跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+0新增论文
+0其中 AI 相关
+0已有论文修订
+93新增 AI 导读

arXiv 最近完成扫描:2026-11-16 01:34 · 全站最近入库:2026-11-14 15:09各信源进度 →

统计口径与数据新鲜度

统计 2026-11-15 10:31 — 2026-11-16 10:31(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:2026-11-16 01:34最近发现新增版本:2026-11-14 15:09库内论文最新更新时间:2026-11-13 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。

23,348 已收录论文19,580 AI 相关6,729 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 17,362 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-16 01:33(北京时间)
新论文 · v1arXiv:2611.05542

Towards Efficient Whole Page Ranking with One-Pass Inference

Qi Xu, Zhigang Hua, Zijie Lei, Yan Xie, Jizhe Zhang, Lynn Lu, Delun Du, Sha Hua 等 13 位作者

原文摘要

Whole-page ranking jointly optimizes advertisements and organic content to balance business outcomes and user engagement under complex layout and business constraints. Existing non-autoregressive (NAR) approaches enable efficient page generation but typically score candidate items independently of previously selected items, limiting their ability to capture order-dependent interactions. Autoregressive (AR) methods address this limitation through sequential conditioning, but incur substantial inference overhead that challenges large-scale deployment. Bridging this quality-efficiency gap remains a challenge in industrial whole-page ranking. We propose Multi-Item Scoring (MIS), a prefix-aware NAR-style framework that incorporates sequential context into efficient multi-item scoring. MIS integrates global candidate interactions, localized prefix conditioning, and position-aware scoring within a shared representation architecture. By computing reusable representations once per request and performing lightweight prefix-conditioned scoring during constrained beam search, MIS captures important sequential dependencies without repeated full-model inference. Experiments on KuaiRand-1K and RL4RS demonstrate that MIS approaches the generation quality of an autoregressive CGA baseline while achieving 4.07x and 3.54x faster CPU decoding, respectively. In a randomized evaluation on a large-scale social-video platform, MIS improves the realization metric by 0.104% and watch time by 0.058%, while reducing ranking-service CPU consumption by 9.73%. These results demonstrate that prefix-aware multi-item scoring can narrow the quality gap between NAR and AR generation while retaining the efficiency required for industrial scalability.

cs.AI · stat.ML

新论文 · v1arXiv:2611.05539

Rewrite, Then Veto: Rewriter-Agnostic Edit Gating for LLM-Based Post-OCR Correction

Jorge Ramón Fonseca Cacho

原文摘要

LLMs can repair noisy OCR transcripts of historical documents, but they also change text that was already correct. We propose EditVeto, a veto gate placed after a full-context LLM rewrite. The rewrite is character-aligned to the OCR input, its differences are split into blocks, and a 0.6B-parameter gate keeps or reverts each block. An oracle analysis motivates the design: given the true error locations, per-span generation is worse than no correction, whereas vetoing a full rewrite's edits helps. Trained on rewrites by two Qwen3 models and evaluated, frozen, on the eight HIPE-OCRepair-2026 test sets, the gate improves all five rewriters tested, two of them unseen in training: weighted cMER falls by 0.0026-0.0044 and the preference score rises by 0.15-0.25 (paired bootstrap, p ~ 0.0002 each). On published competition outputs it lowers cMER for three of four teams but raises it for the winning run (0.0050 to 0.0065). In a second, disclosed test look, a retrained gate still improves LoRA-tuned rewriters (cMER -0.0011 to -0.0021), and an ensemble of their gated edits reaches a cMER of 0.0069 and a preference score of 0.928, mostly through fine-tuning and pooling rather than gating. Built only on public models and data, it is behind the winner (0.0050) and tied with the second-ranked run (0.0071), both from the only team using domain pre-training, and ahead of all other published runs. A third, secondary look shows the unchanged gate improving zero-shot Qwen3.8-27B (cMER 0.0114 to 0.0108) but only the preference score of its LoRA-tuned version.

cs.CL · cs.CV

版本更新 · v2arXiv:2606.09258

Back to the Familiar Future: Failure Recovery for VLA Policies via Pre-Imagined Milestone Selection

Suyeon Shin, Juwon Kim, Hyeonbin Park, Hyunseo Kim, Hyundo Lee, Hyung-Sin Kim, Byoung-Tak Zhang

原文摘要

Vision-language-action (VLA) policies can deviate from nominal trajectories during manipulation, even when tasks remain physically feasible. Recovering from these deviations is challenging, as they push the policy into unfamiliar state spaces where direct re-planning frequently destabilizes action sequences. We propose Back to the Familiar Future (B2FF), a recovery framework for foresight-driven VLAs that leverages future visual conditioning as a recovery interface. Before execution, the VLA generates a milestone bank of familiar future states conditioned on the clean initial observation. At recovery time, a recoverability-aware selector selects a recovery milestone from this bank and enforces it as a fixed visual goal. This enables the VLA to robustly map off-trajectory observations back to a familiar future. On failure-injected LIBERO, under controlled recovery timing aligned with the injected failure, B2FF increases the average success rate of a baseline VLA from 56.3% to 74.0%, demonstrating that pre-imagined milestones can guide recovery without fine-tuning the low-level action generator.

cs.RO

新论文 · v1arXiv:2611.05524

MA-SafeDiffuser: Safe Multi-Agent Planning with Diffusion Probabilistic Models

Kiran Ravish, Ankita Kushwaha, Preeti, Pawan Kumar

原文摘要

We propose MA-SafeDiffuser, a multi-agent extension of SafeDiffuser that equips diffusion-based trajectory planners with finite-time diffusion invariance guarantees for joint-agent safety specifications. Building on the single-agent construction that embeds control barrier function (CBF) constraints into reverse-diffusion updates, we: (i) formalize joint safe sets as intersections of per-agent and pairwise barrier sets; (ii) derive centralized and decentralized (communication-aware) constrained denoising procedures with provable invariance under mild assumptions; (iii) address local-trap and deadlock phenomena via time-varying specifications and liveness CBFs; and (iv) develop a lightweight benchmarking suite including a multi-agent Maze2D domain. Empirically, MA-SafeDiffuser reduces violation counts relative to unconstrained diffusion baselines, while retaining planning quality. We provide algorithms, proofs, and reference implementations.

cs.AI · cs.MA

版本更新 · v2arXiv:2610.32503

Pareto-optimal Non-Clairvoyant Scheduling with Predictions

Ziyad Benomar, Vianney Perchet

原文摘要

We study preemptive single-machine non-clairvoyant scheduling with predictions, where a prediction of the order of the jobs (or of their sizes) is available, and the objective is to minimize the total completion time. An algorithm is $c$-consistent if it is $c$-competitive when the prediction is correct, and $R$-robust if it is $R$-competitive whatever the prediction. Since the introduction of this problem as one of the first examples of learning-augmented algorithms, the best possible trade-off between consistency and robustness has remained open. We determine it exactly for deterministic algorithms. For every $R>2$, we give an $R$-robust algorithm whose consistency is \[ c(R)=R\Big(1-\Big(1-\frac{R+2}{R^2}\Big)^{\frac R{R+2}}\Big), \] and we prove that no deterministic $R$-robust algorithm, with either predicted order or predicted job sizes, has better consistency. In particular, consistency $1+\varepsilon$ is achievable with robustness $\varepsilon^{-1/2}+\frac16+O(\sqrt\varepsilon)$, whereas all previous algorithms required robustness $Θ(1/\varepsilon)$. Our algorithm is greedy: it follows the predicted order as fast as possible, subject to the invariant that the cost paid so far is at most $R$ times the optimum of the instance in which every unfinished job would end immediately. The matching lower bound rests on the observation that every robust deterministic algorithm must satisfy the same invariant along its run on correct predictions. Furthermore, we give a simple randomized algorithm, using predicted sizes, with consistency $1+\varepsilon$ and robustness $(3\varepsilon)^{-1/2}+O(1)$, strictly below the deterministic frontier. The question of determining the Pareto-optimal frontier among randomized algorithms remains open.

cs.DS · cs.GT

版本更新 · v2arXiv:2606.18439

RegimeVGGT: Layer-Wise Spatially Preserving Redundancy Removal for Visual Geometry Grounded Transformer

Jinhao You, Shuo Lyu, Zhuohang Lyu, Tanxuan Li, Zibo Zhao, Jiaxiang Hu, Kai Tang, Yichen Guo

原文摘要

Visual Geometry Grounded Transformer (VGGT) recovers dense 3D scene structure from multi-view images in one forward pass, but quadratic cross-frame attention limits its scalability. Existing training-free accelerators exploit token, frame, or attention redundancy; we investigate how layer-wise functional roles can guide compression. Our spectral, probing, and causal analyses reveal three regimes: shallow layers lack cross-view structure, middle layers drive cross-view alignment, and deep layers are redundant for dense geometry yet their cross-frame attention remains essential for pose. RegimeVGGT applies layer-wise U-shaped compression along two axes: Saliency-Guided Banded Merging protects geometry- and edge-salient tokens, while Selectively Protected K/V Downsampling preserves cross-frame spatial coverage and the pose-critical path through a phase-shifted spatial grid, a reference-frame anchor, and uncompressed camera/register tokens. Without any training, RegimeVGGT achieves a 6.7x speedup over the memory-optimized VGGT* at matched reconstruction quality. Project page: https://tracyou07.github.io/regimevggt/

cs.CV · cs.RO

新论文 · v1arXiv:2611.05517

When to Ask, When to Answer: Strategic Clarification for Ambiguous Reference Resolution in Dialogue

Ibrahim Khebour, Nikhil Krishnaswamy

原文摘要

For humans, referential disambiguation is a collaborative process involving clarification questions asked when they will meaningfully change the outcome. However, large language models (LLMs) have been shown to be biased toward premature answering, preferring definite single-turn responses over more clarification exchanges. In this paper, we study the problem of "strategic clarification" -- asking clarification questions in a reference game when their answers will narrow the set of candidate referents. We construct a controlled test environment from the SIMMC 2.1 dataset that records how many questions each ambiguous reference needs to be successfully resolved, and examine how baseline LLM behavior and common post-training methods ask clarifying questions vs. attempt to answer the referent. We also propose BACE (Belief-Aware Critic with Epistemic tracking), a lightweight action chooser method on top of a frozen LM backbone, and show that BACE more consistently chooses the optimal number of clarifying questions than methods such as GRPO and ArCHer.

cs.CL · cs.AI

新论文 · v1arXiv:2611.05512

SlackBench: Benchmarking Agents on Collaborative Projects Grounded in Real Code Repositories

Mingxuan Li, Huanzhi Mao, Ruitao Zheng, Jarod Stanbury James, Yunze Li, Natanya Anderson, Joseph E. Gonzalez, Alex Dimakis

原文摘要

AI Agents are becoming digital coworkers that can browse the web, write code, run experiments, and assist humans over extended horizons. Yet existing benchmarks fall short of real knowledge work: many rely on synthetic data or isolated tasks, missing the complex, multi-party dynamics of collaborative projects, where critical information is scattered across conversations, code, and evolving decisions. Even simple workplace questions may require locating relevant channels and direct messages, recovering context from long discussions, inspecting repository state, reconciling stale or conflicting evidence, and synthesizing across sources. We introduce SlackBench, a benchmark for evaluating agents on realistic research and engineering workflows that require joint reasoning over workplace communication and evolving repository state. Grounded in privacy-preserving reenactments of real academic research projects, SlackBench provides reproducible environments with realistic multi-party dialogue, evolving decisions, and corresponding code changes grounded in GitHub repositories and Google Docs. It contains 140 queries spanning heterogeneous-source agentic search, abstention on unanswerable or false-premise questions, goal-directed summarization, and circumstance inference over long conversations. These tasks are not reducible to static corpus question answering: agents must determine which conversations matter, traverse threads, inspect repository state, and synthesize evidence across communication and code artifacts. Across 33 frontier models and agent harnesses, the best system scores around 80% and most agents score below 66%, highlighting substantial headroom for improvement. SlackBench thus provides an extensible framework for evaluating agents in collaborative work environments. The SlackBench dataset is available at https://huggingface.co/datasets/HuanzhiMao/SlackBench .

cs.AI · cs.CL

新论文 · v1arXiv:2611.05511

Improved lower bounds on the approximability of Multiway Cut using Sherali-Adams relaxations

Joshua Brakensiek, Neng Huang, Aaron Potechin, Uri Zwick

原文摘要

The Multiway Cut problem is among the most well-studied problems in the area of combinatorial approximation algorithms. The currently best approximation ratio for the problem is 1.2787, obtained recently by the authors (2026). The best lower bound on the approximation ratio that can be achieved for the problem in polynomial time, under the Unique Games Conjecture (UGC), is 1.20016, obtained by Bérczi, Chandrasekaran, Király, and Madan (2020), building on and slightly improving a bound of $\frac65=1.2$, obtained by Angelidakis, Makarychev, and Manurangsi (2017) by introducing the important framework of non-opposite multiway cuts. We obtain a substantially improved lower bound of 1.22232 on the approximation ratio of the Multiway Cut problem. Manokaran, Naor, Raghavendra, and Schwartz (2008) showed that under UGC, the approximation ratio of Multiway Cut is equal to the integrality ratio of a simple LP relaxation, known as the CKR relaxation, introduced by Călinescu, Karloff, and Rabani (2000). Thus, stronger LP relaxations are not required for obtaining an optimal approximation algorithm for the problem. We show, however, that relying on the framework of Angelidakis, Makarychev, and Manurangsi (2017), stronger LP relaxations from the Sherali-Adams hierarchy for non-opposite multiway cuts can be used to obtain improved integrality ratios for the CKR relaxation, and hence improved lower bounds on the approximation ratio of the Multiway Cut problem. One of the novel features of our analysis is considering a continuous limit of discrete LPs defined on a simplex. Our proof of the new 1.22232 bound is completely analytic. We also present strong numerical evidence that suggests that our techniques can be used to improve the lower bound to at least 1.23003.

cs.DS · cs.CC

新论文 · v1arXiv:2611.05509

From Claws to Conferences: Device-Independent Key Agreement Beyond Non-Signaling

Suvradip Chakraborty

原文摘要

Device-independent conference key agreement (DI-CKA) allows a group of users to establish a common secret key without trusting the internal operation of their quantum devices. Existing DI-CKA protocols derive their security from multipartite Bell tests and therefore require the device components not to communicate during each round. We present, to the best of our knowledge, the first DI-CKA protocol that removes this non-signaling assumption: all interfaces and their mutual communication are treated as one untrusted device, which only has to be quantum polynomial-time while the protocol runs. Assuming that the Learning With Errors (LWE) problem is hard for quantum algorithms with quantum advice during the execution, we prove finite-size security against coherent attacks, in which the device may keep quantum memory and correlate and adapt its behavior across rounds. For two parties the protocol is a computational DI-QKD protocol with an explicit finite-size proof against coherent attacks. Technically, we lift the claw state underlying the classical-verifier test of Brakerski et al.\ (FOCS 2018) to multipartite entanglement, obtaining a \emph{GHZ-correlated claw state}. %that is prepared with one coherent claw-free function evaluation and $N-1$ CNOT gates. We then introduce the \emph{collective adaptive hardcore bit}, a multiparty generalization of the adaptive hardcore bit of Brakerski et al.\ and show that it follows from the original property by a tight reduction. Combined with Jordan's lemma, an entropic uncertainty relation, and entropy accumulation, this certifies smooth min-entropy of the key against an external quantum adversary. Our protocol achieves \emph{everlasting security}: LWE needs to hold only during the execution, because the final key is statistically secure and its secrecy persists even if LWE is broken after the protocol ends.

quant-ph · cs.CR

新论文 · v1arXiv:2611.05507

Ctrl-F: Force as an Interface for Humanoid Loco-Manipulation

Mengjie Zhao, Yuxin Chen, Yiyang Shao, Chuye Hong, Jiakang Chen, Koushil Sreenath, Masayoshi Tomizuka

原文摘要

Humanoid motion tracking has scaled to general policies that reproduce diverse human motion, but the resulting behavior is in free-space: the tracker knows where the body should be, not how it should interact with the environment. Other work makes the object part of the objective, yet abstracts that interaction to contact or geometry, which leaves the demanding cases under-explored. We argue that force is a natural command channel between motion imitation and object interaction, one that specifies not just where to make contact but how hard. We present Ctrl-F, a hierarchical motion-force framework that augments motion tracking with an explicit force command, a 3-D force at each designated contact body such as a hand or a foot. The hierarchical framework comprises: (1) A unified motion-force controller tracks the reference motion while applying the commanded force to the world. (2) A high-level force planner that issues a force command online based on object state and proprioception observations. In simulation and on hardware, Ctrl-F completes loco-manipulation that demands large, sustained interaction force and adjusts its command online as the load changes, both out of reach of a force-blind tracker. On hardware, Ctrl-F demonstrates hand-based dragging, pushing, and lifting, as well as foot-based kicking, successfully manipulating boxes weighing up to 20kg in pushing and kicking tasks where the force-blind baseline fails, while adapting online to additional loads introduced mid-task.

cs.RO · cs.LG

新论文 · v1arXiv:2611.05506

Objective-Conditioned Active Preference Learning for Multi-Objective Alignment

Duc Anh Vu, Thong Nguyen, Hoang Pham, Ponhvoan Srey, Luu Anh Tuan

原文摘要

Aligning large language models (LLMs) with several objectives, such as helpfulness, harmlessness, and honesty, typically relies on preference judgment for each objective, growing the annotation cost linearly with the number of objectives. Active preference learning can reduce this cost by selecting the comparisons whose labels are expected to change the policy most. Existing remedies either lack an objective-aware query selection mechanism for the multi-objective setting or regard conflicting preferences as harmful, therefore excluding them from the training data. We introduce OGC-DPO (Objective-conditioned Gradient Coverage DPO), an active learning framework that treats each (response pair, objective) combination as a separate query and measures its informativeness through the policy's own implicit gradient, without relying on an external reward model. OGC-DPO then selects the queries that most expand each objective's gradient coverage. Empirical experiments across varying numbers of objectives demonstrate the effectiveness of OGC-DPO over existing active preference learning methods under the same annotation cost. Further analysis demonstrates that informative conflicts, rather than being uniformly harmful, provide a useful policy training signal.

cs.LG · cs.AI

版本更新 · v2arXiv:2605.23135

The Impact of AI Coding Assistants on Software Engineering: A Longitudinal Study

Annie Vella, Kelly Blincoe

原文摘要

AI coding assistants have become prolific in recent years. Through a longitudinal mixed-methods investigation, we examined how professional software engineers perceive the effects of AI coding assistants in regard to task focus, developer experience, and productivity. Two questionnaires were administered six months apart, yielding 158 eligible participants at the first time point, 101 at the second, and a matched longitudinal cohort of 95. Participants reported spending less time on most development tasks, with 82% reporting less on writing code. We found a broader shift in focus from creation to verification activities. We propose a new category of work we term supervisory engineering work, encompassing the direction, evaluation, and correction of AI output. This construct is broader than the extra review overhead that has been previously reported in literature since it encompasses directing and shaping AI output both before and during creation. We also identified a productivity-experience paradox: consistently positive productivity perceptions alongside eroding developer experience. These findings suggest that AI coding assistants may be reshaping both the nature of software engineering work and how engineers experience it.

cs.SE

新论文 · v1arXiv:2611.05489

Stabiliser codes over prime fields as weighted graphs and as quantum sets of lines

Simeon Ball, Gülizar Günay, Robin Simoens, Ricard Vilar

原文摘要

We further develop the theory of quantum stabiliser codes and its links with graph theory and finite geometry. We prove that an [[n,k,d]]_p stabiliser code over a finite field with p elements, p prime, gives rise to a graph on n-k vertices together with two disjoint independent sets of size k. Its edges are weighted with elements of a finite field of size p. If k=0, such codes are known as graph states. Second, we view stabiliser codes as so-called quantum sets of lines in projective space, allowing us to determined their minimum distance geometrically. We describe two geometrical operations to obtain new quantum sets of lines from given quantum sets of lines. As an application, we list the number of stabiliser codes up to equivalence, for given small parameters.

math.CO · cs.IT · quant-ph

新论文 · v1arXiv:2611.05483

Classical training of conditional instantaneous quantum polynomial-time Born machines

Oriol Balló-Gimbernat, Emiliano Tolotti, Laia Domingo, Fernando Vilariño, Adan Garriga

原文摘要

Instantaneous quantum polynomial-time (IQP) Born machines are attractive quantum generative models, as certain IQP circuit families are conjectured to be hard to sample, yet they can be trained classically. Previously proposed conditional IQP Born machines make the parameters of the diagonal layer condition dependent. We introduce conditional IQP Born machines, in which the condition is encoded in the input state and a single IQP unitary is shared across conditions. Efficient sampling and amplitude-ratio evaluation for the reference state entering the diagonal layer suffice to obtain unbiased classical estimates of a conditional maximum mean discrepancy objective and its gradients. We show that input conditioning can represent conditional families that no diagonally conditioned IQP model with the same number of qubits can reproduce. For the sixteen-qubit Curie-Weiss spin model, a single conditional model captures the magnetization transition at held-out temperatures. Its mean total variation distance is six times lower than that of diagonal conditioning under the same protocol and comparable to that of classical generative models with up to seven times as many parameters. We also train conditional models classically with up to 2048 qubits, which reproduce the mean squared magnetization of the target away from the crossover. These results extend classically trained IQP Born machines to conditional generation.

quant-ph · cs.LG

新论文 · v1arXiv:2611.05377

DreamX:视频扩散模型作为通用潜在动作学习器

DreamX: Video Diffusion Model is a Universal Latent Action Learner

Jisoo Kim, Chaehyun Kim, Junsu Kim, Jiho Park, Seongchan Kim, Eunbeen Hong, Soowon Son, Fu-En Yang 等 9 位作者

AI 速读 基于摘要

作者提出将预训练视频扩散模型改造为通用潜在动作学习器,从视频中提取与外观解耦、可跨具身共享的紧凑潜在动作表示。

cs.CV · cs.AI · cs.RO

查看原文摘要

Learning a universal action representation from video requires modeling dynamics that are consistent across different executions of the same action yet invariant to changes in embodiment and appearance. Existing latent action models infer actions from visual transitions, but their representations often entangle the underlying action with irrelevant visual variations, limiting transfer across embodiments. We introduce DreamX, which repurposes a pretrained video diffusion model as a universal latent action learner. Our approach extracts compact latent actions from the video model's rich spatiotemporal features, compressing each latent video frame by $\boldsymbol{300\times}$ ($\boldsymbol{1{,}200 \rightarrow 4}$ tokens). In addition, by leveraging the video model's generative prior, these latent actions capture action-relevant dynamics disentangled from visual appearance. The resulting latent space serves as a shared action interface across embodiments (human and robot), environments, and action parameterizations. On LARY-Bench, DreamX achieves state-of-the-art performance among latent action models. Moreover, actions encoded in one setting remain effective in another: the latent space supports any-to-any video transfer and zero-shot action transfer across diverse embodiments and environments. Furthermore, this shared interface also enables policy learning in a compact latent action space, reducing the computational cost of video-diffusion-based policies.

新论文 · v1arXiv:2611.05373

将语言模型与通用偏好对齐:直接纳什优化的实证研究

Aligning Language Models with General Preferences: An Empirical Study of Direct Nash Optimization

Austin Tsai, Saurav Nanda, Ganapathy Parthasarathy, Bhuvnesh Kumar, Parivesh Choudhary

AI 速读 基于摘要

作者独立复现并实证研究了直接纳什优化(DNO)的实用变体 DNO-Prct,在两个开源指令模型上考察其对齐效果、成本及与理论的偏离。

cs.LG · cs.AI · cs.CL

查看原文摘要

Direct Nash Optimization (DNO) aligns a language model to a general preference function by approximating the Nash equilibrium of a two-player preference game. Its practical variant, DNO-Prct, iterates on-policy sampling, LLM-based rating of the samples together with a teacher's gold response, large-margin preference-pair selection and a DPO-style contrastive update. We re-implement DNO-Prct independently and study it on two open-weight instruct models, Llama 3.1 8B Instruct and Mistral 7B Instruct v0.1, with GPT-4o or a larger open-weight model of the same family as the annotator. On AlpacaEval 2.0 with GPT-4o as judge, three iterations raise the length-controlled (LC) win rate against GPT-4o from 31.7% to 45.3% for Llama and from 6.8% to 18.4% for Mistral, and the tuned 8B model scores above Llama 3.1 70B Instruct on every reported win rate. With same-family open-weight annotators, the runs retain 62% (Llama) and 82% (Mistral) of the LC gain achieved with GPT-4o as annotator, so the rating step does not require a proprietary model. In a separate ablation configuration, variants that remove the gold responses, remove the data look-back, or accept only teacher-preferred pairs score 6 to 10 LC points below the full procedure, whereas varying the number of on-policy samples per prompt (1 to 7) moves the LC win rate by at most 2.1 points, and a margin sweep (1 to 5) run in its own pipeline by at most 2.4 points. We also report the cost of the pipeline and where the practical algorithm departs from the theory it approximates. All results are single runs, and GPT-4o is both the teacher and the evaluation judge; we discuss what this implies for the reported gains.

版本更新 · v2arXiv:2610.37652

基于学习安全滤波器的灵巧手内物体位姿到达

Dexterous In-Hand Object Pose Reaching with Learned Safety Filters

Ian Chuang, Hiya Shah, Vamsi Chilamkur, Iman Soltani, Claire Tomlin

AI 速读 基于摘要

面向LEAP灵巧手的手内物体位姿到达任务,作者提出无需人类数据的仿真训练方案,使策略零样本迁移到真实手,并叠加可调保守度的学习残差安全滤波器以减少掉落。

cs.RO · cs.LG · eess.SY

查看原文摘要

Dexterous manipulation with multi-fingered hands is the next frontier of robotics, yet learned hand skills remain limited to simple grasps or basic repeated motions, such as rotating an object. As robots attempt more demanding in-hand maneuvers, safety, such as not dropping the object, becomes critical, yet it is rarely measured. We study in-hand object pose reaching, a task that demands diverse and difficult grasps: moving an object to almost any position and orientation within reach of the fingers, at any wrist orientation, through long sequences of consecutive goals. We present a recipe for training such policies for a LEAP hand in simulation without human data, built on a range of insights, from diverse resets and goals via generated grasp datasets to an adaptive friction curriculum. With careful system identification, the policies transfer zero-shot to the real hand, using either motion capture or a single wrist-mounted depth camera, and prove remarkably capable and robust. On top of the task policy, we add a learned residual safety filter with adjustable conservativeness, letting us tune the balance between performance and safety and greatly reduce object drops. In 13.3 hours of real-robot evaluation over 4,800 unseen goals across 4 objects and diverse wrist orientations, the state-based policy reaches 95.2% of goals within 2 cm and 0.4 rad, and the filter cuts its drops by 75% while still reaching 91.5% of goals. The policies can also spin a lightbulb held in an arbitrary pose, reach out-of-distribution goals, withstand fast arm motion and perturbations, and, needing only a wrist camera, serve as portable skills such as screwing in a lightbulb. We release the full recipe as a platform for studying performance, reliability, and safety in high-dimensional dexterous systems. Videos and more are available at https://ian-chuang.github.io/dexsafe/.

新论文 · v1arXiv:2611.05368

GUILD:面向模仿学习的引导式迭代数据收集

GUILD: Guided Iterative Data Collection for Imitation Learning

Shivin Dass, Kevin Nguyen, Rohan Yelandur, Junhong Xu, Roberto Martín-Martín

AI 速读 基于摘要

GUILD 提出一种引导式数据收集方法,利用视觉语言模型的语义先验提出采集任务,并用预测性数据归因评估轨迹对目标部署性能的影响,形成迭代闭环以提升模仿学习的数据效率与部署表现。

cs.RO · cs.LG

查看原文摘要

Imitation learning policies in robotics are trained on datasets collected through costly real-world teleoperation. Often, the data-collection process is unguided, relying on the teleoperator's intuition, resulting in data that contributes little to overall policy performance. Recent work has shown that curating such unguided datasets can substantially improve policy performance, but these approaches operate by filtering existing datasets after collection and therefore do not prevent the acquisition of uninformative data. In this work, we propose GUILD, a novel Guided Data Collection (GDC) method that actively reasons about which data should be collected to maximize downstream policy performance. We introduce an iterative framework that alternates between 1) task proposal and data collection and 2) data evaluation to close the loop. For task proposal, we leverage semantic priors from vision-language models to identify relevant environments, object configurations, and goals for data collection. However, since semantic relevance does not imply policy improvement, we perform data evaluation. By leveraging predictive data attribution we approximate how the collected trajectories influence policy performance on a target deployment setting. This signal is then used as feedback to guide subsequent data collection, closing the data collection loop. We evaluate our approach in simulation and real robot settings, demonstrating that guided data collection substantially improves sample efficiency and deployment performance compared to passive data collection strategies, multiple baselines and experienced roboticists. More information at https://robin-lab.cs.utexas.edu/guild2026/

新论文 · v1arXiv:2611.05459

Can Large Language Models Review the Scientific Literature? A Test Against a 102-Article Benchmark

Abdullah Al Kalbani, David M. Schultz, Alexandra K. Anderson-Frey, Zhonghua Zheng, Catherine McGuire

原文摘要

Large language models (LLMs) are increasingly used to support scientific literature reviews, yet evaluations often examine individual tasks rather than the review process as a whole. We assess six AI tools across four stages: finding relevant articles, interpreting them, synthesizing across them, and proposing future research. The benchmark is a published review of the Spanish plume weather pattern and its 102-article corpus. In the initial searches, five tools collectively identified 57 articles, with the best individual tool finding 42. Institutional library access increased discovery from 42 to 82 articles for Codex and from 15 to 79 for Claude Code. Given the complete corpus of 102 PDFs, three tools correctly identified all 18 articles discussing the Spanish plume substantially, but incorrectly classified 40% to 79% of the 84 passing mentions as substantial. The same three tools produced syntheses evaluated blindly by two domain experts. Although largely accurate, the syntheses provided limited insight and sometimes contained unsupported claims, quotation errors, and exaggerated statements of consensus. Finally, all three tools proposed research directions broader than the Spanish plume literature, although two approached questions identified in the benchmark review. No single tool performed best across all tasks. We provide eight recommendations for researchers using AI tools in literature reviews. Our findings suggest that LLMs can assist with discovering and interpreting scientific literature, particularly when institutional access is available, but cannot replace expert judgment in evaluating evidence or synthesizing research.

cs.AI · cs.DL

版本更新 · v2arXiv:2608.19490

基于自示范生成控制的多任务操作VLA微调

Fine-Tuning VLAs with Self-Demonstrated Generative Control for Multi-Task Manipulation

Prachi Garg, Steve Xing, Prahit Yaugand, Saurabh Gupta, Derek Hoiem

AI 速读 基于摘要

提出一种自监督方法,用零样本VLA生成的在线交互轨迹作为额外训练数据来微调VLA,从而在新机器人上获得多任务操作策略。

cs.RO · cs.CV · cs.LG

查看原文摘要

State-of-the-art vision-language-action (VLA) models such as pi0.5 exhibit strong semantic understanding, instruction following and task behavior. However, when deployed on new robots, even minor mismatches in hardware configuration relative to pretraining can cause severe performance drops. Finetuning the VLA on in-domain expert data from the new embodiment improves performance on the expert task but leads to a loss in its original instruction following and behavioral priors. In this paper, we propose a self-supervised method that generates online interaction rollouts from the zero-shot VLA as additional training data for finetuning. Our experiments show this yields strong multi-task manipulation policies on the target robot that (1) inherit pretrained tasks distilled from the zero-shot VLA without expert demos for them, (2) improve success and generalist instruction following beyond expert-only fine-tuning on expert-teleoperated tasks, and (3) mitigate forgetting of held-out tasks from the pretrained policy, not part of fine-tuning. We demonstrate the success of our approach across test sets probing generalization on a real ALOHA robot and a new simulation benchmark in RoboTwin. Video results are available at https://self-supervised-control.pages.dev/

新论文 · v1arXiv:2611.05366

图运算下Weisfeiler-Leman等价性的传递

Transfer of Weisfeiler-Leman equivalence under graph operations

Dmitriy Kunisky, Hamilton Sawczuk

AI 速读 基于摘要

研究图运算Φ下WL等价关系的传递参数τ_Φ(k),并精确确定线图及(r,S)-线图的传递参数。

math.CO · cs.DM

查看原文摘要

The Weisfeiler-Leman algorithms WL(k) for $k\ge1$ form a hierarchy of increasingly powerful tests for graph isomorphism. We study how the equivalence relations they induce on graphs transfer through a graph operation $Φ$: for a given $k$, what level of WL-equivalence between graphs $H_1$ and $H_2$ guarantees WL(k)-equivalence of graphs $Φ(H_1)$ and $Φ(H_2)$? We call the least such level the transfer parameter $τ_Φ(k)$ and determine it exactly for the line graph operation $Φ= L$: $τ_L(k)=2k+1$ for $k\ge2$, while $τ_L(1)=1$. We also extend these results to the $(r,S)$-line graphs, which generalize the line graph from edges to $r$-cliques by connecting two cliques when their intersection size lies in a prescribed set $S$. For these operations we prove that $τ_{r,S}(1)=r-1$ for every $S$ and, for certain choices of $S$, that $τ_{r,S}(k)=rk+r-1$ for $k\ge r$, and we bound the transfer parameter in the remaining range. Our upper bounds on transfer parameters follow from a treewidth analysis of diagrammatic expansions of homomorphism counts into $Φ(H)$ as linear combinations of homomorphism counts into $H$. The matching lower bounds combine explicit constructions of witness graphs with the homomorphism-distinguishing closedness of graphs of bounded treewidth.

新论文 · v1arXiv:2611.05457

Hybrid LLM-Deterministic Pipelines for Enterprise-Scale Code Migration at Bloomberg

Mario Corchero, David Williams, Laszlo Kiss Kollar, Haowen Liu, Shivam Bairoliya, Gala Malbasic, Serkan Kirbas, Federica Sarro

原文摘要

Large organizations carry a long tail of infrastructure migrations that are worth doing but rarely urgent enough to compete with feature work, because each one costs significant engineering time per repository. This paper reports on our industrial experience from Automated Uplift, a multi-month initiative applying LLM-assisted migration pipelines across thousands of Bloomberg repositories. We examine two distinct production campaigns: a heterogeneous Python packaging migration (approx. 1,900 candidate repositories) and a uniform C++ build system migration (approx. 6,700 candidate repositories). Together, these campaigns generated 2,333 pull requests, resulting in 729 successful migrations. We detail our hybrid architectural solution which maximizes deterministic processing, confines the LLM to bounded file transformations within a pre-computed context, and incorporates runtime production telemetry (such as execution logs and usage traces). Our findings show that generating migrations turned out to be the easier part; the bottleneck was the cost, for owning teams, of reviewing, testing, and deploying them. These costs were lowered when changes could be verified directly in the pipeline before opening a PR (as with C++ compilation and test validation), and when the population was uniform enough for fixes to carry over from one repository to the next. We conclude by distilling our experience and findings into actionable, transferable patterns for architecting hybrid LLM-deterministic pipelines and scaling code migrations across the enterprise

cs.SE · cs.AI

新论文 · v1arXiv:2611.05361

面向植被丰富环境视觉三维重建基准的可见性感知参考生成

Visibility-Aware Reference Generation for Benchmarking Visual 3D Reconstruction in Vegetation-Rich Environments

Zhipeng Zhong, Matthew Coombes, Cunjia Liu

AI 速读 基于摘要

提出基于LiDAR的参考生成流程,用LDGVS可见性评分改进HPR滤波,为植被户外场景的视觉深度估计与三维重建提供评测基准。

cs.CV · cs.RO

查看原文摘要

Reliable evaluation of visual 3D reconstruction and depth estimation in vegetation-rich outdoor environments is limited by the scarcity of geometric ground-truth data and the cost of complete scanner surveys. We present a LiDARbased reference-generation pipeline for evaluating the zero-shot performance of feed-forward visual-geometry models alongside conventional structure-from-motion (SfM) methods. The pipeline reuses camera images, LiDAR scans, and reference poses from existing multi-sensor localization datasets to generate per-view depth maps and visible reference point clouds. To address visibility errors in accumulated LiDAR scans, we introduce the LargeDepth-Gap Visibility Score (LDGVS) for point-wise visibility filtering and automatic scale selection in Hidden Point Removal(HPR). Experiments on TartanAirV2 and TartanGround show that, compared with Poisson surface reconstruction, which is an approach suited to completed scan surveys, the combined HPR and LDGVS filtering retains approximately three times the point density at comparable absolute relative error. We also apply the pipeline to the BotanicGarden dataset to systematically compare depth estimation and 3D reconstruction methods. Feedforward methods produce dense depth predictions efficiently, but their 3D reconstructions can contain duplicated structures. Conventional SfM generally produces more coherent geometry, but its reconstructions remain sparse and more prone to failure in challenging vegetated scenes. The benchmark toolkit and datasets will be released.

新论文 · v1arXiv:2611.05348

OpenBrain:面向全脑MRI分区、可审计的生成标签发布

OpenBrain: An Auditable Generated-Label Release for Whole-Brain MRI Parcellation

Qizhen Lan, Yu-Chun Hsu, Yuxiang Wei, Lijing Zhu, Zenan Sun, Liang He, Lishan Yu, Xiaoqian Jiang

AI 速读 基于摘要

作者提出并发布OpenBrain,一个带置信度与可审计证据的全脑MRI生成分区标签数据集,让用户能按风险筛选、加权或复核生成标签。

cs.CV

查看原文摘要

Automatic tools can now generate whole-brain MRI parcellations at cohort scale, but generated-label releases often provide little evidence about which cases are reliable enough to reuse. We introduce OpenBrain, a confidence-aware release of 35,838 provenance-verified OpenNeuro T1w cases from 607 source datasets. OpenBrain is organized as an auditable case-record release rather than a directory of standalone segmentation files: each record links a primary parcellation, two committee parcellations, source/license provenance, raw QC-7 measurements, percentile risks, a combined risk score R, and a confidence tier. QC-7 is a reference-free reliability panel over label geometry, image-label consistency, and committee disagreement, so users can filter, weight, audit, or re-threshold generated labels without rerunning inference. We evaluate this released evidence under a frozen protocol. Across external cohorts, lower QC-7 risk corresponds to higher generated-label quality; in fixed-budget training, lower-risk selections improve paired macro Dice over random selection by +3.2 to +3.7 percentage points. OpenBrain also exposes raw axes, committee outputs, provenance, and datasheet documentation, so confidence claims remain inspectable after download. It does not turn generated labels into manual annotations or clinical-grade segmentations. Its contribution is a large open generated-parcellation substrate, a reusable case-level risk-evidence layer, and an external validation protocol for release-time QC. Dataset: https://huggingface.co/datasets/lanqz7766/OpenBrain. Code: https://github.com/lanqz7766/openbrain.

新论文 · v1arXiv:2611.05346

通过模仿实现不可知学习

Agnostic Learning by Imitating

Sílvia Casacuberta, Parikshit Gopalan, Varun Kanade, Omer Reingold, Konstantinos Stavropoulos, Pranay Tankala

AI 速读 基于摘要

作者证明不可知学习与多准确度(生成式不可区分)任务在计算复杂度上等价,并给出从多准确度到不可知学习的高效归约。

cs.LG · cs.CC · cs.DS

查看原文摘要

Given a class of machine learning models and sample access to a data distribution with binary labels, which computational task is harder: training a discriminative model that distinguishes positive and negative labels as well as the best member of the class, or training a generative model whose outputs are indistinguishable from real data by all members of the class? We prove that these two fundamental tasks in computational learning theory are not just closely related, but actually equivalent to each other in complexity. One direction of this equivalence was previously known. Indeed, the powerful regularity lemma in complexity theory gives an efficient oracle reduction from the indistinguishability task (a.k.a. multiaccuracy) to the distinguishing task (a.k.a. agnostic learning) in the style of boosting algorithms. Our main contribution is an efficient oracle reduction in the other direction. Taking this idea further, we show that a multiaccuracy oracle is a remarkably powerful primitive, achieving not just agnostic learning but also a wide range of seemingly more demanding learning objectives via similarly efficient and direct constructions. Our results crucially use the power of making adaptive queries to the oracle, and stand in stark contrast to prior work, which showed that post-processing a single multiaccurate predictor is insufficient for even weak forms of learning. On a technical level, we draw a connection between our (offline) problem and a version of no-regret learning in the online setting, which allows us to use follow-the-leader type algorithms to modify the label distribution and aggregate the predictions of the multiaccuracy oracle.

新论文 · v1arXiv:2611.05345

对抗性推测推理提升长程智能体能力

Adversarial Speculative Reasoning Improves Long Horizon Agents

Hongyin Luo, Wei Fang, Lijie Yang, Owen Stepan, Daniel Suit, Jeff Krapf, Dana Wensberg, Jack O'Brien

AI 速读 基于摘要

作者提出将推测解码从纯加速机制转变为上下文精度分配器,通过训练草稿模型在关键推理点被拒绝,以提升长程智能体的推理准确率。

cs.AI

查看原文摘要

Speculative decoding has been treated purely as a systems optimization that speeds up large language model decoding without changing the model behavior. Under this view, the growing effort to train better draft models has been focused solely on acceptance rate. We argue that this view does not hold true for long-horizon agent reasoning. Measuring frontier open-weight models on complex agentic tasks with different speculative decoding approaches, we found that numerical noise grows within verification windows, and the draft acceptance results of the thinking process can change the output distribution of the model after 30 steps, thus noticeably influencing the reasoning accuracy of long-horizon agents in random directions. In this work, we improve the reasoning capability of target models by controlling such noise. While we cannot change the overall token distribution verified by the target model, we can encode critical reasoning with highest precision by training the draft model to be rejected. We identify these points in agent traces and train the draft model to favor adversarial preference. At inference the trained draft and the target part ways precisely at these decision points, verification restarts, so that critical thinking tokens are sampled from the target model and encoded under its least noisy conditions. This approach makes critical reasoning better indexed and more durable over a long horizon. On complex agentic coding benchmarks, our approach raises end-to-end success rate with no change to the target model or its output distribution. Our results recast the speculative decoding mechanism from a pure accelerator into an active allocator for context precision that improves the accuracy of long-horizon agents by training 0.06% to 0.28% of hosted parameters.

新论文 · v1arXiv:2611.05344

上下文学习的电路机制

A Circuit for In-Context Learning

Andrew Gao, William Gao

AI 速读 基于摘要

作者报告在三个3-4B参数Transformer中,少样本任意标签句子分类的上下文学习可分解为门控的键值联想查找电路。

cs.CL · cs.LG

查看原文摘要

In-context learning (ICL) lets a pretrained language model perform a task specified by demonstrations in its prompt, with no parameter updates. With arbitrary labels the model must acquire a mapping it cannot have memorized, so the learning happens within a single forward pass. Prior work found candidate parts but not how they compose. We give the composition for few-shot sentence classification with arbitrary labels in three 3-4B-parameter transformers. The model implements a key-value memory over label-token positions: each label token's residual stream encodes the label's identity, and middle-layer attention heads write into it the class of the preceding demonstration as its key. At the query, upper-layer heads match the query's class against the stored keys and copy out the matching labels. An early-layer signal encoding whether any label has repeated gates this readout; in its absence the readers attend to the start of the prompt and no label is favored. A separate set of heads suppresses the most recently seen label. Each step is established causally by activation patching, head ablations against random-head baselines, and steering with the model's own signals. A softmax model of the readout with two constants per head, fit on one prompt distribution, predicts another. The computation is conserved across the three models, the named heads alone reproduce the behaviour, and a transformer trained from scratch grows the same parts. The circuit transfers to semantic concepts and to labels with meaning, and the same parts, with a causal gate, appear from 0.6B to 8B in one family and survive instruction tuning. ICL in this setting is a gated associative lookup built from a few identifiable component types, traced causally from demonstrations to prediction.

版本更新 · v2arXiv:2606.31004

Where the Real Clips Came From: Corpus Identity in AI-Generated Video Detection

Mert Onur Cakiroglu, Zhihe Lu, Mehmet Dalkilic, Hasan Kurban

原文摘要

Benchmarks for detecting AI-generated video take their real clips from a few curated collections, so a clip's label is collinear with where it came from. We call a score's dependence on this origin corpus identity, and we measure it on four benchmarks and six real collections. Three probes read a file's declared frame types, the motion vectors its codec stores, and the frames' appearance. Frame-type counts alone separate real from generated at AUC 0.999 on GenVidBench, and re-encoding every clip with one setting at a fixed length still leaves 0.61 to 0.63 on three benchmarks. We introduce a fixed frame-type pattern that removes this leak from every clip of at least 2 s. The same re-encode lowers the ReStraV detector on GenVidBench from 0.85 to 0.60, just above the 0.59 its features reach between two real collections, because its 8 fps repeats frames in real clips. Motion vectors alone separate real collections from one another at AUC 0.51 to 0.98, and only one benchmark ships the two labeled real sources needed to measure this separation within it. In deployment, with each threshold set to flag 5% of its training benchmark's real clips, the motion-vector and appearance probes and linear readouts on ReStraV and WaveRep features each flag 15% or more of another real collection. Choosing the threshold on real videos from the target collection brings the rate back to about 5%, at the cost of catching fewer generated clips. Clearing the real-vs-real level does not guarantee replication: of the six feature sets whose GenVidBench score clears it by 0.15 or more, only WaveRep's two keep their score on AIGVDBench. A benchmark score is therefore best read together with that level, a score on a second benchmark, and false-positive rates on other real collections. The toolkit and the clip lists of every evaluation set are at https://github.com/KurbanIntelligenceLab/vidaudit.

cs.CV

版本更新 · v2arXiv:2602.02785

Smell with Genji: Rediscovering Sensory Experience with an AI Co-Smelling Partner

Vera Yu Wu, Awu Chen, Yunge Wen, Yaluo Wang, Jiaxuan Olivia Yin, Yichen Wang, Qian Xiang, Richard Zhang 等 10 位作者

原文摘要

Olfaction contributes substantially to human perception, yet the olfactory-verbal gap often leaves people struggling to articulate what they smell. We present Smell with Genji, an AI-mediated interactive experience adapting Genji-kō, a traditional Japanese scent-matching game. This practice maps comparative judgments across a sequence of scents onto Genji-mon, providing visual patterns as shared reference points for communication. Within this framework, we introduce an AI co-smelling partner integrating multichannel olfactory sensing, a Transformer-based classification model, and a large language model (LLM)-driven conversational interface to translate sensor signals into descriptive dialogue. Rather than deploying machine olfaction purely for identification, the system positions the AI as a co-present partner sharing its sensory impressions while human judgment remains open. Placing the machine's perspective alongside human intuition creates a space for shared reflection, encouraging participants to deliberately evaluate and articulate their choices. This work explores how computational systems can support sensory interaction grounded in dialogue, fostering reflective articulation and preserving human agency in making sense of the olfactory world.

cs.HC