跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

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

部分采集异常
正在读取账号与研究记录…

全站更新概况

+0新增论文
+0其中 AI 相关
+3已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-14 18:17 · 全站最近入库：2026-11-14 15:09各信源进度 →

统计口径与数据新鲜度

统计 2026-11-13 20:10 — 2026-11-14 20:10（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：2026-11-14 18:17最近发现新增版本：2026-11-14 15:09库内论文最新更新时间：2026-11-13 02:59

每分钟刷新已保存的数据。空检查不代表采集异常；新收录可能包含历史论文。AI 导读按新增版本计数。

23,348 已收录论文19,580 AI 相关6,729 有修订112 HF 社区发现

浏览论文库

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 19,580 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-14 18:15（北京时间）
版本更新 · v2arXiv:2606.24033

Block-GTQ: RoPE-Block Rate Allocation for KV-Cache Quantization

Fengfeng Liang, Yuechen Zhang, Jiaya Jia

原文摘要

Larger models and longer contexts make the KV cache a memory and bandwidth bottleneck. We introduce Block-GTQ, a framework that uses the two-dimensional frequency blocks of rotary position embeddings (RoPE) to allocate cached-key precision. A blockwise logit-error bound motivates a label-free query-key energy score, which we combine with codec-dependent rate penalties. Under equal-cost budgets and diminishing marginal gains, largest-marginal-gain allocation exactly minimizes the separable integer proxy. We instantiate Block-GTQ with TurboQuant-MSE (TQ-MSE), grouping equal-rate blocks to support attention over packed caches without materializing a decoded fp16 KV cache. Across ten model configurations, K-only diagnostics reduce layer-averaged logit mean absolute error by about 32-80% relative to uniform TQ-MSE, improving all 367 layers at both 2- and 3-bit average logical key rates. At K2V2 (2 average logical bits per K/V coordinate) on Llama-3.1-8B-Instruct, Block-GTQ raises the six-task needle-in-a-haystack (NIAH) average from 70.6 to 97.4 and LongBench-EN from 33.7 to 44.9; K2V2 gains also hold on the tested 32B and 70B models. On DeepSeek-R1-Distill-Qwen-7B at K3V2, without fp16 sink or recent-token buffers, it achieves 49.6/38.8% avg@8 on AIME 2024/2025 versus fp16's 54.2/37.9%, where uniform TQ-MSE scores zero on both. On Qwen2.5-3B-Instruct, packed K3V3 serving on one H800 reduces resident KV footprint by a factor of 3.24 and retains perplexity close to fp16 at 128K, while uniform TQ-MSE degrades severely.

cs.LG · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.26015

SemantiScene-Edit: Expert-Synthesized Supervision and Dual-Path Source Conditioning for Instruction-Based Video Editing

Xinyu Chen, Song Wu, Dingbao Shao, Jiahang Li, Jiang Lin, Yuhang Liu, Duo Li, Jiaxin Hu 等 15 位作者

原文摘要

Instruction-guided video editing requires executing a requested change while preserving the source video's appearance and temporal structure. We present SemantiScene-Edit, a video editor that couples a multimodal encoder with a pretrained video diffusion transformer. The encoder jointly processes source frames and the editing instruction, and learnable queries convey their semantic context to the generator through a trainable connector and cross-attention. A complementary visual pathway concatenates source-video latents with noisy target latents before patch embedding, supplying dense spatial and temporal information for content preservation. We train the model with flow matching and a three-stage image--video curriculum comprising semantic alignment, joint adaptation, and high-resolution refinement. To support training, we construct over 1.2 million instruction-conditioned video-editing records covering object addition, removal, replacement, and attribute modification. We also construct a 100-case benchmark for evaluating instruction execution, source preservation, temporal consistency, and visual quality. Comparative experiments show that SemantiScene-Edit effectively follows editing instructions while retaining source content. At inference, the model requires only a source video and a natural-language instruction.

cs.AI · cs.GR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39563

Trajeform: Embedding Crowd Data

Marilena Lemonari, Panayiotis Charalambous, Yiorgos Chrysanthou

原文摘要

Crowd simulation aims to generate agent behaviours that are rich, natural, and appropriate to their surrounding environment. Recent advances in Machine Learning have enabled such behavioural patterns to be learned directly from trajectory data, allowing simulation models to capture increasingly complex crowd dynamics. However, the capabilities of these systems remain strongly dependent on the type and diversity of the data used during training. When evaluating how well crowd simulators generalise to real-world datasets, most existing metrics focus primarily on trajectory-level differences rather than behaviour-level similarity. In this paper, we present Trajeform, a framework that trains a reconstruction VAE (Variational Autoencoder) on real trajectory data to learn a meaningful continuous embedding that preserves behavioural characteristics of real crowds. The trained encoder can then be applied to synthetic trajectories generated by simulators and used to compare the resulting embedding distributions. Additionally, the learned embedding can be used to analyse supplementary data, such as trajectories corresponding to a simulator's principal behaviours or captured data from controlled environments (e.g., cycling), providing insight into their ability to span the real behavioural embedding space. The framework compares data from three simulators (CCP, modCCP, and RVO) against ground-truth datasets and is evaluated quantitatively and qualitatively using latent-space analysis, distributional metrics, and trajectory generation through sampling from the aggregated posterior distribution. The results indicate that the learned latent space captures meaningful trajectory dependencies found in the real data, making the framework useful both as an additional measure of synthetic data believability and as a tool for informing the training of future trajectory models.

cs.GR · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39561

Quantifying the Relay-Coverage Trade-off in Mobile Multihop Flooding

Johannes F. Loevenich, Thies Möhlenhof, Roberto Rigolin F. Lopes

原文摘要

Network-wide flooding in mobile multihop networks selects relays from locally maintained topology information. Mobility makes this information outdated, leaving two basic responses: add redundant relays or refresh the topology and re-select relays more frequently. How these mechanisms trade reliability for overhead, however, is not well quantified. We quantify this trade-off on a public trace of 157 vehicles using Optimized Link State Routing version 2 (OLSRv2) and exact minimum-cost relay sets. Twofold coverage increases median relay-cover lifetime by only 2.3x, rather than about an order of magnitude as predicted by an independent-hazard model. The limitation is structural: 43.6 % of two-hop neighbours have only one possible relay, and newly appearing neighbours invalidate existing covers. Moreover, the delivery gain of a second relay falls from 0.061 to 0.016 when relay selection uses instantaneous link state, showing that redundancy mainly compensates for outdated topology information. Relay coverage and topology refresh therefore form a measurable redundancy-freshness trade-off rather than independent robustness mechanisms. In our trace, twofold coverage has lower overhead below about 100 bit/s of application flooding per node, whereas fresher topology information has lower overhead above it. This makes relay redundancy a load-dependent design choice rather than a fixed heuristic robustness setting.

cs.NI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39560

SimTO-Robust: Automated Design of Soft Grippers Robust to Grasp Pose and Object Geometry

Kurt Enkera, Joshua Pinskier, Marcus Gallagher, David Howard

原文摘要

Robotic grippers operating in unstructured environments must robustly grasp objects of different shapes and sizes despite perception and positioning errors. Soft grippers that can achieve this robustness through intelligent mechanical design rather than sophisticated control software offer a promising solution. However, no existing computational design framework explicitly optimises soft gripper morphology for robustness across object geometries and grasp poses. We introduce SimTO-Robust, a generalisation of simulation-driven topology optimisation (SimTO) that simulates grasps across multiple objects and poses and aggregates their contact forces to guide gripper morphology optimisation. We generate 6,646 designs and physically evaluate 24 of them alongside 10 specialised SimTO designs, two rigid baseline grippers, and a baseline generalist soft gripper produced using conventional topology optimisation. All 37 grippers are tested in a pick-and-place task involving five feature-rich objects and six grasp poses, with external disturbances of increasing magnitude applied during the task. On average, SimTO-Robust designs complete pick-and-place more reliably than specialised SimTO designs and the rigid baselines. The best SimTO-Robust designs also withstood more of the applied disturbances than any other tested gripper. These results show that incorporating diverse grasp conditions into simulation-driven topology optimisation is a simple and effective approach to improving real-world soft gripper robustness. More broadly, they show that robust robotic grasping can be achieved through intelligent mechanical design rather than sophisticated sensing and control.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39559

Non-Zero Radius: The Missing Component of Neural Networks

Tiansi Dong, Mateja Jamnik, Pietro Liò

原文摘要

Inspired by the analogy between the all-or-none activation of biological neurons and the true-false of logic circuits, McCulloch and Pitts proposed a mathematical model of the biological neuron in 1943 with the aim of simulating logical reasoning. Although Norbert Wiener considered the model overly simplistic at the time, it later became a building block of modern neural networks, including large language models. Despite their remarkable empirical success, however, conventional neural networks remain largely black-box systems and struggle with reliable symbolic reasoning. Viewing vectors as spheres of zero radius, we relax the zero-radius constraint and represent concepts as spheres with non-zero radii. We argue that sphere-based representations can capture additional features of biological cognition, including representing spatial concepts as regions and reasoning through model construction and inspection. Building on sphere embeddings, we introduce Sphere Neural Networks (SphNNs), which use a transition map to achieve symbolic-level Aristotelian syllogistic reasoning without training data, thereby taking an initial step toward the original goal of McCulloch and Pitts. We suggest that the zero-radius constraint may reflect an aspect of the oversimplification identified by Wiener and may limit conventional neural networks' capacity for symbolic-level logical reasoning.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39558

TabCUQ: Context-Uncertainty Quantification for Tabular Foundation Models

Yuebei Shi, Molei Liu, Zijian Guo

原文摘要

Tabular foundation models use in-context learning to estimate conditional expected outcomes and average treatment effects for specific groups of individuals. Using these estimates to guide scientific decisions requires reliable uncertainty quantification. The challenge is to account simultaneously for two sources of uncertainty: limited-context bias and context variation arising from the small labeled sample supplied at inference. Predictive spread does not directly quantify both sources of uncertainty, and we observe that the ordinary bootstrap may substantially overestimate context variation, whereas subsampling may underestimate it. We introduce TabCUQ, a perturbation-based framework that injects noise into observed outcomes and applies the foundation model to the perturbed contexts. TabCUQ estimates context variation using wild-bootstrap dispersion and accounts for limited-context bias using the maximum deviation between perturbed and original estimates. For a kernel-regression analogue whose estimation error admits an exact decomposition into these two components, we show that our framework provides asymptotically valid pointwise coverage. In simulations, TabCUQ substantially improves coverage, with average interval widths typically about twice those of an oracle bias-aware benchmark. Across seven real-world tasks, it also improves coverage of reference functions learned from much larger samples.

stat.ML · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39557

LatentWeave: Test-Time Latent Optimization for Multimodal Reasoning

Fanci Meng, Kun Wang, Guibin Zhang, Xinlei Yu, Jiaming Zhang, Ming Li, Yang Wang

原文摘要

Recent advances in test-time optimization have shown that the multimodal reasoning performance of large multimodal language models (MLLMs) can be improved during inference without modifying backbone model parameters. However, existing approaches primarily operate at the prompt or output level, leaving the latent reasoning process largely uncontrolled and insufficient to prevent error accumulation during autoregressive generation. To address this limitation, we propose LatentWeave, a test-time framework that treats multimodal reasoning as a controllable latent trajectory. LatentWeave performs structured Latent Weaving, progressively refining intermediate hidden states segment-wise to correct emerging deviations, and further introduces Reasoning Anchors via lightweight WEAVE tokens to stabilize reasoning structure and guide answer-oriented generation. These mechanisms are designed to enable fine-grained, step-aware intervention in the latent reasoning process while keeping the main MLLM backbone parameters fixed. Extensive experiments across diverse multimodal reasoning benchmarks report improvements over the evaluated baselines; the contribution of latent optimization, anchor training, and additional test-time computation is analyzed separately in the ablation and efficiency studies. Our code is available at https://github.com/jins7/LatentWeave.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39556

Explainable and Adaptive Machine Learning for Fraud Risk Detection in Bangladesh's Digital Banking Ecosystem

Md Najmus Swaqeeb

原文摘要

The rapid expansion of digital banking and mobile financial services creates growing challenges for fraud detection, particularly under severe class imbalance and operational constraints. This study presents an explainable and adaptive machine-learning framework integrating chronological evaluation, leakage-conscious feature engineering, probability calibration, SHAP-based explainability, and adaptive risk prioritization. Experiments use the synthetic PaySim mobile-money benchmark and compare Logistic Regression, Random Forest, XGBoost, and LightGBM. XGBoost achieved the strongest fixed-threshold performance, with PR-AUC of 0.5658, ROC-AUC of 0.9068, and F1-score of 0.5369. Platt calibration reduced the test Brier score from 0.1141 to 0.0245, improving probability reliability. SHAP analysis identified temporal, destination-account, transaction-type, and amount features as important model drivers. An adaptive top-1% policy reduced false positives from 192 to 117, but recall declined from 0.4236 to 0.2122, demonstrating a clear alert-capacity trade-off. The results provide a reproducible methodological framework rather than evidence of deployment performance in Bangladesh, since PaySim is synthetic. Validation using governed real-world financial data is therefore an important direction for future research.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2602.19513

Real-time Win Probability and Latent Player Ability via STATS X in Team Sports

Yasutaka Shimizu, Atsushi Yamanobe

原文摘要

This study proposes a statistically grounded framework for real-time win probability evaluation and player assessment in score-based team sports, based on minute-by-minute cumulative box-score data. We introduce a continuous dominance indicator (T-score) that maps final scores to real values consistent with win/lose outcomes, and formulate it as a time-evolving stochastic representation (T-process) driven by standardized cumulative statistics. This structure captures temporal game dynamics and enables sequential, analytically tractable updates of in-game win probability. Through this stochastic formulation, competitive advantage is decomposed into interpretable statistical components. Furthermore, we define a latent contribution index, STATS X, which quantifies a player's involvement in favorable dominance intervals identified by the T-process. This allows us to separate a team's baseline strength from game-specific performance fluctuations and provides a coherent, structural evaluation framework for both teams and players. While we do not implement AI methods in this paper, our framework is positioned as a foundational step toward hybrid integration with AI. By providing a structured time-series representation of dominance with an explicit probabilistic interpretation, the framework enables flexible learning mechanisms and incorporation of high-dimensional data, while preserving statistical coherence and interpretability. This work provides a basis for advancing AI-driven sports analytics.

stat.AP · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39553

BEACON: Distilled Begin/End-Aware Structured Decoding for Continuous Sign Language Segmentation

Guohou Zhang, Kalin Stefanov

原文摘要

In segmentation-based continuous sign language recognition, an untrimmed video is first partitioned into lexical units; segmentation is therefore a means to an end---downstream recognition. However, segmenters are usually judged by local boundary detection rather than by the quality of the lexical segments and the recognition they enable. We present BEACON, a begin/end-aware segmenter that combines four-class Outside/Begin/Inside/End (BIOE) labeling, constrained Viterbi decoding over eight legal transitions, and boundary knowledge distilled from a binary teacher into a shared student. Under strict no-cut evaluation with validation-based model selection, BEACON improves segment-F1 by 14.58/14.59 points and boundary-F1 by 2.17/1.22 points, and reduces the downstream word error rate (WER) by 9.10/4.15 points relative to the state-of-the-art in the PHOENIX-14/BSL Corpus. To examine which segmentation metric better reflects downstream recognition, we evaluated five distinct architecture families. Segment-F1 aligns more consistently with lower WER than boundary-F1 in both corpora (Spearman $ρ=-1.0/-0.9$ versus $-0.9/-0.8$). These results support evaluating sign language segmentation in terms of segment quality and downstream recognition utility rather than local boundary accuracy alone.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2602.09581

Mitigating the Likelihood Paradox in Flow-based OOD Detection: An Entropic Perspective

Donghwan Kim, Hyunsoo Yoon

原文摘要

Deep generative models that can tractably compute input likelihoods, including normalizing flows, often assign unexpectedly high likelihoods to out-of-distribution (OOD) inputs. We mitigate this paradox from an entropic perspective with Semantic Proportional Entropy Manipulation (SPEM), a training-free procedure that applies stronger perturbations to inputs less similar to an in-distribution (ID) memory bank. We derive theoretical lower bounds showing that this entropy gap increases the expected log-likelihood difference in favor of the ID, and experiments on standard benchmarks show that this manipulation realigns the likelihood ordering with human intuition. Strikingly, this realignment persists even when the flow is given only visually meaningless noise instead of the original input, and we analyze this phenomenon theoretically to characterize the conditions under which it occurs.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.13056

A4-MR: Abnormality Aware Anatomical Alignment for MR

Noel D'souza, Zhijian Yang, Nishank Singla, Pranay Doshi, Krisztian Koos, Fei Tan, Bruno Nunes, Laszlo Rusko 等 18 位作者

原文摘要

Recent advances in large-scale foundation models have enabled strong generalization across a wide range of clinical and research tasks in magnetic resonance imaging (MRI). However, existing vision-language MRI models remain limited in anatomy-specific localization and pathology-aware representation, particularly in real-world settings. We introduce A4-MR, a 3D vision-language foundation model trained on approximately 50,000 MRI studies comprising 491,000 series, roughly half of which are paired with radiology reports. A4-MR is designed to: (1) learn anatomy localization through large-scale pretraining with noisy labels; (2) align image and text representations at the anatomical level; and (3) learn distinct representations of healthy and abnormal anatomy. Across a diverse set of downstream tasks, A4-MR outperforms existing foundation models, including a +1.7 AUROC improvement over MedSigLIP for abnormality detection. Using a frozen encoder, A4-MR also surpasses an end-to-end task-specific MedNeXt model for knee segmentation by +1.4 Dice and performs comparably to the best task-specific model for abdominal organ segmentation on AMOS, within 0.4 Dice. Finally, without anatomical prompts, A4-MR localizes 3D anatomy comparably to MedSAM2 provided with ground-truth bounding boxes. Together, these results demonstrate that anatomy-level multimodal alignment and abnormality-aware representation learning can enable a single MRI foundation model to support localization, segmentation, and pathology-related tasks.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2602.23810

ReasonX: Declarative Reasoning on Explanations

Laura State, Salvatore Ruggieri, Franco Turini

原文摘要

Explaining opaque Machine Learning (ML) models has become an increasingly important challenge. However, current eXplanation in AI (XAI) methods suffer several shortcomings, including insufficient abstraction, limited user interactivity, and inadequate integration of symbolic knowledge. We propose ReasonX, an explanation tool based on expressions (or, queries) in a closed algebra of operators over theories of linear constraints. ReasonX provides declarative and interactive explanations for decision trees, which may represent the ML models under analysis or serve as global or local surrogate models for tabular-data black-box classifiers. Users can express background or common sense knowledge as linear constraints. This allows for reasoning at multiple levels of abstraction, ranging from fully specified examples to under-specified or partially constrained ones. ReasonX leverages Mixed-Integer Linear Programming (MILP) to reason over the features of factual and contrastive instances. We present here the architecture of ReasonX, which consists of a Python layer, closer to the user, and a Constraint Logic Programming (CLP) layer, which implements a meta-interpreter of the query algebra. The capabilities of ReasonX are demonstrated through qualitative examples, and compared to other XAI tools through quantitative experiments.

cs.CY · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2607.13472

EgoHTR: Egocentric 4D Demonstrations of Human Terrain Traversal

Alex Brandes, Haig Conti Georges Sajelian, Manthan Patel, Dominik Hollidt, Chenhao Li, Matthias Heyrman, Oliver Hausdoerfer, Manuel Kaufmann 等 14 位作者

原文摘要

Deploying humanoid robots in unstructured terrain remains an open problem. While classic reinforcement learning struggles with the sheer complexity of real-world interactions, more promising methods leveraging human priors remain limited to models lacking contextual awareness. The restricted motion synthesis is a direct consequence of existing dataset pipelines failing to capture human-scene sequences in challenging environments. To bridge this gap between humanoid learning and scene reconstruction, we introduce the Egocentric Human-Terrain Reconstruction (EgoHTR) dataset. We develop and open-source a reconstruction pipeline capturing 55 scene-aligned 4D human motion sequences in diverse, complex environments using a multi-sensor setup of egocentric wearables and a portable 3D scanner. The resulting dataset comprises over 150k frames, which we evaluate against motion-capture ground truth, demonstrating state-of-the-art accuracy and establishing a rigorous benchmark for human motion analysis and synthesis. Further, we leverage this data to train perceptive locomotion policies, demonstrating hardware deployment on a Unitree G1 for reconstructed reference motions. Our pipeline enables community-driven dataset extensions and factors the problem to help researchers build foundational, context-aware robots that reliably traverse uneven terrain.

cs.RO · cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2411.19193

The Price of Failure Risk: Clipped Barrier Policy Gradients with Convex Regularization

Pekka Malo, Lauri Viitasaari, Antti Suominen, Eeva Vilkkumaa, Olli Tahvonen

原文摘要

In many control problems, actions consume a resource budget, such as a wear allowance, and the probability of exhausting it within a given horizon must stay below a tolerance. A simple, widely used approach is to augment the state with the remaining budget, subtract an interior barrier from the utility and penalize exhaustion, so that policy-gradient methods can be applied unchanged. We clip the combined one-step reward from below at a level m to keep the returns of exploratory policies finite. The clip level is a price of failure risk, since the clipped value decomposes exactly into the utility before failure, the cost of the interior margin and m times a geometric failure risk. Consequently, an approximately optimal policy maximizes utility net of margin cost among policies with no greater risk. Its risk exceeds that of any comparison policy by at most order 1/m and can be certified from its value or from validation data. Our main result proves exponential convergence of the population policy-gradient flow for every parameter regularizer that is convex along generalized geodesics and sufficiently strong relative to the price. This extends the mean-field analysis from relative entropy to weight decay and to finite networks. Relative entropy adds parameter noise and a pull toward a prior, whereas weight decay provides only the pull. Action regularization bounds changes in failure risk by the relative entropy to a reference policy. The bounds are evaluated on an exact maintenance benchmark, a fuel-tank controller, a solvable flow and a benchmark-suite task.

cs.LG · cs.AI · math.OC · math.PR · stat.ML

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2510.17150

OmniVIC: A Self-Improving Variable Impedance Controller with Vision-Language In-Context Learning for Safe Robotic Manipulation

Heng Zhang, Wei-Hsing Huang, Gokhan Solak, Arash Ajoudani

原文摘要

We present OmniVIC, a universal variable impedance controller (VIC) enhanced by a vision language model (VLM), which improves safety and adaptation in any contact-rich robotic manipulation task to enhance safe physical interaction. Traditional VIC have shown advantages when the robot physically interacts with the environment, but lack generalization in unseen, complex, and unstructured safe interactions in universal task scenarios involving contact or uncertainty. To this end, the proposed OmniVIC interprets task context derived reasoning from images and natural language and generates adaptive impedance parameters for a VIC controller. Specifically, the core of OmniVIC is a self-improving Retrieval-Augmented Generation(RAG) and in-context learning (ICL), where RAG retrieves relevant prior experiences from a structured memory bank to inform the controller about similar past tasks, and ICL leverages these retrieved examples and the prompt of current task to query the VLM for generating context-aware and adaptive impedance parameters for the current manipulation scenario. Therefore, a self-improved RAG and ICL guarantee OmniVIC works in universal task scenarios. The impedance parameter regulation is further informed by real-time force/torque feedback to ensure interaction forces remain within safe thresholds. We demonstrate that our method outperforms baselines on a suite of complex contact-rich tasks, both in simulation and on real-world robotic tasks, with improved success rates and reduced force violations. OmniVIC takes a step towards bridging high-level semantic reasoning and low-level compliant control, enabling safer and more generalizable manipulation. Overall, the average success rate increases from 27% (baseline) to 61.4% (OmniVIC).

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39551

Comprehensive empirical evaluation of feature extractors in computer vision

Murat Isik

原文摘要

Feature detection and matching are fundamental components in computer vision, underpinning a broad spectrum of applications. This study offers a comprehensive evaluation of traditional feature detections and descriptors, analyzing methods such as Scale Invariant Feature Transform (SIFT), Speeded-Up Robust Features (SURF), Binary Robust Independent Elementary Features (BRIEF), Oriented FAST and Rotated BRIEF (ORB), Binary Robust Invariant Scalable Keypoints (BRISK), KAZE, Accelerated KAZE (AKAZE), Fast Retina Keypoint (FREAK), Dense and Accurate Invariant Scalable descriptor for Yale (DAISY), Features from Accelerated Segment Test (FAST), and STAR. Each feature extractor was assessed based on its architectural design and complexity, focusing on how these factors influence computational efficiency and robustness under various transformations. Utilizing the Image Matching Challenge Photo Tourism 2020 dataset, which includes over 1.5 million images, the study identifies the FAST algorithm as the most efficient detector when paired with the ORB descriptor and Brute-Force (BF) matcher, offering the fastest feature extraction and matching process. ORB is notably effective on affine transformed and brightened images, while AKAZE excels in conditions involving blurring, fisheye distortion, image rotation, and perspective distortions. Through more than 2 million comparisons, the study highlights the feature extractors that demonstrate superior resilience across various conditions, including rotation, scaling, blurring, brightening, affine transformations, perspective distortions, fisheye distortion, and salt-and-pepper noise

cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.32255

Anti-coherence Regularized Absolute Scaling for Out-of-Distribution Detection

Donghwan Kim, Youngwoong Jin, Hyunsoo Yoon

原文摘要

Out-of-distribution (OOD) detection is recognized as a critical problem in AI safety. SCALE is an effective post-hoc OOD detection method in the activation-shaping family that requires no training data and rescales penultimate activations using a percentile-based magnitude ratio. However, this ratio is ill-defined when negative activations are present, since positive and negative contributions cancel within the underlying sum, causing SCALE to degenerate on backbones such as ViT. We address this with an Absolute Fix that computes the ratio over absolute-valued activations rather than discarding negative activations through ReLU. Building on this corrected scale, we propose Anti-coherence regularization, which penalizes the scaling factor by the fraction of a sample's max-logit contributions to the max logit that are sign-mismatched and thereby suppresses unreliable evidence for the predicted class. Despite requiring no access to training data or training labels, our method ties or outperforms activation-shaping methods that rely on training data in terms of AUROC and FPR@95 on CIFAR-10 and ImageNet under the OpenOOD v1.5 protocol.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v5arXiv:2503.07338

Aligned Delta-Triplane Transformers as Occupancy World Models

Haoran Xu, Peixi Peng, Shijun Guo, Guang Tan, Yiqian Chang, Yisen Zhao, Shuaixian Wang, Yonghong Tian

原文摘要

Occupancy World Models (OWMs) aim to predict future 3D occupancy scenes from historical observations and future ego motions, providing a useful world simulation tool for autonomous driving. Existing methods usually rely on large networks to implicitly align multi-frame historical states and predict future occupancy in a full-state manner, which is costly and redundant because most scene regions remain unchanged over short time intervals. In this paper, we propose Aligned Delta-Triplane Transformer (ADTT), a compact 4D OWM that explicitly aligns historical triplanes with ego-motion compensation and predicts only future scene changes. Based on the aligned triplane prior, a query-conditioned Transformer predicts residual changes, where ego-motion queries guide controllable future motion and learnable external queries capture scene changes beyond ego motion. The predicted changes are added to the aligned prior and decoded into future occupancy scenes. Experiments on Occ3D-nus show that ADTT achieves state-of-the-art forecasting performance with fewer parameters and higher FPS. Our code is publicly available online: https://github.com/kyoran/ADTT.

cs.RO · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39549

Non-Asymptotic Confidence Regions for Separable Nonlinear Models

Szabolcs Szentpéteri, Péter Kovács, Balázs Csanád Csáji

原文摘要

This paper studies robust uncertainty quantification for separable nonlinear least squares (SNLLS) problems. We propose two identification methods, (i) Residual-Perturbed Gradient (RPG) and (ii) Global-Fit-Gap (GFG), to construct joint distribution-free confidence regions for both the linear and nonlinear parameters. By exploiting assumed group invariance of the noise (such as symmetry or exchangeability), we apply random perturbations (such as sign-changes or permutations) to build the regions based on resampling and ranking. We prove that both methods guarantee non-asymptotically exact coverage (type I error). Finally, we illustrate the constructions through two numerical experiments: (i) identifying generalized finite impulse response (GFIR) systems using Laguerre polynomials with an adjustable decay rate and (ii) fitting Gaussian radial basis function (RBF) models with variable knots and widths.

eess.SY · math.ST · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39547

Assuring Learning-Enabled Cyber-Physical Systems with Foundation Models: A Neuro-Symbolic Agenda for Testing, Verification, and Runtime Assurance

Xi Zheng, Ivan Ruchkin, Hong Jin Kang, Tevfik Bultan, Vijay Ganesh, Taylor T. Johnson, Ziyang Li, Lei Ma 等 14 位作者

原文摘要

Learning-enabled cyber-physical systems (CPS), including autonomous vehicles and UAVs, increasingly incorporate foundation models, yet fragmented assurance practices provide insufficient support for system-level guarantees. We argue that restoring engineering control across stochastic neural, symbolic, and physical boundaries requires a shift from model-centric evaluation to system-level assurance. We introduce the Foundation Model Assurance Stack, connecting three directions: (i) neuro-symbolic architectures that constrain foundation models through explicit symbolic world models, reasoning layers, and interfaces; (ii) semantically grounded, conformance-based testing that combines formal specifications and symbolic world models with foundation-model-assisted specification mining, scenario generation, and test synthesis; and (iii) compositional verification and runtime assurance that target formally tractable components and interfaces through modular contracts, equivalence checking, verified synthesis, uncertainty-aware reasoning, and runtime monitoring and enforcement. Symbolic abstractions establish assurance boundaries between stochastic learning and formal reasoning, connecting testing, verification, and runtime evidence across the system lifecycle. Foundation models serve as constrained assistants whose outputs are independently checked wherever correctness can be formally specified. We identify research challenges in specification engineering, abstraction fidelity, evidence composition, and lifecycle certification, and outline a staged agenda toward trustworthy, deployable, and certifiable learning-enabled CPS.

cs.RO · eess.SY

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.05880

Grounded and Faithful P&ID Reasoning: Constraining Vision-Language Models with Recovered Evidence Graphs

Prathamesh Gadekar, Sagar Srinivas Sakhinana, Venkataramana Runkana

原文摘要

Piping and Instrumentation Diagrams (P&IDs) are the authoritative maps of process plants: isolation, maintenance, and HAZOP decisions depend on what connects to what. Vision-language models describe these sheets fluently, yet they often invent or miss process connections---and an invented or missed link can reverse an isolation or reachability call, so a plant decision cannot trust a fluent answer that was never checked against the linework. We instead recover an explicit graph of the drawing---its symbols, the process connections between them, and the tags that name them---and then require the model to answer only by querying that graph through seven read-only operators, so a topology claim is returned only when it cites the query results that support it. On TopoPID-VQA, a new suite of 3000 topology questions over these sheets, Graph-Grounded Harness (Ours) raises exact match accuracy from 36.7--41.3% under image-only prompting to 74.3--76.0% for Qwen3-VL-4B, Qwen3-VL-8B, and Gemma-4-E4B. It does so on an imperfect substrate: on Digitize-PID dataset the recovered graph scores F1 0.742 on exact process connections, and 0.801 once symbols and tags are pooled in. The residual errors track that gap---grounding pays off where the recovered graph is right, and perception error still breaks topology questions where it is not.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2602.03423

Origin Lens: A Privacy-First Mobile Framework for Cryptographic Image Provenance and AI Detection

Alexander Loth, Dominique Conceicao Rosario, Peter Ebinger, Martin Kappes, Marc-Oliver Pahl

原文摘要

The proliferation of generative AI poses challenges for information integrity assurance, requiring systems that connect model governance with end-user verification. We present Origin Lens, a privacy-first mobile framework that targets visual disinformation through a layered verification architecture. Unlike server-side detection systems, Origin Lens performs cryptographic image provenance verification and metadata-based AI detection locally on the device via a Rust/Flutter hybrid architecture. Our system integrates multiple signals - including cryptographic provenance, generative-model metadata and watermarks, and optional retrieval-augmented verification - to provide users with graded confidence indicators at the point of consumption. We discuss the framework's alignment with regulatory requirements (EU AI Act, DSA) and its role in verification infrastructure that complements platform-level mechanisms.

cs.CR · cs.CV · cs.CY · cs.HC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.03035

You Can't Escape Your Activations : Evaluation Awareness and Multi-Agent Monitoring

Jaee Ponde, Aritra Das, Mihir More, Debayan Gupta

原文摘要

LLM agents are increasingly deployed in multi-agent systems, where they can collude while keeping their actions benign. Output monitors designed to detect such collusions can be fooled by obfuscation and steganography, motivating the use of probes trained on internal activations. However, these probes are usually evaluated on agents that do not know they are being watched. We study how activation-based detection changes when agents are explicitly informed that their internal activations are being monitored, and when they additionally receive feedback from the monitor. We keep the models, probes, and thresholds fixed and change only what the agents are told: nothing (baseline), that an activation monitor is present (aware), or that a monitor is present together with the previous round's score (feedback). We test two games, a four-agent blackjack game and a two-agent Simmons prisoners game, using Qwen3-32B-AWQ and GPT-OSS-20B in homogeneous and mixed pairings. Telling agents about the monitor does not hide them. The best probes stay accurate in all three conditions, and the agents keep colluding.

cs.MA · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2602.09593

Why Does Counterintuitive Likelihood Behavior Rarely Emerge in Tabular Anomaly Detection?

Donghwan Kim, Junghun Phee, Hyunsoo Yoon

原文摘要

Deep generative models with tractable likelihoods, exemplified by normalizing flows, offer an effective basis for anomaly detection through likelihood-based scoring. We demonstrate that, unlike in the image domain where deep generative models frequently assign higher likelihoods to anomalous data, such counterintuitive behavior occurs rarely in tabular settings. We first introduce a domain-agnostic formulation that enables consistent detection and evaluation of the counterintuitive phenomenon, addressing the lack of a precise definition in prior work. Through extensive experiments on 47 tabular datasets benchmarked against 13 baseline models and on 10 CV/NLP embedding datasets from ADBench, we show that the phenomenon is consistently rare in general tabular data and that normalizing flow likelihood achieves competitive anomaly detection performance. We further provide theoretical and empirical analyses attributing this disparity to differences in dimensionality and feature correlation between tabular and image data. Therefore, our results indicate that likelihood-based detection with normalizing flows is a practical approach for tabular anomaly detection.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39543

From Reasoning to Action: Consequence-Grounded Alignment for Vision-Language-Action Models

Yixue Zhang, Wenke Xia, Kun Wu, Wenbo Yu, Pei Ren, Junnan Nie, Di Hu, Zhengping Che 等 9 位作者

原文摘要

Reasoning informs decision-making by connecting intended actions with their expected consequences. Recent vision-language-action (VLA) models incorporate embodied chains of thought (ECoTs) to guide action generation. However, such guidance remains implicit, as actions are conditioned on ECoTs rather than explicitly optimized to align with them. We introduce CoRAct, a consequence-grounded reasoning-to-action alignment framework that explicitly aligns reasoning and action through reward-guided optimization in action noise space. CoRAct formulates two physically grounded ECoT components as verifiable signals: movement specifies intended motion, while waypoints encode expected spatial consequences. A unified Mixture-of-Transformers jointly models ECoT reasoning, action generation, and action-conditioned future prediction. For candidate actions generated from sampled noise, CoRAct computes alignment rewards based on movement consistency and agreement between predicted outcomes and specified waypoints. These rewards guide group-relative optimization of the initial noise distribution, steering action generation toward consistency with intended actions and expected consequences. Experiments across RoboCasa, VLABench, and real-world manipulation tasks demonstrate improvements in task success, generalization, and reasoning-execution alignment over strong ECoT-based VLA baselines. CoRAct also grounds externally provided ECoTs in executable behavior, enabling zero-shot adaptation to novel scenarios by leveraging knowledge from powerful vision-language models. Project page and dataset: https://onlyxingxingzyx.github.io/CoRAct/

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2605.19342

Semantic-Enriched Latent Visual Reasoning

Tianrun Xu, Yue Sun, Qixun Wang, Jingyi Lu, Yuan Wang, Tianren Zhang, Longteng Guo, Fengyun Rao 等 11 位作者

原文摘要

Multimodal latent-space reasoning aims to replace explicit thinking with images by performing visual reasoning directly in a compact latent space. However, existing approaches largely rely on visual supervision and produce latent representations that lack sufficient semantic richness, limiting their ability to support diverse region-level reasoning tasks. In this work, we introduce Semantic-Enriched Latent Visual Reasoning (SLVR), a two-stage learning framework that enriches latent representations with attribute-level visual semantics and aligns them with diverse reasoning objectives. In the first stage, SLVR learns semantically enriched region-centric latents under fine-grained attribute supervision. In the second stage, we design Multi-query Group Relative Policy Optimization (M-GRPO) to align latent representations across multiple queries grounded in the same region. To support this framework, we construct SLV-Set, comprising approximately 400K region-level attribute annotations and 800K multi-query question answering samples, and introduce SV-QA, a benchmark that evaluates latent reasoning under semantic variation. Experiments demonstrate that SLVR improves the robustness and semantic consistency of latent visual reasoning compared to existing baselines.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39540

The Cost of Working Memory in Streaming Mean Estimation

Zeyu Wu, Zihao Wang, Minghua Deng

原文摘要

A streaming estimator must compute from the evidence that fits in memory. We determine when storing an accurate mean is easier than computing it. For Gaussian mean estimation over the Euclidean unit ball in $\mathbb{R}^d$, we establish the minimax rate under squared error with $K$ persistent states, a known horizon, and a public time index: $\min\{1, K^{-2/d}+\frac{d}{n} (1+\frac{\log(ed)}{1+(\log K)/d})\}$. Unrestricted computation followed by $K$-level encoding has rate $\min\{1,d/n+K^{-2/d}\}$. At a fixed sufficiently small error, statistically optimal sample size therefore requires order $d\log d$ working bits, while order $d$ bits suffice to store the answer. The lower bound tracks repeated state compression through an entropy potential obtained by Gaussian smoothing. A matching construction combines a multiscale modular counter with workspace reused across coordinate groups. In one dimension, it attains the terminal rate $n^{-1}+K^{-2}$. Any fixed confidence requirement that the realized loss not exceed the zero baseline preserves these rates. Increasing confidence creates a further memory requirement: at fixed nontrivial risk in every fixed dimension, failure probability $e^{-γn}$ requires and permits order $\log n$ working states for sufficiently small fixed $γ>0$. In the scalar problem, a fixed terminal alphabet suffices under the same protection. These bounds separate the memory needed to represent an answer from the memory needed to accumulate evidence and validate a decision.

stat.ML · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39539

ROAD: Modern Adversarial Training for Simple One-Step Distillation at Scale

Xiaoou Li, Shan You, Tao Huang

原文摘要

One-step distillation turns pretrained diffusion models into fast generators, but strong results often require substantial training machinery and compute. Pure adversarial distillation offers a simpler route, yet has struggled at modern text-to-image scale. To address this limitation, we propose ROAD (Representation-grounded One-step Adversarial Distillation), a one-stage framework that distills text-to-image models with one adversarial objective and a lightweight representation-space critic. First, we replace the classical convolutional head with a Lipschitz-controlled Transformer head with token-level text conditioning, which matches the semantic tokens of modern visual encoders. Second, we observed a fixed random feature mixing leads to long-horizon degradation. We attribute it to generator-critic co-adaptation around one realization-specific view, and periodically re-draw the mixing to keep the randomization effective. Third, for our dense and vector-valued logits, we introduce Jacobian R1 which penalizes the full input-logit Jacobian, overcoming pooled R1's limitation of neglecting most of logit sensitivities. A single adversarial objective then suffices: in one step, ROAD reaches 11.03 FID on SDXL and 13.73 on SD3.5-M on COCO-10K, surpassing the multi-step teachers at a fraction of distribution matching's training compute.

cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗