跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+0新增论文
+0其中 AI 相关
+0已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-09 07:12 · 全站最近入库：2026-11-08 06:02各信源进度 →

统计口径与数据新鲜度

统计 2026-11-08 09:57 — 2026-11-09 09:57（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：2026-11-09 07:12最近发现新增版本：2026-11-08 06:02库内论文最新更新时间：2026-11-06 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。

17,100 已收录论文14,661 AI 相关4,057 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

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 17,100 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-09 07:10（北京时间）
新论文 · v1arXiv:2610.37571

TeamGym: A Gym for Team Decision-Making by AI Agents with Distributed Information

Chanwoo Park, Jaywoong Jeong, Zachary Wojtowicz, Yubin Kim, Taekyun Lee, Kaiqing Zhang, Asuman Ozdaglar

原文摘要

Many real-world decisions require teams to integrate information distributed across participants. Yet AI agents are still primarily trained and benchmarked in isolation. We introduce TeamGym, an environment for evaluating and training language model-based agents on team decision-making problems constructed from real-world legal, finance, medical, and software engineering corpora. TeamGym introduces a method to identify a minimal set of facts, each element of which is necessary and all of which are collectively sufficient for a correct final decision, which we call pivotal information. This enables TeamGym to both control the distribution of pivotal information and track how well agents identify and integrate pivotal information when making team decisions. Examining 8 language models on 12 source corpora, we find that current AI agents often fail to effectively share information: Distributing pivotal information across participants lowers success rate by 22.9 percentage points on average relative to giving the same information to a single model (a communication gap). We also document that participants do not effectively retrieve decision-relevant information on their own: A team's success rate is lowered by a further 19.9 points when participants must identify and extract pivotal information from source material rather than receiving it directly (a retrieval gap). To help remedy these deficits, we use TeamGym to train policies through reinforcement learning on team decision loss. Across two policy-training experiments, we find that training improves final-decision quality and induces emergent coordination in participation, speaker selection, and communication, even though the reward evaluates only the final decision.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37570

LCM-Promo: An LLM-Based Uplift Model for Promotion Allocation

Nesta Midavaine, Floris Fok, Paulo Mendes, Joao Silva, Önder Akaçık, Dimas Lima, Zülküf Genç

原文摘要

We present LCM-Promo, an LLM-based uplift model for promotion allocation. LCM-Promo is a task-specific Large Commerce Model (LCM): a finetuned LLM trained on transactional commerce data to predict user intent and promotion response. It learns monotonic promotion-response curves from production logs by interpreting single-token outputs as conversion-threshold probabilities, while conditioning on session context such as day and delivery shift. In a production A/B test on churn reactivation, LCM-Promo increased conversion by 1% and reduced promotion cost by 6% relative to the Segment-EMA production baseline.

cs.LG · cs.IR

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.20077

Tailored to you: longitudinal effects of personalising language models

Canfer Akbulut, Justine Breuch, Arianna Manzini, Lujain Ibrahim, Matija Franklin, Roma Patel, Iason Gabriel, Kristian Lum 等 9 位作者

原文摘要

Interest in developing personalised language models is rapidly growing. While personalisation is often viewed as a mechanism to better serve diverse user needs, the effects of sustained interactions with personalised models on people's perception of and behaviour toward AI remain poorly understood. Most critically, downstream consequences outside the immediate human--AI interaction loop, such as effects on users' self-perceptions and interpersonal relationships, remain largely unexamined. In this study, we recruited 992 participants to complete daily advice-seeking interactions with language models over the course of five days, comparing outcomes from a non-personalised baseline against two personalisation approaches: memory-based (conditioned on prior conversational history) and survey-based (conditioned on information collected through a pre-study intake survey). We find that several changes in human-AI interaction over time are driven primarily by repeated exposure rather than personalisation itself. However, participants interacting with personalised models experienced differences in advice-seeking and information-sharing attitudes and behaviours. We conclude by highlighting the nuanced effects of different personalisation approaches on interaction outcomes, and discussing the implications of these findings for the responsible design and deployment of personalised AI systems.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37567

Gym-Anything-RT: Scaling Real-Time Environments for Vision-Language Agents

Pranjal Aggarwal, Sean Welleck

原文摘要

AI agents have made substantial progress in domains where they have a non-trivial amount of time to deliberate between actions, such as mathematics, software engineering, and performing tasks on desktop applications. It is less clear how such models fare in settings that demand real-time interaction, such as playing a video game or operating a physical device. In these settings, the environment state may evolve as the agent is reasoning, or even as the underlying model is performing a forward pass. To gain insight into the real-time interaction capabilities of vision-language agents, we introduce Gym-Anything-RT. Our key idea is to construct visual minigames that demand a portfolio of capabilities required for interactive real-time settings. Gym-Anything-RT uses an agentic pipeline to automatically generate such environments based on a taxonomy of six capabilities required for real-time interaction, including the ability to perceive the environment and act under an evolving environment state. A key feature of Gym-Anything-RT is that it allows for controlled comparison of real-time interaction capabilities: we can run the same minigame in real time, or pause or slow down the environment to relax the requirement for real-time actions. We use Gym-Anything-RT to construct 100 real-time minigames and evaluate AI agents on them. We find large capability gaps in real-time interaction. For example, GPT-6 Astra (xHigh) achieves a pass rate of only 9.0% on the real-time minigames, which rises to 75.0% when the environment is paused. We also identify intriguing behaviors by the most powerful frontier agents: for instance, when given the ability to write code, these agents write code that bypasses the need to perceive and act in real time. We publicly release Gym-Anything-RT and the generated minigames to spur further research on AI agents in real-time interactive settings.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37566

ReferStream: Interactive Subject Injection for Streaming Video Generation

Shuolin Xu, Guanyuan Li, Boyu Li, Kelu Yao, Xiaogang Xu, Hongchuan Yu, Shuicheng Yan, Xiaobin Hu

原文摘要

Injecting new subjects naturally during streaming video generation requires integrating newly supplied visual references into the existing video while preserving established subjects and the scene. Encoding references independently of the current scene provides little guidance for this integration, while keeping their features in persistent memory can interfere with established context. We propose ReferStream, a framework that requires no additional training and combines reference construction using the current scene with transient cache injection. Joint Latent places reference latents in target regions of the latest scene latent, allowing reference features to be extracted in context. Cache Restoration uses these features to condition the injection chunk, then restores the overwritten global cache entries while retaining the newly generated history. This procedure incorporates new visual conditions without retraining the generator or revising emitted frames. We further introduce ReferStream Bench, a new benchmark with scheduled reference arrivals, evolving instructions, and explicit annotations of subject presence for InShot and MultiShot generation. Evaluation follows the event schedule and measures both the fidelity of new subjects and the preservation of established subjects, alongside video quality, text adherence, and count accuracy. Experiments on ReferStream Bench show higher scores for text adherence, subject similarity, and count accuracy than the compared baselines, including offline methods given all references in advance. Project page: https://xushuolin.github.io/ReferStream/.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2601.00592

Beyond Checklist Compliance: A Tale of the Accessibility-Usability Dilemma across Government and Non-Government Web Systems in Bangladesh

Sanjida Islam Era, Tanjeem Azwad Zaman, Ishika Tarin Ime, Ashequl Islam Tofa, Farzin Awsaf Zaman, A. B. M. Alim al Islam

原文摘要

Examining whether technical accessibility measures align with users' usability experiences across web systems in Bangladesh is of utmost significance, given the country's rapidly expanding digital ecosystem. We, therefore, evaluated 207 web systems using WAVE, AChecks, and Squidler and surveyed 103 young adult users. Automated evaluation revealed mixed patterns across government and non-government sectors, with neither consistently performing better across accessibility, functionality, web practices, and performance. In contrast, participants clearly favored non-government platforms for navigation, usability, clarity, and cross-device experience. Qualitative analysis identified three barriers to practical access: system instability disrupting task completion, interaction and navigational friction, and socio-technical barriers involving information access, service continuity, and trust. These findings show that automated accessibility measures capture only part of users' experiences. Accessible web services therefore require attention beyond detectable accessibility problems to reliable task progression, understandable interaction, information access, and continuity across the broader service process.

cs.HC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37563

Pneuma: A Large-Scale Real-World Time Series Benchmark for Commercial Aircraft Predictive Maintenance

Jiafeng Lin, Yutian Zhang, Huan Zhang, Yuxuan Wang, Jinyan Feng, Yuhui Liu, Zhongyi Pei, Jianmin Wang

原文摘要

Predictive maintenance is vital for commercial aviation, yet progress remains hindered by the lack of public, large-scale real-world datasets. As a result, most methods are developed and evaluated on proprietary data, limiting reproducibility. We introduce Pneuma, the first publicly available large-scale benchmark for predictive maintenance using onboard time series from in-service commercial aircraft. Built around bleed air systems, Pneuma contains over 920 million multivariate time steps across four aircraft types and 9 verified fault scenarios, directly aligned with real maintenance logs. The dataset exhibits key real-world challenges, including substantial class imbalance, subtle fault evolution patterns, and significant variance across aircraft configurations. We structure the benchmark around three tasks: multivariate forecasting, supervised fault classification, and unsupervised anomaly detection, with labels derived from actual maintenance records. Under unified settings, we evaluate over 25 models from four methodological families on 9 carefully curated subsets. The results reveal that even strong contemporary models struggle with subtle fault signatures. Further analyses show consistent gains from additional in-context examples and multivariate inference, while forecasting quality is strongly associated with anomaly detection performance. Together, these findings provide practical insights into effectively modeling complex real-world aviation time series. We hope Pneuma will serve as a rigorous and reproducible foundation for advancing data-driven predictive maintenance toward real-world deployment in commercial aviation.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37561

When uncertainty quantification fails: structural vulnerabilities and corrections for selective prediction under clinical class imbalance

Walter Endrizzi, Flavio Ragni, Raffaele Marchesi, Stefano Bovo, Monica Moroni, Giuseppe Jurman, Venet Osmani

原文摘要

Background. Selective prediction systems improve the safety of clinical artificial intelligence by deferring ambiguous cases to human experts while automating high-confidence decisions. However, this safety mechanism relies entirely on the premise that uncertainty scores accurately reflect clinical ambiguity. In prognostic tasks characterized by severe class imbalance, where the clinical outcome of interest is a minority, this assumption breaks down. Standard uncertainty measures cease to capture clinically aligned ambiguity; instead, they become a proxy for class membership, systematically penalizing minority patients regardless of their individual predictive clarity. Results. Across 56 synthetic conditions and three neurodegenerative cohorts spanning severe class imbalance to near-balanced conditions (multiple sclerosis, Parkinson's Disease, Alzheimer's Disease), our framework consistently maintained bounded, balanced risk across trajectories. In contrast, global metrics either collapsed minority Sensitivity or protected the minority at the expense of majority patients. Applying CCR with standard entropy fails to protect the minority because it breaks within-class monotonicity when tau=0.5. Combining CCR with threshold-aware metrics restores strict monotonicity, correctly identifies ambiguous patients, and safely mitigates minority exclusion. Conclusions. Under clinical class imbalance, standard uncertainty quantification measures dataset sparsity rather than clinical ambiguity, creating a systemic illusion of safety. This bias is a correctable structural flaw. Clinical pipelines deploying selective prediction under imbalance should adopt threshold-aligned uncertainty measures and class-stratified evaluation. This reduces class-specific risk imbalance, supporting safer selective prediction under the evaluated conditions without silently excluding the most vulnerable patients.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37557

Learning Visuomotor Quadrotor Flight Through Dynamic Narrow Gaps via Differentiable Simulation

Riccardo Bianco, Yunfan Ren, Jiaxu Xing, Davide Scaramuzza

原文摘要

Threading a quadrotor through a moving narrow gap is a demanding test of agile flight, requiring centimeter-level spatial alignment and precise temporal execution. We address this challenge using a control policy that operates directly on onboard visual and inertial measurements to output collective thrust and body-rate commands. The task is difficult because success lies on a thin feasible manifold: small errors in timing, position, attitude, or visual observability cause collision. Prior planning and learning methods rely on privileged state, teachers, planners, or distillation; learning dynamic narrow-gap traversal directly, from scratch, remains open. We introduce a differentiable moving-gap formulation that gates centering, alignment, and smooth collision terms by signed distance to a time-varying gap plane, turning a sparse traversal event into a dense pathwise objective. We integrate this formulation into a visual-feature-to-command policy trained in one stage from random initialization, without a teacher, planner, or distillation. We validate our approach in both synthetic and real-world experiments. In controlled benchmarks, we demonstrate that pathwise gradients significantly outperform score-function gradients for precision-critical tasks, yielding a 99.3% success rate in simulation after only a few minutes of training on a single GPU. Furthermore, the policy transfers directly to a real quadrotor, successfully crossing a dynamic narrow gap from varied initial conditions using onboard sensing and inertial measurements, achieving an 80% success rate over 10 physical trials.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37553

Collective Dynamics of Self-Reinforcement: How Cross-Task Coupling Drives Policy Collapse in Unsupervised RLVR

Peize Ding

原文摘要

Label-free reinforcement learning with verifiable rewards (RLVR) rewards a language model for agreeing with its own majority vote. It improves reasoning at first but eventually collapses: the self-assessed reward goes to one while accuracy falls, often until the model gives the same answer to every problem. The collapse appears only when training uses many problems. We explain this dataset-size dependence as a collective instability. In a solvable many-problem model in which problems share parameters, a population whose problems prefer different answers amplifies any shared perturbation for as long as the population-averaged slope $\langle F'\rangle$ of the single-problem self-reinforcement drift $F$ is positive. This holds while problems are still uncertain about their answers. Per-problem sharpening, slowed by $1/N$ for $N$ training problems, races against the shared mode, which grows at a rate $\proptoλ^2$ independent of $N$, where $λ$ is the strength of the shared coupling. This yields a critical number of problems $N_c\simeq\ln(1/δ)/(λ^2G)$, where $δ$ seeds the shared mode and $G$ decreases with the initial confidence. Simulations of the model confirm the predictions: a sharp transition, $N_c\proptoλ^{-2}$ up to a logarithmic correction, a single critical amplification $λ^2NG$ across couplings, confidence profiles and training variants, a logarithmic dependence on batch size, and no collapse for confident initial models. A kernel version of the theory identifies a protective coupling (generalization of sharpening) and a marginal-entropy bonus that stabilizes the uniform collective mode. In label-free RL of a small Transformer, removing the shared direction prevents collapse entirely, restoring it causes collapse, and collapse grows with training-set size and base-model entropy.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:1611.05991

Almost-Polynomial Ratio Almost-ETH-Hardness of Approximating Densest $k$-Subgraph

Pasin Manurangsi

原文摘要

In the Densest $k$-Subgraph problem, given an undirected graph $G$ and an integer $k$, the goal is to find a subgraph of $G$ on $k$ vertices that contains maximum number of edges. Even though the state-of-the-art algorithm for the problem achieves only $O(n^{1/4 + \varepsilon})$ approximation ratio (Bhaskara et al., 2010), previous attempts at proving hardness of approximation, including those under average case assumptions, fail to achieve a polynomial ratio; the best ratios ruled out under any worst case assumption and any average case assumption are only any constant (Raghavendra and Steurer, 2010) and $2^{Ω(\log^{2/3} n)}$ (Alon et al., 2011) respectively. In this work, we propose the Almost-Exponential Time Hypothesis (Almost-ETH), which postulates that no algorithm can solve 3SAT on $n$ variables in $O(2^{n^{1 - γ}})$ time for any constant $γ> 0$. Assuming Almost-ETH, we show that, for any constant $\varepsilon > 0$, there is no polynomial-time algorithm that approximates {\sc D$k$S} to within $2^{(\log n)^{1 - \varepsilon}}$ factor of the optimum. In addition, our result has perfect completeness, meaning that, assuming Almost-ETH, no polynomial-time algorithm can even distinguish between the case in which $G$ contains a $k$-clique and the case in which every induced $k$-subgraph of $G$ has density at most $2^{-(\log n)^{1 - \varepsilon}}$.

cs.CC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37550

Kinematic Constraint-Referenced Evaluation for Articulated Object Manipulation

Baptiste Bonin, Caro Strickland, Audrey Durand

原文摘要

Manipulation policies are evaluated predominantly by binary task success, which cannot tell whether the commanded gesture is the one the object's kinematics admit. We introduce Constraint-Referenced Strategy (CRS), which projects the commanded end-effector twist onto the object's joint axis, separating progress along the joint from off-constraint waste. CRS requires a joint model and a joint-following scripted controller derived from it, but no recorded demonstration or learned judge. On 74 simulated articulated objects, success registers three transfer failures as lower rates but attributes none, while the two CRS channels give each a distinct signature. A door-trained behavior-cloning policy opens drawers in 59 of 110 episodes, and in these passes it commands about $40\times$ the off-axis rotation of a drawer-trained policy's passes ($1.27$ vs.\ $0.032$~rad/s). Relative to a scripted controller scored with the same axis, CRS verdicts are unchanged under joint-axis errors up to $30^\circ$; absolute thresholds tolerate about $8^\circ$.

cs.RO · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37547

When, Where, and What to Correct: Human-Guided Adaptive Residual Correction for Robot Policies

Anukriti Singh, Maxime Caniot, Pratap Tokekar, Firas Abi-Farraj

原文摘要

Imitation policies that reliably execute most of a manipulation trajectory can still fail in localized regions requiring last-mile precision. Updating the full policy or exploring residual actions everywhere treats this local failure as a global learning problem. We introduce Adaptive Residual Correction (ARC), a lightweight post-training module that uses reinforcement learning (RL) to learn a residual correction on top of a frozen policy while using sparse human corrections to structure autonomous exploration. Rather than treating human corrections as imitation targets, ARC uses pre-intervention states to determine 'when' residual control should become active and correction geometry to determine 'where' in residual action space autonomous refinement should explore; task reward determines 'what' residual is ultimately executed. Across three precision-manipulation tasks on a real robot, ARC improves average task success from 33.3% to 75.0%. The human corrections define task-dependent 2-3 dimensional subspaces of the seven-joint residual space that retain 96.0-97.7% of squared correction magnitude. Together, these results show that sparse human corrections can localize and constrain autonomous post-training without requiring the observed correction itself to serve as the final action target.

cs.RO · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.34554

LunarRF: A Terrain-Aware Propagation Engine and Pole-Wide 3GPP Surface Coverage Atlas of the Lunar South Pole

Christopher J. Santorelli, Alexander M. Wyglinski

原文摘要

Artemis surface operations will depend on 3GPP cellular links, yet no public product shows where such links are physically possible across the lunar south pole. We present LunarRF, a GPU system for terrain-aware surface coverage, and the pole-wide atlas produced with it. A footprint engine casts 8192 radial profiles from one of 11,827 candidate masts enumerated by stated rules on the orbit-adjusted LOLA elevation model, takes the viewshed, and evaluates ITU-R P.1812 Delta-Bullington propagation on every profile, continuous through the radio horizon. An order-independent resolver merges the footprints per 20 m cell, making the run shardable and resumable. The atlas covers the disc south of 80°S at 20 m for four SFCG-recommended surface bands and the IM-2 demonstration band, 1.8 to 25.375 GHz, under a stated link budget, storing per cell the best-server power and identity, redundancy count, line of sight and coverability. The engine is validated against a parabolic-equation solver, ray tracing and analytic solutions. Swapping Deygout for Delta-Bullington, or adding terrain noise at the level of the published height-error map of the DEM, moves the coverable class on under 1% of a mast's disc in the mean. With every candidate active, 90.5% of the disc is coverable at 1.8 GHz, 59% at 5.855 GHz and 10% at 25.375 GHz, or 84, 43 and 5% after the measured 3-4 dB engine optimism. A mast covers about 90% of its visible area within its budget-set range, and no band is terrain-limited. The nine current Artemis regions are 85-99% coverable at 1.8 GHz and 22-85% at 5.855 GHz. The atlas and candidate table are released with a DOI.

cs.NI · astro-ph.EP · astro-ph.IM

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37545

GroundControl: Satellite-Conditioned Multi-View Diffusion for Reconstruction-Free Novel View Synthesis

Akshay Krishnan, Matias Turkulainen, Jamie Wynn, Zawar Qureshi, Mohamed Sayed, Guillermo Garcia-Hernando, Sara Vicente, James Hays 等 10 位作者

原文摘要

Multi-view or video diffusion models have recently emerged as state-of-the-art approaches for novel-view synthesis from sparse image collections. While they can produce high quality images, they tend to hallucinate unrealistic spatial layouts when synthesizing views outside the input views (scene extrapolation). We propose to address this challenge for outdoor scenes by using satellite images as an additional information source to condition the multi-view generative model. We introduce a new satellite-conditioned multi-view diffusion model that combines conditioning from a satellite image and street-level input images when generating novel-views. Our cross-attention based conditioning allows us to retain pretrained multi-view diffusion priors to generate seamless, realistic, novel views from a handful of source views, while also adhering to the scene layout as seen from satellite images. Our model does not use 3D scene reconstruction, and only relies on posed street and satellite views. Our experiments on outdoor datasets show that our model is better than both satellite-conditioned or street-view conditioned baselines on novel-view synthesis, especially on challenging cases where target views have very little overlap with source views. Project page: https://nianticspatial.github.io/groundcontrol

cs.CV · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37543

Rendering-Free Event Frame Simulation for Fast Reinforcement Learning of Autonomous Robot Navigation

Dequan Ou, Austin Lopez, Quentin Missinne, Christophe De Wagter, Guido C. H. E. de Croon

原文摘要

Event cameras offer low latency, high dynamic range, and milliwatt-level power consumption, making them ideal for agile robots such as tiny drones navigating through cluttered environments. However, existing simulators generally render photorealistic images before converting them into events, making large-scale reinforcement learning prohibitively slow. We propose an analytic event simulator that exploits what event cameras fundamentally measure - moving contrast edges - to synthesize event streams directly from scene geometry and ego-motion without visual rendering. Our simulator generates a 64x64 event observation in 17 microseconds on a single GPU - over 400x faster than a state-of-the-art rendering pipeline - enabling end-to-end reinforcement learning for goal-directed obstacle avoidance to converge in under 30 minutes - three orders of magnitude faster than training on rendered events. Policies transfer zero-shot to physically based event simulations (ray-traced Isaac Sim). Our policy reaches 83% success in cluttered courses unseen during training (mid-difficulty, traversability probability approx. 0.57), at 2.4 m/s average goal velocity, and retains 70% in a simulated texture-dense indoor hall. Furthermore, we quantized the policy to a 1.2 MB int8 network running fully onboard a 56-gram Crazyflie equipped with a Prophesee GenX320 event camera and an OpenMV N6 microcontroller board. Without any fine-tuning, external processing, or positioning, the policy achieves an average success rate of 82% (5/5, 5/6, 4/6 flights) across three real-world obstacle courses of increasing difficulty. Code: https://github.com/tudelft/rendering-free-event-nav

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37741

Agentic Backdoors via Pretraining Poisoning

Xinyan Hu, Pingbang Hu, Chloe Loughridge, Xuanli He, Nicholas Carlini, Matthew Jagielski, Javier Rando, Yiming Zhang

原文摘要

Large language models are pretrained on vast, uncurated corpora scraped from the public web. This creates a security risk from attackers who plant poisoned content in the pretraining data. We show for the first time that such poisoning can plant a remote code execution backdoor in an agent, causing it to execute attacker-chosen commands on the user's machine. To measure the threat end to end, we pretrain Qwen3 models from scratch at sizes 0.6B, 1.7B, and 4B, and then post-train each into a CLI agent using a clean pipeline. Poisoning only 0.1% of the pretraining corpus with our new poison design implants the backdoor: the deployed agent executes the malicious command when the trigger is present while behaving normally on clean inputs. The attack success rate (ASR) increases with model scale, with the 4B model reaching roughly 92% ASR at a 0.1% poison rate and staying positive even when the poisoning rate drops to 0.0005%. Our code is available at https://github.com/safety-research/agentic-backdoor.

cs.CR · cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37535

Predict the Swing, Match the Speed: Robotic Pipe Stabbing With Learned Stereo Vision and Residual Reinforcement Learning

Mohamed Ashraf Mostafa, Taher El-Fakharany, Samir Khaled

原文摘要

A joint of pipe run into the hole swings from the elevator over the well and strikes a fixed stabbing guide at whatever speed the swing has. StabBot, a robotic stabbing system, predicts the swing and meets the pipe at its own speed. A pendulum Kalman filter tuned from the pipe tally tracks the joint in stereo images. A six-axis arm with an open V-shaped roller head closes in at matched velocity, confirms the last millimetres by touch, aims the pin over the box when the elevator hangs off centre, and follows the block down with lateral compliance. A ResNet-18 keypoint network locates the pipe, pin nose and box mouth in 3-D, and a residual reinforcement-learning policy refines the capture. On 200 paired random jobs with nine sizes from 2-3/8-in. tubing to 20-in. casing, StabBot seated every joint with the pipe touching only rollers, against 74% for a conventional fixed guide. Median contact speed fell from 18.4 to 2.3 cm/s and median peak head-pipe force from 11.3 to 1.4 kN, and the force was lower in all 200 jobs (Wilcoxon $p < 10^{-30}$). The network locates the pipe with 0.4-mm median error in 2.3 ms per stereo pair. With the network in the loop, success stayed at 100% under 20 mm of added noise, 300-ms delay, 85% frame loss, 20-mm calibration offset, 20-cm elevator offset and 40-cm swings. All results come from a 1:4 Froude-scaled MuJoCo model and are reported at full scale.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37534

Computing GR(1) Assume-Guarantee Contracts

Yigit Narter, Emily Zhao, Inigo Incer

原文摘要

Assume-guarantee contracts provide a set of algebraic operations that enable the efficient compositional design and analysis of complex engineering systems. The explicit computation of these operations at component interfaces is currently supported only for some logics lacking a notion of time. This paper develops theory and algorithms to compute these operations when the contracts are expressed in the GR(1) modulo theory. The key challenge is the computation of two quantifier elimination problems for temporal formulas. We develop context-aided variable elimination procedures on GR(1)-modulo formulas, establish their soundness, characterize subproblem-wise optimal solutions within an admissible class of formulas, and use the procedures to compute contract operations, including composition and quotient. We implement the resulting framework in Pacti, automating compositional reasoning over GR(1) contracts. Finally, we demonstrate the framework on an automated emergency-braking case study, where we compute system-level contracts and expose compatibility conditions arising from the interaction of component specifications. Experiments on synthetic families show that the cost is governed by the number of eliminated variables and liveness conjuncts, and a comparison with exact automata-based elimination shows complementary scaling.

cs.LO · eess.SY

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37533

Which Hand Was Late? Diagnosis for Robot Failure Recovery in Bimanual Tool Use

Baptiste Bonin, Caro Strickland, Audrey Durand

原文摘要

Failure diagnosers for robot manipulation are increasingly vision--language models (VLMs), trained and evaluated on single-arm failures produced by perturbing a successful demonstration. Bimanual tool use adds failures of other kinds: a tool that slips out of its socket while still held, two correct gestures made at different times, and attempts that fail for two reasons at once. On a simulated bimanual tool-use task whose failure causes are read from the recorded trace, we measure what each sensing channel lets a diagnoser tell. The tool's slip is read on the tool hand; which hand was late is read on both arms, while a sensor on one hand reads its own hand's delay and at most part of the other's; and whether a late attempt was also pushed too weakly is not identifiable from passive sensing when the tool hand is late. Within two attempts, a repair policy that escalates when the cause is not identifiable repairs as many failures as one told the true cause. A VLM's internal state carries the late hand almost perfectly, along a direction no closer to the one its answer reads than a random one; whether the answer reports it depends on the wording of the question.

cs.RO · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37740

EUReCA: End-to-End Unified CBCT Reconstruction Across Clinical Acquisitions

Jiening Zhu, Chengzhu Zhang, Jason Fan, LiCheng Kuo, Weixing Cai, Xiuxiu He, Laura Cervino, Jean Moran 等 11 位作者

原文摘要

Cone-beam computed tomography (CBCT) is widely used for image-guided radiotherapy, but reducing the number of projections to lower dose and scan time makes reconstruction increasingly ill-posed. We present EUReCA (End-to-end Unified REconstruction across Clinical Acquisitions), a geometry-aware feed-forward model for variable-view clinical linac CBCT. For a given acquisition trajectory, EUReCA accepts 8-100 projections with a single set of weights, without view-count-specific retraining; the same architecture and training recipe extend unchanged to other clinical trajectories. It combines learned projection features with an in-frame Feldkamp-Davis-Kress (FDK) reconstruction. The model encodes each projection with a shared multiscale backbone, back-projects features into multiresolution 3D grids using the acquisition geometry, aggregates variable numbers of views at fixed computational cost, and refines the volume with a global 3D transformer and multilevel decoder. On simulated data, EUReCA achieved 29.9-33.2 dB PSNR with 10-100 views and outperformed all applicable feed-forward baselines; it also exceeded iterative optimization-based methods while running orders of magnitude faster. On 15 measured patient CBCT scans evaluated against vendor reconstructions, EUReCA achieved the best performance at every tested view count. These results suggest that geometry-aware, measurement-anchored feed-forward reconstruction can provide a practical and flexible foundation for variable-view linac CBCT.

eess.IV · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2603.01563

Efficient Token-Level Policy Optimization for Masked Diffusion Models via Velocity Alignment

Chenxing Wei, Jiazhen Kang, Hong Wang, Jianqing Zhang, Hao Jiang, Xiaolong Xu, Ningyuan Sun, Ying He 等 11 位作者

原文摘要

Reinforcement Learning with Verifiable Rewards (RLVR) successfully aligns autoregressive models in rigorous domains like mathematical reasoning and code generation. However, applying RLVR to Diffusion Large Language Models (dLLMs) is hindered by intractable sequence-level likelihoods, forcing existing methods to rely on unstable, high-variance approximations. We propose Sequence Likelihood-Free Policy Optimization (LFPO), an efficient framework that circumvents this bottleneck by formulating policy alignment as discrete velocity alignment. Inspired by continuous flow matching, LFPO eschews trajectory-level estimation and directly optimizes denoising logits via contrastive token-level updates, providing a stable, low-variance surrogate. Furthermore, predicting terminal solutions from intermediate states implicitly straightens the generation trajectory, enabling high-quality sampling with significantly fewer denoising iterations. Extensive experiments on reasoning and coding benchmarks demonstrate that LFPO matches or exceeds the accuracy of likelihood-based baselines while substantially accelerating inference.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.35747

Correspondence Is Not Transfer: A Pairing-Controlled Study of Clinical Audio-Metadata Alignment

Liu He, Xi Wang, Jiahong Yuan, Yuanchao Li

原文摘要

Clinical audio models are often trained by aligning recordings with participant metadata or text derived from it. This metadata is rarely a clean disease signal, since a single profile also contains symptoms, age, sex, missing responses, and recruitment information. We examine what alignment adds to frozen audio features by varying only the audio-meta data pairing. We keep the audio backbones fixed and train only a projector under correct pairing and three shuffled conditions that progressively preserve the disease label and recorded sex. We then evaluate each projector on profile retrieval, attribute probing, and disease classification on covariate-matched test sets. On UKCOVID, correct pairing clearly improves retrieval and makes sex easier to decode, confirming that the pairing manipulation works. Most of the sex-probe gap disappears when the control also preserves recorded sex, while a small retrieval gap remains. Matched disease AUROC differences are small, and every interval includes zero, so modest benefits or harms are not ruled out. The same pattern appears when we rerun the frozen pipeline on CODA TB, Cambridge COVID-19 Sounds, and Coswara, where retrieval and sex-probe contrasts are consistently positive but disease contrasts are not. We find no consistent evidence that better profile correspondence translates into better disease prediction and suggest reporting these outcomes separately.

cs.SD · eess.AS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37739

OpenFrontiers: A Collection of Open Research Problems and a Benchmark for Scientific Rediscovery

Jiarui Yao, Ruida Wang, Tong Zhang

原文摘要

Large language models (LLMs) have shown increasing promise in research-level problem solving, yet a comprehensive collection of such problems is still missing, and evaluating them on research-level problems remains challenging. We introduce OpenFrontiers, a cross-disciplinary resource that combines a structured corpus of open research problems with a retrospective benchmark of recently resolved problems in mathematics. The corpus records problem statements, context, progress, and other information for 12,151 problems. The benchmark contains 200 problems, 110 resolved in 2026 and 90 still open, each with a Lean~4 statement checked by automated probes and two independent reviews; a subset HQ-50 further filters based on quality score, etc. Our evaluation protocol grades formal proofs with two independent checkers in an isolated sandbox under closed-book, frozen-retrieval, and live-web conditions. Evaluating seven LLM agents on the HQ-50 subset under a standardized budget, we find that closed-book rediscovery is rare, at most 7 of 40 resolved problems, whereas live-web success mostly reflects retrieval of published solutions. By linking a broad research-problem corpus to a formally graded evaluation subset with documented solutions, OpenFrontiers provides a foundation for measuring research-level rediscovery and studying progress toward solving currently open scientific problems. The dataset and benchmark could be found in https://huggingface.co/collections/FlippyDora/openfrontiers.

cs.AI · cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37527

Extending the W3C Data Privacy Vocabulary to Cover the German Health Data Use Act - Lessons Learned

Julian Flake, Christian Henke, Alessandra S. Kuntz, Matthias Löbe, Harshvardhan J. Pandit, Christian Draeger

原文摘要

Finding, sharing, and reusing data requires common interoperable vocabularies to adequately describe machine-actionable data policies. Semantic Web standards are a proven way to express such information describing data access and reuse. Narrative descriptions get a stable and agreed meaning by formal definitions of terms that have a globally unique identifier. The Data Privacy Vocabulary (DPV) represents a community standard for privacy, data protection, and related topics. DPV uses modular namespaces to define jurisdictions, such as "EU", and to represent concepts from laws within that jurisdiction, such as the General Data Protection Regulation (GDPR) and the European Health Data Space (EHDS). In this work, we present the creation of a DPV extension representing the German Health Data Use Act (Gesundheitsdatennutzungsgesetz (GDNG)) that has been set into force in March 2024. The GDNG regulates sharing and using health data for secondary use, such as research purposes and policymaking. It builds the German legal foundation for the future EHDS as the European initiative and regulation providing rules for sharing of health data within Europe. The parallel development of the EHDS and GDNG extensions resulted in many shared concepts, which contributed to an overarching extension: the DPV sector health extension. It sets the foundation of aligned privacy terms for future EHDS member states looking to build a national vocabulary aligned with the EHDS. All extensions were released as draft extensions with the latest DPV version 2.3, released 25th of February 2026.

cs.CY

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2508.04189

BadTime: An Effective Backdoor Attack on Multivariate Long-Term Time Series Forecasting

Kunlan Xiang, Haomiao Yang, Wenbo Jiang, Haoxin Wang, Shiyue Huang, Shaofeng Li, Yijing Liu, Ji Guo

原文摘要

Multivariate long-term time series forecasting (MLTSF) models are increasingly deployed in critical domains such as climate, finance, and transportation. Despite their growing importance, the security of MLTSF models against backdoor attacks remains entirely unexplored. To bridge this gap, we propose BadTime, the first effective backdoor attack tailored for MLTSF. BadTime can manipulate hundreds of future predictions toward a target pattern by injecting a subtle trigger. BadTime addresses two key challenges that become particularly severe in MLTSF: (i) the rapid dilution of local triggers over long horizons, and (ii) the extreme sparsity of backdoor signals under stealth constraints. To counter dilution, BadTime leverages inter-variable correlations, temporal lags, and data-driven initialization to design a distributed, lag-aware trigger whose influence persists over long-range forecasts. To overcome sparsity, it mixes label-similar and label-dissimilar poisoned samples and adopts a decoupled backdoor training objective that explicitly up-weights the sparse backdoor signal, enabling reliable learning at a poisoning rate as low as 1%. Extensive experiments show that BadTime significantly outperforms the state-of-the-art backdoor attack on time series forecasting by extending the attackable horizon from at most 12 timesteps to 720 timesteps (a 60x improvement) and reducing the MAE on target variables by 57% on average, while changing the average clean forecasting error by less than 1%.

cs.CR

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.33036

A Benchmark for Controllable Speaking-Style Captioning in Audio-Language Models

Shreeram Suresh Chandra, Ashwyn Sharma, Liang Lu, Xiutian Zhao, Leda Sari, Björn Schuller, Berrak Sisman

原文摘要

Speaking-style captioning (SSC) aims to generate natural language descriptions of how speech is delivered, capturing paralinguistic attributes such as vocal timbre, prosody, and expressivity. Many downstream applications, including conversational AI agents, controllable speech generation, and large-scale audio annotation, require dimension-specific style captions that describe targeted aspects of speech (e.g., speaker traits, emotion, or delivery style), rather than a single undifferentiated description. However, existing work lacks a unified formulation for controllable speaking-style captioning. We address this gap by formulating SSC as an instruction-following audio-language task, where explicit instructions specify the speaking-style dimensions to be described. We introduce StyleInstructCaps, the first standardized benchmark for controllable speaking-style captioning in audio-language models. StyleInstructCaps provides a dataset and evaluation framework that measures metadata groundedness, hallucination, instruction-following ability, generalization to unseen instructions and audio datasets, and speaker-style consistency. Across nine state-of-the-art audio-language models, we find that strong instruction-following ability does not necessarily imply grounded speaking-style understanding, and that SSC-specific instruction-diverse training substantially improves groundedness, controllability, and speaker consistency.

cs.CL · cs.AI · cs.SD · eess.AS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37524

GTFormer: A Syntax-Free Graph Network Alternative to Transformers for 8192$\times$ Length Extrapolation in Linear Time

Elisabeth Fink

原文摘要

Self-attention mechanisms have established the Transformer as the dominant backbone across natural language processing, source code intelligence, and automated theorem proving. However, all-to-all pairwise token comparison enforces a quadratic $\mathcal{O}(N^2)$ compute and memory barrier alongside severe softmax attention dilution as sequence length $N$ scales beyond the training horizon. Inspired by recent advances in algebraic graph learning (\textbf{WPNet}), this work introduces \textbf{GTFormer}, a syntax-free hierarchical Graph Neural Network (GNN) that replaces flat self-attention for general long-context sequence modeling. GTFormer organizes raw token streams into a bounded-degree hierarchy combining a balanced binary reduction tree ($\lceil \log_2 N \rceil$ depth), horizontal boundary-bridging shift edges, random expander shortcuts, multi-channel convex highway gating, and a top-down broadcast pass. Across eight long-context code, log, and multi-hop retrieval benchmarks trained exclusively on sequences of length $N \le 512$, GTFormer extrapolates zero-shot to $N = 4{,}194{,}304$ ($8192\times$) on a single commodity GPU in linear $\mathcal{O}(N)$ memory, maintaining near-perfect accuracy where standard and RoPE Transformers suffer from out-of-distribution attention collapse and out-of-memory exhaustion.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37523

The Structure Gap: When More Data Cannot Replace Structured Reasoning

Kheer Sagar Patel, Mojtaba Soltanalian

原文摘要

A persistent belief in modern AI is that sufficiently large learners trained on sufficiently much data can make explicit domain knowledge optional. This paper examines a limitation of that belief. We define structure-encoded problems: tasks whose input-output map is determined, or sharply constrained, by known structure such as a solver, symmetry group, graph, physical law, measurement operator, grammar, combinatorial search space, or optimization objective. For such tasks, the central question is not expressivity--a dense neural network may contain the desired map--but finite-data identification, extrapolation, and certification. We introduce the structure gap: the finite-resource gap between a method that receives the governing structure and a learner that receives only examples. The strongest useful form of the claim is asymptotic rather than absolute: structure-agnostic learning may approach a structured solver as coverage grows, but every finite dataset can leave residual uncertainty that the structure resolves by construction. We prove this exactly for a Gaussian inverse problem: the known-operator Wiener solver attains Bayes risk, while the dense empirical learner in the correct linear class has persistent expected excess risk. We also prove a cell-coverage lower bound and an unobserved-orbit non-identifiability result. Controlled experiments in known-operator inversion, sparse recovery, and graph reachability with size extrapolation instantiate the mechanisms. When validated structure is available, it can constrain the hypothesis space before learning begins, leaving learning to address components the structure does not specify.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37522

The Minimum Subpacketization of Reed-Solomon Codes with Linear Repair Achieving the Cut-Set Bound

Weijun Fang, Jing Qiu, Shu-Tao Xia, Fang-Wei Fu

原文摘要

In this paper, we study the minimum subpacketization of $(n,k)$ Reed-Solomon (RS) codes over $\mathbb{F}_{q^\ell}$ admitting cut-set-optimal exact $\mathbb{F}_q$-linear repair of every coordinate from any $d$ helpers. For $3\le k<d\le n-1$, write $s=d+1-k$ and denote this minimum by $\ell_{min}(n,k,d;q)$. Using divisibility and relative-degree constraints on cross-ratio fields of evaluation sets, we establish $\ell_{min}(n,k,d;q)\ge sG_s(d+1)$, where $G_s(m)$ is the minimum product of $m$ pairwise coprime integers, each at least $s$. Let $Δ_s(n,d)$ be the minimum of $lcm(a_1,\ldots,a_n)$ over positive integers $a_1,\ldots,a_n$ satisfying $lcm(a_j:j\in J\cup\{i\})\ge s~lcm(a_j:j\in J)$ for every $d$-subset $J\subseteq[n]$ and every $i\in[n]\setminus J$. We construct RS codes with subpacketization $sΔ_s(n,d)$ and further prove that $\ell_{min}(n,k,d;q)=sΔ_s(n,d)=sG_s(n)$ whenever $d(d+2)\geq 4(n+1)$, for every prime power $q$. In particular, this determines the minimum subpacketization in the full-helper case $d=n-1$, resolving the corresponding exact linear-repair case of Open Problem 20 posed by Ramkumar et al. in their survey on codes for distributed storage. We further give a finite formula for $G_s(n)$ and determine the exact threshold for its closed-form expression in terms of the first $n$ primes. For fixed $k$ and $d$, we prove $\log\ell_{min}(n,k,d;q)= Θ_{k,d}(\log n\log\log n)$ as $n\to\infty$, using divisor-function estimates and cover-free families. An affine-plane construction shows that $Δ_s(n,d)<G_s(n)$ for some parameters, so $sG_s(n)$ is not a universal formula. We conjecture that $\ell_{min}(n,k,d;q)=sΔ_s(n,d)$ for every prime power $q$ and all $3\le k<d\le n-1$.

cs.IT

查看论文
arXiv ↗PDF ↗