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

+979新增论文
+781其中 AI 相关
+119已有论文修订
+95新增 AI 导读

arXiv 最近完成扫描:2026-11-20 08:48 · 全站最近入库:2026-11-20 19:58各信源进度 →

统计口径与数据新鲜度

统计 2026-11-20 06:46 — 2026-11-21 06:46(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:2026-11-20 08:48最近发现新增版本:2026-11-20 19:58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。

28,961 已收录论文24,030 AI 相关8,912 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 2,485 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-20 08:46(北京时间)
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.

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:2610.14802

面向端到端自动驾驶的可组合驾驶风格

Composable Driving Style for End-to-End Autonomous Driving

Guantian Zheng, Lidong Yu, Tianyu Gao, Jiashu Li, Jiaxing Chen, Wilfried Ariel Mulyawan, Chen Lv

AI 速读 基于摘要

提出 YOUDrive,一种视觉—语言—动作规划器,通过任务向量在推理时连续、可组合地控制驾驶风格,并在 NAVSIM navtest 上报告了风格调节与任务性能结果。

cs.CV · cs.AI · cs.RO

查看原文摘要

End-to-end driving policies can achieve strong task performance while offering limited control over their driving style. Driving style describes how a vehicle accelerates, brakes, and maintains distance. Policies trained without explicit preference conditioning lack a direct mechanism for adjusting these behaviors at inference. We propose YOUDrive, a vision--language--action planner for continuous and composable driving-style control. Each teacher's behavior is distilled into a task vector, a learned parameter update that induces a style direction in the planner's representation. These directions can be scaled and combined at inference without retraining the backbone. Conditioned on these directions, a flow-matching decoder models a multimodal trajectory distribution and generates kinematically feasible motion alternatives. We introduce the Style Alignment Score (SAS) to describe human-referenced kinematic behavior after safety and task gating. On NAVSIM navtest, a single coefficient monotonically controls assertiveness across six teacher-derived personas, while PDMS remains above 0.90 across the tested individual and blended configurations, reaching 0.954. Further analyses reveal systematic policy-specific kinematics after controlling for scene context, whereas the evaluated discrete style labels provide limited additional explanatory power. Code, checkpoints, and the metric will be released.

新论文 · v1arXiv:2611.26531

面向大规模模型集群的成本感知智能体特征优化系统

Cost-Aware Agentic Feature Optimization System for Fleet-Scale Ranking Models

Chang Yang, Yao Xuan, Wendan Yan, Nhat Le, Jiang Liu, Longhao Jin, Zhen Peggy Yao, Alireza Vahdatpour 等 9 位作者

AI 速读 基于摘要

提出一个由LLM智能体与确定性工具协同的端到端系统,在共享与单模型资源约束下为大规模排序模型集群优化特征选择,并已上线取得线上指标提升。

cs.IR · cs.AI · cs.LG

查看原文摘要

Large Web platforms operate large fleets of ranking models, each selecting features from a shared pool of tens of thousands. We present an end-to-end agentic system that optimizes features across the fleet under resource constraints shared across models and those set per model, such as feature pipeline cost and serving throughput (QPS), respectively. In this system, LLM agents propose hypotheses, and deterministic tools execute experiments and verify them. For each model, an LLM generates and shortlists cross features from a combinatorial candidate space, and all features are then ranked by several importance methods. Feature blending mixes these rankings into a single selection, using Pareto fronts across tasks for multi-task models. An LLM Researcher agent then tunes the feature selection in 10--25 asynchronous trials under resource caps, and a trimming step keeps the pipeline cost within budget. Across production models, the system improves normalized entropy by 0.31% on average within each model's budget, and the trimming step cuts pipeline cost by 2.3% with no regression beyond measurement noise. The optimized models were launched, and in online A/B tests they improved a primary online metric by 0.20%.

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:2611.26503

JARVIS:自主设计、构建与测试电路板的智能体

JARVIS: An Agent That Designs, Builds, and Tests Circuit Boards on Its Own

Shibo Zhou, Tianqi Hong, Zheng Yan, He Yang

AI 速读 基于摘要

作者提出具身智能体 JARVIS,用数字孪生预演加机器人执行,在无人干预下完成电路板的设计—制造—测试—学习闭环。

cs.RO · eess.SY

查看原文摘要

Power electronics is central to the energy transition, but developing new hardware still relies on human-led design, fabrication, testing, and iteration. We present JARVIS, an embodied AI agent that autonomously closes this loop for circuit boards. JARVIS maintains machine-specific capabilities and constraints, scans its workspace using a robot-mounted 3D scanner, and constructs an executable digital twin in which it rehearses robot motions, fabrication steps, and circuit behavior before consuming materials. A single text instruction initiates the physical experiment. Using unmodified desktop equipment, the agent coordinates a robot arm, a PCB printer that deposits conductive silver ink and solder paste, and a pick-and-place machine. It verifies progress using cameras and sensors, then tests the fabricated circuit with an OPAL-RT real-time simulator and an oscilloscope. Based on the measurements, JARVIS diagnoses deviations from the design and generates a revised design in KiCad for subsequent rehearsal. In a demonstration involving a 60 Hz notch filter for grid-connected converter sensing, JARVIS completed a first-run experiment in 2 h 39 min without human intervention, achieving 50.6 dB attenuation at 60 Hz. Its digital-twin rehearsal identified five issues before fabrication, including a test criterion that would have incorrectly rejected a functioning board. During execution, the agent also resolved encountered faults autonomously. These results demonstrate an integrated agent-driven workflow for physical design, fabrication, measurement, and iterative improvement of power-electronic circuitry. To our knowledge, JARVIS is the first system in power electronics in which an agent closes the physical design-build-test-learn loop for circuit boards.

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

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

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.

cs.CV

新论文 · v1arXiv:2611.26444

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

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.

cs.RO · cs.AI · cs.CV

新论文 · v1arXiv:2611.26438

Risk-Controlled Test-Time Adaptation for Vision-Language-Action Models

Zixuan Liu, Hashem Haghbayan, Zizhan Zheng, Siavash Khajavi

原文摘要

Retrieval-augmented vision-language-action (VLA) models enable efficient test-time adaptation by leveraging expert demonstrations as additional context without updating model parameters. However, even when retrieved demonstrations are relevant to the current task, the VLA may fail to effectively utilize the retrieved information, ultimately leading to task failure. To address this challenge, we propose R2-VLA, a risk-controlled retrieval-augmented VLA framework that enables reliable test-time adaptation by satisfying a user-specified task success rate requirement with minimal expert assistance. Specifically, R2-VLA learns an uncertainty predictor that estimates the uncertainty of the VLA's predicted actions given the retrieved demonstrations, guiding when to act autonomously or request expert assistance. We further introduce a task-level risk-control procedure that calibrates the uncertainty threshold to satisfy a user-specified task-failure risk requirement. Moreover, R2-VLA continually incorporates expert corrections into its retrieval memory to improve future adaptation while preserving the prescribed task-level risk guarantee. Experiments across three VLA backbones and four LIBERO benchmark suites demonstrate that R2-VLA improves average task success by 9.2--11.2 percentage points, achieving the desired target with fewer expert requests. These results highlight the effectiveness of connecting the usefulness of retrieved demonstrations with task-level risk control to enable successful robotic manipulation.

cs.CV

新论文 · v1arXiv:2611.26434

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

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.

cs.CV · cs.RO

新论文 · v1arXiv:2611.26414

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

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.

cs.AI

新论文 · v1arXiv:2611.26407

Flow Matching from Non-Gaussian Sources: A Theory of Efficient Sampling

Yuchen Zhou, Lili Zheng, Yuxin Chen, Gen Li

原文摘要

Flow matching is a versatile framework for generative modeling that transports a source distribution to a target data distribution. A key advantage is its flexibility in the choice of source distribution, such as heavy-tailed and multimodal sources. Yet finite-step sampling guarantees for non-Gaussian sources remain limited. We establish a nonasymptotic convergence theory for Euler discretization of flow matching with linear interpolation. Suppose the source distribution on $\mathbb{R}^d$ has an everywhere positive, continuously differentiable density, finite total variance $\mathsf{TotVar}_{\mathsf{base}}$, and an $L$-Lipschitz score. Using the population velocity field and a suitable time grid, this sampler achieves total variation error at most $\varepsilon$ in $\widetilde{O}(Ld\mathsf{TotVar}_{\mathsf{base}}/\varepsilon)$ iterations, provided the target distribution satisfies a mild second-moment condition. These assumptions cover, among many examples, source distributions such as multivariate Student's $t$ distributions with more than two degrees of freedom and finite Gaussian mixtures with shared covariance, while accommodating target distributions with neither a smooth density nor bounded support.

stat.ML · cs.AI · cs.IT · cs.LG

新论文 · v1arXiv:2611.26405

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

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.

cs.RO · cs.CV

新论文 · v1arXiv:2611.26385

Beyond the Sink Interpretation: Radial Attention in Flow-Based VLA Policies

Yuxi Zheng, Yueqian Lin, Yudong Liu, Zijia Tang, Junyu Pan, Yiheng Wang, Hai Helen Li, Yiran Chen

原文摘要

Prior work calls the high attention on the first and last action tokens of a flow-based VLA policy a radial action sink, and uses these tokens to set the execution horizon. In language models, a sink is a token with high incoming attention, a small value, and little effect on the output. We test whether that profile holds, not the horizon rule, in one $π_{0.5}$ checkpoint on five RoboCasa tasks. The two endpoints receive 5.4% of action-key mass, 1.4 percentage points above their uniform share, and rotary positional encoding produces this excess: directly in shallow layers and through upstream action-token RoPE deeper in the network. The endpoints do not fit the sink profile. Their value norms stay near the action-token mean in all 18 layers. On 250 paired episodes, masking them or zeroing their values changes success by less than 4 points, and replacing their value directions with those of another observation lowers it by 3.2 to 7.2 points across three donors, whereas the same replacement on two non-endpoint tokens in the executed prefix lowers it by 28.4 points. The token that does fit the sink profile on mass and value norm is the prefix BOS; on this checkpoint, zeroing its value raises success in two paired runs, by +13.2 points (95% CI [+7.0, +19.4]) and +6.0 points ([+0.2, +11.8]). Inside the action chunk, a relative-offset routing profile estimated on other tasks keeps 75% of action-token spread and keeps closed-loop success on three held-out tasks (42.7% against a 38.7% baseline), while uniform or shuffled routing drops success to 3-4%. High attention mass alone does not tell what a token does.

cs.RO

新论文 · v1arXiv:2611.26370

Fast Self-Supervised Generative CT Denoising via Few-Step Sampling

Xingyi Yao, Zhengtao Ma, Zhennong Chen

原文摘要

Low-dose and thin-slice computed tomography (CT) images suffer from elevated noise that obscures anatomical detail, while clean references for supervised denoising are often unavailable. Although Noise2Noise permits self-supervised training from noisy pairs, direct regression tends to oversmooth fine structure. Averaging multiple independently generated samples mitigates this blur, though repeating multi-step diffusion sampling is costly. We introduce Noise2Noise with Improved Mean Flow (N2N-iMF) to accelerate this process via few-step sampling. N2N-iMF learns to generate one noisy image conditioned on its paired counterpart; at inference, independent outputs are sampled and averaged to suppress noise. We evaluated image quality and sampling efficiency on simulated thin-slice brain and low-dose abdominal CT across four sampling methods and averaging counts from 1 to 20, and validated the approach on real-world photon-counting CT (PCCT) brain scans. With ten samples per conditioning input and three network evaluations per sample, N2N-iMF achieved a mean absolute error of 2.60 HU on brain CT and 14.02 HU on abdominal CT, outperforming 50-evaluation denoising diffusion implicit model (DDIM) sampling (2.91 and 14.53 HU). On the same GPU, per-output generation time dropped from 7.29 to 0.43 s. Across eight PCCT cases, N2N-iMF reached a mean gray-white matter contrast-to-noise ratio of 1.341, versus 0.916 for Noise2Noise and 1.176 for DDIM. N2N-iMF accelerates self-supervised generative CT denoising without distillation while keeping the number of averaged outputs adjustable at inference.

cs.CV

新论文 · v1arXiv:2611.26358

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

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.

cs.CL · cs.AI

新论文 · v1arXiv:2611.26328

Conformal Selection for Hierarchical Streaming Data

Zhenyuan Sun, Chengyao Yu, Ruixing Ming, Bingyi Jing

原文摘要

Many real-world tasks involve making sequential decisions about whether to select candidates before their responses of interest are revealed. In this work, we address the online selection problem in the context of hierarchical data, where candidates arrive sequentially from different populations. This extends existing online conformal selection frameworks beyond the standard i.i.d./exchangeable data assumption. The primary challenge lies in constructing valid statistics for each candidate sequentially under the hierarchical data structure. To this end, we first develop Online Hierarchical Selection (OHS), a distribution-free method that enables principled candidate selection for hierarchical data streams. Specifically, we introduce methods to construct rank-based e-values for both between-group and within-group samples, and apply averaged e-values to the online e-BH procedure. We then develop OHS with feedback (OHSF), which boosts the power of OHS by leveraging potential response feedback. Theoretically, the proposed methods achieve false discovery rate control under mild hierarchical exchangeability and data arrival assumptions at any time. We also generalize methods to broader settings, such as data with covariate shift and selection under effect-related responses. Extensive experiments on both simulated and real-world datasets demonstrate the effectiveness of the proposed methods.

stat.ML · cs.LG

新论文 · v1arXiv:2611.26293

LocoMuJoCo: A Comprehensive Imitation Learning Benchmark for Whole-Body Control

Firas Al-Hafez, Davide Tateo, Oleg Kaidanov, Aditya Bhatt, Artur Zelik, Zhengyi Luo, Jan Peters

原文摘要

LocoMuJoCo is an open-source benchmark for imitation learning (IL) and reinforcement learning (RL) on whole-body control. The library couples MuJoCo (CPU) with MJX and the MjWarp backend (GPU) under a single API, exposes 9 humanoid, 3 (musculo-)skeletal, and 4 quadruped embodiments, and ships a curated native motion-capture dataset for every humanoid, to which it can also retarget AMASS and LAFAN1. A modular plug-in architecture makes observations, rewards, control modes, terrains, and domain randomization fully interchangeable, while compact JAX implementations of many RL and IL algorithms provide JIT-compiled end-to-end training, and the companion loco-mujoco-real repository provides sim-to-real deployment. We describe the design, the SMPL-to-robot and robot-to-robot retargeting pipeline, and a usage example. LocoMuJoCo is released under MIT at https://github.com/robfiras/loco-mujoco.

cs.RO

版本更新 · v2arXiv:2611.17794

Federated Physics-Informed Thermal Field Prediction Across Unseen Geometries in Distributed Additive Manufacturing

Amirul Islam Saimon, Zhenyu James Kong

原文摘要

In additive manufacturing (AM), each change in part geometry requires a new thermal simulation, which makes design evaluation over many candidates costly. Geometry-aware models reduce this cost by predicting thermal fields on unseen parts with a single learned model, but they assume that diverse geometries are available centrally. This assumption is restrictive when each manufacturing site holds only a limited set of proprietary part designs that it cannot share. We propose Fed-PIGANO, a federated framework that trains physics-informed geometry-aware neural operator (PI-GANO) models at individual sites and aggregates their geometry encoders and prediction networks without sharing part geometries. We evaluate the framework on a 2D steady-state thermal benchmark for metal AM, with geometries from five polygonal families distributed across three sites under four scenarios that range from identical to strongly different family compositions. Over seven replications, Fed-PIGANO achieves mean relative L2 errors of 1.83% to 2.04% across all 12 scenario-site cases, compared with up to 20.46% for local-only training, and consistently yields lower PDE residuals. Its prediction accuracy is comparable to that of a centralized model trained on the pooled geometries of all sites. These results demonstrate that federated learning lets manufacturing sites benefit from each other's geometries without sharing them, enabling rapid thermal prediction on new part designs for tasks such as shape optimization, inverse design, and uncertainty quantification.

cs.LG

版本更新 · v3arXiv:2604.10547

Agent^2 RL-Bench: Can LLM Agents Engineer Agentic RL Post-Training?

Wanyi Chen, Xiao Yang, Xu Yang, Tianming Sha, Qizheng Li, Zhuo Wang, Bowen Xian, Fang Kong 等 10 位作者

原文摘要

We introduce Agent^2 RL-Bench, a compact diagnostic benchmark for evaluating agentic RL post-training, which tests whether LLM agents can autonomously design, implement, debug, and execute post-training pipelines that improve foundation models. RL post-training increasingly drives model alignment and specialization, yet existing benchmarks are largely static, rewarding supervised fine-tuning or script generation without assessing an agent's ability to close an interactive RL loop. Agent^2 RL-Bench provides a unified agent-facing interface: each run starts from an isolated workspace containing a base model, task data, instructions, and a grading API, and agents must iterate within a fixed budget by training models and submitting artifacts for evaluation. The benchmark spans six tasks across three levels, from static rule-based training to judge-based optimization and closed-loop online RL with trajectory collection. Two diagnostic skills, namely runtime recording and post-hoc summarization, enable structured analysis of agent behavior, facilitating smooth and effective iteration of the benchmark's evaluation framework. Across five agent systems and six driver LLMs, agents show intelligent behavior but clear limitations: one RL-oriented run improves ALFWorld from 4.85 to 93.28 via SFT warm-up and GRPO with online rollouts, yet DeepSearchQA remains difficult, most successful routes rely on supervised pipelines, and interactive outcomes show large differences across agent stacks. Overall, Agent2 RL-Bench shows that current agents can sometimes engineer online RL, but stable agent-driven RL post-training remains rare under fixed budgets. It also demonstrates that our benchmark provides a strong and effective evaluation framework for future research in this direction. Code is available at https://github.com/microsoft/RD-Agent.

cs.AI

版本更新 · v3arXiv:2608.29519

FuncRoom-Agent: Sequential Feed-Forward 3D Functional Indoor Scene Generation

Hao Feng, Zhi Zuo, MingJian Liang, Jingyu Hu, Xiaowei Hu, Liupengfei Wu, Dian Zhang, Guoxin Fang 等 9 位作者

原文摘要

We introduce Function-Room Generation, a new indoor 3D scene generation setting that creates rooms supporting explicit functional goals rather than merely visually plausible layouts. Existing agentic and executable methods improve controllability, but often depend on costly test-time generate--evaluate--revise loops, making functional room generation slow and computationally expensive. We address this challenge with three technical contributions. First, we design a recursive domain-specific language to effectively organize the hierarchical object compositions required by functional rooms, from room structure and major furniture to dense support-surface and nested small objects. It represents rooms as staged executable programs with explicit geometric and functional relations. Second, we propose a sequential feed-forward scene construction framework that distills recursive construction traces into a scene construction expert. At inference time, the expert writes executable DSL code stage by stage, and a deterministic executor directly instantiates each stage without teacher agents, online critics, or iterative repair. Third, we introduce ScenePRM, an execution-grounded process reward framework that improves the expert through reinforcement learning with functional, geometric, relational, and future-constructability feedback. We further establish a function-oriented benchmark and show state-of-the-art performance on both general indoor scene generation and function-room generation, achieving stronger functional completeness, relation correctness, geometric executability, and generation efficiency.

cs.CV

新论文 · v1arXiv:2611.26211

SpecWM: Turning Verification into Refinement for Streaming World Models

Jiaming Li, Lingzhen Li, Xiaze Yang, Chenyu Zhu, Kaiqi Liu, Xiaotong Zhao, Songlian Li, Toyota Li 等 12 位作者

原文摘要

Recently, video world models have advanced interactive generation, with large models offering higher quality and smaller models enabling faster inference. Existing speculative methods combine their strengths through fast draft generation and selective target regeneration guided by rewards on decoded frames. However, verification covers only the external scorer's evaluation dimensions and adds decoding and scoring costs. Moreover, these scores provide no correction, requiring costly target regeneration for rejected drafts. To address these limitations, we propose Speculative World Model (SpecWM), a unified, training-free inference framework for streaming world models. It verifies draft chunks using the target's latent velocity field. Verification also yields a reusable correction; two thresholds select Accept, Refine, or Reject. Specifically, one-step refinement reuses it to improve perceptual quality, while three-step refinement strengthens camera following and trajectory consistency. These findings motivate transition-aware refinement. On WBench Navigation, SpecWM improves visual quality at 1.63$\times$ speedup over the target and raises NavScore from the draft's 75.99 to 85.63, achieving the best quality-speed-control trade-off. Additionally, our LongSpecBench shows sustained quality and control over long, multi-turn rollouts, while experiments on Hy-Nomas validate SpecWM across backbones and denoising budgets.

cs.CV

版本更新 · v3arXiv:2606.27786

SPARK: Adaptive Parametric Knowledge Participation for Faithful Retrieval-Augmented Generation

Ruochang Li, Pengcheng Huang, Zhenghao Liu, Yukun Yan, Huiyuan Xie, Yu Gu, Ge Yu, Maosong Sun

原文摘要

Retrieval-augmented generation (RAG) enhances the faithfulness of large language models (LLMs) by incorporating external knowledge into the generation process. However, conflicts between retrieved context and parametric knowledge can cause LLMs to rely on inconsistent internal knowledge, hindering their ability to faithfully leverage retrieved evidence. Existing approaches mitigate this issue by editing parametric knowledge to resolve such conflicts. However, locating and modifying knowledge encoded in model parameters is challenging and may inadvertently compromise the backbone LLM's capabilities. In this paper, we introduce SPARK, a novel framework that formulates parametric knowledge control as a latent participation policy learning problem, enabling LLMs to adaptively regulate the contribution of parametric knowledge during generation. Specifically, SPARK introduces a lightweight participation policy that dynamically modulates the contribution of FFN-mediated parametric knowledge while keeping the backbone LLM frozen. The participation policy is optimized with a faithfulness-oriented reward, enabling fine-grained control over parametric knowledge participation during generation. Extensive experiments on six datasets validate the effectiveness of SPARK, which introduces and optimizes only 0.01\% additional trainable parameters while keeping the backbone LLM fully frozen, thereby preserving its general capabilities and achieving more faithful generation than competitive baselines. All datasets and code are available at https://github.com/OpenBMB/SPARK.

cs.CL · cs.AI

新论文 · v1arXiv:2611.26167

Planning to Stop: Factored Certification and Terminal Repair for Noncircular Robots

Runtian Zheng, Congpeng Zhang, Ying Liu

原文摘要

Tight-space navigation requires a robot to clear obstacles and stop inside its goal despite uncertainty. We present GeoDiff, a motion-program planner coupling original-goal stopped-set inclusion, witness-guided terminal repair, and factored proof compilation. An exact feasible-translation characterization guides repair; request-local reuse reduces repeated geometric work. We establish conditions for compiler equivalence and reach-and-stop soundness. Across 11,440 floorplan-derived jobs, GeoDiff certifies 61/139 tasks at 5-cm tolerance within 15 s, versus 44/139 for the stop-set baseline. The strongest observed external certificate adapter certifies 13/139 tasks from 119/139 native routes, separating route availability from certification. On tasks derived from public BARN maps, GeoDiff certifies 202/270 at 5-cm tolerance for a Jackal-shaped body, versus 3/270 for the portal baseline. Development analyses distinguish emitter savings from solver coverage, and 1,420 route-tracking episodes characterize the execution interface. These results show how terminal reasoning and proof reuse increase finite-budget certification coverage while preserving the original physical task and goal.

cs.RO

新论文 · v1arXiv:2611.26145

Can World Models Predict Rice Growth? Toward Agricultural World Models

Wenkai Ji, Zeteng Li, Yinkun Guo, Jie Zhou, Liang He, Zhenong Jin

原文摘要

World models can imagine how a physical scene evolves over the next few seconds, but growers need to know how a crop will develop over weeks to months: will this rice plant have headed a month from now, and how will it look at harvest? We introduce agricultural world modeling, the task of predicting how the same plant will look at a requested horizon of days to months, from one photo of it, its cultivar, and its camera view. In preliminary analysis, even state-of-the-art image generators get this wrong: they often grow the plant too little or give it the color and form of the wrong growth stage. We argue that they do not work out the plant's developmental state, which the photo reveals only indirectly. We therefore propose AgroWM, which reasons about development before it draws growth. Its reasoning module, PhenoClock, works out the current growth stage, predicts the future one, and writes a Growth Script with numeric targets for height, plant area, and color; its generation module, the Rooted Renderer, then edits the photo to follow this script, adding new organs and colors to the photographed plant. Because pixel scores can prefer an unchanged copy of the photo, we instead check each forecast's traits and developmental timing against the plant's own later photos. On rice, 54.6% of the forecasts of AgroWM are matched to the target stage (Stage R@1), against 34.8% for GPT Image 2.5, 24.0% for Qwen Image 2.1, and 47.4% for the strongest domain-specific baseline, the same backbone fine-tuned without Growth Scripts; 9 to 20 weeks ahead, it still reaches 46.4%, against 35.7% for that baseline. On maize, a crop with a different body plan and stage scale, the same design again scores best on all four measures.

cs.CV · cs.CL

新论文 · v1arXiv:2611.26117

ChronoPatch: Black-Box Energy-Latency Attacks on Vision-Language Models

Jiawei Xing, Li Wang, Xiangtao Meng, Chuanchao Zang, Rui Wen, Zheng Li

原文摘要

Vision-language models (VLMs) are increasingly deployed as generative inference services, where autoregressive decoding makes response length a key determinant of latency and computational cost. This creates an availability risk: adversarial visual inputs can prolong generation and increase serving overhead. Existing energy-latency attacks typically rely on gradients, logits, or token-level feedback, leaving open whether such risks persist when an attacker observes only the final response. We present ChronoPatch, a black-box attack that induces prolonged VLM generation requiring only the final response. It discovers visual delay anchors through response-length-guided evolutionary search, then minimizes perturbation magnitude through subspace-calibrated decision-based optimization. Across four open-source VLMs, ChronoPatch increases inference latency by 47.86%--293.34% and GPU energy consumption by 41.44%--249.70% under a 5% spatial budget. It also induces more repetitive outputs, as reflected by increased n-gram repetition ratios. On three commercial VLM APIs, ChronoPatch increases response length by 37.6%--81.5% and client-observed latency by 1.82x--2.29x under query budgets of 500 per API. These results reveal a generation-based availability risk that persists under final-response-only access and motivate generation-aware safeguards for deployed generative AI services.

cs.CR · cs.AI

新论文 · v1arXiv:2611.26107

HiUni: Harmonizing Understanding and Generation in Shared Visual Space

Jiahao Hu, Jingdong Du, Yichen Zhang, Yi Song, Zhenyu Zhang, Jiaxin Niu, Ruihang Li, Xiangzhao Hao 等 13 位作者

原文摘要

Unified multimodal models aim to support visual understanding and generation within a single framework. However, prevailing approaches often separate their visual representations or backbone computation to accommodate the different requirements of these two tasks, which limits the degree of unification. In this paper, we present HiUni, which revisits this design choice and explores whether a pretrained vision language model can be directly extended into a unified model with extensive parameter sharing. Specifically, HiUni reuses the same language-aligned ViT and dense Transformer backbone for both capabilities, while confining task-specific computation to the output side. Yet such a design introduces two key challenges. Generation in pixel space is difficult to optimize, and semantic abstraction in pretrained ViT discards fine spatial details required for synthesis. To address these challenges, HiUni introduces a \emph{Pixel Diffusion Head} tailored to direct pixel-space optimization and a lightweight \emph{HiGate} pathway that provides fine-grained spatial details near the output stage. Extensive experiments show that HiUni achieves a similar average understanding score to the pretrained VLM while attaining competitive performance on image generation and editing. Controlled comparisons and analyses further demonstrate that a single dense backbone can effectively support both capabilities without task-specific backbone computation, highlighting a simpler path toward unified multimodal modeling.

cs.CV · cs.AI