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

+2471新增论文
+2025其中 AI 相关
+163已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-10 22:42 · 全站最近入库：2026-11-10 15:22各信源进度 →

统计口径与数据新鲜度

统计 2026-11-09 22:59 — 2026-11-10 22:59（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：2026-11-10 22:42最近发现新增版本：2026-11-10 15:22库内论文最新更新时间：2026-11-10 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。

20,643 已收录论文17,531 AI 相关5,643 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 15,443 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-10 22:38（北京时间）
版本更新 · v3arXiv:2605.01418

TimeTok: Granularity-Controllable Time-Series Generation via Hierarchical Tokenization

Seokhyun Lee, Jaeho Kim, Changjun Oh, Mihaela van der Schaar, Changhee Lee

原文摘要

Time-series data are inherently multiscale, spanning diverse temporal granularities from coarse trends to fine-scale dynamics. However, existing time-series generative models provide limited control over the temporal granularity of both inputs and outputs, restricting their ability to condition on user-provided coarse sketches and generate samples at a desired target granularity. To address this, we introduce TimeTok, a unified framework for Granularity-Controllable Time-Series Generation (GC-TSG), which generates time series at any target granularity from any coarser input (e.g., rough sketches) or without conditioning. At the core of TimeTok is a hierarchical tokenization strategy that maps time series into an ordered sequence of tokens, from coarse to fine temporal granularity. Our autoregressive generation process operates across these granularity levels, producing token blocks that are decoded back into continuous time series. This design naturally enables GC-TSG within a single framework, where controlling the number of token blocks provides explicit control over output detail. Experiments show that TimeTok excels at GC-TSG tasks while achieving state-of-the-art performance in standard generation. Furthermore, we showcase TimeTok's potential as a foundational tokenizer by training on multiple datasets with heterogeneous temporal granularities, verifying strong transferability that consistently outperforms models trained on individual datasets. To our knowledge, this is the first unified framework that covers the full generative spectrum for time series, offering a valuable foundation for models that benefit from diverse temporal granularities.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2512.18563

OpenView: Empowering MLLMs with Out-of-view VQA

Qixiang Chen, Cheng Zhang, Chi-Wing Fu, Jingwen Ye, Jianfei Cai

原文摘要

Recent multimodal large language models (MLLMs) show great potential in natural image understanding. Yet, they perform well, mainly on reasoning in-view contents within the image frame. This paper presents the first study on out-of-view (OOV) understanding, i.e., the ability to reason about objects, activities, and scenes beyond the visible frame of a perspective view. Our technical contributions are threefold. First, we design OpenView, a four-stage pipeline that leverages panoramic imagery for large-scale and diverse multi-choice VQA synthesis, where full-scene coverage enables flexible view framing while preserving global scene awareness. Second, we curate OpenView-Dataset, a high-quality synthetic dataset from diverse real-world panoramas to empower MLLMs upon supervised fine-tuning. Third, we build OpenView-Bench, a benchmark that jointly measures choice and rationale accuracy for interpretable and diagnosable evaluation. Experimental results show that despite having a large gap from human performance in OOV VQA answer selection, multiple MLLMs, upon empowered by OpenView, can consistently boost their performance, uplifted from 48.3% to 62.3% on average. Code, benchmark, and data are available at https://github.com/q1xiangchen/OpenView.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09060

Fair Selection of Generalized Nash Equilibria: A Comparability Perspective

Sophie Hall, Heinrich H. Nax, Saverio Bolognani

原文摘要

Generalized Nash equilibrium (GNE) problems model self-interested agents coupled through their costs and shared constraints, and arise throughout control applications that allocate a scarce common resource. Such problems typically admit a continuum of equilibria, so any implementation must \emph{select} one. This selection is not neutral: it decides how the cost of the shared constraint is distributed among the agents, a decision often expected to be fair. The variational GNE (v-GNE), which charges all agents a uniform shadow price, is the conventional choice and is frequently advocated as fair. Through the lens of \emph{comparability} from social choice theory, we show that the GNE set itself requires no inter-agent comparability of costs, whereas the v-GNE implicitly assumes cardinal unit comparability, one of the stronger notions. We then introduce the fair GNE (f-GNE), which selects an equilibrium by explicitly optimizing a fairness metric matched to the comparability at hand, and give constructive routes to compute it for single-constraint and linear-quadratic games. An electric-vehicle charging game serves as a running example throughout this self-contained tutorial.

cs.GT · eess.SY · math.OC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09059

Robust Readout of Cross-Point Resistive Arrays via Time-Domain Optimization

Taro Tako, Hiroshi Kaminaga, Taisuke Kobayashi

原文摘要

Cross-point resistive arrays are attractive for high-density tactile sensing because they reduce wiring complexity. However, conventional frequency-based readout methods can become inaccurate in robotic sensing environments, where long interconnects and measurement and environmental noise degrade the observed signals. We propose a time-domain optimization method for robust readout of cross-point resistive arrays. The method determines resistance values by fitting a time-domain observation model to the measured waveform over the interval, rather than relying solely on spectral amplitudes. By exploiting the full waveform, the proposed method improves robustness under noisy observation conditions. In simulations of a 16 x 16 array, the proposed method reduced the mean readout error by 20% compared with the baseline method. Furthermore, validation over 1,000 trials showed that the proposed method achieves more robust estimation than the conventional method, reducing the mean error and standard deviation by 24.6% and 77.6%, respectively. The improvement was also confirmed in cross-point array simulations with resistance distributions emulating tactile sensor responses.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09058

ProtoCouncil: Multi-Encoder Anatomical Prototypes for Prostate Cancer Detection in Micro-Ultrasound

Mohammad Mahdi Abootorabi, Nooshin Maghsoodi, Armin Saadat, Obed Dzikunu, Zhuoxin Guo, Hannes Cash, Ferdinand Luger, Adam Kinnaird 等 11 位作者

原文摘要

Purpose: Micro-ultrasound ($μ$US) is a promising modality for prostate cancer (PCa) detection, but identifying suspicious tissue depends heavily on clinical experience. Models trained on sparse, noisy core-level pathology offer little insight into their decisions and can fail under domain shift. Clinical use needs a traceable decision process and a flag for uncertain predictions. Methods: We introduce ProtoCouncil, in which three foundation encoders (MedSAM, DINOv3 and V-JEPA 2.1) learn case-based prototypes at three anatomical levels: whole gland, needle track and gland sectors. Prototypes are projected onto real training-core regions, and label-free fusion keeps every class logit as a bias plus an exact sum of prototype similarity contributions. Encoder disagreement triggers selective prediction. Results: In five-fold patient-level cross-validation (6,588 cores, 693 patients), ProtoCouncil reaches 82.9% AUROC for clinically significant PCa (csPCa, Grade Group $\geq$3), 4.3 points above the best previously published method. In zero-shot evaluation on two external cohorts, ProtoCouncil achieves higher all-cancer and csPCa AUROC than all previous methods. Nearest same-class exemplars match test-core tumor involvement better than random same-class cases. Externally, csPCa accuracy falls from 79% when encoders agree to 27% when two oppose the fused call. Abstaining on disagreement raises balanced accuracy by 7 and 15 points, while retaining 58% and 54% of the cores. Conclusion: ProtoCouncil grounds core-level predictions in exact similarity-based evidence from real, anatomically indexed training cases, which makes its reasoning interpretable. It achieves the highest csPCa AUROC across three cohorts and identifies unreliable predictions through encoder disagreement.

cs.CV · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09057

Real-Time Short-Response Selection for Spoken Dialogue Systems

Hien Ohnaka, Kazuyo Onishi, Koichiro Yoshino

原文摘要

To realize spoken dialogue systems that can interact naturally with users, it is important for the system to respond to user utterances at appropriate timings. To achieve such natural turn-taking, the system needs not only to predict appropriate response timings but also to mask delays caused by language generation and speech synthesis so that they are not perceived by the user. We propose a real-time short-response selection task that can be integrated with existing turn-taking models to mask generation delay. To address this task, the proposed model learns the mapping between dialogue context and short responses using contrastive learning. When a turn-taking event is detected, the system selects a response from a set of pre-generated candidates. The selected response is played while the main response is being generated. Experimental results show that the proposed method learns to select short responses based on dialogue context, outperforming random and LLM-based baselines. Moreover, integrating response selection maintained turn-taking prediction performance and added minimal processing overhead.

cs.SD · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09055

OmniLatent: Unified Latent for 3D Part Modeling

Yunhan Yang, Yunfei Zhao, Zeqiang Lai, Jiachen Xu, Minxiu Wang, Xintong Han, Xiangyu Yue, Xihui Liu 等 9 位作者

原文摘要

3D part decomposition is a central capability for editable asset creation, yet existing workflows typically segment a completed mesh as a post-processing step, making the result sensitive to geometric artifacts, texture ambiguity, and limited part-level annotations. We present OmniLatent, a unified latent modeling framework for 3D part decomposition. Instead of predicting part labels in isolation, OmniLatent learns a shared latent space that jointly encodes geometry, deformation, appearance, and binary part IDs, allowing data-rich geometric and visual priors to support data-scarce part learning. Given a single input image, the base model generates geometry, deformation, texture, and surface part IDs in one pass, producing a part-aware 3D asset without a separate segmentation stage. We further tune the pretrained model for two extensions: a point-prompt adapter that maps arbitrary 3D point prompts with binary part IDs into latent tokens for full segmentation, refinement, and part subdivision, and an amodal part completion model that completes partial surface masks into a coherent full-object decomposition through dynamic per-part token allocation, cross-attention to the given geometry latent, and alternating part-local and global attention. Extensive experiments show that OmniLatent produces semantically meaningful part segmentations with precise boundaries, supports interactive part editing, and completes partial part observations while preserving global object consistency.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.01454

PROBE: Learned Proxy-Based Execution for Highly Selective Multimodal Semantic Queries

Haikai Zhao, Haisheng Fu, Zhengjie Miao, Zhenman Fang

原文摘要

Large language models (LLMs) enable semantic queries over unstructured data, but invoking an LLM on every row is prohibitively expensive. Proxy-based execution can reduce this ple with the LLM and training a lightweight proxyto label the remaining rows. Nevertheless, in practical scenarios where semantic queries are highly selective, it remainschallenging to identify representative samples foLM budget and to achieve accurate predictions overthe remaining data using the proxy. We present PROBE, a learned proxy-based execution framework for highly selective multimodal semantic queries. PROBE uses selectivity-adaptive sampling to discover rare polightweight proxy on the acquired labels. It thenrefines proxy predictions through residual correction and homogeneity smoothing over a similarity graph. To address sampling bias, PROBE jointly calibrates refined scores usiarate calibration sample, then selectively routescandidates to the LLM by optimizing the tradeoff between estimated F1 and evaluation cost. On queries from SemBench and LRO-Bench with positive rates as low as 2.17x10^-5 budget yields a geometric-mean F1 of 0.762,compared with 0.797 for exhaustive LLM evaluation, at a geometric-mean speedup of 4.87x and a maximum speedup of 9.3x.

cs.DB

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09054

From Emergence to Reversibility: Toward Reversible Multi-Agent Systems

Zhengye Han, Linda Ng Boyle

原文摘要

Multi-agent systems become capable through institutional mechanisms, such as rules that route information to agents that act on it. These mechanisms are also natural places to restrict the system. Yet as agents learn, share memory, delegate, and repair failures, the collective can find other paths to the same effects: a restriction on the original mechanism still operates but no longer stops them, while routine performance and compliance checks pass. We propose \textbf{Reversible Multi-agent Systems} as a research agenda: collectives that grow while an authorized supervisor can still restrict specified effects, keep them restricted as agents adapt, and reconstitute useful cooperation under renewed authority. What is reversed is the ability to produce a specified effect; restrictions must hold even if learned knowledge persists. The goal is to preserve effective intervention, not a particular mechanism: at every step of growth, some authorized intervention must keep a specified prohibited effect rare while maintaining required service. We identify three research problems: tracking what capabilities depend on, handing off control before an old mechanism loses its effect, and separating legitimate repair from unauthorized reconstruction. We outline how to evaluate control across growth paths, back control claims with evidence, and allocate the rights to restrict and restore.

cs.MA

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09052

StreamTab: Training-Free Temporal Link Prediction with Tabular Foundation Models

Mingqi Yang, Renqi Wu

原文摘要

Temporal link prediction uses past interactions to predict whether two nodes will interact in the future. Temporal graph neural networks achieve strong results on this task, but they are trained separately for each graph. How a model should use interaction history also depends on the candidates it is compared with. A past interaction can distinguish a recurring link from a random pair that has never interacted, but when the negative candidates have also interacted before, other signals are needed. We propose StreamTab, a training-free framework built on a frozen tabular foundation model pretrained only on synthetic tables. StreamTab describes each candidate pair by statistics of its past interactions and shows the model recent observed interactions and sampled negative pairs as labeled examples, from which the model scores new candidates. Its central design, regime conditioning, samples the negative examples according to how the candidates are sampled, so the examples show the distinction the model must make. As new interactions arrive, StreamTab updates the statistics and refreshes the examples while the model parameters stay fixed. On thirteen datasets against 21 temporal graph baselines, StreamTab achieves the highest average precision on twelve datasets under historical sampling and eleven under inductive sampling, and ranks first or stays within one point of the best on seven datasets under random sampling. With the same features and model, regime conditioning raises average precision over examples with random negatives by a median of 12.6 points under historical sampling.

cs.LG · cs.DB · cs.SI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09047

Grounding-Aware Judge Reward Reinforcement Learning for Out-of-Domain Face Anti-Spoofing

Xiaoyong Yu, Xinge Yu

原文摘要

Face Anti-Spoofing (FAS) must distinguish genuine faces from presentation attacks. A unified Multimodal Large Language Model (MLLM) is an attractive solution: it detects physical attacks (print, replay, mask) in one model and produces interpretable forensic evidence via Chain-of-Thought (CoT). A central obstacle to post-training such a model with reinforcement learning is that FAS reasoning has no rule-verifiable ground truth: only the binary verdict is checkable, while the reasoning chain cannot be verified by any hand-crafted rule. Optimizing the verdict alone is therefore a sparse, hackable signal. The model can reach the correct answer through a shortcut such as a false-rejection bias, which does not generalize. We address this with a grounding-aware judge reward. A 32B vision-language judge scores each reasoning chain against the image on evidence anchoring, logical coherence, and domain knowledge, turning the image itself into the verification signal. The reward is applied in a Group Relative Policy Optimization (GRPO) stage after CoT supervised fine-tuning. It is the judge, rather than the RL objective, that supplies the process supervision a verdict-only reward cannot. Our study starts from a model that already performs well In-Domain (ID) after CoT-based supervised fine-tuning and asks how to improve its Out-of-Domain (OOD) generalization. We find that grounding-aware rewards are an effective means to that end. We validate the method on OOD generalization, where the reward reduces ACER on two physical benchmarks (LCC-FASD 0.288 to 0.273, MSU-MFSD 0.431 to 0.409) while preserving ID accuracy (CelebA-Spoof 0.033 to 0.035). Against ResNet-50/101 and CLIP-ViT-B/16 baselines, the MLLM dominates ID and matches or surpasses the strongest baseline OOD. To our knowledge this is the first use of LLM-as-judge process supervision for FAS.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09046

When Can You Trust Neural Critics? Auditing Mutual Information Estimates of Higher-Order Epistasis in Protein Language Models

Maryam Rahimimovassagh, Waldemar Karwowski, Niloofar Yousefi

原文摘要

Mutual information (MI) estimation is used to probe what neural representations encode, including in protein language models, but variational MI estimators have variance that scales at least exponentially in the true MI. We audit a prior neural-MI study of order-resolved epistasis in ESM-2 on the four-site GB1 landscape. Run-to-run differences show no systematic bias and a magnitude comparable to ordinary cross-seed retraining variability, and the evaluation-pairing scheme shifts scores substantially. At the original dimensionality, two of three alternative estimator families stabilize the estimate across seeds and one does not. In a synthetic calibration at the representation dimensionalities of two other protein language models (a Gaussian channel with known MI; no model representations), all three families recover materially less signal than required, despite correct signal ordering and stable seeds. A control critic given the true signal direction, which also reduces its input to one dimension, recovers 93.3% and 98.7% of the analytic MI at gain 1.5 (at 5,120 and 4,096 dimensions), so the signal is recoverable with privileged information, but the control does not identify why blind estimation fails. We package the checks into a reusable diagnostic protocol and conclude that even a stabilized estimator is not currently sufficient for order-resolved dependence claims made under blind search at this dimensionality and sample size.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09045

When to Trust the BIM: Identifiability-Aware LiDAR-Inertial--BIM Fusion under As-Built Deviations

Yujie Zhang, Yuxuan Guo, Xinbao Sun, Chunlei Zhao, Langqi Miao, Xiaohui Jia, Jinyue Liu

原文摘要

Building information models (BIM) can provide a global geometric reference for robot localization with LiDAR-inertial odometry (LIO). However, as-built deviations from the as-designed model mean that a disagreement between a scan and the BIM may arise from a pose error, an offset wall surface (an as-built deviation or an unmodeled object in front of the wall), or a shifted room, and in some geometries these explanations produce identical observations. In this paper, we formalize this attribution problem as fault identification over three fault classes and derive a geometric criterion for when attribution is possible. Building on it, we propose an identifiability-aware method that reports an attribution only when the fault is attributable; otherwise, it retains the candidates, defers BIM updates and BIM-based pose corrections in the ambiguous directions, and recovers once new references arrive. In the pre-registered two-dimensional study, on cases whose fault is detectable but not attributable, the method's conditional error rate was 0.83%, against 31.67% for a baseline with uncertainty-based abstention at the same answer rate. On the 5,600 attributable cases, the method reported a unique attribution 5,574 times, with no incorrect attributions. In paired fault injections in a laboratory room with its IFC model and on three floors of the SLABIM dataset, it raised no off-target attribution (0 of 168 conditions in the laboratory; 0 of 1,302 on SLABIM) and attributed all eight laboratory faults predicted to be attributable, whereas both reproduced baselines raised off-target structural flags in every setting.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2607.13460

LPM: Industrial-Scale Generative Video Restoration

Bichuan Zhu, Fulin Li, Jiachao Gong, Jinhua Hao, Kai Zhao, Kun Yuan, Pengcheng Xu, Qiang Wang 等 18 位作者

原文摘要

We present the Large Processing Model (LPM), a diffusion-based generative framework for photorealistic video restoration under complex, in-the-wild degradations. To our knowledge, LPM is the first generative video restoration model deployed at industrial scale. LPM addresses the diverse degradations in user-generated content (UGC) through a unified system encompassing large-scale data engineering, foundation-model training, and efficient inference. Its enhanced architecture, progressive training strategy, and temporal-pyramid inference mechanism jointly enable high-fidelity, temporally consistent restoration of arbitrarily long videos across the broad content distribution encountered on UGC platforms. LPM has been deployed in production at Kuaishou, where videos processed by the model account for approximately 45% of total viewing time, delivering consistent improvements across key quality-of-experience metrics. Beyond perceptual enhancement, LPM delivers substantial system-level benefits: at comparable perceptual quality, it reduces bitrate by 20% relative to Kuaishou's in-house codec, yielding annual bandwidth cost savings on the order of hundreds of millions. Its low serving cost also enables integration into products such as Kling, demonstrating that generative restoration can be practical, scalable, and cost-effective for large-scale video processing.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2610.35318

Unified Heterogeneous Feature Interaction via Effective-Rank Scaling for Recommender Systems

Ao Zhang, Haochuan Li, Boya Du, Jian Yang, Qihang Fang, Yulin Xu

原文摘要

Large-scale industrial ranking models must jointly capture heterogeneous feature interactions, long-term user behaviors, and multi-scenario dependencies under stringent online serving constraints. Existing architectures typically process sequential and non-sequential features with separate modules, limiting bidirectional information exchange. Directly applying homogeneous self-attention to all semantic tokens can also be inefficient when sequential and non-sequential signals exhibit different effective-ranks (eRanks). Meanwhile, shared representations can overlook scenario-specific patterns and induce negative transfer between scenarios. In this paper, we propose HiRank, a unified framework for multi-scenario recommendation that jointly models Heterogeneous feature Interactions via effective-Rank scaling. HiRank integrates gated sequential attention with heterogeneous feature interaction within a unified backbone, enabling bidirectional fusion between sequential and non-sequential representations. HiRank further uses scenario-aware aggregation to compress heterogeneous low-order tokens into a compact representation. Distinct learned projections transform the full compact representation into scenario-aware composite tokens with complementary global feature views and more uniform information density, enabling more effective high-order self-attention. Extensive experiments on industrial-scale datasets demonstrate favorable performance scaling with parameter count and consistent improvements over competitive baselines. Online A/B tests further show a 2.27% increase in orders per user.

cs.IR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09042

Failure Profiling and Reachable Trajectory Selection for Reasoning Distillation

Yijun Zhu, Jianxin Wang, Chengchao Shen

原文摘要

Training smaller language models on reasoning solutions generated by a larger teacher model is the prevailing approach for transferring mathematical reasoning capabilities. However, the student tends to overfit the output distribution of the teacher and generalizes poorly when its own behavior at inference time deviates from the training data. Recent methods attempt to bridge this gap by incorporating error data, yet the corrective trajectories still reflect the reasoning patterns of the teacher, which the student cannot reliably reproduce, leaving the distribution mismatch largely unresolved. We propose a method, Failure Profiling and Reachable Trajectory Selection (FPRT), built on the insight that effective training data should be jointly determined by what the student fails on and what it can realistically learn. Our method first profiles the failure behavior of the student on each problem through repeated sampling, characterizing it in terms of error rate and error consistency to reveal qualitatively distinct failure modes. Each mode demands a fundamentally different training signal. The diagnosed mode then guides candidate generation from the teacher via distinct prompting strategies tailored to each failure type. Among the correct candidates, our method selects the one whose initial reasoning steps after the point of divergence are most reproducible by the student. These first corrective steps constitute the primary bottleneck, while the remaining steps follow an already corrected context and can therefore be continued more readily. This contrasts with standard reranking approaches, which score the trajectory as a whole and thereby dilute the signal at the critical reasoning transition. Experiments demonstrate that our method achieves the SOTA performance across the five benchmarks on both student backbones.

cs.CL · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09041

DobotTrack: Target-Grounded Vision-Language-Action Learning for Embodied Person Tracking

Shengjun Deng, Yinghan Zhang, Chengrui Wei, Liu Liang, Songyuan Liu, Pengkun Zheng, Yajun Zheng, Ying Zhang 等 11 位作者

原文摘要

Language-guided embodied person tracking requires a mobile agent to identify a target from a referring description and consistently follow the target under egocentric observations. We present DobotTrack, a target-grounded vision-language-action (VLA) framework that integrates auxiliary grounding supervision with efficient temporal modeling. We systematically investigate five auxiliary tasks---person segmentation, bounding-box grounding, visual-spatial classification (VSC), future DINO feature prediction, and future-frame prediction---and adopt complementary mask and bounding-box supervision to enhance target delineation and localization. We introduce Q-identity, a target-conditioned historical visual compression module that leverages target-grounding predictions to selectively preserve identity-discriminative appearance features and spatial cues in compact historical tokens. On EVT-Bench, our 0.8B-parameter model achieves an average success rate of 77.9%, exceeding OmTrackVLA by 16.9 percentage points across the three tasks. We further construct a real-world person-tracking dataset collected using a quadruped robot, comprising 126 episodes and 596,323 mask-annotated frames. The target masks enable automatic derivation of bounding boxes and visual-spatial labels encoding horizontal position and apparent image scale, providing additional grounding supervision without separate manual annotation of these labels. Together, our framework and annotation pipeline support learning target-grounded tracking policies from simulated and real-world data. Code is available at https://github.com/Dobot-Team/dobot_track.

cs.RO · cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09040

MV-IVF: Multi-Vector Retrieval via Multi-Vector Clustering

Kishen N Gowda, Laxman Dhulipala, Lars Gottesbüren, Rajesh Jayaram

原文摘要

Multi-vector retrieval represents each query and document as a set of embeddings and scores relevance via fine-grained set-to-set interactions such as MaxSim (Chamfer similarity). This expressiveness improves retrieval quality over single-vector representations, but makes search substantially more expensive. Existing systems address this challenge primarily through proxy representations or filter-and-rerank pipelines that reduce candidate generation to single-vector search. We study the complementary direction of building a native IVF-style index directly over multi-vector data. We introduce MV-IVF, an inverted-file index for multi-vector retrieval built on MV-Lloyd, a new Lloyd-style algorithm for clustering point clouds under a Chamfer objective. Our key observation is that once point clouds are assigned to clusters, the center-update step reduces to standard single-vector clustering over the flattened embeddings in each cluster. This enables efficient construction of a hierarchical IVF tree with center point clouds at internal nodes. At query time, MV-IVF performs best-first beam search over the tree to identify promising leaf clusters, then scores the documents in those leaves. We further accelerate search using low-bit quantization, query compression, and cache-efficient batched search. We implement MV-IVF in MVSIC, an optimized C++ library and unified evaluation framework for multi-vector retrieval that includes several major approaches. Across BEIR and LoTTE text retrieval benchmarks, MV-IVF achieves strong latency--recall tradeoffs, the best batched throughput frontiers, and favorable build-time and index-size profiles. At $90\%$ Recall-$10$@$10$, MV-IVF achieves up to $8.03\times$ lower single-query latency and up to $173.5\times$ higher QPS than the baselines, demonstrating that native IVF-style indexing is practical and effective for scalable multi-vector retrieval.

cs.IR · cs.DB

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.08177

BabyTheorist: A Benchmark for Learning to Theorize the World from Observation Alone

Doojin Baek, Junyeob Baek, Mingyu Jo, Hosung Lee, Taegu Kang, Gyubin Lee, Sungjin Ahn

原文摘要

How would we know whether a machine truly understands the world? We argue that one key capability is observational theory learning: acquiring reusable theories from pure observations and applying them to new situations. Current visual reasoning benchmarks focus primarily on the latter, presenting each task as a few-shot puzzle grouped by a common rule. We introduce BabyTheorist, a benchmark for controlled training and evaluation of observational theory learning. BabyTheorist generates continual streams of before-after visual observations from hidden compositional programs; during training, learners see only the resulting transitions, with no program labels, task identities, or support sets. To support theory learning and evaluation, BabyTheorist controls the program language, a curriculum over program complexity, recurring frequent subprograms, and a continual train-test protocol with level skipping. Seven representative baselines plateau well below ceiling, with the gap widening as the curriculum advances---evidence that BabyTheorist isolates a capability current program-learning approaches do not yet address.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2606.16454

SDS-LoRA: Overcoming Anisotropic Gradient Scaling in Low-Rank Adaptation

Junghun Oh, Sungyong Baik, Kyoung Mu Lee

原文摘要

Low-Rank Adaptation (LoRA) enables efficient adaptation of large pretrained models to downstream tasks by parameterizing weight updates with low-rank matrices. In this paper, we investigate the limitations of the LoRA parameterization from a geometric perspective. Specifically, we show that when a full fine-tuning gradient is backpropagated to the low-rank matrices, it undergoes anisotropic scaling driven by their singular values. We argue that this phenomenon is undesirable because it distorts the full fine-tuning gradient by skewing it toward dominant singular directions while suppressing others. Our analyses demonstrate that anisotropic gradient scaling reduces the effective rank of the low-rank matrices' gradients and fails to provide the best possible alignment between the full fine-tuning gradient and its low-rank approximation in LoRA for arbitrary gradients, thereby exacerbating the gap to full fine-tuning. To address these limitations, we propose a new low-rank parameterization, SDS-LoRA, which Structurally Decouples Singular values from the backward pass. Our method ensures that the full fine-tuning gradient backpropagates only through the orthonormal bases of the low-rank matrices' subspaces, independent of their scales. Convergence analysis demonstrates that while LoRA's convergence rate degrades with the condition number of the low-rank matrices, that of SDS-LoRA remains independent of it. Experimental results across natural language and vision benchmarks show that SDS-LoRA improves loss convergence and reduces the gap to full fine-tuning, significantly enhancing adaptation performance. The code is available at https://github.com/JungHunOh/SDS-LoRA_NeurIPS2026.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.08251

VoxCanvas-41M: A Large-Scale Bilingual Dataset for Instruction-Based Speech Editing and Its Learning Dynamics

Zhikang Niu, Wenming Tu, Yalin Li, Yanru Huo, Junxi Liu, Tianrui Wang, Ruiqi Yan, Junxuan Liang 等 11 位作者

原文摘要

Recent advances in speech generation have spurred the development of speech editing techniques. However, achieving high-quality speech editing remains challenging due to two key limitations. First, the major hurdle is the lack of large-scale, high-quality speech editing datasets. Constructing such datasets is costly, while open-source, scalable data pipelines remain limited. Second, the learning dynamics of speech editing models remain poorly understood. In particular, how models acquire editing capabilities and the relationship between generation and editing remain unclear. To address these challenges, we introduce VoxCanvas-41M, a large-scale bilingual dataset comprising approximately 41 million speech editing pairs. VoxCanvas-41M covers two major categories: content editing, including single-span, multi-span, and location-reference editing, and paralinguistic editing, covering the insertion and deletion of 39 classes of nonverbal events such as laughter, sighs, and coughs. Building on VoxCanvas-41M, we train VoxCanvas-Edit, an instruction-based speech editing model, demonstrating the effectiveness of our dataset in improving editing performance. Furthermore, we systematically investigate the learning dynamics of speech editing, examining how models learn different editing operations and how data scale, task interactions, and training strategies affect editing performance. The dataset, pipeline, and demos are publicly available.

cs.SD · eess.AS

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.22791

Gated DeltaNet-2: Decoupling Erase and Write in Linear Attention

Ali Hatamizadeh, Yejin Choi, Jan Kautz

原文摘要

Linear attention replaces the unbounded cache of softmax attention with a fixed-size recurrent state, reducing sequence mixing to linear time and decoding to constant memory. The hard part is not just what to forget, but how to edit this compressed memory without scrambling existing associations. Delta-rule models subtract the current read before writing a new value, and Kimi Delta Attention (KDA) sharpens forgetting with channel-wise decay. But the active edit still uses a single scalar gate to control two different things: how much old content to erase on the key side and how much new content to commit on the value side. We introduce Gated DeltaNet-2, which generalizes both Gated DeltaNet and KDA by inheriting adaptive forgetting and channel-wise decay while addressing their shared limitation, the scalar tie between erasing and writing. Gated Delta Rule-2 separates these roles with a channel-wise erase gate b_t and a channel-wise write gate w_t, reducing to KDA when both gates collapse to the same scalar and to Gated DeltaNet when the decay also collapses. We derive a fast-weight update view, a chunkwise WY algorithm with channel-wise decay absorbed into asymmetric erase factors, and a gate-aware backward pass that preserves efficient parallel training. At 1.3B parameters trained on 100B FineWeb-Edu tokens, Gated DeltaNet-2 achieves the strongest overall results among Mamba-2, Gated DeltaNet, KDA, and Mamba-3 variants across language modeling, commonsense reasoning, and retrieval. Its advantage is most pronounced on long-context RULER needle-in-a-haystack benchmarks, where it improves the evaluated multi-key retrieval setting and remains strong in both recurrent and hybrid settings. Code is available at https://github.com/NVlabs/GatedDeltaNet-2.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.08080

Spatiotemporal Dynamics-Aware Industrial Anomaly Detection and Reasoning

S-Wei Chen, Siangyu Yang, Yi-Chen Jan, Chun-Yi Lee, Shao-Yuan Lo

原文摘要

Industrial Anomaly Detection (IAD) is a long-established problem that aims to detect defects in industrial products during manufacturing for quality control. Most existing studies focus on static visual patterns as the basis for detection. However, in real manufacturing environments, many anomalies are dynamics-based, such as irregular movements that cannot be perceived from static cues alone. We observe that even recent Multimodal Large Language Model (MLLM)-based approaches fall short in identifying such dynamic anomalies due to limited temporal modeling capability. To address this, we introduce MUSTARD: MUltimodal SpatioTemporal Anomaly Reasoning and Detection, a framework that equips MLLMs with fine-grained spatiotemporal dynamics awareness for detecting and reasoning about dynamics-based defects. MUSTARD introduces optical-flow-guided keyframe selection and augmented modalities to capture critical motion irregularities through local motion patterns and global dynamic evolution. Its normal pattern-based reasoning pipeline requires only a few normal reference samples as the detection basis, avoiding any model updates. This enables efficient adaptation across various products and provides high decision interpretability. MUSTARD is the first MLLM-based framework for dynamics-based IAD. Experiments demonstrate its superior performance in detecting spatiotemporal anomalies and providing plausible explanations. Our code is available at https://github.com/racercode/Mustard

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09026

Beyond a Single Commit: Anchor-Guided Reconstruction of Multi-Commit Patches

Jialiang Dong, Willy Susilo, Xu Gai, Liuhuo Wan, Chao Zhang, Elisa Bertino, Siqi Ma

原文摘要

Vulnerability patch identification plays a critical role in software security by linking reported vulnerabilities and the corresponding fixes, enabling reliable vulnerability analysis, mitigation, and automated security tool development. As software systems evolve in complexity, vulnerability remediation has increasingly shifted from single-commit fixes to multi-commit fixing processes. Although many studies have been proposed to identify fixing commits associated with target vulnerabilities automatically, they often suffer from inaccurate semantic analysis or excessive workload for language models. These limitations reduce both the effectiveness and comprehensiveness of fixing commit identification. To improve patch identification, we propose an effective and comprehensive patch identification framework, HARPOON, which not only enhances the accuracy of identifying individual fixing commits, but also investigates dependencies among commits to achieve comprehensive commit recognition for target vulnerabilities. Experimental results show that HARPOON significantly outperforms the state-of-the-art approaches. HARPOON successfully identified 895 vulnerability patches that were not previously maintained in public vulnerability databases. Among them, 663 are previously unrecorded fixes associated with 323 CRITICAL- or HIGH-severity vulnerabilities.

cs.CR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09022

Optimal Probabilistic Answer Set Programming: Complexity and Implementations

Damiano Azzolini, Giuseppe Mazzotta, Francesco Ricca, Fabrizio Riguzzi

原文摘要

Probabilistic Answer Set Programming (PASP) extends Answer Set Programming with the possibility of representing uncertain data. Among the possible available semantics, we focus here on the credal semantics. In this setting, prior work has focused exclusively on plain ASP programs, i.e., programs without optimization constructs. However, many real world tasks define optimality criteria over the possible solutions, which cannot be conveniently modeled with existing probabilistic ASP frameworks. In this paper, we close this gap and propose optimal Probabilistic Answer Set Programming, which extends PASP by also allowing weak constraints, which are the standard optimization construct of ASP. We define the semantics of such programs, study the computational complexity of the inference and most probable explanation tasks, and propose practical implementations based on Algebraic Model Counting and Answer Set Programming with Quantifiers. An empirical evaluation of the proposed approach on three real world tasks confirms the applicability of our framework.

cs.LO · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.08777

Measuring and Decomposing Mode Separation via the Canonical Diffusion

Shaul Tolkovsky, Ori Meidler, Or Zuk

原文摘要

Mode separation, namely how sharply a distribution fragments into barrier-separated clusters, is a fundamental geometric property of densities, difficult to quantify in high dimensions. Modes are often the meaningful alternatives in the data, such as the conformations of a molecule or the distinct semantic types among a generative model's outputs. Mode separation is distinct from dispersion, which is what standard label-free tools capture: differential entropy rises with spread regardless of fragmentation, and PCA orders directions by variance regardless of barriers. Mutual information does capture it, but only given the latent component labels, which are usually unavailable. We measure mode separation through a single stochastic process intrinsic to the density, namely the unique reversible diffusion with $f$ as its stationary distribution and a constant scalar diffusion coefficient. From its autocovariance matrix we extract two readouts. The first, SSA (Sum of Squared Autocorrelations), is a scalar barrier-sensitive measure. The second, DA (Dominant Autocorrelation directions), gives linear projections ordered by metastability rather than variance. Under an isotropic-Gaussian null, we derive the limiting spectrum of the empirical autocovariance in closed form, generalizing the Marchenko--Pastur law. Its upper edge gives a noise floor that separates metastable directions from sampling noise. Both readouts use only samples and a score function, scaling to high dimensions through pretrained score-based generative models via Tweedie's identity. We apply our framework to three settings: (i) synthetic Gaussian mixtures, where SSA tracks mutual information; (ii) SDXL text-to-image generations, where SSA and DA capture structure that entropy and PCA miss; and (iii) molecular dynamics of alanine dipeptide, where DA recovers the known slow backbone dihedrals from static samples alone.

stat.ML · cs.LG · math.PR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09020

Reconfiguration of Time-Bounded Descriptions

Dimitrios Myrisiotis

原文摘要

Time-bounded Kolmogorov complexity measures a string by the length of its shortest program that prints it within a deadline. An adjunction-universal machine (Bauwens, Kozachinskiy, and Shen, arXiv, 2025) is a Turing machine that simulates every Turing machine $M$ on every input $z$ with polynomial overhead when given a code of $M$, computable from $M$ in polynomial time, followed by $z$ unchanged. Any two adjunction-universal machines give the same measure up to an additive constant and a polynomial change of the deadline. However, this measure records only the shortest program for a string. We study all programs of one length that print a string within one deadline, join two of them when they differ in one bit, and ask when this graph is connected. Fix any adjunction-universal machine. For almost all $m$-bit strings and every deadline beyond some polynomial, the graph is disconnected at program length $m+O(1)$ and has at least $2^{m-O(1)}$ components at length $2m+3$. In contrast, we build an adjunction-universal machine in which every such graph is connected or empty, at every deadline, once the program length reaches a computable threshold that is at most exponential in the length of the string. Exponential thresholds are unavoidable: for every adjunction-universal machine with such thresholds and every large $m$, more than three quarters of the $m$-bit strings need a threshold exponential in $m$. For our machine, above the threshold, every program for the string is within three bit flips of a connected set of fastest programs for the string, along a path inside the graph, at every deadline by which that program halts. For this machine, deciding whether two given programs are connected in this graph is $\mathsf{PSPACE}$-complete when the input is the string, the deadline in unary and the two programs; for each fixed string it takes polynomial time.

cs.CC · cs.DM

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09019

Capacity of Multi-Layer Manhattan-Grid UAV Corridors Served by Terrestrial 5G NR Networks

Saad Masrur, M M Sadman Shafi, Md Sharif Hossen, Ismail Guvenc

原文摘要

Advanced air mobility (AAM) is expected to organize unmanned aerial vehicle (UAV) traffic into corridors at multiple altitudes. In this paper, we study the downlink (DL) and uplink (UL) capacity of a multi-layer Manhattan-grid corridor mesh served by a terrestrial fifth-generation (5G) new radio (NR) macro network. The corridor spacing and the numbers of layers, UAVs, and base stations are configurable. We combine the 3GPP aerial channel and antenna models, correlated UAV mobility, and frequency-selective fading with an NR physical-layer abstraction that includes channel aging and link adaptation. Results show that UAVs above 90 m experience a DL signal-to-interference-plus-noise ratio (SINR) about 17 dB below that of ground users, and that a dense macro network with $10^\circ$ downtilt leaves 17-29% of corridor positions without DL service under full-buffer load, regardless of corridor spacing. On a common layout, the carrier frequency (700 MHz, 3.5 GHz, or 7.2 GHz) changes the UAV SINR by less than 0.5 dB, since the corridor links are strongly interference-limited. The UL is the bottleneck: at 85% satisfaction, a 20 MHz carrier supports only about 3.4-4.1 UAVs/km$^2$ with 4 Mb/s of UL video per UAV.

eess.SP · cs.PF

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09017

Frontier3DBench: Benchmarking Coding Agents for 3D Creation across Objects, Scenes, and Interactive Open Worlds

Xinjie Lin, Qingle Liu, Wenyi Li, John Lam, Xiaoqiu Wang, Deyao Hong, Mingju Gao, Zheng Jiang 等 13 位作者

原文摘要

Coding agents combine visual understanding with program execution, offering a new route to automated 3D creation. By translating images and instructions into editable programs, they bring reconstruction, generation, and editing into a shared workflow. Yet existing benchmarks fragment evaluation across task scopes and protocols, leaving their capabilities across construction levels unclear. We propose Frontier3DBench, a unified benchmark of 145 tasks across 9 categories spanning object, scene, and interactive open-world creation, with joint evaluation of appearance, structure, and behavior. Experiments with 11 model-harness configurations reveal strengths that vary by level: GPT-6.1-sol leads the object and scene levels and achieves the highest overall score of 66.02/100, whereas GPT-6-astra leads interactive world construction. However, all configurations score lower on reference reconstruction than on text-driven generation in object and scene tasks. Producing plausible content thus remains easier than reproducing specified geometry, layouts, and visual details. Moreover, generated worlds average 83.08/100 on local mechanisms but only 20.82 on motion clearance and 30.26 on stateful workflows: individual mechanisms often function, whereas complete activities that require coordinated actions and persistent state remain difficult. These results identify reference fidelity and coordinated activity completion as central bottlenecks for coding agents in 3D creation.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09015

SIMBAD: Spatio-Temporal Traffic Forecasting Robust to Aperiodicity

Daniel Y. Lee, Seungwon Shin, Seunghoon Han, Sungsu Lim, Susik Yoon

原文摘要

Accurate traffic prediction is essential for urban planning but remains challenging due to the irregular patterns caused by unexpected events. While Spatio-Temporal Graph Neural Networks (STGNNs) effectively model periodic data, they often struggle with these aperiodic fluctuations. To address this, we propose SIMBAD, which improves generalization irregular patterns via two key mechanisms: 1) adaptive regulation of periodic signals to prioritize recent signals, and 2) dynamic spatial modeling that adjusts influence between connected nodes based on contextual relations. Built upon simple similarity metrics to adapt to aperiodic patterns, SIMBAD outperforms existing methods on real-world benchmark datasets, demonstrating superior performance in predicting unseen and irregular traffic events.

cs.AI

查看论文
arXiv ↗PDF ↗