跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+0新增论文
+0其中 AI 相关
+0已有论文修订
+92新增 AI 导读

arXiv 最近完成扫描:2026-11-23 01:07 · 全站最近入库:2026-11-21 12:19各信源进度 →

统计口径与数据新鲜度

统计 2026-11-22 02:13 — 2026-11-23 02:13(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-23 01:07最近发现新增版本:2026-11-21 12:19库内论文最新更新时间:2026-11-20 02:59

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

29,158 已收录论文24,181 AI 相关8,992 有修订112 HF 社区发现

浏览论文库

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 4,643 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-23 01:05(北京时间)
版本更新 · v2arXiv:2602.04417

EMA策略梯度:用EMA锚点和Top-k KL驯服LLM强化学习

EMA Policy Gradient: Taming Reinforcement Learning for LLMs with EMA Anchor and Top-k KL

Lunjun Zhang, Jimmy Ba

AI 速读 基于摘要

作者提出用指数移动平均(EMA)锚点替代固定锚点策略,并引入Top-k KL估计器,与GRPO结合后在数学推理和智能体RL任务上取得性能提升。

cs.LG · cs.AI

查看原文摘要

Reinforcement Learning (RL) has enabled Large Language Models (LLMs) to acquire increasingly complex reasoning and agentic behaviors. In this work, we propose two simple techniques to improve policy gradient algorithms for LLMs. First, we replace the fixed anchor policy during RL with an Exponential Moving Average (EMA), similar to a target network in deep Q-learning. Second, we introduce Top-$k$ KL estimator, which allows for flexible interpolation between exact KL and sampled KL. We derive the stability conditions for using EMA anchor; moreover, we show that our Top-$k$ KL estimator yields both unbiased KL values and unbiased gradients at any $k$, while bringing the benefits of exact KL. When combined with GRPO, the two techniques (EMA-PG) lead to a significant performance boost. On math reasoning, it allows R1-distilled Qwen-1.5B to reach 53.9% on OlympiadBench compared to 50.8% by GRPO. On agentic RL domains, with Qwen-3B base, EMA-PG improves GRPO by an average of 35.6% across 7 datasets of Q&A with search engines, including 29.7% $\rightarrow$ 45.8% on HotpotQA, 27.4% $\rightarrow$ 40.5% on 2WikiMultiHopQA. Overall, we show that EMA-PG is a simple, principled, and powerful approach to scaling RL for LLMs. Code: https://github.com/LunjunZhang/ema-pg

新论文 · v1arXiv:2611.26617

一个先验,两种动力学:复用视频扩散Transformer进行自监督潜在动作学习

One Prior, Two Dynamics: Repurposing Video Diffusion Transformers for Self-Supervised Latent Action Learning

Yuxin Jiang, Wenqiang Sun, Jiaqi Li, Yuchao Gu, Lvmin Zhang, Ivor Tsang, Mike Zheng Shou

AI 速读 基于摘要

O²LaF 从同一个预训练视频 DiT 初始化逆动力学和正动力学模型,通过控制信息访问和端到端瓶颈优化,从无标签视频中学习可迁移的潜在动作。

cs.CV · cs.AI · cs.LG · cs.RO

查看原文摘要

Videos reveal how the world changes, but rarely the actions that cause those changes. Latent action learning recovers such supervision from visual transitions, yet often learns the underlying dynamics largely from scratch. We ask whether a pretrained video generator can instead provide the prior for both inverse and forward dynamics. We introduce O$^{2}$LaF, built on a simple principle: one prior, two dynamics. We initialize both models from the same pretrained video DiT and adapt them to their distinct roles: a feed-forward transition encoder with learnable action queries for inverse dynamics, and a causal, action-conditioned video generator for forward dynamics. By controlling information access and optimizing both dynamics end-to-end through a compact bottleneck, O$^{2}$LaF learns transferable actions from unlabeled videos. Across navigation and robotic manipulation, O$^{2}$LaF sets a new state of the art in few-shot action probing and enables stronger zero-shot action transfer across visual contexts and embodiments. Beyond generative video priors, we further extend our framework to predictive representation priors such as V-JEPA2, achieving competitive performance. Our findings suggest a broader paradigm for latent-action learning: repurposing pretrained video models to discover transferable actions and predict their consequences.

新论文 · v1arXiv:2611.26615

ScaleWorld:通过共享预测与细化实现高分辨率世界生成

ScaleWorld: High-Resolution World Generation through Shared Prediction and Refinement

Yansong Qu, Wesker Zheng, Quanjian Song, Zhiyuan Zhang, Xiao Cao, Shengchuan Zhang, Liujuan Cao

AI 速读 基于摘要

ScaleWorld 用一个共享骨干网络在单个因果视频模型中统一低分辨率世界预测与高分辨率细化,从而以更低计算和内存开销生成高分辨率世界视频。

cs.CV

查看原文摘要

High-resolution generation enables video world models to render fine-grained scene structures and textures, but directly generating high-resolution video incurs substantial computational and memory costs. We present ScaleWorld, a causal video model that unifies low-resolution world prediction and high-resolution refinement within a single shared backbone. By refining its own predictions, ScaleWorld produces high-resolution world videos without requiring a separate refinement model. For each video chunk, the shared backbone first completes a low-resolution prediction and then performs one-step high-resolution refinement conditioned on that prediction. To support efficient streaming generation, we maintain separate causal states with a long low-resolution history for prediction and a short high-resolution history for refinement. To address task interference during distillation, we separate specialist optimization from capability consolidation and introduce task-asymmetric on-policy distillation (TA-OPD). This procedure transfers prediction and refinement behaviors from specialized teachers into a shared student through local velocity matching under their respective sampling and history policies. {Extensive experiments demonstrate that ScaleWorld achieves high-quality world generation with improved computational and memory efficiency.

版本更新 · v2arXiv:2610.01054

用任务算子刻画上下文学习动态

Capturing In-Context Learning Dynamics with Task Operators

Guangzhi Xiong, Zhenghao He, Bohan Liu, Sanchit Sinha, Wenqian Ye, Aidong Zhang

AI 速读 基于摘要

作者提出任务算子(Task Operator),把上下文学习(ICL)中注意力头的仿射变换参数提取为对注意力输出投影的解析更新,从而在无需完整示例上下文的情况下近似 ICL 效果。

cs.CL · cs.AI · cs.LG

查看原文摘要

In-context learning (ICL) enables language models to perform new tasks from demonstrations without weight updates. However, every ICL inference requires processing the full set of examples, resulting in inefficient deployments, and how ICL works mechanistically is not fully understood. Prior work compresses ICL into fixed activation vectors extracted from specific layers or positions, but these input-independent interventions fail on complex tasks where the output depends on fine-grained interactions with the input. By analyzing the ICL forward pass, we show that each attention head's output is an affine transformation of its context-masked counterpart, and that the parameters of this transformation are empirically stable across samples for a given task. Building on this, we introduce Task Operator (TO), which replays this transformation as an analytically derived update to the attention output projection. Across lexical, algorithmic, and reasoning tasks, TO achieves the best overall performance among prior methods and substantially narrows the gap between zero-shot inference and ICL. We further show that the extracted knowledge concentrates in a task-specific sparse circuit across layers and positions, and that averaging operators from disjoint demonstration batches enables effective many-shot scaling without expanding the context window. Our code is available at https://github.com/gzxiong/task_operator.

新论文 · v1arXiv:2611.26595

Coda-DaVinci:用代码到视频重新构想视频生成

Coda-DaVinci: Reimagining Video Generation with Code2Video

Yiyan Ji, Qixun Wang, Yang Shi, Zhuoran Zhang, Yifan Xu, Tengfei Liu, Yuqi Tang, Xiaohan Zhang 等 23 位作者

AI 速读 基于摘要

通过受控实验揭示Code2Video中代理粒度、物理模拟和提示的权衡,并提出任务自适应多智能体框架Coda-DaVinci以提升视频生成质量。

cs.CV

查看原文摘要

Code2Video uses agent-authored 3D proxies to guide video generation, enabling explicit control over structure and dynamics. However, how to construct proxies and prompts for optimal downstream quality remains underexplored, as do the capabilities and limitations of this paradigm. Through controlled experiments and blinded human evaluation, we study proxy granularity, physics simulation, and prompting. The results reveal task-dependent trade-offs: coarse proxies favor natural motion, while medium-grained proxies favor consistency. Physics simulation and proxy-aligned prompting further improve average quality. Guided by these findings, we introduce Coda-DaVinci, a task-adaptive agentic framework for Code2Video generation that selects between proxy-guided and direct generation, adapts modeling granularity to each entity, and coordinates simulation with proxy-grounded prompting. Its multi-agent harness preserves scene assets and guides repairs through visual inspection and independent review. Experiments demonstrate leading instruction following on VTR and scene consistency on R2M, improved physical plausibility over direct generation, and higher visual realism than the compared Code2Video baselines. Long-video evaluations further show gains in event structure and consistency across successive interactions, while revealing limitations in transition stability and adherence to scene settings.

版本更新 · v2arXiv:2605.20158

重新审视大型视觉语言模型在胸部X射线推理中的视觉归因

Rethinking Visual Attribution for Chest X-ray Reasoning in Large Vision Language Models

Guangzhi Xiong, Qiao Jin, Sanchit Sinha, Zhiyong Lu, Aidong Zhang

AI 速读 基于摘要

作者通过因果评估框架发现现有视觉归因方法常无法识别LVLM在胸片推理中使用的证据,并提出基于概念的MedFocus方法以改善归因。

cs.CV · cs.AI · cs.CL

查看原文摘要

Large Vision Language Models (LVLMs) show promise in medical applications, but their inability to faithfully ground responses in visual evidence raises serious concerns about clinical trustworthiness. While visual attribution methods are widely used to explain LVLM predictions, whether these explanations actually reflect the visual evidence underlying the model's decision is largely unverified, since ground-truth annotations for internal model reasoning are typically unavailable. We address this question for chest X-ray (CXR) reasoning by developing a causal evaluation framework that retains only CXR-VQA samples for which the expert-annotated region is verified, via counterfactual editing, to be causally responsible for the model's prediction. Using this framework across 11 attribution methods, six open-source LVLMs, and two output modes (direct answer and step-by-step reasoning), we find that existing attribution methods often fail to identify the evidence used by LVLMs. To address this failure, we propose MedFocus, a concept-based attribution method that localizes clinically meaningful anatomical regions via unbalanced optimal transport and measures their causal effect on model outputs through targeted interventions. MedFocus produces spatial, concept-level, and token-level attributions and substantially outperforms prior methods, taking a step toward more trustworthy attribution for medical LVLMs. Our data and code are available at https://github.com/gzxiong/medfocus/.

新论文 · v1arXiv:2611.26569

文本感知、视觉盲区:多模态图像编辑系统如何处理不安全输入

Text-Aware, Vision-Blind: How Multimodal Image Editing Systems Handle Unsafe Inputs

Ziqing Yang, Yixin Wu, Michael Backes, Yang Zhang

AI 速读 基于摘要

作者构建 EditSafetyBench 基准,发现主流图像编辑系统存在系统性的文本-视觉安全错配:对不安全文本指令拒绝率高,但对携带风险的不安全图像拒绝率低。

cs.CR · cs.CV · cs.LG

查看原文摘要

Multimodal image generation systems have made rapid progress and increasingly emphasize content safety. However, their safety mechanisms tend to rely on a single modality and lack joint consideration of both visual content and text prompts, particularly in instruction-guided image editing, where the uploaded image may itself carry risk. We thus introduce EditSafetyBench, a benchmark that measures system-level safety awareness of advanced image editing systems, containing 5,940 image-instruction pairs, covering safe and unsafe images across 11 risk categories and three edit intents. We then probe the benchmark dataset on four systems, including Gemini, GPT, Qwen API, and Qwen Local. Based on our evaluation, we observe a systematic text-vision safety mismatch: Gemini and GPT refuse 87.1\% and 81.6\% cases containing unsafe-intent editing prompts, while only refusing 24.2\% and 22.4\% cases with both unsafe images and neutral instructions. At the category level, most risks are considered inconsistently by different systems, e.g., GPT allows 70.4\% editing attempts of unsafe political content while Gemini only allows 34.8\%. Notably, sexual content shows the strongest visual sensitivity, likely benefiting from mature NSFW identification works. Our findings highlight the need for safety guardrails that jointly reason over both visual and textual modalities in image editing systems.

版本更新 · v4arXiv:2605.29486

PhoneWorld:从真实应用轨迹到动态可验证的手机智能体环境

PhoneWorld: From Real-App Trajectories to Dynamic and Verifiable Environments for Phone-Use Agents

Yuxuan Liu, Xin Lai, Junyi Li, Pengyuan Lyu, Chenxin Li, Yiduo Guo, Zhengyao Fang, Yang Ding 等 24 位作者

AI 速读 基于摘要

PhoneWorld 将真实应用轨迹转化为可运行、可重置、可验证的 Android 环境,用于手机智能体的训练与评测。

cs.CL · cs.AI · cs.LG

查看原文摘要

Real applications provide the training setting closest to phone-agent deployment, but are difficult to reset, scale safely, and verify programmatically. Static screenshots and interaction trajectories preserve realistic evidence but cannot generate new experience. We introduce PhoneWorld, a trace-grounded framework that converts such evidence into runnable, resettable, and verifiable Android environments. PhoneWorld induces a usage-weighted interaction skeleton from observed pages, transitions, and state-changing operations; translates it into a behavior-grounded app specification; realizes the specification through an autonomous build--inspect--repair loop; and synthesizes executable tasks with programmatic verifiers. The resulting suite spans 34 consumer-facing apps across 16 domains and supports an audited online benchmark, verified trajectory generation, and online RL through common reset and verification interfaces. Evaluations with diverse general and open-source GUI agents show that PhoneWorld supports reliable end-to-end online interaction and exposes capabilities complementary to AndroidWorld. Controlled SFT experiments further show that PhoneWorld trajectories complement AndroidWorld supervision, transfer across online and offline benchmarks, and become more effective as data volume and app coverage increase. Under a matched RL budget, combining PhoneWorld mock-app rollouts with real-app rollouts improves performance over real-app RL alone on both real-phone tasks and AndroidWorld. Together, these results demonstrate that trace-grounded executable abstraction can bridge realistic mobile behavior and scalable agent learning, turning limited real-app evidence into a growing supply of controllable and verifiable environments for training and evaluation.

版本更新 · v2arXiv:2411.13711

马尔可夫噪声下随机逼近与强化学习的几乎必然收敛速率与集中不等式

Almost Sure Convergence Rates and Concentration of Stochastic Approximation and Reinforcement Learning with Markovian Noise

Xiaochi Qian, Zixuan Xie, Xinyu Liu, Shangtong Zhang

AI 速读 基于摘要

该论文为马尔可夫噪声下的收缩随机逼近算法建立了首个几乎必然收敛速率和首个具有次Weibull尾部的最大集中不等式,并应用于Q学习和离策略时序差分学习。

cs.LG · math.OC · stat.ML

查看原文摘要

This paper establishes, to our knowledge, the first almost sure convergence rate and the first maximal concentration bound with sub-Weibull tails for general contractive stochastic approximation algorithms with Markovian noise. As a corollary, we also obtain convergence rates in $L^p$. Key to our successes is a novel discretization of the mean ODE of stochastic approximation algorithms using intervals with diminishing (instead of constant) length. Applications yield the first almost sure convergence rate for $Q$-learning without count-based learning rates and the first maximal concentration bound for off-policy temporal difference learning, both with Markovian samples.

版本更新 · v3arXiv:2609.39601

GroundingPI:面向物理智能的视觉基元定位基础模型

GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives

Qize Yu, Lianrui Fan, Boyu Chen, Jiaqi Liang, Xini Ding, Yue Chen, Zetian Song, Yuran Wang 等 26 位作者

AI 速读 基于摘要

作者提出一个4B参数的定位基础模型GroundingPI,以点和框作为共享词表中的量化坐标,在34个定位基准上取得领先,并作为视觉骨干提升机器人与自动驾驶下游任务表现。

cs.CV · cs.AI · cs.LG · cs.RO

查看原文摘要

Precise grounding matters. It specifies which object is the target and where that object is, even in clutter and for tiny objects, and it has to be fast enough for closed-loop control. Yet vision-language-action (VLA) and world-action models (WAMs) take perception from general-purpose vision-language and video-generation backbones, which still fail in these settings. We introduce GroundingPI, a 4B grounding foundation model that generates points and boxes as quantized coordinates in a shared vocabulary. Training combines multimodal and spatial pretraining, supervised fine-tuning, and reinforcement learning with GRPO, using supervision from public datasets and dedicated data engines. Against 44 baselines across 34 grounding benchmarks spanning 11 perceptual capabilities, GroundingPI establishes a new state of the art, averaging 73.68%, above the larger GPT-6 Astra (71.54%). As a downstream visual backbone, GroundingPI improves performance on robotic manipulation and autonomous driving. Across RoboTwin 2.0 and RoboCasa-GR1, it outperforms all evaluated backbones in all four out-of-distribution settings, with relative gains of up to 24.8% over the strongest baseline. On RoboCasa-GR1, GroundingPI trained with 50% of the demonstrations outperforms those baselines trained with 75%. Its mean open-loop L2 error on nuScenes is 0.296 m. We systematically analyze GroundingPI's pretraining in scale and data composition. Grounding quality and downstream manipulation improve with pretraining scale, with generalization tracking perceptual gains most closely. Analyzing the data recipe across these 11 perceptual capabilities shows dense grounding's substantial benefits for both, and OCR's potential as a catalyst for perceptual learning. These results support grounding as a perceptual foundation, and dedicated perceptual pretraining as a promising direction for foundation models of physical intelligence.

新论文 · v1arXiv:2611.26519

ACE-Brain-0.7:为具身智能体学习基于执行的推理

ACE-Brain-0.7: Learning Execution-Grounded Reasoning for Embodied Agents

Yinhe Wang, Shijun Shi, Feng Pan, Tao Tao, Wei Mao, Jiangning Zhang, Zhiyao Ren, Yihang Jiao 等 14 位作者

AI 速读 基于摘要

作者提出一个9B视觉语言模型ACE-Brain-0.7,通过融合空间定位、任务理解和进度估计,在多个公开基准上取得优于部分闭源模型的执行感知推理表现。

cs.RO

查看原文摘要

Reliable reasoning for long-horizon embodied tasks requires predictions grounded in the observed execution state. We present ACE-Brain-0.7, a 9B vision--language model that combines spatial grounding, task understanding, and progress estimation. To train the model, we curate 3.7 million question--answer pairs, drawing execution supervision from egocentric human videos, robot episodes, and simulation. These questions span different stages of an execution and connect task-level judgments with observed progress and outcomes. We then fine-tune Qwen3.5-9B on this collection together with additional task, spatial-grounding, and progress-estimation data. Across six public task-reasoning benchmarks, ACE-Brain-0.7 achieves an average score of 76.5, ahead of GPT-6 Astra at 72.7 and Claude Opus 5.5 at 73.5. Our model also leads the evaluated models in spatial grounding, averaging 75.90 across seven benchmarks and reaching 91.25 Acc@0.5 on RefCOCOg. Controlled evaluations further indicate that our task-only model makes more effective use of visual history and more accurately distinguishes execution states. Together, these results show that ACE-Brain-0.7 effectively combines spatial perception with temporal understanding, delivering strong execution-grounded reasoning and comparing favorably with closed-source models.

新论文 · v1arXiv:2611.26516

Plan4D:可生成规划的四维世界

Plan4D: Generative Plannable 4D Worlds

Hangwei Zhang, Rujing Dang, Ruimin Lin, Jiahong Wu, Xiangxiang Chu, Chuanxia Zheng

AI 速读 基于摘要

Plan4D 通过拼接视频生成器与三维重建器,从场景上下文和文本动作生成带稠密四维几何的未来 RGB 视频。

cs.CV

查看原文摘要

Most world models for future prediction prioritize aestetic quality of generated videos, but offer only weak physical grounding and limited geometric consistency over time, due to the lack of explicit 4D modeling. In this paper, we introduce plan4d, a possible next milestone towards building a generative plannable 4D world model that predicts future RGB videos together with dense 4D geometry, including depth, cameras, point clouds, and scene flow from an observed scene context and text-specified actions. Since training data with paired actions and dense 4D annotations is inherently scarce, plan4d leverages the complementary priors of foundational video generators and 3D reconstructors. Specifically, we propose a model-stitching architecture that couples Depth Anything 3 with LongCat-Video and augments it with an auxiliary DPT head for scene-flow prediction. The resulting model allows us to plan and generate complex, long-horizon, and fine-grained actions in a dynamic 3D scenes, while substantially improving both visual fidelity and geometric accuracy of the generated future videos. Extensive experiments on both synthetic and real-world datasets demonstrate that plan4d achieves state-of-the-art performance in generative 4D modeling of environmental reactions. Project Page: https://fogradio.github.io/plan4d-project

新论文 · v1arXiv:2611.26511

Direct3D-V3:原生体素域中的无潜变量扩散Transformer

Direct3D-V3: Latent-Free Diffusion Transformers in the Native Voxel Domain

Shuang Wu, Jiachen Qian, Youtian Lin, Feihu Zhang, Philip Torr, Yao Yao, Xun Cao

AI 速读 基于摘要

Direct3D-V3提出一种无需VAE的扩散Transformer框架,直接在原生SDF体素网格上训练和采样,并通过隐式流形正则化与相机参数预测提升几何质量与图像对齐。

cs.CV

查看原文摘要

Native 3D generation has largely been built around latent diffusion, with recent advances concentrating on stronger variational autoencoders (VAE) and increasingly elaborate latent representations, from vecset and triplanes to structured sparse voxels. Despite their architectural differences, these methods all share the same premise: geometry is first compressed into a latent space and only then modeled by the generator. We take a different route and propose Direct3D-V3, a latent-free diffusion transformer (DiT) framework that discards the VAE altogether and operates in the native voxel domain, directly modeling raw SDF voxel grids during both training and sampling. To make this direct voxel formulation geometrically reliable, we introduce an implicit manifold regularization over neighboring voxels to suppress non-watertight surfaces, and convert predicted SDF grids into meshes via Marching Cubes so that rendered normal losses can supervise the model directly from its predicted SDF. To improve alignment between the conditioning image and generated geometry, Direct3D-V3 also predicts the camera parameters of the conditioning image as an auxiliary task, encouraging the DiT to learn the mapping from image observations to 3D shape. This latent-free design removes the reconstruction bottleneck, brings training under an objective in the native voxel domain, and yields meshes with substantially richer local detail. The predicted camera and native SDF voxel output further make Direct3D-V3 extensible to generative reconstruction, where diffusion is interleaved with normal-guided refinement to improve alignment with the observed view while the generative prior completes unseen regions. Project page: https://dreamtechai.github.io/Direct3D-V3.

版本更新 · v3arXiv:2609.39600

GroundAnything:以极速并行解码实现精准视觉定位

GroundAnything: Reconciling Parallel Decoding with Precise Visual Grounding at Flash Speed

Qize Yu, Lianrui Fan, Bowen Ping, Xini Ding, Zetian Song, Junbo Niu, Kaixuan Wang, Tianxing Chen 等 22 位作者

AI 速读 基于摘要

提出4B参数的视觉定位基础模型GroundAnything,用块级去噪的双向扩散并行解码替代自回归串行生成,在30个定位基准上兼顾精度与速度。

cs.CV · cs.AI · cs.LG · cs.RO

查看原文摘要

Autoregressive (AR) grounding models serialize spatial predictions, introducing sequential latency and imposing a causal order on output tokens. We view grounding as visual evidence extraction: objects, locations, and spatial relations are jointly constrained by the image and query, yet their dependencies do not imply an intrinsic left-to-right generation order. This distinction makes bidirectional diffusion a natural fit, allowing spatial hypotheses to emerge in parallel and be jointly refined through iterative denoising. We introduce GroundAnything, a 4B-parameter grounding foundation model that reconciles fast parallel decoding with precise localization through blockwise denoising. Training combines grounding pretraining from public datasets and dedicated data engines, direct AR-to-diffusion conversion with joint AR and diffusion objectives, supervised fine-tuning, and GRPO-based reinforcement post-training. Across 30 grounding benchmarks, our autoregressive variant, GroundAnything-VLM, establishes a new overall state of the art among similarly sized models at 72.42%, remaining competitive with GPT-6 Astra (71.35%). With entropy-guided decoding, GroundAnything also surpasses the prior state of the art at this scale, averaging 61.75% versus 53.32% for the fast MTP-based LocateAnything model. We further explore decoding strategies, showing that an optional self-speculative mode achieves a 4.51$\times$ speedup over the AR counterpart with a 0.74 percentage-point drop in COCO F1mIoU. Infrastructure experiments show that progressive inference optimizations translate parallel decoding into practical speedups. These gains support efficient visual grounding in latency-sensitive real-world systems.

版本更新 · v3arXiv:2509.26442

Robbins-Siegmund 定理的扩展及其在强化学习中的应用

Extensions of Robbins-Siegmund Theorem with Applications in Reinforcement Learning

Xinyu Liu, Zixuan Xie, Shangtong Zhang

AI 速读 基于摘要

作者将 Robbins-Siegmund 定理中零阶项可和的条件放宽为平方可和,并引入对增量温和的新假设,从而建立几乎必然收敛到有界集及多种收敛速率,并应用于随机逼近与强化学习。

cs.LG · math.OC

查看原文摘要

The Robbins-Siegmund theorem establishes the convergence of stochastic processes that are almost supermartingales and is one of the most commonly used approaches for analyzing stochastic iterative algorithms in stochastic approximation and reinforcement learning (RL). However, its original form has a significant limitation as it requires the zero-order term to be summable. In many important RL applications, this summable condition, however, cannot be met. This limitation motivates us to extend the Robbins-Siegmund theorem for almost supermartingales where the zero-order term is not summable, but only square-summable. In particular, we introduce a novel and mild assumption on the increments of the stochastic processes. This together with the square-summable condition enables an almost sure convergence to a bounded set. Additionally, we further provide almost sure convergence rates, high probability concentration bounds, and $L^p$ convergence rates. We then apply the new results to stochastic approximation and RL. Notably, we obtain the first almost sure convergence rate, the first high probability concentration bound, and the first $L^p$ convergence rate for $Q$-learning with linear function approximation.

版本更新 · v2arXiv:2609.38169

STEPQuant:Delta规则循环状态量化中误差何时何地重要

STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantization

Bingchen Yao, Haobo Xu, Haokun Lin, Yichen Wu, Ziyu Guo, Renrui Zhang, Zhichao Lu, Zhenan Sun 等 9 位作者

AI 速读 基于摘要

STEPQuant 是一种面向 Delta 规则循环状态的空间-时间训练后量化框架,依据误差大小与内存寿命分配精度,并联合拟合键行与值列缩放。

cs.CL · cs.AI · cs.LG

查看原文摘要

Linear attention replaces growing KV caches with fixed-size recurrent states, yet these persistent states can become a substantial memory bottleneck under concurrent serving. Directly quantizing recurrent states to low precision often leads to severe accuracy degradation, as quantization errors propagate through successive state updates. We discover that the impact of these errors depends on two complementary dimensions: temporally, errors in long-lived memory can persist across many decoding steps; spatially, errors in different key rows affect model outputs differently, while state magnitudes vary substantially along both rows and columns. Motivated by these observations, we propose STEPQuant, a spatial-temporal post-training quantization framework for Delta-rule recurrent states. STEPQuant allocates precision according to error magnitude and memory lifetime, and jointly fits key-row and value-column scales based on state distributions and key-row impact on output error. Experiments on Qwen3.8-27B and Kimi-Linear-48B-A3B-Instruct across both long- and short-generation benchmarks show that STEPQuant closely matches FP32-state accuracy under a nominal 6-bit budget and outperforms uniform INT8 in its 4-bit configuration. Integrated into SGLang with optimized GPU kernels, 6-bit STEPQuant achieves over 5x recurrent-state compression and reduces total serving memory by up to 68.7%. Our code is available at https://github.com/Dreamer-Toby/STEPQuant.

版本更新 · v3arXiv:2602.07643

分割基础模型在结构与功能医学影像间的泛化能力如何?

How Well Do Segmentation Foundation Models Generalize Across Structural and Functional Medical Imaging?

Yichi Zhang, Le Xue, Feiyang Xiao, Wenbo Zhang, Gang Feng, Chenguang Zheng, Yuan Qi, Yuan Cheng 等 9 位作者

AI 速读 基于摘要

作者构建配对的PET/CT与PET/MRI全身多器官数据集UMD,并直接比较五个代表性3D分割基础模型在结构与功能影像上的开箱即用表现。

cs.CV

查看原文摘要

Segmentation foundation models offer reusable tools for universal medical-image segmentation, but their development and evaluation have largely centered on structural CT and MRI imaging. Functional imaging such as PET provides complementary metabolic information yet remains less studied and validated. Moreover, existing evaluations often involve different datasets and tasks, making modality-associated variation difficult to distinguish from differences in segmentation targets and data distributions. To enable a more direct comparison, we introduce UMD, a whole-body multi-organ dataset comprising 490 PET/CT and 464 PET/MRI examinations with 13 annotated organs (approximately 675,000 2D slices and 12,000 3D organ annotations). UMD evaluates structural and functional images separately on corresponding organs within the same examination, reducing variation in patient anatomy and target selection. We benchmark the out-of-the-box segmentation capabilities of five representative 3D foundation models on UMD. Overall, most evaluated models show limited PET segmentation performance, and some configurations also yield near-zero overlap on CT or MRI under the evaluated workflows. These findings highlight the need to assess tool applicability across different imaging conditions and identify opportunities for cross-modality generalization. UMD provides a paired data resource and evaluation setting for this investigation.

新论文 · v1arXiv:2611.26444

Mind2Act World:面向机器人操作中具身心智、物理动作与心智-动作组合的诊断基准

Mind2Act World: A Diagnostic Benchmark for Embodied Mind, Physical Action, and Mind-Action Composition in Robotic Manipulation

Yuzhi Huang, Jie Wu, Fanding Huang, Junchao Lin, Weichen Zhang, Ziyi Xiong, Yang Li, Zhengwei Xie 等 43 位作者

AI 速读 基于摘要

作者提出一个包含30个仿真操作任务、180种配置的诊断基准,用Mind、Act、Mind2Act三个视图区分系统是缺少某种能力还是无法组合已有能力。

cs.RO · cs.AI · cs.CV

查看原文摘要

Embodied intelligence aims to let robots perform complex physical tasks with human-like adaptability and reliability, which requires three complementary capabilities: history-based cognitive reasoning, precise and timely physical execution, and the composition of reasoning and execution through environmental feedback. Yet existing benchmarks either evaluate reasoning and execution within the same tasks or assess them separately without their composition, so they reveal little about whether a failure comes from reasoning, execution, or their composition. We introduce Mind2Act World, a diagnostic benchmark of 30 simulated manipulation tasks from five real-world application domains. Each task has three difficulty levels and two scene settings (Clean and Random), yielding 180 configurations. The tasks form three views: Mind tests decisions based on past observations, Act tests precise and timely execution, and Mind2Act combines both in closed-loop tasks where action outcomes guide later decisions. Comparing the three views shows whether a system lacks a capability or fails to compose capabilities it already has. A diagnosis harness further attributes the failed episodes of three representative systems to Mind, Act, or their composition and summarizes each system in a profile card. Our evaluation of multimodal agents, vision-language-action models (VLAs), and world-action models (WAMs) shows that competence in a single view does not carry over to Mind2Act tasks. Even the strongest agent succeeds in 52.7% of Mind and 39.0% of Act episodes but in only 12.0% of Mind2Act episodes. The strongest agent retains task state but struggles with sustained contact, whereas end-to-end policies execute practiced motions but retain little task state. These findings point to composing reasoning and execution through environmental feedback as the main open problem.

新论文 · v1arXiv:2611.26434

HumanCOIN:面向第一人称操作中人类意图的12,500小时数据集

HumanCOIN: A 12,500-Hour Dataset for Human Intent in Egocentric Manipulation

Shihan Wu, You Liu, Chunyu He, Minghui Qin, Longhan Jiao, Jinbang Guo, Shaoxuan Xie, Kaixi Tian 等 51 位作者

AI 速读 基于摘要

HumanCOIN 是一个围绕人类意图构建的第一人称操作数据集,通过三层代理信号(注视、肌电、脑电)在万小时规模上记录从决策到动作的意图通路。

cs.CV · cs.RO

查看原文摘要

First-person manipulation datasets treat the observation-action pair as the atomic unit and compress the generation and execution of an action into a policy network's weights, rendering the intent state behind the action unobservable. Human motor control research shows that intent mediates between observation and action and leaves observable traces along the intent pathway from decision to effect: gaze reaches the target before the hand, muscle load builds before contact, and cortical activity precedes the motor command. To record this pathway at scale, we present HumanCOIN, a first-person manipulation dataset built around human intent: 12,500 hours across 38 scene classes with three tiers of proxies. At the output end, the L1 attention tier (10,000 h) infers gaze from headband camera video, exposing the operator's next object of attention and reach before the hand moves. Midway, the L2 exertion tier (2,000 h) records surface EMG from armbands, making load expectations readable before execution is complete. At the origin, the L3 cognition tier (500 h) records scalp EEG, giving early readouts of task decisions and monitoring. Each tier inherits all proxies from the tiers below. The dataset further provides multi-view RGB images, depth maps and point clouds, 6-DoF head and wrist pose, and step-level action and object annotations. The controlled L3 setting additionally measures gaze, hand pose and finger kinematics directly. Clock and calibration data are released with the dataset so that any read rate can be re-aligned. The three tiers cover three stations, from visual orienting to cortical preparation, making the process behind visual-action pairs available for modeling at dataset scale. Project page: https://flagopen.github.io/HumanCOIN.

新论文 · v1arXiv:2611.26427

MemFolder:面向高效智能体记忆管理的结构引导记忆折叠

MemFolder: Structure-Guided Memory Folding for Efficient Agent Memory Management

Xuyang Liu, Chenwen Lu, Junxi Wang, Siyu Ren, Xinying Lin, Siteng Huang, Hongli Sun, Linfeng Zhang 等 9 位作者

AI 速读 基于摘要

MemFolder 通过结构引导的记忆折叠,依次减少记录数量和上下文长度,以降低长期智能体的存储、检索与生成成本。

cs.CL · cs.CV

查看原文摘要

Long-term agents accumulate large external memory stores as interactions unfold, increasing the costs of storage, retrieval, and response generation. Efficiency is constrained by two coupled factors: a growing record count increases retrieval overhead, while longer retrieved contexts increase prefill computation and decoding-time attention costs. Existing methods prune or consolidate records, but pruning can discard useful evidence, whereas consolidation may produce fewer yet longer retrieval units. We introduce MemFolder, a structure-guided memory folding framework that sequentially reduces record count and context length. The framework comprises two core components that share memory groups, using cross-record structure to guide both evidence consolidation and compact representation. RecordFolder grounds entity mentions, progressively selects representative yet complementary anchors, and combines semantic and entity affinity with temporal chaining to consolidate compatible records into fewer retrieval units. ContextFolder encodes the original records within these groups into compact text and uses verification feedback to revise encodings when key facts cannot be recovered. Experiments on the three text-based memory benchmarks LoCoMo, PersonaMem, and LongMemEval and the two multimodal benchmarks M3-Bench-web and M3-Bench-robot demonstrate the strong performance of our methods. Notably, on Mem0, RecordFolder retains 99.0% of the original average performance across the three text-based benchmarks with 50% fewer records, exceeding the strongest baseline by 1.9 percentage points in performance retention. Combined with ContextFolder, existing record compression methods further shorten their output records while retaining most of their performance.

新论文 · v1arXiv:2611.26422

基于大语言模型推理轨迹分析的可解释Q矩阵构建

Reasoning-Trace Analysis Using Large Language Models for Interpretable Q-Matrix Construction

Jihong Zhang, Zijing Jin, Mingfeng Xue

AI 速读 基于摘要

提出推理轨迹分析(RTA)框架,通过链式思维提示让大语言模型生成属性标注的推理步骤,以重建、比较和检查Q矩阵的每个项目-属性分配,并报告了模拟与实证研究结果。

cs.AI

查看原文摘要

Large language models (LLMs) can generate Q-matrices for diagnostic classification models that approximate expert specifications, but evaluations have focused on the final matrices, leaving the basis of individual item-attribute assignments unexamined. This opacity limits the responsible use of AI in measurement. We propose Reasoning-Trace Analysis (RTA), a framework in which an LLM generates attribute-labeled reasoning steps through chain-of-thought (CoT) prompting and these steps are analyzed to reconstruct, compare, and inspect each assignment. RTA is intended to supplement expert review and empirical validation. In a simulation study with perturbed fraction subtraction items, four LLMs recovered the required attributes and withheld attributes the items did not require. In an empirical study with 11 fraction subtraction items, responses from 536 examinees, four LLMs, up to three temperatures, and 100 replications per condition, CoT-derived Q-matrices overlapped substantially with the reference Q-matrix (mean overlap .809) but less than directly generated Q-matrices (.877), and they varied more across replications. Inspection of the traces linked disagreements to item-type coding, labeling rules, and how operations were expressed as steps. Q-matrices with similar overlap differed in fit to examinee responses. RTA provides inspectable evidence that matrix-level agreement and fit do not.

新论文 · v1arXiv:2611.26414

ZeroVLN:无需对VLM大脑进行监督微调的导航学习

ZeroVLN: Learning to Navigate without Supervised Fine-Tuning of the VLM Brain

Zixuan Huang, Yang Zhou, Guli Zhang, Sunzhu Li, Hongyan Xie, Zehao Chen, Fuzhen Zhuang, Kaixuan Wang 等 11 位作者

AI 速读 基于摘要

ZeroVLN 提出慢-快导航框架,让 VLM 大脑通过语义工具调用接口下达自然语言移动指令,并在不对 VLM 大脑做导航域监督微调的情况下,用闭环强化学习联合优化大脑决策与动作专家执行。

cs.AI

查看原文摘要

Representative vision-language navigation (VLN) methods typically couple a vision-language model (VLM) brain with a learnable action head and fine-tune the VLM brain on navigation-domain data to predict geometric goals. However, such adaptation can substantially alter base VLM weights and degrade general visual capabilities. We introduce ZeroVLN, a slow-fast navigation framework that achieves effective navigation with zero navigation-domain SFT of the VLM brain. Rather than teaching the brain to predict geometric goals, we equip it with a semantic tool-calling interface for conveying movement decisions to an action expert in natural language. We first adapt the action expert to carry out these movement requests, then jointly improve the brain's movement decisions and the action expert's continuous execution through closed-loop reinforcement learning (RL). Trained on the same navigation episodes, ZeroVLN substantially outperforms representative SFT-based hierarchical VLN methods on standard VLN-CE (continuous environments) benchmarks, while inducing only minor changes to the brain's weights and largely preserving its general capabilities. To our knowledge, ZeroVLN is the first slow-fast VLN framework with zero navigation-domain SFT of the VLM brain, and the first to jointly optimize its slow and fast policies through closed-loop agentic RL in VLN-CE.

新论文 · v1arXiv:2611.26409

WeMM-Video: Pushing the Frontiers of Open-Source Omni-Modal Video Understanding

Changli Tang, Jie Yang, Tianyi Wang, Lei Li, Daoze Zhang, Zijie Xin, Zhan Liu, Li Li 等 12 位作者

原文摘要

Video understanding, particularly with accompanying audio, remains a central challenge in multimodal intelligence. In this report, we introduce \textbf{WeMM-Video}, a family of Chinese-English bilingual omni-modal foundation models spanning 2B, 4B, 9B, and 35B-A3B variants. Centering on joint audio-visual perception and reasoning, WeMM-Video unifies text, image, audio, and video processing within a hybrid-thinking paradigm, seamlessly supporting both a non-thinking instruct mode for fast, direct responses and a thinking mode for explicit step-by-step reasoning. The models are trained on a large-scale multimodal corpus of approximately 1.2 trillion tokens through progressive pre-training and a multi-stage post-training pipeline incorporating multi-teacher OPD, anti-repetition MrDPO, and specialist RL. Evaluated across more than 120 benchmarks, WeMM-Video demonstrates superior performance in omni-modal video understanding and reasoning, while maintaining highly competitive capabilities across general audio, silent video, image, and text tasks. Specifically, in omni-modal video evaluations, our flagship WeMM-Video-35B-A3B establishes a new open-source state of the art, substantially outperforming proprietary models such as Qwen3.5-Omni-Flash and Seed2.0-Mini-0428 while narrowing the gap with the strong Gemini-3.0-Flash, and our compact WeMM-Video-9B surpasses the larger open-source Qwen3-Omni-30B-A3B-Instruct. We publicly release the WeMM-Video family along with our evaluation and reproduction pipeline to foster further research and development in the open-source community.

cs.CV · eess.AS

新论文 · v1arXiv:2611.26405

TacInno:让视觉-语言-动作模型学习视觉与动作之外的接触动力学

TacInno: Teaching Vision-Language-Action Models the Contact Dynamics Beyond Vision and Action

Weile Li, Yunfan Lou, Muqing Shi, Zihao Zhang, Zhenbiao Huang, Boxian Yao, Xiyu Zhu, Zhibo Pang

AI 速读 基于摘要

TacInno 把视觉观测与已执行动作无法解释的触觉变化(触觉创新)作为训练目标,让 VLA 策略预测该离散编码,部署时不增加额外模块。

cs.RO · cs.CV

查看原文摘要

Vision-Language-Action (VLA) models have recently been equipped with tactile sensing to perceive visually subtle contact events in contact-rich manipulation. However, adding tactile input yields inconsistent gains, and some visuo-tactile VLA models rely little on tactile input, because much of the tactile change, such as the gel deformation during gripper closure, is predictable from visual observations and executed actions. To address this problem, we introduce TacInno, which isolates the contact dynamics that vision and executed actions cannot explain, termed tactile innovation, and uses tactile innovation only as a training target. Specifically, the TacInno tokenizer, conditioned on visual observations and executed actions, compresses the future tactile change into a discrete code, and the policy, TacInno-VLA, learns to predict the code, adding no module for the code at deployment. TacInno-VLA achieves average success rates of 87.5% across six simulation tasks and 70.5% across four real-world tasks, outperforming the strongest visuo-tactile baseline by 10.7 and 9.0 percentage points, respectively. Ablation studies validate the contributions of visual and action conditioning, multi-frame encoding, and auxiliary code prediction. Together, these results demonstrate the effectiveness of tactile innovation as a supervision signal for contact-rich manipulation.

新论文 · v1arXiv:2611.26389

ViDecide:教视频扩散模型逐步推理与规划

ViDecide: Teaching Video Diffusion Models to Reason and Plan Step by Step

Kaiwen Zhang, Yiming Gao, Zeqi Xiao, Xintao Wang, Pengfei Wan, Kun Gai, Xingang Pan

AI 速读 基于摘要

ViDecide 将视频生成训练从固定长度片段预测转变为以决策为中心的框架,通过预测状态转移和停止决策,显著提升多步推理与规划任务的成功率。

cs.CV

查看原文摘要

Current leading video generation models can synthesize highly realistic videos, while still frequently violating physical and logical constraints in multi-step reasoning and planning, even after training with large-scale reasoning data or existing diffusion RL methods. We attribute these failures to the conventional video training paradigm, which treats a solution as a fixed-length clip rather than a chain of decisions. We present ViDecide, a decision-centric framework that trains video diffusion models to predict state transitions causally and decide when to stop, with a decision-focused training schedule. We further propose Corrective Fine-tuning (CFT), which corrects failed decisions by mapping their noise to the model's own successful continuations, achieving stable improvement without policy-gradient optimization. Across abstract games, planning tasks, and a new benchmark of multi-step robot planning, ViDecide achieves an average strict success rate of 83.8%, far above 23.3% for standard fine-tuning and 67.8% for the strongest prior method, and generalizes to larger puzzles and unseen layouts. Our framework therefore unlocks greater potential for video generation models as reliable reasoners and planners in the visual world. Project page: https://kevin-thu.github.io/ViDecide.

版本更新 · v2arXiv:2605.17170

TriAxialKV:面向智能体推理任务的极低精度 KV 缓存量化

TriAxialKV: Toward Extreme Low-Precision KV-Cache Quantization for Agentic Inference Tasks

Hanzhang Shen, Haoran Wu, Yiren Zhao, Robert Mullins

AI 速读 基于摘要

作者提出按时间、模态、语义角色三轴为每个 token 打标签并校准敏感度,在固定显存预算下分配 INT2/INT4 位宽,实现智能体推理的混合精度 KV 缓存量化服务系统。

cs.LG

查看原文摘要

Agentic workloads have emerged as a major workload for LLM inference. They differ significantly from chat-only workloads, requiring long-context processing, the ability to handle multimodal inputs, and structured multi-turn interactions with tool calling capabilities. As a result, their context exhibits structure that can carry different importance along three key axes: temporal recency to the current turn, modality such as text or image tokens, and semantic role such as user queries, tool calls, observations, or reasoning. These axes capture distinct token behaviors and lead to different sensitivities to KV-cache compression. However, existing KV-cache quantization methods are typically homogeneous or exploit only heterogeneity on a single dimension, such as temporal proximity or modality, overlooking the interactions among them. To this end, we introduce TriAxialKV, a novel mixed-precision KV-cache quantization scheme that assigns each token a triaxial tag, calibrates per-tag sensitivity, and allocates INT2/INT4 bit-widths under a fixed memory budget. We implement TriAxialKV as an end-to-end serving system, comprising calibration, mixed-precision quantization and memory management, and custom fused Triton decode kernels. When using Qwen3-VL-32B-Thinking as a computer-use agent operating the OSWorld, TriAxialKV matches the accuracy of SGLang with BF16 KV cache while supporting 4.5$\times$ KV cache capacity and achieving 30% higher end-to-end throughput, when running on real GPU systems.

新论文 · v1arXiv:2611.26380

EgoCaptioner:面向全面且细粒度的第一人称视频描述

EgoCaptioner: Towards Comprehensive and Fine-Grained Egocentric Video Captioning

Yuqi Tang, Yang Shi, Yuran Wang, Tengfei Liu, Rundong Wang, Zongyang Qiu, Qixun Wang, Zhuoran Zhang 等 17 位作者

AI 速读 基于摘要

提出EgoCaptioner,通过粗到细标注和GRPO强化学习,生成兼具全局概览与细粒度时序步骤的第一人称视频描述。

cs.CV

查看原文摘要

Egocentric video captioning requires fine-grained detail and accurate timing, yet current multimodal large language models (MLLMs) often miss brief actions, confuse their order, or misinterpret the wearer's motion. Existing caption formats also offer limited support for combining detailed narration with precise timing. We present EgoCaptioner, which pairs a video-level overview of the setting, participants, and the wearer's overall activity with timed steps whose narration adapts to varying perceptual demands and marks key moments at specific timestamps. We develop a coarse-to-fine annotation pipeline that establishes event structure before expanding step descriptions, yielding 50,000 training examples from eight egocentric video sources. Complementary rewards assess factual accuracy and coverage, measure step-level temporal alignment, and penalize fragmented or redundant narration, guiding caption refinement through Group Relative Policy Optimization (GRPO). To improve the reliability of factual supervision, we supplement caption references with pose-derived motion facts when sensor data are available. Across five egocentric benchmarks, EgoCaptioner achieves leading performance among evaluated open-source models in caption quality, caption-conditioned question answering, and temporal alignment. It also surpasses Gemini 3.1 Pro on PhysCapBench and all evaluated proprietary baselines on Minerva-Ego under the caption-to-QA protocol. Ablations support the complementary roles of factual and temporal rewards and show that coarse-to-fine annotation provides more effective supervision than single-pass annotation.

新论文 · v1arXiv:2611.26358

Beam 模型技术报告

Beam Model Technical Report

Reflection Team, Adam Abdulhamid, Osama Abuelsorour, Yasmin Alameddine, Carlo Alfano, Duarte Alves, Brandon Amos, Selvaraj Anandaraj 等 230 位作者

AI 速读 基于摘要

Beam 是一个面向编码、推理与智能体工作负载的稀疏 MoE 模型,总参数 501.3B、激活参数 23.4B,作者报告其推理算力需求比同类模型低 3–4 倍。

cs.CL · cs.AI

查看原文摘要

Beam is a sparse Mixture-of-Experts (MoE) model with 501.3B total parameters and 23.4B active parameters, specifically built and optimized for coding, reasoning, and agentic workloads. Beam delivers frontier level reasoning, while requiring 3-4x less inference compute than many models of its class. Pretrained on 23.8T diverse, curated, high-quality tokens, Beam features a 1M-token context window achieved through a novel two-stage midtraining phase, built on verifiable, correctness-anchored data. Post-training leveraged a large-scale, fully asynchronous reinforcement learning (RL) campaign across 10.5K GB300 GPUs, generating over 100M rollouts over 4 weeks of training. We believe this is one of the largest scale RL runs conducted by any open lab to date. Across our evaluation suite, capabilities continued to improve as we increased RL compute, with no sign of a plateau. Supported by deep hardware-model co-design, FP8/NVFP4 quantization, and a 1.93B-parameter speculative decoding drafter (DFlash 2), Beam maximizes serving throughput with efficient, flexible deployment. Averaged across conversation turns and harm categories, Beam refuses or pivots on 88.9% of harmful requests while complying with 81.5% of harmless requests, achieving the highest refusal/pivot rate on harmful requests among open-weight models on the Pareto frontier.

新论文 · v1arXiv:2611.26341

按需推理:面向长时程机器人操作的高效智能体控制

Reasoning on Call: Efficient Agentic Robot Control for Long-Horizon Robot Manipulation

Zilang Cen, Chao Tang, Fangcheng Liu, Weishi Mi, Wei Hao, JiaYu Xu, Dehao Huang, Yehui Tang 等 11 位作者

AI 速读 基于摘要

RoC 通过在线任务状态监测器按需触发高层推理智能体,在长时程机器人操作中兼顾成功率与 token 成本。

cs.RO

查看原文摘要

Large multimodal models can support long-horizon robot manipulation, but frequent model calls incur substantial latency and token costs. The central challenge is determining when agent assistance or intervention is needed and whether errors require correcting robot execution, subtask planning, or both. To address this problem, we propose RoC (Reasoning on Call), an efficient framework that coordinates a low-level policy and a high-level reasoning agent through an online task-state monitor. The monitor combines temporal visual observations with ordered interaction memory to jointly estimate progress within the active subtask and predict its successor. These predictions guide event-triggered agent review for coordinated execution repair and plan revision. Verified outcomes govern memory updates and subtask transitions, allowing routine execution to remain with the policy while reasoning focuses on decisions requiring additional assessment. On RMBench, RoC improves task success rate by 24.0 percentage points and reduces token consumption by 65.3% compared with the strongest agent-based baseline. It also outperforms the strongest policy-based baseline by 15.1 percentage points in task success rate. Real-world experiments further validate its effectiveness across three long-horizon manipulation tasks. Overall, RoC supports efficient agent intervention and coordinated recovery across execution and planning for long-horizon robot manipulation.

新论文 · v1arXiv:2611.26317

面向语言的语义建模用于目标语言提取

Language-Oriented Semantic Modeling for Target Language Extraction

Mehmet Sinan Yıldırım, Ke Zhang, Shuai Wang, Haizhou Li

AI 速读 基于摘要

提出面向语言的语义建模框架,用语言感知提示和参数高效微调生成目标语言语义表示,为多语混合语音的目标语言提取提供超越语言身份标签的语义引导。

cs.CL · eess.AS

查看原文摘要

Target Language Extraction (TLE) aims to isolate speech in a target language from multilingual mixtures. Existing approaches primarily rely on acoustic modeling with language identity labels, which provide only coarse categorical guidance. In this work, we propose a language-oriented semantic modeling framework that augments acoustic extraction with language-specific semantic representations. A pre-trained speech semantic model is adapted via language-aware prompt conditioning and parameter-efficient fine-tuning to generate target-language-focused semantic representations from the mixture. {These capture high-level semantic structure of the acoustics and they} are integrated into the extraction model to provide structured semantic guidance beyond identity labels. Experiments on the CommonVoiceMix dataset show that incorporating semantic representations consistently improves over acoustic-only baselines, achieving up to 1.16 dB SI-SDR gain.