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

+197新增论文
+151其中 AI 相关
+16已有论文修订
+91新增 AI 导读

arXiv 最近完成扫描:2026-11-21 12:19 · 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 2026-11-21 06:38 — 2026-11-22 06:38(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:2026-11-21 12:19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 308 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-21 12:17(北京时间)
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: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: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.

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.

版本更新 · v2arXiv:2611.23010

PhysScope: Agentic Multimodal Physics Reasoning with Grounded Visual Memory

Haoyang Liu, Kecheng Liang, Xinyu Li, Weixing Chen, Yang Liu

原文摘要

Vision-language models (VLMs) can correctly interpret physics diagrams yet apply constraints outside the states or conditions in which they hold, causing premise errors to propagate through subsequent calculations. We introduce PhysScope, an inference-time visual harness that supports self-correction of these scope mismatches without updating model weights. PhysScope enables the model to link physical scopes directly to its visual observations and explicitly constructs derived views to support reasoning. The harness imposes explicit constraints on state distinctions, conditions, and physical scopes during model reasoning, and checks agent-proposed revisions against sources and scopes. Accepted revisions invalidate registered dependents, thereby maintaining scope-aware working memory. On PhysAlign, PhysScope achieves higher solving scores than direct solving across all six evaluated VLMs. With Gemini-3.8-flash, it outperforms Canvas-CoT by 9.34 percentage points and substantially improves solving accuracy on the out-of-distribution (OOD) PhysUniBench benchmark. Ablation studies support explicit scope management and dependency maintenance as design principles for multimodal physics reasoning agents.

cs.AI

新论文 · v1arXiv:2611.25946

Point Dynamics as Proxy for Robotic World Models

Dong An, Tianyu Liu, Haoran Ding, Wen Yang, Anqing Duan, Zhengzhong Liu, Eric P. Xing, Guangyi Liu

原文摘要

Robotic world models predict future video frames from the current observation and a sequence of robot actions. While recent models follow the given actions closely, manipulated objects often collapse or move inconsistently with the action. We attribute this to the conditioning: an action, or a rendering of the robot, specifies where the robot goes but not how the scene responds, leaving a single video model to infer the interaction dynamics implicitly while also rendering appearance. We therefore separate dynamics prediction from visual rendering, with 3D point dynamics as the proxy between them. Specifically, we lift the first frame into 3D points, simulate how they respond to the robot's motion with a learned point dynamics model, and render the simulated points back into pixel-aligned videos that any video model can read. In controlled experiments on the DROID dataset with two video renderers of different architectures, this point dynamics proxy reduces object motion error by 8.6% and 6.2% without degrading image quality, and by 8.1% on a real bimanual robot. Moreover, the video follows the simulation: more accurate dynamics yield more accurate object motion, and editing the points steers the video. This suggests that advances in dynamics modeling can translate into more faithful robotic world models.

cs.CV

版本更新 · v3arXiv:2611.06120

ReactWorld: Structuring Interaction Responses for Embodied Video Generation

Hanwei Liu, Huijia Zhang, Hanzhang Wang, Guangyu Liu, Hanbei Zhan, Linjie Hu, Bin Xiao, Xuan Zhou 等 9 位作者

原文摘要

Embodied video world models predict scene changes caused by robot actions, yet generated object responses may remain inconsistent with task intent and contact dynamics. Critical responses in embodied scenes often concentrate in local regions and specific time intervals. Inspired by chain-of-thought reasoning, we introduce ReactWorld, an embodied video generation model guided by structured interaction anticipation. In the generation backbone's feature space, an interaction response field predictor anticipates how the interaction will unfold, explicitly describing participant roles, future motion response intensity, and local motion changes. A response feedback adapter forms increments to object features from the difference between the object branch's outputs with predicted and zeroed local dynamics inputs. It also converts predicted displacements into positional biases for temporal attention. These two mechanisms guide object feature updates and information retrieval across frames, respectively. Through interaction anticipation and generative feedback, ReactWorld achieves an average score of 77.51 on RBench, outperforming PhysisForcing by 3.29 points with improvements in all nine categories. On EZS-Bench, it achieves a Domain score of 86.98 and an average score of 81.87.

cs.CV · cs.RO

版本更新 · v4arXiv:2509.22050

BrainPro: Process-conditioned Pretraining with Topographic Retrieval for Large EEG Models

Yi Ding, Muyun Jiang, Weibang Jiang, Shuailei Zhang, Xinliang Zhou, Chenyu Liu, Shanglin Li, Yong Li 等 9 位作者

原文摘要

EEG foundation models are pretrained on heterogeneous corpora, but two challenges remain underexplored: (1) experimental protocols provide mental-process cues that are rarely used in masked pretraining, and (2) electrode montages vary across datasets, making spatial representations montage-dependent. Existing methods typically learn a single general-purpose representation and model spatial structure implicitly, limiting their ability to exploit process-related information under montage heterogeneity. We introduce BrainPro, a process-conditioned self-supervised pretraining framework that couples topographic retrieval with shared and process-associated representation learning. BrainPro maps dataset-specific montages to a universal channel-region template and retrieves channel- and region-level spatial filters to form a topographically aligned spatial basis. Over this basis, BrainPro learns a shared encoder for general EEG structure and additional affective, motor-related, and auxiliary residual branches for process-associated variation. Protocol-derived mental-process cues condition branch activation and region-weighted masked reconstruction, incorporating topographic spatial priors and process information. Across nine public BCI benchmarks, BrainPro achieves strong performance among evaluated baselines. Ablations, channel-drop analysis, encoder-configuration studies, and spatial-filter visualizations suggest that topographic retrieval and process-conditioned representation learning jointly improve EEG decoding. Our code is available at https://github.com/yi-ding-cs/BrainPro.

cs.LG

版本更新 · v2arXiv:2609.17488

LimiX-2: A Contextual Mechanism Network Towards General Structured-Data Intelligence

Xingxuan Zhang, Gang Ren, Hao Yuan, Hao Zou, Hongze Tan, Hui Wang, Jianhao Song, Jiansheng Li 等 60 位作者

原文摘要

We introduce LimiX-2, a new model in the LimiX family, developed through model and data scaling guided by our previously established scaling laws. LimiX-2 adopts the Contextual Mechanism Networks (CMNs) paradigm and is pretrained with Context-Conditional Masked Modeling (CCMM). CMNs shifts the organizing principle of in-context learning from target-centric prediction to mechanism-oriented joint modeling. Rather than centering the network on the $p(y \mid x, D_{\mathrm{context}})$ objective of conventional tabular PFNs, it is designed around learning $p(x, y \mid D_{\mathrm{context}})$, a context-dependent representation of the joint structure underlying data generation. Pretraining uses synthetic datasets generated by structural causal models (SCMs) spanning diverse graph structures, functional mechanisms, and observation processes. Evaluations on TabArena, TALENT, and BCCO show that LimiX-2 outperforms current dataset-specific models and tabular foundation models. Beyond predictive performance, the CMN paradigm also promotes causal awareness in LimiX-2: its feature attention encodes direct causal relationships, enabling accurate causal skeleton recovery.

cs.AI

版本更新 · v2arXiv:2611.24259

Do Thinking VLMs Need to Keep Looking at Long Videos? Write It Down, Then Look Away

Pengyu Li, Zhitao Gao, Lingling Zhang, Heng Wang, Chengqian Ma, WenHao Wang, Wenxuan Huang, Chen Zheng 等 9 位作者

原文摘要

Vision-language models (VLMs) reason about long videos over hundreds to thousands of tokens. Every decoding step re-reads the key-value (KV) cache of the entire video. Must the model keep looking while it reasons? In LookAway, the model first writes timestamped notes on what the question needs and then puts the video away. Once the notes close, the inference engine hides the video's KV cache for the rest of the response. Across both hybrid and pure-attention VLMs, dependence on the video is concentrated early in the response. On Qwen3.6-27B, writing notes preserves accuracy better than free reasoning at the same withdrawal step. Replacing them with another video's notes harms accuracy, whereas keeping the video visible alongside the model's own notes adds no significant benefit. Without additional training, LookAway nearly matches full-video thinking accuracy at 0.12-0.13 times its modeled decode cost. To shorten this initial look, we fine-tune the model on its own correct LookAway responses. Reinforcement learning then rewards correct answers while penalizing KV reads. The trained model puts the video away after a median of 66-68 tokens. Across three held-out benchmarks, it writes more tokens than an identically trained full-video model yet reads only 27-35% as many KV positions at matched accuracy.

cs.CV

版本更新 · v2arXiv:2611.24267

Look Closer, Look Back, or Wait for Agentic Streaming Video Understanding

Pengyu Li, Zhitao Gao, Lingling Zhang, Wenxuan Huang, YiCheng Xiao, Chen Zheng, Jun Liu

原文摘要

Streaming video models must answer questions about a live video under strict memory and latency limits. Feeding only the latest few frames keeps present perception sharp, whereas adding past frames dilutes attention on the current scene and triggers hallucinations. Recent cascade methods retrieve past frames when uncertain, but they still fail when current frames are blurry or when decisive future clues have not appeared yet. We introduce ActiveForager, a streaming video agent that maintains a clean short working window and gathers extra evidence only on demand. For each query, the agent either answers directly, zooms into high-resolution recent frames, recalls past events from memory, or waits for upcoming frames. When recalling history, a shared-weight sub-agent verifies candidate clips in isolation and returns a compact evidence summary. A stream-decoupled attention mask then keeps historical evidence from interfering with present visual tokens. We train this policy using counterfactual information gain, which rewards a tool call only when the gathered evidence makes the true answer more likely and prevents tool collapse across all actions. Across Qwen2.5-VL-7B and Qwen3-VL-8B on OVO-Bench, ActiveForager improves real-time perception, historical recall, and proactive response at once, lifting overall accuracy on Qwen3-VL-8B from 47.6% to 65.9%. It also doubles zero-shot accuracy on the multi-hop Video-Holmes benchmark while adding minimal visual tokens per query.

cs.CV

新论文 · v1arXiv:2611.25452

FamilySpace: From Emergent Chemical Semantics to Controllable Crystal Generation

Haowei Hua, Irwin King, Wanyu Lin

原文摘要

Latent crystal generative models typically combine a variational autoencoder (VAE) for learning atom-wise representations with a flow model that transports a simple source distribution to the learned latent distribution. However, previous studies have mainly focused on the quality of generated crystals, leaving the structure and generative utility of the atom-wise latent space largely unexplored. In this work, we show that even a vanilla crystal VAE implicitly organizes atom-wise latent representations according to elemental families, with different families occupying largely separated regions of the latent space. We term this phenomenon emergent chemical semantics. This structure suggests that sampling from a family-specific latent region can bias the decoder toward atoms from the corresponding elemental family. Building on this insight, we propose FamilySpace, a framework for controlling the elemental-family composition of generated crystals. FamilySpace assigns each elemental family a distinct source component, forming a family-indexed multi-source distribution, and trains a flow model using source-target pairs matched by family. In inference, a user-specified family template selects the source component for each atom-wise representation, enabling direct control over the family composition of generated crystals. Experiments on MP-20 and MPTS-52 show that FamilySpace achieves competitive crystal-generation performance while matching prescribed elemental-family compositions. Moreover, selected family templates increase the fraction of generated crystals predicted to be stable or metastable, demonstrating that latent-space composition control can support targeted exploration of promising chemical regions without additional optimization techniques such as reinforcement learning. Code is available at https://github.com/hhw11/FamilySpace

cs.LG · cond-mat.mtrl-sci

新论文 · v1arXiv:2611.25398

RefreshGrad: An Online Adaptive Data-sampling Method for Diffusion-based Visuomotor Learning

Dijia Zhan, Jinyi Li, Xuemiao Xu, Yan Zhou, Yu Liu, Shaoshan Liu, Jie Tang

原文摘要

Training vision-language-action (VLA) policies from demonstrations typically samples trajectory segments uniformly or relies on static offline data curation before training. However, we find that demonstration data vary sharply in supervision value across temporal windows, and that each window's value to the policy evolves substantially during training rather than being fixed or captured by raw loss alone. Motivated by this finding, we propose RefreshGrad, an online adaptive data-sampling framework that periodically scores temporal windows from the evolving policy using five policy-native signals and dynamically adjusts their sampling weights during training. RefreshGrad focuses optimization on informative, learnable windows without altering the policy architecture, training objective, or inference cost. Across ten LIBERO-Plus manipulation tasks, RefreshGrad boosts average success from 60.7% (Uniform) and 68.2% (FAKTUAL) to 76.1% under visual perturbations, and from 57.4% and 73.3% to 81.3% in clean scenes.

cs.RO

新论文 · v1arXiv:2611.25296

CalibCache: Cache-to-Full Feature Dynamics Calibration for Diffusion Transformers

Mingyu Liang, Dingkun Xu, Jingwei Xu

原文摘要

Diffusion Transformers generate high-quality images, but iterative sampling remains computationally expensive. Feature caching reduces the number of full network evaluations, yet its approximation error can become more severe under short sampling schedules, where fewer full-compute steps and a coarser sampling grid can make history-based extrapolation less reliable. In this paper, we propose CalibCache, a lightweight offline calibration method that corrects systematic discrepancies between cached and full-compute feature dynamics. Specifically, CalibCache calibrates feature acceleration, defined as the second-order finite difference across sampling steps. Using only a single pair of full-compute and naive-cache trajectories at each setting, CalibCache fits scalar acceleration maps offline by centered least squares. These maps are then applied during sampling without additional full-network evaluations or online optimization. Across FLUX.1-dev and Qwen-Image on DrawBench and DiT-XL/2 on ImageNet-256, CalibCache consistently improves fidelity or generation quality over TaylorSeer under 20-step sampling at cache intervals $N=3,4,5$. At $N=5$, it reduces FLUX.1-dev LPIPS from $0.563$ to $0.429$ while achieving a $2.86\times$ denoising speedup over full-compute sampling, and lowers DiT-XL/2 FID from $16.39$ to $10.37$ relative to TaylorSeer.

cs.CV

新论文 · v1arXiv:2611.25248

Branch Caching After Step Distillation in Four- and Eight-Step Image Generators

Mingyu Liang, Dingkun Xu

原文摘要

Can a distilled image generator save time by reusing features between its few remaining denoising steps? We study a fixed branch cache that replaces selected attention and MLP evaluations while preserving the student's noise schedule. One full trajectory and one raw-cache trajectory from the same initial noise supply a scalar correction for each branch type and reuse position. At $1024^2$, one internal reuse reduces four-step Qwen-Image-Lightning denoising time from 1.279 to 0.977 seconds. Three reuses yield $1.51\times$ speedup on eight-step Lightning and $1.53\times$ on eight-step Hyper-FLUX. We evaluate image quality on all 200 DrawBench prompts. With the reuse positions held fixed, correction improves mean same-seed image fidelity over raw reuse by 0.66 and 0.87 dB on the two Lightning students. On Hyper-FLUX the PSNR difference is 0.01 dB, while LPIPS improves from 0.1625 to 0.1546. These results measure the effect of branch caching and correction while retaining each student's original sampling grid.

cs.CV

新论文 · v1arXiv:2611.24887

Ground, Iterate, Trace: Decomposing AI Research Ideation

Samson Yu, Qiran Zou, Jing Yu Lim, Rushi Shah, Anirudh Goyal, Dianbo Liu

原文摘要

Large language models have been widely used to generate plausible research ideas, yet it remains unclear what makes automated ideation effective and how generated novel proposals arise from prior scientific work. We introduce the Creative AI Researcher (CAR), an agentic framework combining literature grounding, iterative development and explicit conceptual operators. CAR constructs a semantic knowledge graph from retrieved literature and equips an ideation agent with graph-retrieval tools and four operators: bisociation, analogy, exploration and elaboration. Each operator call is checked against structural acceptance conditions and recorded, producing a trace of intermediate transformations and declared literature sources. We evaluate CAR with two language-model backbones across 40 LiveIdeaBench research topics and two execution benchmarks. CAR achieves significantly higher methodological novelty (MN) than single-shot prompting and The AI Scientist. Its methodological novelty does not differ significantly from the Research Ideation Agent, while its feasibility scores are higher on both backbones. With a shared experiment executor, CAR achieves the highest pairwise win rate among the evaluated AI methods on FML-bench-Lite and BioXArena. In a ten-condition ablation study, MN point estimates favor CAR over one-step proposal on both backbones, but no MN contrast survives correction for multiple comparisons. The results do not establish a consistent quality benefit from explicit operators beyond free-form iteration. CAR makes the sequence of operations and declared literature sources inspectable, separating judged idea quality from procedural traceability.

cs.CL

新论文 · v1arXiv:2611.24877

仅通过查询用大语言模型审计黑盒临床预测模型:一项植入缺陷的双盲测试

Auditing black-box clinical prediction models with a large language model through queries alone: a blinded test with planted flaws

Zhiyu Liu, Xinyu Yang

AI 速读 基于摘要

在仅能查询模型预测值的条件下,GPT-6 Astra 能较忠实地描述黑盒临床预测模型并发现大多数植入缺陷,但其报告的问题和发现需进一步核查。

cs.LG · cs.AI

查看原文摘要

Large language models (LLMs) are used to explain clinical prediction models, on the promise that they can say what a model computes, find its faults and even reveal new knowledge in it. We tested the three promises where the answers could be checked. From the International Stroke Trial we trained four kinds of model (logistic regression, explainable boosting machine, gradient-boosted trees, neural network) for two outcomes on patients randomised earlier, planted one flaw in each of 24 copies (an under-predicted subgroup, a reversed risk factor or an implausible step) and mixed them with the 8 clean models. GPT-6 Astra audited each model three times, blind, through a tool that only returned the model's predictions; the judging rules were committed before any run and applied by program. Its surrogate models, with a median of 128 terms, reproduced the audited models' log-odds with a mean $R^2$ of 0.976 (0.959 for an additive surrogate of 42 terms fitted by an analyst). It found the planted flaw in 69 of 72 runs (96%; 95% CI 80% to 99%); a script written for the purpose found all 24. It also reported many more problems: 60% of 1,089 checkable reports failed the pre-specified check against the model's average behaviour; post hoc, most of these were real but small steps, and 15% of the checkable reports were not found in the model. Of 601 unexpected relationships it read out of the clean models, 11% held in patients randomised later (random pairs 6%; a regression scan's shorter list of its strongest candidates, 28%); after a check on the training data, 33% against 30%. With query access alone, an LLM can describe a black-box model faithfully and find nearly every planted flaw, as a purpose-written script also did; its reports of problems must be checked on the model and its discoveries on data.

新论文 · v1arXiv:2611.24633

H3Remover: Reinforcing Video Object Removal without Paired Data

Kangjie Chen, Xiangyu Li, Jinhao Deng, Dongbin Zhang, Chaoda Zheng, Shijia Chen, Yuqi Zhang, Choo Sin Wai 等 13 位作者

原文摘要

Pretrained video editors possess rich removal and completion priors, yet may retain targets or alter unrelated content. We present H3Remover, which reinforces MiniMax-H3 Base Ref2VA for video object removal without paired object-free training targets. To discourage superficial edits such as recoloring, a target-removal reward favors calibrated depth changes consistent with revealing farther content. To limit unintended scene changes, a background-geometry reward encourages preservation of relative depth ordering. To preserve background appearance without retaining unwanted shadows or reflections, an appearance reward constrains RGB changes in source-derived protected regions while exempting targets and estimated effects. Frozen HPSv3 complements these constraints with perceptual-quality feedback for synthesized content. Evaluation regions remain fixed across candidates, and DiffusionART optimizes LoRA adapters with the backbone frozen. Experiments show substantial reconstruction gains over original H3, with qualitative comparisons demonstrating more effective object removal and better preservation of surrounding scene content.

cs.CV · cs.AI

新论文 · v1arXiv:2611.24578

BaseRSI: Recursive Self-Improvement of a Base Vision-Language Model via Training-Free Harness Internalization

Mingda Zhang, Yuanhao Dong, Qiang Huang, Rui Qian, Yanjin Li, Zhenyu Liu, Xiao Huang, Zihao Yang 等 11 位作者

原文摘要

Recursive self-improvement (RSI) is moving from the harness of prompts and tools around a base model toward the model itself. However, existing RSI still faces key challenges, including harness-bound gains that stay outside the base model, black-box supervision that reads only the model's outputs, and imprecise edits whose site and strength are fixed in advance. To address these challenges, we propose BaseRSI, a new paradigm of Recursive Harness Internalization: the base model improves its harness, then writes what the harness adds into its own weights through training-free edits, round after round on its own responses. To support this paradigm, we introduce ReGap, a mechanism that supervises every transformer block with the high-dimensional activation difference that the harness makes at that block alone, and updates the block's weights along this signal in a low-dimensional subspace. Building on this mechanism, we further propose ReKey, an algorithm that writes this signal by regression into a few key-value neurons of every block, and measures the site and strength of each edit on the model's own responses. Moreover, the base model fills every role of this recursion with forward passes alone, and its edits, written at different sites, compose in one checkpoint without refitting. Experimental results on ten visual reasoning benchmarks show that BaseRSI consistently improves a base vision-language model both in distribution and on held-out benchmarks. Our code is available at https://github.com/beita6969/BaseRSI.

cs.CV · cs.AI

版本更新 · v3arXiv:2608.05049

OmniEdit-Bench: A Comprehensive Benchmark for Instruction-based Video Editing

Chenxuan Miao, Yutong Feng, Yi Lu, Yunfeng Yan, Donglian Qi, Shiwei Zhang, Yu Liu, Xi Chen 等 9 位作者

原文摘要

Instruction-based video editing (IVE) offers diverse applications, yet evaluating editing models remains challenging. Existing benchmarks suffer from two key limitations: narrow task coverage inherited from image editing that overlooks video-specific dimensions, and metrics that inadequately capture instruction fidelity, allowing visually plausible but incorrect edits to receive high scores. To address these limitations, we introduce OmniEdit-Bench, a comprehensive benchmark covering spatial, temporal, audio, and reference-based editing. It distinguishes between explicit and implicit instructions and incorporates reasoning-based scenarios to reflect real-world editing requirements. We further propose an evaluation framework that assesses accuracy, preservation, realism, and consistency using both human judges and a state-of-the-art vision-language model (VLM). An accuracy-aware penalty mechanism conditions the other three scores on accuracy, prioritizing instruction fidelity and penalizing plausible but incorrect edits. Experiments on prominent open-source and commercial IVE models reveal substantial room for improvement. OmniEdit-Bench provides a structured testbed for identifying model limitations and advancing instruction-based video editing. Project page: https://omniedit-bench.github.io.

cs.CV

版本更新 · v2arXiv:2605.10313

Signature Approach for Contextual Bandits with Nonlinear and Path-dependent Rewards: Regret Bound and Statistical Inference

Xin Guo, Grace He, Xinyu Li

原文摘要

We study contextual bandits with nonlinear and path-dependent rewards through a novel signature-transform-based approach. Leveraging the universal nonlinearity property of signatures, we approximate continuous path-dependent reward functionals by linear functionals in the signature space. This representation enables the use of efficient linear contextual bandit methods while preserving expressive sequential structure. Building on this framework, we propose \texttt{DisSigUCB}, a signature-based disjoint upper confidence bound (UCB) algorithm. Under boundedness and non-degeneracy assumptions, we establish a high-probability regret bound of order \(\tilde\mathcal{O}\bigl(d_{\text{Sig}} \sqrt{KT} + \ varepsilon_N T \sqrt{d_\Sig}\bigr)\) with \(K\) being the number of actions, \(d_{\text{Sig}} \) the signature feature dimension, and \(\varepsilon_N\) the finite-depth approximation error. We further introduce $ζ$-\texttt{DisSigUCB}, a randomized variant that ensures persistent exploration for statistical inference. Under additional margin and long-run design conditions, we prove consistency and asymptotic normality of the action-specific ridge estimators. Both the synthetic experiments and the numerical studies on temperature sensor monitoring, sleep-stage classification, and hospital nurse staffing demonstrate the effectiveness of \texttt{DisSigUCB} over linear and kernelized contextual bandit baselines in nonlinear and path-dependent settings.

cs.LG · math.OC

新论文 · v1arXiv:2611.24077

AeroRSI: Recursive Self-Improvement for Aerial Vision-Language Navigation

Shiwei Wu, Yuwen Pan, Zhi Li, Yaowen Li, Yan Zhou, Xuemiao Xu, Yu Liu

原文摘要

Vision-language-action (VLA) models enable unmanned aerial vehicles (UAVs) to follow natural-language instructions, yet still fail frequently in closed-loop flight. Correcting these failures requires repairs, i.e., actions that avoid them at the states the policy itself reaches, which human pilots cannot label at scale and rule-based planners cannot supply reliably. In this paper, we present AeroRSI, a recursive self-improvement framework in which an aerial navigation policy iteratively learns from its own failures. Our key insight is that a failing policy should judge its own repairs by flying on from them. Judged in this way, its sampled actions and even rule-based proposals that hurt it when imitated directly become reliable supervision. Moreover, an episode terminates at its first failure, concealing subsequent failures until the earlier ones are repaired. AeroRSI thus renews its supervision in every round, anchoring the failures of the current policy, verifying repairs by its continuation, and distilling them while keeping its behavior elsewhere. On TravelUAV, three rounds raise the success rate of a supervised 2B-parameter policy from 46.4% to 67.5% and reduce collisions by half, surpassing the previous state of the art by 10.6 points from the same initialization without extra human labels or inference cost. Code and models are available at https://github.com/starsholic/AeroRSI.

cs.CV · cs.AI · cs.RO

版本更新 · v3arXiv:2610.16352

LoongSage: A Production-Grade, High-Efficiency Agentic RL Framework for Frontier LLMs with Validated Recipes

LoongSage Team, Bowei Song, Caiwei Zhao, Chuwen Liu, Dechuang Gu, Dong Fang, Feiyu Xie, Huaiyu Li 等 48 位作者

原文摘要

Reinforcement learning (RL) has emerged as a critical phase in the post-training pipeline of large language models (LLMs). As the frontier of LLM capabilities shifts from static reasoning to agentic tasks--characterized by external tool invocation, multi-turn interactions, and long-horizon decision-making--existing mainstream RL frameworks have grown increasingly unwieldy, raising the overhead of adoption, usage, and debugging. To address these challenges, we present LoongSage, an agent-native, fully asynchronous RL framework with a lightweight core of roughly 14K lines of code. Built upon Megatron for distributed training and SGLang for high-throughput inference, LoongSage centralizes orchestration within a single controller process and encapsulates all GPU-resident components as Ray actors. It introduces AgentFlow, a unified execution paradigm that orchestrates both white-box and black-box agents. For asynchronous execution, it integrates sliding-window strategies that bound trajectory staleness, and employs TransferMesh, a topology-aware synchronization mechanism that routes weights after each step over the fastest transport available to each receiver. Beyond agentic RL, LoongSage incorporates a memory-efficient Teacher Manager that decouples the scaling of teacher models from GPU memory constraints, natively supporting Multi-Teacher On-Policy Distillation. Extensive evaluations across four complete training runs, spanning complex reinforcement learning and multi-teacher distillation, demonstrate that task rewards improve steadily while the train-inference gap is kept under continuous control, and the fully asynchronous pipeline removes synchronous idle bubbles, sustaining hardware utilization.

cs.LG · cs.CL

新论文 · v1arXiv:2611.23926

GTI: Grounding Task Intent Throughout Long-Horizon VLA Manipulation

Tianqi Gong, Haochen Niu, Yusheng Zhao, Lantao Zhang, Haoyu Liu, Rendong Ying, Peilin Liu

原文摘要

Vision-language-action (VLA) models generate local actions from visual observations, language, and robot state, but long-horizon manipulation requires the global task intent to remain grounded in the currently executable context. We propose GTI (Grounding Task Intent), which uses the current observation and execution history to localize the active subtask and its execution phase. For the same local subtask, GTI generates two phase-dependent visual targets: an interaction/contact state and a local completion state. The local language instruction and the corresponding phase-specific visual target jointly condition the VLA, specifying both what to do now and what state should be reached at the current phase. During execution, anomaly monitoring and local recovery re-establish an intent-consistent execution context through rollback, re-observation, and phase re-evaluation after persistent deviation. We evaluate GTI on RoboCasa365, VLA-Arena Horizon-Long, and real-world PiPER tasks. Relative to matched Global-FT baselines, GR00T success on seen composite RoboCasa365 tasks increases from 14.6%/12.1% to 31.8%/20.4% under ID/OOD evaluation. On VLA-Arena, GTI+$π_{0.5}$ reaches 47.6% overall success versus 45.2% for an adapted ForeAct baseline, with gains of 5.2/6.0 percentage points on the harder L1/L2 tasks. In the three real-robot task experiments, mean full-task success increases from 21.7% to 59.2%. The results indicate that persistent semantic intent localization and phase-conditioned visual grounding improve multi-stage execution, while failure-triggered local recovery provides additional deployment-time support.

cs.RO

新论文 · v1arXiv:2611.23925

Cardiac MRI-informed electrocardiography enables biologically grounded cardiomyopathy detection

Zhengyao Ding, Kewen Wang, Yujian Hu, Ziyu Li, Yiheng Mao, Yue Wang, Haitao Li, Dengnan Zhang 等 30 位作者

原文摘要

Precise myocardial phenotyping at population scale is limited by the cost and accessibility of cardiac magnetic resonance (CMR), whereas electrocardiography (ECG) is widely available but reflects electrical rather than structural and functional information. Here we develop MyoECG, a cross-modal representation learning framework that distils myocardial structural and functional knowledge from CMR into standard 12-lead ECGs, enabling imaging-informed cardiomyopathy detection and subtype classification from ECGs alone. MyoECG was pretrained on 45,241 paired ECG-CMR examinations from UK Biobank and a tertiary cardiovascular centre, then developed and validated across more than 1.8 million ECGs from seven independent datasets. Across internal and external datasets spanning prevalences of 0.2-54.7%, MyoECG outperformed five pretrained ECG foundation models, with AUROCs of 0.800-0.974 for cardiomyopathy detection. In a multi-reader study of six cardiologists, MyoECG assistance improved mean sensitivity by 0.109 (95% CI, 0.041-0.175; P = 0.009) and specificity by 0.056 (95% CI, 0.004-0.108; P = 0.040). In 41,128 UK Biobank participants, the MyoECG score showed genetic correlations with cardiomyopathy (rg = 0.409) and dilated cardiomyopathy (rg = 0.371), genome-wide associations at four loci, including regions mapped to NFIA and KCNQ1, and associations with 69 circulating proteins related to myocardial stress, cell adhesion, vascular biology and metabolism. The cardiomyopathy correlation attenuated to non-significance after adjustment for 27 measured CMR traits (rg = 0.131; P = 0.143), indicating that the score captures CMR-derived information rather than dataset-specific shortcuts. MyoECG offers a scalable route to CMR-informed cardiomyopathy assessment and a strategy for transferring knowledge from resource-intensive imaging to widely deployable physiological signals.

cs.AI · q-bio.QM

版本更新 · v2arXiv:2611.15314

AcrossPlace: Do Vision--Language Models Recognize Places Beyond Their Source Views? A Comprehensive Benchmark

Zhenyu Li, Tianyi Shang, Shuhan Dong, Ruotong Xu, Qingyu Zhu

原文摘要

Language-guided place recognition requires recovering geographic identity across visual observations beyond the image from which a description originates. However, aggregate retrieval scores often entangle observation transfer, gallery competition, and linguistic evidence, obscuring the underlying recognition capability. We introduce AcrossPlace, a provenance-aware benchmark establishing a systematic evaluation standard for bidirectional language--vision place recognition. Built upon GSV-Cities, AcrossPlace comprises 56,726 places across 23 cities, 156,800 automatically generated, rule-filtered descriptions, and 113,404 target images. Each description retains its source-image provenance, while retrieval operates on disjoint target observations. Text-to-image (T2I) and image-to-text (I2T) retrieval share a unified place-identity relevance criterion supporting multiple valid matches. Two geographic protocols evaluate unseen places within represented cities (P0) and generalization to held-out cities (P1). Paired observation comparisons, gallery-controlled evaluations, fixed-query scaling, and blinded annotation auditing systematically characterize retrieval performance. Across three training seeds, place-supervised SigLIP2 T2I Recall@1 decreases from 19.69% on source images to 12.31% on independent targets under P0. For fixed P1 queries, expanding the gallery from 500 to 8,425 places reduces Recall@1 from 14.67% to 2.87%. A 240-description audit further reveals discrepancies between automated acceptance and factual evidence. These findings establish AcrossPlace as a reproducible evaluation standard for assessing transferable place identity across visual observations and geographic environments.

cs.CV

版本更新 · v2arXiv:2610.32433

Tempo-Zero: Recursive Self-Play in Executable Worlds for Video Reasoning

Jingmin Zhu, Yanyan Zou, Xiuyu Li, James Bailey, Dinh Phung, Tao Yu, Yunyun Hou, Jun Liu 等 13 位作者

原文摘要

Video reasoning requires understanding how events unfold over time, yet videos with accurate temporal annotations are expensive to collect. Self-play offers an alternative by letting a model generate and solve its own tasks without manual annotation. However, existing video self-play methods train on fixed sets of recorded videos, so they cannot alter the underlying event dynamics and rely on noisy pseudo-labels derived from the model's own outputs, such as majority voting, that risk reinforcing shared model errors. To overcome these limitations, we introduce Tempo-Zero, a self-improvement framework that closes a loop of executable environments, execution-verified self-play, and environment evolution, where executing a program renders a video with the ground-truth option and interval of every question. A single policy plays both Questioner and Solver, proposing questions and answering them with timestamped evidence lines, and is trained on execution-grounded rewards instead of model consensus. The Solver's performance steers a curriculum over tasks and difficulty levels, and the policy selects rule changes that enrich the event dynamics of later rounds. Despite being trained solely on simple programs, without supervised fine-tuning or external video data which prior methods typically require, Tempo-Zero outperforms the base models and recent self-play baselines on average across twelve real-world video benchmarks at different model scales, with particularly strong gains on temporal grounding tasks. Project page: https://alchemist-jo.github.io/tempo-zero/

cs.CV

版本更新 · v2arXiv:2611.00515

AStockArena: Beyond Returns, Can We Entrust Real Capital to the Decisions of Financial Agents?

Zeyu Liu, Sing Kwong Lai, Xuanzhi Feng, HaoYang Shang, Yang Li, Zihao Fang, Xuan Liu, Song Guo

原文摘要

Large language models (LLMs) are increasingly used in dynamic financial trading, yet real-time trading benchmarks mainly evaluate agents by cumulative returns and risk-adjusted performance. Such outcome metrics cannot show whether trades are faithfully reported, supported by available evidence, and consistent with account states. We introduce AStockArena, a real-time decision-auditing benchmark for continuous trading in China's A-share market. Under shared market conditions and execution constraints, we evaluate 13 open- and closed-source models over 3,198 sequential decisions. AStockArena reconstructsthe actions actually posted to accounts by aligning reports, trade requests, execution responses, and account states, and audits them with eight checks spanning execution traceability (O), evidence sufficiency (RK), and financial meta-awareness (B), combining record verification with consensus expert annotation. Of 1,070 trading points, 72.99% exhibit at least one audit gap; model-level rates range from52.2% to 91.2%, with evidence gaps most prevalent. Historical trade-filtering replay further shows thatportfolio outcomes are sensitive to these flagged trades. Decision-process auditing thus offers a verifiable complement to return-based evaluation of financial agents.

cs.CL · cs.AI

新论文 · v1arXiv:2611.23212

EviSlide-MIL:用于类增量全切片图像分类的多查询池化与共享预测

EviSlide-MIL: Multi-Query Pooling and Shared Prediction for Class-Incremental Whole-Slide Image Classification

Zhouhan Qian, Sicheng Chen, Chad Wong, Tianyi Zhang, Enhui Chai, Zeyu Liu, Fei Xia

AI 速读 基于摘要

EviSlide-MIL 通过每类多查询池化与共享预测模块,结合经验回放和知识蒸馏,缓解全切片图像类增量分类中的遗忘问题。

cs.CV

查看原文摘要

Histopathological analysis of whole-slide images (WSIs) plays a critical role in cancer diagnosis, and multiple instance learning (MIL) is widely adopted for WSI analysis under weak supervision. As new tumor subtypes are introduced, extending existing MIL models requires learning new classes while retaining knowledge of previously learned ones. This presents a class-incremental learning challenge, where models must acquire new classes with limited access to historical training data and recognize all learned classes without task identifiers at inference. A major obstacle is forgetting, as updates to feature aggregation and prediction modules can degrade performance on previously learned classes. To address this challenge, we propose \textbf{EviSlide-MIL}, a class-incremental WSI framework that integrates multiple learnable queries per class with a shared prediction module. The queries aggregate frozen patch features into class-specific representations, while the shared prediction module limits parameter growth across incremental stages. By freezing queries associated with previously learned classes, EviSlide-MIL preserves their attention patterns for identical inputs, while experience replay and knowledge distillation further mitigate forgetting as shared parameters are updated. Experiments on eight tumor subtypes from The Cancer Genome Atlas demonstrate that EviSlide-MIL achieves improved performance and reduced forgetting compared with competing methods across most learning settings, demonstrating its potential for scalable and knowledge-preserving WSI classification. Code and pretrained models will be released.

新论文 · v1arXiv:2611.23153

VIVID:超越静态多图推理——视频多模态大语言模型中的局部视觉差异与文本实体动态

VIVID: Beyond Static Multi-Image Reasoning with Localized Visual Differences and Textual Entity Dynamics in Video MLLMs

Chengqian Ma, Yuanze Zeng, Hongyu Wang, Mingfeng Lin, YiCheng Xiao, Yu Chen, Pengyu Li, WenHao Wang 等 11 位作者

AI 速读 基于摘要

VIVID 通过保留关键帧间的局部视觉差异和实体状态链,让视频多模态大语言模型摆脱静态多图推理的局限。

cs.CV

查看原文摘要

Video question answering under tight frame budgets requires preserving localized motion and event order, yet current video multimodal large language models (MLLMs) reduce comprehension to static multi-image reasoning by discarding unselected frames and encoding keyframes independently: (1) Spatially, whole-frame pooling dilutes small moving targets into static backgrounds; (2) Temporally, dropping intermediate frames or averaging tokens erases inter-frame motion, confusing direction, speed, and order. We propose VIVID (Visual Inter-frame Variations and Individual Dynamics), which moves beyond static snapshots like human vision: keyframes capture core states while inter-frame Patch Diffs preserve neighboring changes within $K_f$ keyframes. Autonomous Delta-Driven Keyframe Planning (ADKP) selects anchors from a $3\text{ fps}$ pool and feeds surrounding patch differences into Dual-Road Change Memory (DRCM), forming Dynamic Tokens at zero extra anchor tokens alongside a camera-stabilized Active Motion Region of Interest (ROI) and chronological Entity State Chains. Adding $0.22\%$ trainable parameters to a frozen $27\text{B}$ backbone, VIVID-Small ($50$ examples, $\sim 1.5$ GPU hours) beats all eleven baselines in overall accuracy across $8,083$ questions and trails only VIVID-Large ($3,600$ examples), which leads on MotionBench, Video-MME, and TempCompass.