental results show that GeoCFNet achieves RMSE 0.0480, PSNR 27.1995, SSIM 0.3397, and CC 0.2466, indicating accurate and geometrically stable confidence field estimation for robot-assisted ESD guidance.

阅读与讨论 → 访问原文 →

05.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2605.25449

Pantheon360: Taming Digital Twin Generation via 3D-Aware 360{\deg} Video Diffusion

作者:

Ting-Hsuan Chen ↗Ying-Huan Chen ↗Tao Tu ↗Jie-Ying Lee ↗Cho-Ying Wu ↗Fangzhou Lin ↗Hengyuan Zhang ↗David Paz ↗Xinyu Huang ↗Yuliang Guo ↗Yu-Lun Liu ↗Yue Wang ↗…

Generating complete digital twins from videos requires precise camera control, global scene coverage, and strict spatial-temporal consistency constraints that remain challenging for perspective video generators due to their limited field of view (FoV). Their narrow FoV forces long or multi-view trajectories, amplifying cross-view inconsistency and temporal drift. We argue that 360{\deg} video generation offers a natural solution: panoramic coverage simplifies trajectory design and provides a strong global context for maintaining coherence. We introduce Pantheon360: Taming Digital Twin Generation via 3D-Aware 360{\deg} Video Diffusion, a controllable 360{\deg} video generation framework that synthesizes high-fidelity videos from sparse 360{\deg} inputs. The key idea is an explicit 3D Cache, reconstructed from the input, which serves as a geometric scaffold for any user-defined camera path. This allows the diffusion model to focus on photorealistic texture refinement while the 3D Cache enforces global geometric consistency. Experiments show that Pantheon360 achieves superior visual quality and unmatched geometric coherence, enabling reliable and flexible 360{\deg} scene generation for downstream simulation and digital-twin applications.

阅读与讨论 → 访问原文 →

06.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.15457

Lesion-DDPM: Lesion-Enhanced 3D Diffusion for MS MRI Synthesis

作者:

Weidong Zhang ↗Yongchan Jung ↗Shafayat Mowla Anik ↗Furen Xiao ↗Vasudevan Janarthanan ↗Enkhzaya Chuluunbaatar ↗Byeong Kil Lee ↗Jeeho Ryoo ↗

3D FLAIR MRI is widely recommended as one of the standard MRI sequences for brain imaging in multiple sclerosis (MS), but publicly available MS datasets remain relatively small and vary across scanners, acquisition protocols, and lesion patterns. This scarcity and variability hinder the development of robust neuroimaging machine learning models and are particularly challenging for generative models that aim to synthesize images while preserving small, sparse lesions. We propose Lesion-DDPM, a 3D conditional diffusion framework for lesion-aware FLAIR synthesis that incorporates multi-level anatomical mask injection together with a lesion-weighted reconstruction loss to emphasize lesion voxels while maintaining global brain structure. Using a curated subset of the MSLesSeg dataset, we compare Lesion-DDPM with representative state-of-the-art GAN- and diffusion-based models, assessing both image-generation metrics and downstream 3D U-Net segmentation. In our experiments, Lesion-DDPM achieved the lowest lesion-region reconstruction error among all methods. In a downstream 3D U-Net lesion segmentation task, a model trained only on Lesion-DDPM-generated scans and evaluated on real MRIs reached a Dice score of 0.616 compared with 0.569 for the best competing synthetic dataset. When Lesion-DDPM images were added to the real training set, the Dice score further increased to 0.685.

阅读与讨论 → 访问原文 →

07.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.15007

Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning

作者:

We introduce Nemotron 3 Ultra, a 550 billion total and 55 billion active parameter Mixture-of-Experts Hybrid Mamba-Attention language model. We pre-trained Nemotron 3 Ultra on 20 trillion text tokens, then extended the context length to 1M tokens, and post-trained using Supervised Fine Tuning (SFT), Reinforcement Learning (RL), and Multi-teacher On-Policy Distillation (MOPD). Nemotron 3 Ultra is our most capable model yet, employing multiple key technologies - LatentMoE, Multi Token Prediction (MTP), NVFP4 pre-training, multi-environment RLVR, MOPD, and reasoning budget control. Nemotron 3 Ultra achieves up to ~6x higher inference throughput as compared to state-of-the-art publicly available LLMs while attaining on-par accuracy. The state-of-the-art accuracy, high inference throughput, and 1M token context length make Nemotron 3 Ultra ideal for long-running autonomous agentic tasks. We open-source the base, post-trained, and quantized checkpoints, along with the training data and recipe on HuggingFace.

阅读与讨论 → 访问原文 →

08.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.20227

QMFOL: Benchmarking Large Language Model Reasoning via Quantifiable Monadic First-Order Logic Test Case Generation

作者:

Xinyi Zheng ↗Ling Shi ↗Tianlong Yu ↗Yongxin Zhao ↗Lorenz Goette ↗Kailong Wang ↗

arXiv:2606.20227v1 Announce Type: new Abstract: Large Language Models (LLMs) have made significant progress in reasoning, particularly in deductive reasoning, which is crucial for high-stakes decision-making. As models improve, evaluation benchmarks should evolve to keep pace. However, existing benchmarks lack fine-grained control over logical complexity and struggle to balance semantic diversity with logical consistency. To address these issues, we propose QMFOL, an automated framework for generating monadic first-order logic reasoning tasks with quantifiable and controllable complexity. It constructs formal logical structures using conjunction and disjunction patterns, enabling precise control over reasoning depth, width, label types, and distractors. These structures are then translated into natural language via LLMs, with logical consistency ensured through round-trip verification using an external prover. Based on our framework, we build QMFOLBench, a benchmark comprising 2880 instances with 960 configurations across diverse logical and semantic dimensions. Evaluations on six large reasoning models (LRMs) and two LLMs show that performance degrades and computational overhead increases with rising logical complexity. Models perform better on True-labeled tasks than on False or Unknown ones, and exhibit sensitivity to semantic variation. Overall, QMFOL offers a scalable and reliable approach for constructing deductive reasoning benchmarks with controllable complexity, enabling more precise evaluation of reasoning capabilities in modern language models.

阅读与讨论 → 访问原文 →

09.

arXiv (CS.LG) 2026-06-15 DOI: arXiv:2606.14159

Curvature-Guided Geometric Representation for Protein-Ligand Binding Affinity Prediction

作者:

Shuai Li ↗Chuan-Xian Ren ↗Yuhao Li ↗Ziqi Huang ↗Yue Pan ↗Mingzhe Tang ↗Hong Yan ↗

arXiv:2606.14159v1 Announce Type: new Abstract: Protein-ligand binding affinity (PLA) prediction is critical in drug discovery. Despite the notable advancements in machine learning-based approaches, existing methods struggle to jointly characterize local geometric organization and globally coordinated cross-molecular interactions, limiting their ability to model complex binding mechanisms. Here, we propose RicciBind, a geometric representation framework that integrates curvature-guided hierarchical structure learning with optimal transport (OT)-based cross-domain alignment to model molecular interactions. Specifically, RicciBind leverages Ricci curvature to capture local interaction tightness within molecular structures, enhancing structural awareness and organizing atomic interactions into curvature-aware hierarchical representations. An OT-based cluster matching mechanism then aligns protein and ligand clusters across heterogeneous domains under geometric constraints, enabling globally consistent correspondences and revealing higher-order interaction patterns beyond local neighborhoods. By coupling curvature-guided structure encoding with OT-driven cross-domain alignment, RicciBind effectively models complex interaction semantics and substantially improves both the accuracy and interpretability of binding affinity prediction. Extensive experiments demonstrate that RicciBind achieved superior predictive performance and generalization across PLA benchmarks and virtual screening tasks. Ablation studies further confirmed the essential role of Ricci curvature in enhancing molecular interaction representations.

阅读与讨论 → 访问原文 →

10.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2606.12429

Muse Spark Safety & Preparedness Report

作者:

Cristina Menghini ↗Peter Ney ↗Hamza Kwisaba ↗Zifan ↗Wang ↗Miles Turpin ↗Felix Binder ↗Jean-Christophe Testud ↗Aidan Boyd ↗Nathaniel Li ↗Ivan Evtimov ↗Klaudia Krawiecka ↗…

arXiv:2606.12429v1 Announce Type: cross Abstract: Muse Spark is the latest large language model developed by Meta. In this report, we first present evaluations for catastrophic risk domains under Meta's Advanced AI Scaling Framework, along with the evidence that informed our launch decision. We then discuss additional considerations, such as Muse Spark's broader content safety and behavioral profile, that are relevant to overall safety but fall outside the catastrophic risk domains governed by the Framework. Our preparedness results covering Chemical and Biological, Cybersecurity, and Loss of Control risks assess Muse Spark's deployment within Meta AI as presenting acceptable levels of residual risks under our Advanced AI Scaling Framework. We conducted a broad set of evaluations targeting dual-use and high-risk capabilities across these catastrophic risk domains. Those evaluations identified elevated risks prior to mitigations, with Chemical and Biological capabilities assessed as likely reaching the "high risk" category under the Advanced AI Scaling Framework before safeguards were applied. We have implemented a multi-layered set of mitigations that address the identified risks, and Muse Spark demonstrates state-of-the-art refusal across a range of benchmarks related to hazardous workflows in chemistry and biology. We therefore release Muse Spark as the underlying model of Meta AI.

阅读与讨论 → 访问原文 →

11.

arXiv (CS.CL) 2026-06-18 DOI: arXiv:2606.19002

Enhancing Multilingual Reasoning via Steerable Model Merging

作者:

Zhuoran Li ↗Rui Xu ↗Jian Yang ↗Junnan Liu ↗Zhijun Chen ↗Qianren Mao ↗Hongcheng Guo ↗Jiaheng Liu ↗Likang Xiao ↗Ming Li ↗Xiaojie Wang ↗

Model merging is an effective technique for composing the capabilities of a multilingual model and a reasoning model. It has achieved promising generalization in multilingual reasoning tasks by aligning feature spaces of different models. However, the merged single model often fails to address the conflicts between source models, leading to suboptimal performance. In other words, the one-size-fits-all merging strategy may not align with the characteristics of different inputs which may require prioritizing certain models over others. To this end, we propose a Steerable Model Merging (ST-Merge) framework to modulate the contribution of each source model. To realize this idea, we introduce a gated cross-attention mechanism to weight or filter the two attended source models in an adaptive manner. Extensive experiments demonstrate that ST-Merge consistently outperforms multiple strong baselines on four multilingual reasoning benchmarks across 21 different languages.

阅读与讨论 → 访问原文 →

12.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.01561

S-SPPO: Semantic-Calibrated Self-Play Preference Optimization

作者:

Xiwen Chen ↗Wenhui Zhu ↗Jingjing Wang ↗Peijie Qiu ↗Zhipeng Wang ↗Huayu Li ↗ZhengXiao He ↗Xuanzhao Dong ↗Prayag Tiwari ↗Mingkun Xu ↗Yujian Xiong ↗Feng Luo ↗…

arXiv:2606.01561v2 Announce Type: replace Abstract: Aligning Large Language Models (LLMs) with human preferences is often formulated via Direct Preference Optimization (DPO). However, the standard Bradley-Terry instantiation of DPO is limited in modeling common departures from transitivity in human preferences. To address this, recent work has introduced Self-Play Preference Optimization (SPPO), which iteratively refines the policy by training on self-generated win-lose pairs. Our investigation, however, reveals a critical instability in SPPO: the optimization is prone to policy degeneration when the preference oracle assigns overly confident wins to semantically indistinguishable responses. To mitigate this, we propose S-SPPO, a dual-space semantic calibration framework comprising: i) Supervision Calibration via semantic gating, which anneals win rate targets toward the maximum-entropy baseline as semantic overlap increases; and ii) Representation Calibration via latent repulsion to enforce geometric diversity to prevent manifold collapse and maintain latent diversity between chosen and rejected samples. Theoretically, we show that the calibration preserves the constant-sum game structure, facilitating convergence to a Nash Equilibrium. Empirically, S-SPPO avoids the performance degradation seen in prior methods, achieving 52.19% win rate and 47.46% length-controlled win rate on AlpacaEval 2.0 with Llama-3-8B, without using additional human-annotated preferences during training. The code will be available at https://github.com/xiwenc1/s-sppo.

阅读与讨论 → 访问原文 →

13.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2606.10968

Beyond Uniform Token-Level Trust Region in LLM Reinforcement Learning

作者:

Renjie Mao ↗Xiangxin Zhou ↗Lvfang Tao ↗Yixin Ding ↗Yu Shi ↗Yongguang Lin ↗Yuheng Wu ↗Honglin Zhu ↗Qian Qiu ↗Wenxi Zhu ↗

arXiv:2606.10968v2 Announce Type: replace-cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has become standard for improving LLM reasoning. However, existing PPO-style trust-region mechanisms remain position-agnostic by enforcing uniform thresholds across all tokens independently. This pointwise treatment conflicts with autoregressive generation in two critical ways. First, uniform thresholds ignore autoregressive asymmetry. Early-stage deviations produce compounding sequence-level drift, causing static thresholds to under-regulate early divergence and excessively constrain late-stage exploration. Second, evaluating token-level divergence in isolation overlooks cumulative prefix drift, granting the same divergence allowance regardless of how far the conditioning history has already deviated from the rollout policy. To address this limitation, we propose CPPO (Cumulative Prefix-divergence Policy Optimization), a token-level masking rule that aligns updates with a finite-horizon policy-improvement bound via two coupled mechanisms. First, a position-weighted threshold imposes stricter limits at early positions whose effects persist longer, relaxing constraints for late-stage tokens. Second, a cumulative prefix budget tracks historical deviations, dynamically restricting further token-level deviation to prevent compounding errors along the prefix. Empirically, CPPO enhances training stability and significantly improves reasoning accuracy across various model scales.

阅读与讨论 → 访问原文 →

14.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.16031

The Third Challenge on Image Denoising at NTIRE 2026: Methods and Results

作者:

Lei Sun ↗Hang Guo ↗Bin Ren ↗Shaolin Su ↗Xian Wang ↗Danda Pani Paudel ↗Luc Van Gool ↗Radu Timofte ↗Yawei Li ↗

This paper reports on the NTIRE 2026 Challenge on Image Denoising, specifically focusing on the high-noise regime ($\sigma = 50$). The competition investigates advanced neural architectures designed to restore high-fidelity details from images corrupted by additive white Gaussian noise (AWGN). Unlike constrained benchmarks, this track emphasizes peak quantitative performance, measured by Peak Signal-to-Noise Ratio (PSNR), without limitations on parameter count or computational overhead. By synthesizing contributions from 20 finalist teams out of 116 registrants, this report benchmarks the latest technical innovations and provides a comprehensive snapshot of the current state-of-the-art in unconstrained image restoration.

阅读与讨论 → 访问原文 →

15.

arXiv (CS.CV) 2026-06-17 DOI: arXiv:2606.17598

MuseVLA: An Adaptive Multimodal Sensing Vision-Language-Action Model for Robotic Manipulation

作者:

Xingyuming Liu ↗Ruichun Ma ↗Heyu Guo ↗Qixiu Li ↗Qingwen Yang ↗Lin Luo ↗Shiqi Jiang ↗Chenren Xu ↗Jiaolong Yang ↗Baining Guo ↗

Humans naturally leverage diverse sensing modalities to interact with the physical world, while most Vision-Language-Action (VLA) models for robotics rely solely on RGB observations. This limits their ability to perceive physical properties that are difficult or impossible to infer from RGB cameras, such as temperature, sound, or radar response. We present MuseVLA, an adaptive multimodal sensing VLA model that integrates novel sensors as on-demand tools for robotic manipulation. Given a task instruction and visual context, MuseVLA first generates a sensor token and target description that select the sensing modality to invoke and what to attend to, analogous to a tool call with arguments. It then converts the selected sensor measurement into a grounded sensor image, a unified intermediate representation that encodes heterogeneous readings for multimodal fusion and action generation. This design decouples sensor-specific processing from the VLA backbone, enabling efficient integration of diverse modalities. To reduce the need for expensive multisensory robot datasets, we further introduce a data synthesis pipeline that augments existing RGB video datasets with grounded sensor images, enabling generalization to unseen sensor-guided tasks. We evaluate MuseVLA on a real-world robot across challenging dexterous hand manipulation tasks that require multimodal sensing inputs, including temperature-guided pick-and-place, audio-driven object search, and radar-assisted hidden object retrieval. MuseVLA achieves 80.6% success rate on average, outperforming RGB-only and multisensory VLA baselines significantly, and exhibits strong zero-shot capabilities on unseen tasks.

阅读与讨论 → 访问原文 →

16.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.15079

Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scale

作者:

Ang Li ↗Ben Liu ↗Bin Han ↗Bin Hu ↗Bin Jing ↗Binbin Hu ↗Bing Li ↗Cai Chen ↗Caizhi Tang ↗Changxin Tian ↗Chao Huang ↗Chao Zhang ↗…

Efficient and scalable agentic intelligence requires models that can deliver both low-latency responses and strong reasoning capabilities while remaining practical to train, serve, and deploy. In this report, we present Ling-2.6 and Ring-2.6, a family of models designed to address this challenge at scale. Ling-2.6 is optimized for instant response generation and high capability per output token, whereas Ring-2.6 is tailored for deeper reasoning and more advanced agentic workflows. Instead of training from scratch, we upgrade the Ling-2.0 base model through architectural migration pre-training and large-scale post-training. This upgrade is guided by a unified co-design of model architecture, optimization objectives, serving systems, and agent training environments, enabling improvements in both model capability and deployment efficiency. At the architectural level, we introduce a hybrid linear attention design that integrates Lightning Attention with MLA, improving the efficiency of long-context training and decoding. To further enhance token efficiency, we optimize capability per output token through Evolutionary Chain-of-Thought, Linguistic Unit Policy Optimization, bidirectional preference alignment, and shortest-correct-response distillation. For agentic capabilities, we propose KPop, a reinforcement learning framework designed to support stable training of Ring-2.6-1T on large-scale environment-grounded data. KPop improves training efficiency through asynchronous scheduling across coding, search, tool use, and workflow execution, enabling scalable learning from complex agent-environment interactions. Together, Ling-2.6 and Ring-2.6 provide a practical pathway toward efficient, scalable, and open agentic systems. We open-source all checkpoints in the 2.6 family to support further research and development in practical agentic intelligence.

阅读与讨论 → 访问原文 →

17.

arXiv (CS.LG) 2026-06-18 DOI: arXiv:2606.18531

When Does Trajectory-Level Supervision Permit Efficient Offline Reinforcement Learning?

作者:

Xuanfei Ren ↗Tengyang Xie ↗

arXiv:2606.18531v1 Announce Type: cross Abstract: Offline reinforcement learning is typically analyzed under process-level reward supervision, yet many sequential decision datasets record only trajectory-level outcomes. We develop a statistical theory for offline policy optimization from such outcome-level supervision. We first study the canonical setting where the target remains the expected cumulative reward, but each offline trajectory provides only a scalar label whose conditional mean is the cumulative return. We propose OPAC, a pessimistic actor-critic algorithm that learns a latent reward model and optimizes a policy from trajectory-level labels. We prove a high-probability guarantee of order $\widetilde O(H^2\sqrt{C_{sa}(\pi^\star)/n})$ and a matching lower bound, characterizing the sharp statistical cost of replacing process-level rewards with one trajectory-level label. We then extend the principle to preference-based feedback, preserving the leading horizon and concentrability dependence up to preference-model constants. Finally, we study generalized outcome-based offline RL, where both the supervision and the objective are trajectory-level quantities induced by a nonlinear aggregation of latent per-step rewards. This problem is not learnable in general: for all-success objectives, any offline learner may require $\Omega(2^H)$ trajectories even with deterministic transitions and constant concentrability. We then identify a tractable regime through two structural coefficients, $\kappa_\mu(\sigma)$ and $\chi_\mu(\sigma)$, capturing information loss in outcome aggregation and generalized Bellman updates, under which generalized OPAC achieves polynomial sample complexity. Together, our results delineate when outcome-level supervision enables sample-efficient offline control and when missing process-level rewards create fundamental statistical barriers.

阅读与讨论 → 访问原文 →

18.

arXiv (CS.AI) 2026-06-17 DOI: arXiv:2509.26633

OmniRetarget: Interaction-Preserving Data Generation for Humanoid Whole-Body Loco-Manipulation and Scene Interaction

作者:

Lujie Yang ↗Xiaoyu Huang ↗Zhen Wu ↗Angjoo Kanazawa ↗Pieter Abbeel ↗Carmelo Sferrazza ↗C. Karen Liu ↗Rocky Duan ↗Guanya Shi ↗

arXiv:2509.26633v3 Announce Type: replace-cross Abstract: A dominant paradigm for teaching humanoid robots complex skills is to retarget human motions as kinematic references to train reinforcement learning (RL) policies. However, existing retargeting pipelines often struggle with the significant embodiment gap between humans and robots, producing physically implausible artifacts like foot-skating and penetration. More importantly, common retargeting methods neglect the rich human-object and human-environment interactions essential for expressive locomotion and loco-manipulation. To address this, we introduce OmniRetarget, an interaction-preserving data generation engine based on an interaction mesh that explicitly models and preserves the crucial spatial and contact relationships between an agent, the terrain, and manipulated objects. By minimizing the Laplacian deformation between the human and robot meshes while enforcing kinematic constraints, OmniRetarget generates kinematically feasible trajectories. Moreover, preserving task-relevant interactions enables efficient data augmentation, from a single demonstration to different robot embodiments, terrains, and object configurations. We comprehensively evaluate OmniRetarget by retargeting motions from OMOMO, LAFAN1, and our in-house MoCap datasets, generating over 8-hour trajectories that achieve better kinematic constraint satisfaction and contact preservation than widely used baselines. Such high-quality data enables proprioceptive RL policies to successfully execute long-horizon (up to 30 seconds) parkour and loco-manipulation skills on a Unitree G1 humanoid, trained with only 5 reward terms and simple domain randomization shared by all tasks, without any learning curriculum.

阅读与讨论 → 访问原文 →

19.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2606.13578

LabVLA: Grounding Vision-Language-Action Models in Scientific Laboratories

作者:

Baochang Ren ↗Xinjie Liu ↗Xi Chen ↗Yanshuo Liu ↗Chenxi Li ↗Daqi Gao ↗Zeqin Su ↗Jintao Xing ↗Zirui Xue ↗Rui Li ↗Xiangyu Zhao ↗Shuofei Qiao ↗…

Scientific laboratories increasingly rely on AI systems to reason about experiments, but the physical act of doing science remains largely outside their reach. AI can help read literature, generate hypotheses, and plan protocols, yet the execution of those protocols at the bench still requires a human operator. Vision-Language-Action (VLA) models provide one possible interface between written protocols and robot execution, but existing policies are trained mostly on household and tabletop demonstrations and rarely encounter the instruments, transparent liquids, or fixed protocol workflows found in scientific laboratories. Closing this gap requires both laboratory-specific supervision and a unified learning framework that can accommodate the diverse robot embodiments used to execute experimental protocols. We therefore identify data and embodiment as central bottlenecks alongside model design. To address the data side, we build RoboGenesis, a simulation-based workflow and data engine that composes configured laboratory workflows from atomic skills, validates and filters rollouts, and exports structured demonstrations across supported robot profiles. On the policy side, we present LabVLA, trained with a two-stage recipe: FAST action token pretraining first makes the Qwen3-VL-4B-Instruct backbone action aware before any continuous control is learned, and flow matching posttraining then attaches a DiT action expert under knowledge insulation. On the LabUtopia benchmark, LabVLA achieves the highest average success rate among all evaluated baselines under both in-distribution and out-of-distribution settings.

阅读与讨论 → 访问原文 →

20.

arXiv (CS.CL) 2026-06-17 DOI: arXiv:2606.17057

Correct When Paired, Wrong When Split: Decoupling and Editing Modality-Specific Neurons in MLLMs

作者:

Tingchao Fu ↗Wenkai Wang ↗Fanxiao Li ↗Huadong Zhang ↗Jinhong Zhang ↗Dayang Li ↗Yunyun Dong ↗Renyang Liu ↗Wei Zhou ↗

Although Knowledge Editing provides an efficient mechanism for updating the knowledge of Multimodal Large Language Models (MLLMs), we find that current paradigms still suffer from an important yet remain underexplored issue : editing decoupling failure, where entity-related knowledge can be updated when the model is triggered by multimodal inputs (text–image query pairs), however, it often reverts to outdated pre-edit facts when the paired inputs are split into unimodal ones. Our in-depth empirical analysis reveals that the entity knowledge in MLLMs is not stored as a unified representation, but is instead distributed across disentangled modality-specific pathways. As a result, updates biased toward multimodal queries fail to propagate effectively to unimodal circuits. To bridge this gap, we propose DECODE, which explicitly disentangles and localizes modality-specific neuron groups for targeted knowledge. Extensive experiments demonstrate that DECODE consistently achieves effective knowledge updates under different modality triggers, thereby mitigating editing decoupling failures.

阅读与讨论 → 访问原文 →

21.

arXiv (CS.CV) 2026-06-19 DOI: arXiv:2506.06952

LaTtE-Flow: Layerwise Timestep-Expert Flow-based Transformer

作者:

Ying Shen ↗Zhiyang Xu ↗Jiuhai Chen ↗Shizhe Diao ↗Jiaxin Zhang ↗Yuguang Yao ↗Joy Rimchala ↗Ismini Lourentzou ↗Lifu Huang ↗

Recent advances in multimodal foundation models unifying image understanding and generation have opened exciting avenues for tackling a wide range of vision-language tasks within a single framework. Despite progress, existing unified models typically require extensive pretraining and struggle to achieve the same level of performance compared to models dedicated to each task. Additionally, many of these models suffer from slow image generation speeds, limiting their practical deployment in real-time or resource-constrained settings. In this work, we propose Layerwise Timestep-Expert Flow-based Transformer (LaTtE-Flow), a novel and efficient architecture that unifies image understanding and generation within a single multimodal model. LaTtE-Flow builds upon powerful pretrained Vision-Language Models (VLMs) to inherit strong multimodal understanding capabilities, and extends them with a novel Layerwise Timestep Experts flow-based architecture for efficient image generation. LaTtE-Flow distributes the flow-matching process across specialized groups of Transformer layers, each responsible for a distinct subset of timesteps. This design significantly improves sampling efficiency by activating only a small subset of layers at each sampling timestep. To further enhance performance, we propose a Timestep-Conditioned Residual Attention mechanism for efficient information reuse across layers. Experiments demonstrate that LaTtE-Flow achieves strong performance on multimodal understanding tasks, while achieving competitive image generation quality with around 6x faster inference speed compared to recent unified multimodal models.

阅读与讨论 → 访问原文 →

22.

arXiv (quant-ph) 2026-06-11 DOI: arXiv:2606.12363

Fermions are fundamentally more nonlocal than Bosons

作者:

Fatemeh Moradi Kalarde ↗Sadra Boreiri ↗Xiangling Xu ↗Lucas Tendick ↗Salman Beigi ↗Paolo Perinotti ↗Tommaso Guaita ↗Marc-Olivier Renou ↗

arXiv:2606.12363v1 Announce Type: new Abstract: Bell's theorem shows that entangled quantum particles can exhibit correlations that classical particles cannot reproduce without an additional nonlocal resource, such as communication. In this sense, quantum particles are fundamentally more nonlocal than classical ones, and entanglement becomes unavoidable in physics. Here we prove the analogous result within quantum theory itself: indistinguishable fermions transmitted through a quantum network can generate correlations that distinguishable particles or indistinguishable bosons cannot reproduce without additional communication. In the same sense, fermions are fundamentally more nonlocal than bosons or distinguishable particles, motivating fermionic anticommutation and indistinguishability as unavoidable operational resources. Our result further implies that fermions can strictly surpass all qubit-based protocols for certain distributed computing tasks, demonstrating that a complete understanding of information processing requires going beyond qubits to fermionic information carriers - febits.

阅读与讨论 → 访问原文 →

23.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2606.13464

Ontology Memory-Augmented ASR Correction for Long Text-Speech Interleaved Conversations

作者:

Xinxin Li ↗Huiyao Chen ↗Meishan Zhang ↗Yunxin Li ↗Zulong Chen ↗Zhibo Ren ↗Xiaoqing Dong Baotian Hu ↗Min Zhang ↗

Automatic speech recognition (ASR) correction has traditionally focused on isolated utterances or short local contexts. However, as text and speech become increasingly interleaved in long interactions, ASR correction requires conversation-level contextual evidence. Existing ASR correction methods often rely on the current hypothesis or concatenate raw dialogue history. In such contexts, sparse correction evidence can be difficult to locate amid redundancy and noise. Addressing these challenges, we propose an ontology memory-augmented ASR correction framework for long text-speech interleaved conversations. The framework organizes preceding interaction history into a dynamically updatable ontology memory, where entities, terminology, surface variants, potential ASR confusions, and semantic relations are stored as retrievable nodes for context-grounded correction. To evaluate this setting, we construct RAMC-Corr, a dataset derived from MAGIC-RAMC for long-range ASR correction with grounded context. Experiments on RAMC-Corr show that our method improves over direct correction in 9 out of 10 paired backbone-setting combinations and encourages more selective and evidence-grounded corrections for context-dependent ASR errors.

阅读与讨论 → 访问原文 →

24.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.12370

Breaking Entropy Bounds: Accelerating RL Training via MTP with Rejection Sampling

作者:

Yucheng Li ↗Huiqiang Jiang ↗Yang Xu ↗Jianxin Yang ↗Yi Zhang ↗Yizhong Cao ↗Yuhao Shen ↗Fan Zhou ↗Rui Men ↗Jianwei Zhang ↗An Yang ↗Bowen Yu ↗…

Reinforcement learning (RL) has become a key component in modern large language models, yet the rollout stage remains the key bottleneck in RL training pipelines. Although Multi-Token Prediction (MTP) offers a natural solution to accelerate rollouts through speculative decoding, many studies have observed that MTP acceptance rates degrade significantly during RL training, leading to limited speedup performance. To address this bottleneck, we present Bebop, a systematic study of MTP in LLM post-training, and offer practical recipes to integrate MTP into large-scale RL pipelines. First, we reveal that the MTP acceptance rate is fundamentally bounded by the fluctuation of model entropy, which demonstrates a clear negative linear relationship with the rise of entropy in the RL stage. Second, we show that probabilistic rejection sampling largely alleviates the disturbance introduced by entropy in RL compared to greedy draft sampling. We further identify that the conventional MTP training objectives (cross-entropy or KL) are suboptimal in such settings, and therefore we propose a novel end-to-end TV loss that directly optimizes multi-step rejection sampling acceptance rate, yielding ~10% acceptance rate improvements, achieving up to 95% acceptance rates and up to 25% extra inference throughput gains across mathematical reasoning, code generation, and agentic tasks. Third, we test various online MTP training strategies during RL and show that pre-RL MTP training with e2e TV loss and rejection sampling achieves a consistent acceptance rate and speedup throughout the entire RL, eliminating the need for costly online MTP updating. We provide extensive experiments and analysis that validate our findings. Experimental results show our method achieves up to 1.8x end-to-end acceleration in async RL training of Qwen3.5, Qwen3.6, and Qwen3.7 models.

阅读与讨论 → 访问原文 →

25.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2606.13513

CloudCons: A Comprehensive End-to-End Benchmark for Cloud Resource Consolidation

作者:

Xiaobin Zhang ↗Lefei Shen ↗Mouxiang Chen ↗Zhuo Li ↗Hongkai Li ↗Han Fu ↗Jianling Sun ↗Xiaoxue Ren ↗Chenghao Liu ↗

arXiv:2606.13513v1 Announce Type: new Abstract: Driven by conservative over-provisioning to guarantee service reliability, resource utilization in cloud data centers remains at low levels. To mitigate this, the forecast-then-optimize paradigm has emerged to optimize consolidation by anticipating future demands. While emerging time series foundation models promise to enhance this paradigm through zero-shot generalization, existing benchmarks focus solely on prediction error metrics. The actual decision utility of these advanced models remains unverified, rendering their practical value for downstream tasks uncertain. To bridge this gap, we propose CloudCons, a comprehensive end-to-end benchmark designed to evaluate forecasting models within the specific context of cloud resource consolidation. We build high-quality datasets that cover diverse workloads from Huawei Cloud, Microsoft Azure, and Google Borg, capturing distinct service characteristics ranging from synchronized diurnal rhythms to stochastic, pulse-like bursts and high-frequency noise. We conduct an extensive evaluation of statistical, deep learning, and foundation models. Our experiments reveal a pivotal finding: while foundation models demonstrate superior zero-shot forecasting accuracy, this advantage does not inherently translate into better decision utility. Of practical significance, we systematically analyze how the selection of predictive quantiles acts as a critical lever. We provide actionable guidelines for calibrating these selections to balance the trade-off between resource efficiency and service reliability, offering vital insights for real-world deployment decisions.

阅读与讨论 → 访问原文 →

探索全球前沿学术脉络