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

+1072新增论文
+845其中 AI 相关
+94已有论文修订
+99新增 AI 导读

arXiv 最近完成扫描：2026-11-10 00:52 · 全站最近入库：2026-11-09 13:22各信源进度 →

统计口径与数据新鲜度

统计 2026-11-09 00:55 — 2026-11-10 00:55（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 00:52最近发现新增版本：2026-11-09 13:22库内论文最新更新时间：2026-11-07 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。

18,172 已收录论文15,506 AI 相关4,527 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 18,172 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-10 00:50（北京时间）
版本更新 · v4arXiv:2609.00566

EEG-VID: Task-Guided Latent Predictive Pretraining for EEG Decoding and Assistive Target Selection

Guanzhong Sun, Junyi Ma, Yuxuan Wu, Wei Tang, Yanzi Miao

原文摘要

We propose EEG-VID, a task-guided latent predictive pretraining framework for EEG decoding under session and subject shifts. EEG-VID predicts future latent EEG states from recent history using an exponential-moving-average target encoder and weak task guidance, followed by supervised fine-tuning. Across VIG-48 and BCI Competition IV-2a/IV-2b, Stage 1 improves mean accuracy in 41 of 42 matched backbone-dataset-protocol comparisons, including all 12 leave-one-subject-out settings, with a maximum gain of 16.22 percentage points. On the 48-region cross-day VIG-48 task, EEG-VID achieves 6.52% Top-1 and 30.50% Top-5 accuracy. In a separate six-participant offline robot-scene study, candidate-constrained target selection reaches 40.24% versus a 25% chance level after subject-specific calibration. These results support task-guided latent prediction as a transferable pretraining strategy for EEG decoding and scene-constrained assistive target selection.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35032

AutoPRL: Automated Path Representation Learning via a Learnable View Generator

Sean Bin Yang, Ying Sun, Yunyao CHeng, Hao Miao, Jilin Hu, Bin Yang, Torben Bach Pedersen, Christian S. Jensen

原文摘要

Self-supervised learning has emerged as a powerful paradigm for Path Representation Learning (PRL) in road networks. PRL aims to learn informative representations of paths traversed by moving objects, such as vehicles, where each path consists of a sequence of connected road segments. These representations are essential for various downstream tasks, including travel-time estimation and path ranking. However, existing methods often suffer from ineffective view generation and inefficient training procedures due to their reliance on heuristic augmentations and computationally intensive contrastive learning. To address these issues, we propose AutoPRL, an effective and efficient self-supervised PRL framework that integrates three key components. The Automatic Data Augmentation (AutoDA) module employs variational autoencoders to generate semantically meaningful and diverse feature-level path views by modeling each topology-aware node embedding with a Gaussian latent distribution, thereby mitigating information loss and enhancing representation quality. Second, the Cross-View Decoupled Contrastive (CVDC) learning mechanism improves training efficiency by disentangling the optimization of positive and negative pairs across node- and path-level views, enabling more stable contrastive learning. Third, an Adaptive Co-Training (ACT) module dynamically adjusts uncertainty-based loss weights to balance multiple objectives, ensuring efficient and scalable training. Extensive experiments on three real-world datasets demonstrate that AutoPRL achieves strong and consistent performance in both effectiveness and efficiency across multiple downstream tasks.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35031

PatentAgentBench: Benchmarking LLM Agents with Professional Patent Task Suites

Yijie Hu, Wei Li, Junjie Zhou, Zhiqi Jiang, Yi Jin, Licong Xu, Xinkai Sun, Kai Duan 等 9 位作者

原文摘要

Patent practice lies at the intersection of technical, legal, and linguistic work, making it challenging yet crucial to technological innovation. Recently, rapid advances in large language models (LLMs) and agentic systems have demonstrated the potential to complete realistic business workflows and even patent works. This raises a question: can current AI systems perform patent work reliably? Existing benchmarks cover a limited range of patent tasks and simplify evidence acquisition by providing reference materials or candidate documents. In this paper, we introduce PatentAgentBench, a benchmark comprising 510 instances across eight task suites: novelty search, freedom-to-operate (FTO) search, design FTO, invalidity search, claim charting, patent drafting, office-action response, and patent translation. Curated from real patent records and professional materials, the benchmark combines task-specific metrics with expert-reviewed annotations and rubrics. Retrieval tasks such novelty search, FTO, etc., require agents to search and compare patent collections without a supplied candidate pool. The drafting and OAR tasks assess the quality of agents' work given technical disclosure and office action notice. We evaluate seven LLMs across four agent harnesses on PatentAgentBench, finding that current systems still struggle to identify novelty, assess risk, and understand practitioner intent throughout patent workflows.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35029

Synthetic Child-Adult Interactions Are Not Developmentally Plausible

Bastian Bunzeck, Francesca Padovani

原文摘要

Synthetic data has become a common resource for training language models, and this trend has spilled over into research on developmentally plausible language modeling. However, it remains unclear whether LM-generated child-adult interactions actually resemble natural ones. We compare the synthetic TinyDialogues dataset to natural dialogue across a broad range of linguistic measures. While synthetic data matches natural data on the lexical level, it drastically underestimates the messy, fragmented nature of spoken interaction. To mitigate this, we propose instruction-tuning with data created from real dialogues, and show in a pilot study that a small model approximates the statistical tendencies of natural data after moderate parameter-efficient fine-tuning.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2607.00687

LUMA: Benchmarking Segmentation via a Lightweight Universal Mask Adapter

Tobias Christian Nauen, Anosh Billimoria, Federico Raue, Stanislav Frolov, Brian B. Moser, Andreas Dengel

原文摘要

Comparing transformer backbones for image segmentation is confounded: each is paired with a different decoder, recipe, and pretraining, so reported differences rarely reflect the backbone itself. We introduce the Lightweight Universal Mask Adapter (LUMA), a lightweight, backbone-agnostic mask-transformer head that treats any backbone as a black-box feature extractor, letting a set of queries read from its features through cheap cross-attention. LUMA matches the accuracy of EoMT, the state-of-the-art efficient ViT-segmenter, at cost parity, while attaching unchanged to hierarchical, convolutional, and mixture-of-experts backbones alike. Holding this head fixed, we benchmark 20 backbones, 11 pretraining schemes and a range of resolutions on ADE20K, COCO, and Cityscapes under one modern recipe. We find that ``efficient'' token mixers fail to deliver efficiency even at the high resolutions that motivate them, with plain ViT holding the throughput Pareto front at every resolution. Additionally, the pretraining objective, not the architecture, the lever the field has tuned hardest, governs segmentation quality. Code: https://github.com/tobna/LUMA

cs.CV · cs.AI · cs.LG · cs.PF

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2605.30488

CoMo3R-SLAM: Collaborative Monocular Dense SLAM with Learned 3D Reconstruction Priors for Outdoor Multi-Agent Systems

Zhihao Cao, Qi Shao, Shuhao Zhai, Feng Tian, Anh Nguyen, Hesheng Wang, Baoru Huang

原文摘要

Outdoor robot teams need a shared dense map despite limited overlap, independent reference frames, and uncertain monocular scale. Collaborative dense SLAM systems typically resolve this with depth sensors, which add payload, power, and calibration cost. We present CoMo3R-SLAM, a collaborative monocular dense SLAM system that places learned feed-forward 3D reconstruction priors at the center of the multi-agent problem: their dense pointmaps anchor scale across agents and supply correspondences strong enough to verify inter-agent links geometrically. Each agent tracks and fuses its own keyframes from a single RGB stream, while a coordinator retrieves cross-agent keyframes over the prior's encoder features, verifies them by bidirectional dense pointmap matching, synchronizes the independent similarity gauges in closed form, and refines every keyframe in one unified multi-agent sim(3) graph. Finally, a pose-depth alternation over geometry-aware segments lets inter-agent observations constrain dense structure as well as trajectories. Requiring neither measured depth nor supplied intrinsics, CoMo3R-SLAM attains the lowest trajectory error on three of four Tanks and Temples scenes, and competitive accuracy on Waymo driving sequences, while running at approximately 6-8 FPS on RTX 3080 Ti. A long-horizon traversal, independently captured day and night streams, and teams of up to four agents further map its operating range.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35026

Detection of Single Stuck-at and Bridging Faults in Cluster-based FPGA Architectures

Nachiketa Das, Sudip Ghosh, H. Rahaman

原文摘要

This paper presents a new technique for detecting single stuck-at and bridging faults in cluster-based FPGA architectures, using same set of test vectors generated by a test pattern generator circuitry. This technique is based on configuration of logic elements using test logic structure and the outputs of two separated logic elements are compared to detect a fault. To do this, block under test, TPG and output response analysis circuitry are generated in FPGAs. The configurations of test pattern generation, block under test and output response analysis are also discussed in this paper. The novelty lies in the fact that the same set of test vectors can detect all the stuck-at as well as bridging faults if the test vectors are applied in a particular sequence and analyzing the output results. We presented a detail analysis of results to detect faults as well.

cs.AR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35023

BellowsKV: One Latent for Many Layers, Expanded on Demand

Jiamu Zhang, Hanjie Chen

原文摘要

Large language models (LLMs) now serve as the backbone of agents that reason over many turns, call tools, and pursue long-horizon tasks. To avoid recomputation, a model stores the attention keys and values of all past tokens in a key-value (KV) cache. Each layer maintains its own cache, so KV-cache memory can become the main bottleneck for GPU serving. Most compression methods operate within a single layer, by quantizing the cache entries, reducing the channel dimension, or evicting less important tokens. All three lose substantial accuracy at high compression ratios. Cross-layer methods share one compressed cache across adjacent layers to go beyond this limit. However, these methods also degrade sharply at high compression ratios. We find that the KV-cache representations of adjacent layers are quite different, whereas the input hidden states of adjacent layers are highly similar. We also find that, under the same memory budget, reducing the dimension of this shared latent loses far more accuracy than quantizing it. Based on these findings, we propose BellowsKV, a training-free method that maps the hidden states of n adjacent layers to one shared latent per token. At inference time, each layer reads its own keys and values from this latent through a layer-specific projection. We keep the latent at full dimension and compress it in two other ways: BellowsKV-Quant stores the latent at low precision, which is nearly lossless because the latent has no dominant outlier channels; BellowsKV-Evict makes one shared eviction decision per block, because the layers rank token importance very similarly. Across Llama-3.1-8B, Mistral-7B and Qwen2.5-7B, BellowsKV-Quant retains about 99% of full-cache accuracy at 3.6x compression and 97-98% at 13-14x, where the strongest cross-layer method retains at most 84% at 16x. Code: https://github.com/MorrisZJ/BellowsKV

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.23135

Wait to Learn: Timing the Gradient Return in Over-the-Air Split Learning over an Aging Single-Antenna Channel

Xianzhong Li, Yuzhi Yang, Tianhao Guo

原文摘要

In over-the-air split learning over an aging single-antenna Rayleigh channel, the mean returned gradient equals the antenna-domain gradient scaled by the temporal correlation. Uncorrected training collapses in negative-correlation lobes. Near a correlation zero, no nonzero scalar calibration improves the ratio of mean power to innovation power for an individual transmission, and, on the tested grid, using sixteen times as many pilots recovers only 7 percent of the training gap. Returning at the first correlation extremum with phase correction, 1.3 ms later at 3.5 GHz and 15 m/s, achieves 90.2 percent accuracy, compared with 91.8 percent with CSI. In the tested line-of-sight setting, the near-zero gap becomes negligible.

eess.SP · cs.IT

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35020

Attention under Bounded Key-Query Similarity: Space Complexity and Transformer Anisotropy

Justin Y. Chen, Ying Feng, Piotr Indyk, Michael Kapralov, Ekaterina Kochetkova, Boris Prokhorov

原文摘要

A growing body of work on KV-cache compression aims to reduce the memory requirements of autoregressive generation. These methods compress the stored context while approximately preserving attention computation, enabling generation with reduced memory consumption. Almost tight theoretical results on the worst case space complexity of attention have recently been obtained, but they are achieved by instances where queries can be perfectly aligned with keys. This directly contradicts the observed anisotropy of the key/query geometry in real transformers. In particular, it has been shown empirically that key/query cosine similarities are small even for most correlated pairs, i.e., near-perfect alignment of queries with keys does not happen in practice. In this paper, we study the space complexity of attention approximation under the assumption that key/query cosine similarities belong to a small interval around zero, i.e., a query cannot align too much with any key. We give a nearly space optimal algorithm and a corresponding space lower bound. Surprisingly, the distribution of key/query cosine similarities in our lower bound exhibits the anisotropy property empirically established and studied in the literature. Additionally, we show that the simple uniform sampling algorithm is nearly optimal for a typical range of parameters, supporting its surprising effectiveness on real datasets.

cs.LG · cs.DS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35018

Zero-Shot Monocular Depth Estimation for Visual Perception in Lower-Limb Prostheses

Ishi Vijayvergiya, Marc Hölle, Youssef Dawoud, Amir El-Ghoussani, Michele De Vita, Rohan Asthana, Philipp Beckerle, Vasileios Belagiannis

原文摘要

Monocular depth estimation has advanced rapidly with the development of foundation models that demonstrate strong zero-shot generalisation across diverse visual domains. However, the applicability of these models to visual perception for lower-limb prosthetics remains largely unexplored. Reliable depth perception is particularly important for prosthesis users, who often experience significant challenges when navigating stairs, uneven terrain, and other complex environments. To address this gap, we introduce the Lower-Limb Prosthesis (LP) dataset, a benchmark designed to evaluate depth perception from an emulated knee-level prosthetic viewpoint. Using this dataset, we evaluate four state-of-the-art monocular depth estimation foundation models. Our results provide the first systematic benchmark of monocular depth estimation performance from a prosthetic viewpoint, while highlighting both the challenges and the potential of deploying foundation models in prosthetic perception systems. The code and dataset are available at https://github.com/Ishivijay/lp_dataset.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35017

When Pointing Becomes Profiling: Social Bias and Refusal in Text-Steerable Visual Encoders

Seyedarmin Azizi, Parsa Razmara, Sajjad Ghiasvand, Ardalan Aryashad, Tina Khezresmaeilzadeh

原文摘要

Text-steerable visual encoders condition a frozen Vision Transformer on a natural-language prompt and point at the matching image region, producing prompt-conditioned heatmaps and features. We audit the released SteerViT model and find that its steering interface turns language-driven pointing into demographic profiling. On counterfactual face mosaics and real multi-person photographs, "the person" selects a man more often than the base rate, crime words select Black people more often than occupation words do, "the man" among four women selects the Black woman 75.6% of the time on SocialCounterfactuals, and "the monkey" selects Black people. None of them is in the backbone's unsteered saliency, and the crime association is not in the frozen text encoder; the race effects grow with steering strength and enter through the last two cross-attention layers: giving the prompt to those layers alone reproduces them. Four other grounding models, CLIPSeg, Grounding-DINO, SAM 3, and Qwen2.5-VL, show no crime routing and weaker race routing. The model cannot refuse. Its patch softmax must place its mass somewhere, and its heatmap separates a groundable request ("the police officer") from one that is absent ("the pizza") or that would require a stereotyped demographic inference ("the criminal") only at chance (AUROC 0.52). We introduce SafeSteer, which adds a learned abstention output and counterfactual-invariance training on the same 23M steering parameters. SafeSteer separates should-point from should-abstain prompts at AUROC 0.997, generalizes to held-out sensitive and absent words (0.998; at a 0.5 threshold it refuses 99.8% of trained and 62% of held-out sensitive words) with no over-refusal of visible people on the benchmark, and removes most race routing while keeping localization and retrieval within 1 point of the released model. Code, benchmarks, and the curated mosaic sets will be released.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35016

From Single Spins to Ensembles: A Calibrated Symbolic Regression Pipeline for NV Spectroscopy

Evan Zhang, Zhenghang Zhi, Zewei Wang, Zeheng Wang

原文摘要

Characterizing nitrogen-vacancy (NV) ensembles requires connecting their collective spectra to individual centers that experience different local environments. We develop a symbolic-regression pipeline that carries single-center spin structure into a calibrated ensemble model by generating individual spectral responses and combining them with explicit weights. A constrained search selects Hermitian operator terms from single-center optically detected magnetic resonance spectra, fits their coefficients, and retains the selected expressions as source models for the ensemble. Ensemble calibration then accounts for resonance shifts, local disorder, orientation, and optical response while keeping the individual spectral contributions accessible. On public single-center and ensemble data, the zero-field ensemble held-frequency root-mean-square error decreases from 0.008835 to 0.003872 in normalized photoluminescence, a 56.2% improvement over matched uncorrected composition. In controlled QuTiP ensembles of 128 sites spanning four NV orientations, models calibrated at 0 and 3 mT predict an independently held-out 5.17 mT spectrum with errors of 0.000207-0.000228 across three random seeds, comparable to the 0.000200 noise standard deviation. Resolving the simulated response into its individual-center contributions shows how local spectral diversity combines into the ensemble line shape. By retaining the source Hamiltonians while calibrating sample-dependent spectral differences, the pipeline connects local spin physics to collective optical readout and makes the contributions to an ensemble line shape available for physical interpretation.

quant-ph · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35011

Critic's Eye: Review-Grounded Graph Reasoning for Long-Form Motif Discovery

Xinyu Sun, Zhangyue Yin, Xinyi Ju, Xin Wang

原文摘要

Deep narrative understanding requires distinguishing what happens from how it is presented, moving beyond the chronological fabula to decode the sjuzet, the discursive organization through which themes are staged. We study this through the recurrence of literary motifs (blood in Macbeth, for instance), where symbolic significance emerges not from local cues, but through repetition-with-variation across the whole work. We operationalize this setting as Computational Motif Discovery, a transductive task that predicts missing line-motif links using the full narrative structure of a play. We propose Critic's Eye, which models the work as a heterogeneous Narrative Topology Graph and performs discriminative inference over global structural evidence. Critic's Eye achieves 84.8% Hit@5 on our benchmark, nearly quadrupling state-of-the-art proprietary foundation models (Gemini-3-pro-preview, ~22.6%). Our analysis reveals that despite massive scaling, sequence-based models hit a "semantic ceiling", struggling to resolve dispersed dependencies. These findings suggest that explicit structural priors are a far more effective inductive bias than parameter scaling for decoding the complex architecture of long-form literature.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35010

JevVLA: Jev-Inspired Energy-Based Adaptation for Vision-Language-Action Policies

Wei Wang, Wenqiao Zhang, Zheqi Lv, Zheng Dong, Yingjie Niu, Jiaqi Zhu, Jun Xiao, Chao Li 等 9 位作者

原文摘要

Vision-language-action (VLA) policies can select among discrete candidates for pick-and-place manipulation or generate continuous action chunks for motion control. Improving both forms of decision making through a common mechanism while retaining the capabilities of a pretrained policy is an important adaptation problem. Inspired by Jev's structured, probabilistic decision interface, we propose JevVLA, a lightweight energy-based adaptation framework for VLA policies. JevVLA instantiates this inspiration by modeling the relative quality of action proposals: with the base policy frozen, it learns a differentiable scalar energy conditioned on observations, task context, and actions, using execution feedback, expert corrections, or demonstration-derived preferences. JevVLA uses this single learned action preference function in two ways: its values compare discrete candidates, while its action gradients correct continuous actions or guide their generation. Candidate selection and continuous control thus share one trainable decision core. Each benchmark uses independently trained weights and fixed input/output encodings, while retaining the same core network with approximately 80,000 trainable parameters. On the held-out test sets, JevVLA improves task success over the respective matched base-policy controls by 1.28, 2.31, 1.60, 1.52, and 1.28 percentage points on MetaWorld MT50, VIMA, LanguageTable, LIBERO Plus, and CLIPort, respectively. These results support the feasibility of a lightweight, Jev-inspired energy model for adapting both discrete action selection and continuous action guidance. The JevVLA implementation will be open-sourced at https://github.com/ZJU4EmbodiedAI/JevVLA.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35008

When the Persona Contradicts the Line: Diagnosing Plan-to-Synthesis Failures in Chain-of-Thought TTS

Joonyong Park, Jerry Li

原文摘要

Chain-of-thought TTS systems rely on language-model planners to translate persona and context into vocal delivery, but it is unclear where this intent is lost when the requested affect conflicts with lexical sentiment. We introduce a bilingual Japanese--English persona--line conflict benchmark in which each item pairs one line with congruent and conflicting personas and pre-declares the expected acoustic direction. We probe this direction in the planner-generated delivery phrase, the planner-written emotion vector, the QwenEmotion-generated vector, and the rendered waveform. Planner outputs are usually direction-correct, while downstream agreement can be substantially lower. Bypassing QwenEmotion provides only modest gains over the full planner-controlled Base. Supervising QwenEmotion raises the direction rate to 75% in Japanese and 84% in English. A learned text-to-latent interface reaches the highest English rate of 89% and the highest Japanese arousal rate of 88%. These results show that learned repair of the plan-to-synthesis interface can recover counter-textual delivery, although its effect differs across languages and acoustic axes.

cs.CL · cs.SD · eess.AS

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.23137

Wait or Rotate: Statistical Repair of the Backward Pass in Over-the-Air Split Learning Under Channel Aging

Xianzhong Li, Yuzhi Yang, Tianhao Guo

原文摘要

Over-the-air split learning returns the receiver's loss gradient through the reciprocal channel, so terminal motion between the forward and backward transmissions corrupts the backward pass. We repair the aged return at a fixed receive array using only second-order statistics. Two numbers taken from the forward-backward cross-covariance, the alignment reachable by the best common phase and by the best unitary correction, bound the main term of every repair. In the 3GPP tapped-delay-line channels TDL-A/B/C, where every antenna ages by the same scalar, the two numbers coincide, and at a correlation zero all tested fixed corrections stay between 58% and 62% accuracy, whereas a return delayed to the next correlation lobe reaches 98.4%. In 3GPP clustered-delay-line channels a statistical unitary correction stays within 0.02 in mean cross-entropy of ideal channel knowledge in all six tested profile and speed combinations, while common-phase correction falls to 69% for CDL-A at 3 km/h and the tested delay loses up to 10 points. In a two-cluster model spatial correction is decisive only where the common-phase alignment nearly vanishes (64% to 95%). With a ResNet-18 on CIFAR-10, only the delayed return trains at a separable correlation zero (86% against at most 16%), and at 30 km/h in a clustered-delay-line channel the unitary correction reaches 80% where the common phase reaches 60%. Given geometry, displacement and angular statistics, a port permutation chosen by linear assignment reaches 99.5-99.7% accuracy for hexagonal and square arrays in oblique motion without pilots or digital feedback during training, where nearest-position matching drops to 89%.

eess.SP · cs.IT

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.17661

ScenePercept: Scenario-Conditioned Perceptual Assessment of Real-World User-Generated Content Images

Shuhan Xia, Yu Chen, Xiang Wang, Shuai Li, Peipie Li, Zekun Li

原文摘要

The rapid development of mobile imaging and social platforms has led to explosive growth in user-generated content images, making their systematic and comprehensive perceptual assessment increasingly important. Existing image perception benchmarks are typically task-oriented, curating specific scenarios for quality or aesthetic assessment and applying a uniform perceptual criterion across diverse scenarios. This limits their ability to capture the scene diversity and perceptual complexity of real-world UGC images. To address these limitations, we introduce ScenePercept-Bench, a benchmark designed to reflect the distribution of real-world UGC images, comprising 23,100 images across 21 categories and 105 fine-grained scenes. To account for the influence of scene context on human perception, we design a hierarchical, scene-aware annotation protocol, covering visual quality, aesthetic perception, and scene semantics, with 15 attributes in total. Each image is annotated with an overall score, 15 attribute-level scores, and structured explanatory reasoning. Building on this benchmark, we further introduce Scenario-Conditioned Perceptual Alignment, a training framework that tackles the heterogeneity of perceptual criteria across scenarios. SCPA jointly optimizes absolute score prediction, preference ranking, and cross-scenario calibration, preserving the model general perceptual assessment ability while encouraging it to explore and adapt perceptual criteria across different scenarios. Extensive experiments demonstrate that SCPA achieves state-of-the-art performance in UGC image perception and generalizes effectively to established IQA and IAA benchmarks.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35005

Shifted Window Temporal Transformer for YOLO-Guided Phase Recognition in Laparoscopic Cholecystectomy Surgery

Sheekar Banerjee, Md. Shahabuddin, Md. Mahbub Hasan Akash, Nabilah, Mohammad Arafat Hussain

原文摘要

Intelligent operating rooms require accurate awareness of surgical workflow for better intra-operative decisions, teamwork, and surgical documentation. Therefore, accurately recognizing surgical phase during surgery is crucial. However, previous artificial intelligence-based methods provide fluctuating predictions for the transitions, restricting their clinical use. To address this challenge, we propose a clinically meaningful framework that integrates a Swin Transformer and Temporal Transformer Encoder (TTE) for effective surgical phase recognition and a parallel YOLOv11s network for real-time surgical instrument localization. To avoid phase flickering and to produce stable workflow predictions, a causal temporal smoothing is applied. The proposed framework is tested on the Cholec80 dataset for the simultaneous recognition of the surgical phases and instruments. The overall phase recognition accuracy of this model was 92%, and the macro average F1-score was 0.86. This performance surpasses CNN based methods such as EndoNet (81.7%) and SV-RCNet (85.3%), as well as temporal convolutional and transformer-based approaches including TeCNO (88.6%), Trans-SVNet (90.9%), and LoViT (91.5%). Besides, the module of instrument detection achieved mAP@0.5 = 0.863. The reliability of the results is confirmed, obtaining a high recognition rate of the workflows, and a high accuracy of the localization of the instruments. The proposed framework can serve as a foundation for intelligent surgical assistance, enriching situation awareness, and potential robotic surgery applications. Code will be made publicly available at: https://github.com/ac005sheekar/LapChol-Surgery-Swin-Cholec80

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35004

Follow the Regularized Leader Does Not Converge in Constrained Optimization

Ioannis Anagnostides, Ioannis Panageas, Nikolas Patris, Tuomas Sandholm

原文摘要

Follow the regularized leader (FTRL) is a foundational algorithm in online learning whose regret properties have been extensively studied for decades. However, in stark contrast to mirror descent---and gradient descent in particular---the convergence of FTRL to first-order stationary points in constrained nonconvex optimization was not well understood. In this paper, we show that continuous-time FTRL can fail to converge even asymptotically in infinitely smooth constrained optimization problems: its Karush-Kuhn-Tucker (KKT) gap can remain bounded away from zero indefinitely. This is especially surprising in light of the fact that continuous-time FTRL guarantees a monotonic improvement of the objective value. As a result, we establish that non-convergent behavior of no-regret dynamics---which besets general variational inequality problems---can occur even in potential systems. From a technical standpoint, our construction relies on an infinitely differentiable function where the gradient flow dynamics exhibit decelerating oscillations without ever converging pointwise, which we in turn embed into higher-dimensional FTRL dynamics that sustain a perpetually large KKT gap. We complement our negative result by showing that FTRL with Euclidean regularization does converge when the objective function is analytic. This shows that the analytic property plays a more fundamental role for FTRL than for gradient flow: it governs not only pointwise convergence, but convergence to first-order stationarity itself.

cs.GT · math.OC

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2604.13870

Gradient Descent's Last Iterate is Often (slightly) Suboptimal

Guy Kornowski, Ohad Shamir

原文摘要

We consider the well-studied setting of minimizing a convex Lipschitz function using either gradient descent (GD) or its stochastic variant (SGD), and examine the last iterate convergence. We prove that $Θ(\sqrt{\log(T)/T})$ is the optimal anytime rate attainable with a fixed stepsize schedule (that does not depend on the total number of steps $T$). The upper bound holds already for SGD, and improves on the $\log(T)/\sqrt{T}$ rate of Shamir and Zhang [2013], as well as the $\sqrt{\log(T)/T}$ rate of Zamani and Glineur [2023] which was proven only for deterministic GD. The matching lower bound holds already for GD, and confirms the conjecture of Jain et al. [2019], namely that the optimal $1/\sqrt{T}$ rate for the last iterate cannot be obtained without prior knowledge of $T$.

math.OC · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35002

DUET4D: Self-Corrective Coupled Guidance for Sparse-View 4D Reconstruction

Beizhen Zhao, Nanjie Yao, Boyi Fu, Qingsong Yan, Haofan Ren, Kaiyong Zhao, Hao Wang

原文摘要

Sparse-view 4D reconstruction is highly under-constrained when only a few cameras are available. Generative priors can recover missing appearances, but video models are computationally impractical for iterative reconstruction, whereas single-view models produce temporally inconsistent pseudo-observations. Moreover, directly absorbing uncertain generative outputs into Gaussian optimization often creates redundant primitives and floating artifacts. To address these challenges, we propose DUET4D, a self-corrective coupled guidance framework for sparse-view 4D Gaussian splatting. The core of our approach is a self-corrective framework where the 4D representation guides generative prior for spatio-temporal consistent supervisions. We first construct sequential alignments from current Gaussian evidence to steer the latent restoration. Then we use Sequential Fidelity Resampling to lift generative supervisions into Gaussian space to selectively distinguish repeatedly supported primitives. The corrected representation then provides more reliable Gaussian evidence for the next restoration cycle. Extensive experiments demonstrate that DUET4D significantly improves rendering quality and rendering efficiency.

cs.CV · cs.CG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.26433

The Geometry of Agent Memory: Forecasting Retrieval-Bound Memory Failures, and Characterizing Its Limits

Iliya Zhechev, Radoslav Ralev, Chris Coleman, Srijith Rajamohan, Jen Agarwal, Tyler Hutcherson, Simba Khadder

原文摘要

We study whether geometric relationships between conversation turns, memory texts, and queries can predict answer correctness before generation. We evaluate four memory implementations with dense or hybrid retrieval and one observation-summary comparator. We embed these texts in a shared space. A logistic classifier uses 25 features describing query proximity, memory-conversation correspondence, and conversation structure. On LongMemEval-small, pooled AUROC is 0.640 over 2,367 question-system pairs, below a question-difficulty baseline of 0.655. Performance varies by question type: geometry reaches 0.841 on single-session-assistant questions, but system identity alone reaches 0.826. After controlling for difficulty and identity, geometry adds no statistically established pooled improvement (delta = +0.002, 95% CI [-0.010, 0.014]). A fixed-store context-selection experiment finds higher accuracy with proximity-ranked memories than with random subsets, consistent with ordinary retrieval relevance. On LoCoMo, nearest-turn similarity has modest predictive value for single-hop questions and near-chance estimates for several other categories. Training uses correctness labels; prediction uses pre-answer features and no additional LLM generation call. The results characterize associations between memory representations and correctness, rather than establish a reliable deployment diagnostic. In particular, embedding proximity does not verify fact coverage or distinguish memory-construction, retrieval, and generation errors.

cs.CL · cs.IR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35001

More Memory, Better Videos? A Controlled Study of Visual Memory in Long-Video Generation

Yuzhuo Chen, Huafeng Shi, Xinyu Wang, Yulong Xu, Yucheng Wang, Haoqin Hong, Guoxin Zhang, Zehua Ma 等 9 位作者

原文摘要

Long-video generators increasingly retrieve past visual observations to prevent identity drift. The intuition is compelling: more access to history should make future video more consistent. But an image can be faithful to the past and wrong for the present. Does visual memory always improve the generated story? We investigate this question through VMem-Bench, a two-track diagnostic study. Track-A measures which references are selected from 92 real films (16,548 segments), before generation and without generator confounds. Track-B compares four retrieval policies with no-memory and gold-informed last-seen controls on 30 causally generated stories (2,824 segments) using a shared generator. Retrieval increases entity recall from 0.559 to 0.628-0.693 and improves similarity to past appearances, but decreases precision from 0.977 to 0.915-0.938 and forbidden-entity avoidance from 0.968 to 0.845-0.898. It can also reinforce obsolete appearances after the story changes them. Conversely, high long-gap recall can arise without memory when the prompt itself supplies the appearance; an appearance-stripping analysis exposes this confound. These results distinguish historical fidelity from current-story correctness and show why retrieval relevance or final-video consistency alone does not establish memory utility.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2608.25376

GPU-Accelerated Quantum Annealing-Inspired UAV Path Planning for Smart Agriculture

Maho Hirahara, Aohan Li

原文摘要

With the rapid advancement of smart agriculture, Unmanned Aerial Vehicles (UAVs) have become indispensable for efficient coverage and path planning in grid-mapped agricultural fields. However, optimizing UAV flight paths in large-scale environments remains a complex Nondeterministic Polynomial-time (NP)-hard problem. Traditional path planning methods are often constrained by local optima, limited scalability, and slow convergence, which significantly restrict their effectiveness in solving large-scale problems. To address these limitations, this paper proposes a novel optimization framework utilizing a Graphics Processing Unit (GPU)-parallelized Ising solver. Our method mimics the operational principles of quantum annealing on GPU hardware, enabling rapid search for the minimum-energy state of Ising models. Unlike physical quantum devices, which are often constrained by the number of qubits, our approach leverages the Fixstars Amplify (FA) platform to perform parallel annealing on highly parallelized GPUs. This enables the simultaneous evaluation of thousands of potential path candidates and vast state transitions. By leveraging large-scale parallel processing, this framework's core strength lies in minimizing computation time even as the problem scale increases. Simulation results demonstrate that our proposed method consistently identifies superior flight paths while maintaining stable computational performance compared with the genetic algorithm and simulated annealing method.

cs.ET · eess.SY

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2510.04159

Proofs of Quantum Memory

Minki Hhan, Tomoyuki Morimae, Yasuaki Okinaka, Takashi Yamakawa

原文摘要

In this paper, we introduce a new concept, proofs of quantum memory (PoQM). A PoQM is an interactive protocol between a classical verifier and a quantum prover over a classical channel where the verifier can verify that the prover has possessed a specified number of qubits for a specified period of time. PoQM generalize proofs of quantumness (PoQ) [Brakerski, Christiano, Mahadev, Vazirani, and Vidick, JACM 2021] where a classical verifier can verify that the prover is not classical. Our contributions are summarized as follows: We introduce PoQM. We also introduce a variant of PoQM, which we call inefficient-verifier PoQM (IV-PoQM), where the verifier's final computation to make the decision is not necessarily efficient. We construct PoQM based on the hardness of LWE. Specifically, we give two constructions of PoQM. The first one is of two-round and has negligible soundness error under the subexponential-hardness of LWE. The second one is of polynomial-round and has inverse-polynomial soundness error under the polynomial-hardness of LWE. We show that IV-PoQM imply one-way puzzles. Moreover, we show that a certain restricted version of PoQM implies quantum computation classical communication key exchange, which suggests the difficulty of black-box constructing PoQM from one-way functions. We show that constant-round PoQ imply PoQM or single-round PoQ (with a quantum verifier). Single-round PoQ are ``trivial'' PoQ in the sense that the verifier asks the prover to solve a classical problem which is quantumly easy but classically hard. The result therefore demonstrates that PoQM capture ``genuinely-interactive'' PoQ. We show that if constant-round IV-PoQ that are black-box constructed from quantumly-secure falsifiable assumptions exist then IV-PoQM exist. This result implies that IV-PoQM can be constructed from quantumly-secure constant-round statistically-hiding commitments.

quant-ph · cs.CC · cs.CR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34999

Conformal Novelty Detection via Data-enhanced Localization

Xiaoyang Wu, Jiajun Liu, Haojie Ren, Changliang Zou

原文摘要

Novelty detection is an important area of research in both statistics and machine learning. In this paper, we focus on the conditional novelty detection problem, where novelties arise from the relationship between different variables. We first adopt the conformal inference framework and propose a data-enhanced localized conformal p-value, constructed by recalibrating an enhanced conditional distribution estimator. This estimator efficiently captures conditional information by incorporating both calibration and test data into its kernel estimation. We show that our p-values are valid in finite samples and can improve detection efficiency. Based on this p-value, we then develop a novel conditional novelty detection algorithm, along with a data-driven bandwidth selection method that ensures finite-sample false discovery rate control while enhancing detection power. Both simulated and real data experiments demonstrate the advantages of our proposed approach.

stat.ME · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34995

Reinforcement learning for constrained stochastic linear--quadratic control in continuous time

Weiping Wu, Qitong Pan, Xun Li, Peng Wu

原文摘要

We study continuous-time stochastic linear--quadratic control with a scalar state and nonnegative control constraints. With quadratic running costs, randomized exploration can change the optimal mean feedback. We introduce an auxiliary problem without entropy in which the conditional policy mean is nonnegative and the covariance is prescribed in proportion to the squared state. Moment reduction and state separation yield two regional Riccati equations and characterize the finite-horizon value function and optimal conditional mean. We give a sufficient control--cost compatibility condition under which this mean coincides with the optimal feedback of the original constrained problem. For time-invariant coefficients, we characterize the undiscounted infinite-horizon optimum and establish mean square asymptotic stability under the stated assumptions. For unknown dynamics, we develop model-free actor--critic schemes for finite and infinite horizons. Numerical experiments compare the learned policies with their analytical targets and examine the effect of exploration on the optimal mean.

math.OC · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34994

Why Are LLMs Confidently Wrong? Correcting Overconfident Errors via Causal Head Intervention

Jing Ren, Bowen Li, Ziqi Xu, Xuechao Yang, Feng Xia

原文摘要

Modern large language models (LLMs) often exhibit overconfident errors, assigning high confidence to incorrect predictions and thereby undermining reliability in real-world use. Existing calibration methods typically rely on post-hoc adjustment or retraining, operating at the output level without addressing the underlying causes of miscalibration. We propose CoCHI, (Class-oriented Causal Head Intervention), a framework that improves calibration by identifying and intervening on internal components responsible for distinct confidence behaviours. By analysing predictions through correctness-confidence patterns, CoCHI enables targeted intervention on model internals, reducing overconfident errors while preserving correct predictions. Our approach provides a mechanistic perspective on calibration, linking reliability to identifiable structures within the model rather than treating it as an output-level issue. Experiments across multiple LLMs show consistent improvements in calibration metrics, including Expected Calibration Error, Negative Log-Likelihood, and Brier Score, while maintaining accuracy on five multiple-choice question answering benchmarks. These results suggest that effective calibration requires not only adjusting outputs, but also addressing the underlying causal mechanisms within the model.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34993

Reason or Recite: Complementary Specialists with an LLM Judge for Traffic Anomaly Reasoning

Mayur Kulkarni

原文摘要

Road anomalies such as collisions, violations, and sudden hazards demand more from video understanding than detection: a practical system must verify what happened, describe the scene, and explain the cause. We find these competences pull in opposite directions for vision-language models: closed-form questions reward precise, evidence-grounded reasoning, while open-ended answers are scored by similarity to reference text, where matching the annotation style matters as much as reasoning correctly. We present Reason-or-Recite (RoR), a two-specialist framework for the Traffic Anomaly Reasoning track of the 2026 AI City Challenge. RoR (1) rewrites the official chain-of-thought annotations into a structured, temporally grounded schema and LoRA-tunes a 9B vision-language model on the enhanced traces; (2) fine-tunes a 4-bit-quantized 27B model on answers alone, absorbing the annotation style; and (3) selects between the two candidates per question with a training-free LLM judge. RoR ranks first on the in-domain leaderboard with mean score 0.6788.

cs.CV · cs.CL

查看论文
arXiv ↗PDF ↗