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

+1028新增论文
+790其中 AI 相关
+128已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-12 06:59 · 全站最近入库：2026-11-12 06:37各信源进度 →

统计口径与数据新鲜度

统计 2026-11-11 10:58 — 2026-11-12 10:58（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：2026-11-12 06:59最近发现新增版本：2026-11-12 06:37库内论文最新更新时间：2026-11-11 08:00

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。

21,675 已收录论文18,323 AI 相关6,056 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 21,544 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-12 06:57（北京时间）
版本更新 · v4arXiv:2605.25379

StateRAG: Typed State Contracts for Complex Retrieval-Augmented Generation

Miaohe Niu, Xinyu Liu, Runsong Zhao, Pengxiang Li, Jingbo Zhu, Tong Xiao

原文摘要

Multi-step retrieval-augmented generation requires tracking evolving information needs, selected evidence, and unresolved gaps. However, free-form trajectories conflate this history, forcing each step to implicitly reconstruct the current state, while existing explicit-state methods remain vulnerable to inconsistent state overwrites. To address these limitations, we introduce StateRAG, a framework that coordinates a Planner, Navigator, Retriever, and Verifier through an explicit retrieval state with checked updates. These roles propose updates across four state fields: the plan, retrieval trace, evidence, and sufficiency assessment. A dedicated controller validates each proposal against the accepted state, rejecting inconsistent updates and guiding revisions within the query budget. A final Reader then answers strictly from the validated evidence. Ablation experiments on a shared graph backend show that StateRAG outperforms free-form trajectory and unverified explicit-state baselines on LongBench by 7.7 and 4.1 Macro F1 points, respectively. These gains consistently extend to document QA and flat passage retrieval. Furthermore, StateRAG surpasses the strongest external baselines by 5.3, 5.0, and 4.3 points on LongBench, QASPER, and DocVQA.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.14029

Where do we Jam? - The Impact of Real and Virtual XR Spaces on Musical Creativity, Co-Presence, Affect, and Flow

Ruben Schlagowski, Jonas Bordewick, Luca Turchet, Hannes Ritschel, Elisabeth André

原文摘要

Extended Reality (XR) technologies can place musicians in virtual, mixed, or real environments during networked music performance (NMP). To examine how NMP applications in XR should be positioned on the reality-virtuality continuum, we conducted a laboratory study (N = 28) comparing a simulated NMP experience in Virtual Reality (VR) with one in Augmented Reality (AR). In both conditions, musicians saw their remote partners in real time as 3D point clouds rendered with an optimized Gaussian Splatting shader. While VR allowed participants to select and customize fully virtual 3D environments, AR showed a pass-through view of the laboratory environment. We measured creativity support, flow, involvement, co-presence, and affect, and complemented these data with qualitative interviews on participants' preferences and requirements for creative environments. Our results show that participants felt significantly more involved by the immersive XR experience in VR than in AR. Positive affect, flow, and creativity support were strongly correlated in both conditions, whereas involvement correlated with flow and creativity support only in VR. Qualitative findings showed substantial variation in participants' preferences for AR or VR and also regarding the design of creative virtual environments. Together, these findings suggest that the surrounding environment is a critical design dimension in networked Musical XR, shaping collaborative musical experiences beyond merely representing remote collaborators and mitigating communication latency. Future XR-mediated NMP systems should therefore treat the surrounding space as an integral component of the collaborative musical experience, rather than as a mere visual backdrop. At the same time, they should support experiences across a broad spectrum of the reality-virtuality continuum to accommodate highly individual user requirements.

cs.HC

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2403.01361

Bandit Profit-maximization for Targeted Marketing

Joon Suk Huh, Ellen Vitercik, Kirthevasan Kandasamy

原文摘要

We study a sequential profit-maximization problem, optimizing for both price and ancillary variables like marketing expenditures. Specifically, we aim to maximize profit over an arbitrary sequence of multiple demand curves, each dependent on a distinct ancillary variable, but sharing the same price. A prototypical example is targeted marketing, where a firm (seller) wishes to sell a product over multiple markets. The firm may invest different marketing expenditures for different markets to optimize customer acquisition, but must maintain the same price across all markets. Moreover, markets may have heterogeneous demand curves, each responding to prices and marketing expenditures differently. The firm's objective is to maximize its gross profit, the total revenue minus marketing costs. Our results are near-optimal algorithms for this class of problems in an adversarial bandit setting, where demand curves are arbitrary non-adaptive sequences, and the firm observes only noisy evaluations of chosen points on the demand curves. For $n$ demand curves (markets), we prove a regret upper bound of $\tilde{O}(nT^{3/4})$ and a lower bound of $Ω((nT)^{3/4})$ for monotonic demand curves, and a regret bound of $\tildeΘ(nT^{2/3})$ for demand curves that are monotonic in price and concave in the ancillary variables.

cs.LG · cs.GT · econ.GN · q-fin.GN

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.14027

Software Refactoring Research with Large Language Models: A Systematic Literature Review

Sofia Martinez, Luo Xu, Mariam Elnaggar, Eman Abdullah AlOmar

原文摘要

Background: Code refactoring is the improvement of code internally without changing the external functionalities of the program. Due to its exhaustive nature, developers often avoid manually refactoring code. Researchers have since looked into utilizing LLMs to automate the task of refactoring. Aim and Method: Despite the promising results, there is a lack of clear un- derstanding of LLMs' effectiveness in automated refactoring. Result: From our literature review we found that: (i) there are various tools that different studies use to enhance and study LLM-driving refactoring, with tools that were used to detect code smells, generate code bases, and compare refactoring outcomes. (ii) Various datasets were collected from multiple open- source projects in multiple programming languages for analysis. These platforms included GitHub, Apache, and F-Droid, with the most popular language collec- ted and analyzed being Java. (iii) One-Shot, Few-Shot, Context-Specific, and Chain-of-Thought prompting methods have been shown to be the most effective depending on the language used. In some instances, being capable of reducing code smell by up to 89%. (iv) The definition of "accuracy" varies significantly across the literature surveyed, as this depends on the context of the study, thus calling for a need to have a standardized measurement for Accuracy. (v) The most often mentioned code smells were Large Class and Long Method, with a lot of studies also not specifying, while the most often applied refactoring type is Extract Method, showing promising results in using LLM to perform this refactoring type. (vi) When working with LLMs, they often generate erroneous code, struggle with more complex refactoring, and often misunderstand the developers' requests and miss refactoring requests.

cs.SE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.14025

HiPFuse: Real-Time LiDAR Semantic Segmentation for Robotic Perception on Edge Devices

Haiyang Wu, George Vosselman, Ville Lehtola

原文摘要

Real-time robotic perception requires accurate LiDAR semantics under limited resources. Bird's-eye-view (BEV) aggregation is efficient but can mix differently labeled surfaces in columns. We present HiPFuse, a point-BEV fusion framework that exchanges point and height-partitioned BEV features across horizontal scales, combining point-wise detail with 2D spatial context from one LiDAR scan. Fixed height assignments preserve separate vertical aggregation groups, with auxiliary supervision of initial BEV features using targets from the same 3D cells. A dual-scale BEV context module adds broader context from a coarser grid. On SemanticKITTI and MCD, HiPFuse achieves 63.7% and 62.5% mIoU at 14.2 and 22.4 FPS on Jetson AGX Orin, respectively, exceeding the 10 Hz scan rate. Separate training and evaluation show indoor applicability. Replacing only the baseline semantic front end with HiPFuse in fixed robotic systems reduces odometry absolute trajectory error RMSE by 10.6% on average across two outdoor sequences and increases accepted-loop recall by 8.7 percentage points on SemanticKITTI. Qualitative semantic maps show more continuous road labeling. Our code is available at https://github.com/haiyang2022/HiPFuse.

cs.CV · cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.14026

Energy-Proportional Serverless Computing on SBC Clusters

Yuliya Sasinskaya, Natalie Carl, Niklas Kowallik, David Bermbach

原文摘要

Serverless computing promises to run code only on demand, yet the servers beneath it draw most of their power while idle, so energy consumption does not scale to zero with the workload. We show that the statelessness of serverless functions makes it possible to extend scale-to-zero from function instances to physical nodes, enabling energy proportionality. Our platform, built on tinyFaaS for clusters of single-board computers, treats node power state as part of worker selection, powering workers off when idle and back on under load. On a physical cluster, our approach reduces mean power draw by 39.6 % on a bursty, trace-based workload and by 46.7 % on a sparse one, without a detectable change in median latency on the bursty workload. The cost lands in the tail, where invocations that arrive while all workers are off wait about a minute for a node to boot. Under continuous load, the platform behaves like an always-on cluster.

cs.DC

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2601.02126

Remote Sensing Change Detection via Weak Temporal Supervision

Xavier Bou, Elliot Vincent, Gabriele Facciolo, Rafael Grompone von Gioi, Jean-Michel Morel, Thibaud Ehret

原文摘要

Semantic change detection in remote sensing aims to identify land cover changes between bi-temporal image pairs. Progress in this area has been limited by the scarcity of annotated datasets, as pixel-level annotation is costly and time-consuming. To address this, recent methods leverage synthetic data or generate artificial change pairs, but transferring change detection models across datasets and acquisition conditions remains challenging. In this work, we introduce a weak temporal supervision strategy that leverages additional temporal observations of existing single-temporal datasets, without requiring any new annotations. Specifically, we extend single-date remote sensing datasets with new observations acquired at different times and train a change detection model by assuming that real bi-temporal pairs mostly contain no change, while pairing images from different locations to generate change examples. To handle the inherent noise in these weak labels, we employ an object-aware change map generation and an iterative refinement process. We validate our approach on extended versions of the FLAIR and IAILD aerial datasets, showing competitive zero-shot and low-data regime performance. Lastly, we showcase results over large areas in France, highlighting the scalability potential of our method.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.14019

Program-Aided Patchable Skill Evolution

Jiahao Wang, Yuqi Xiong, Qing Yang, Zhipeng Xu, Zhenghao Liu, Zulong Chen, Yubin Bao

原文摘要

Agent skills have emerged as an effective means of enabling LLM agents to solve complex, interactive tasks by encoding reusable knowledge without modifying model parameters. Recent approaches further improve skill adaptation by distilling reusable experience from agent execution trajectories and evolving skills based on downstream task feedback. However, existing methods primarily represent skills as natural language documents, intertwining procedural logic with descriptive knowledge and making skills difficult to maintain and evolve. To address this limitation, we propose PASE (Program-Aided Patchable Skill Evolution), a program-aided framework that iteratively evolves skills by associating them with executable programs. Unlike prior approaches that encode trajectory-derived experience primarily in natural language, PASE separates reusable procedural logic into editable programs, enabling targeted updates to executable components while reducing the need to repeatedly revise natural language skills. Extensive experiments across diverse models and benchmarks demonstrate that PASE consistently outperforms all baselines, by achieving over 2.8% improvements. Further analyses show that PASE exhibits greater evolutionary stability and generalisation capability, highlighting the critical role of programmatic knowledge in skill evolution. We will release all data and code via GitHub.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.14018

Interleaving anatomical inspection and diagnostic reasoning for explainable radiology report generation

Chentao Huang, Runlong Lin, Zhijun Wang, Yunxiang Li, Yuanyuan Sun, Jian Wang, Hongfei Lin, Ling Luo

原文摘要

Automated radiology report generation can draft clinically plausible reports, yet the pathway from visual evidence to reported findings remains opaque, leaving the diagnostic basis of these reports unexplained and the generated reports difficult to review or revise. We introduce ARIVE (Anatomy-guided Reasoning with Interleaved Visual Evidence), an explainable report generation framework that interleaves anatomical inspection with diagnostic reasoning prior to final report composition. To support this process, we constructed 159,416 multimodal chain-of-thought (MCoT) trajectories from MIMIC-CXR, wherein visual evidence from inspected anatomical regions informs subsequent clinical interpretation. Trained on these trajectories and further optimized using anatomical and clinical-content rewards, ARIVE achieved superior clinical-efficacy performance compared with strong baselines on MIMIC-CXR and the abnormality-centered MIMIC-ABN. ARIVE's reports were competitive with those of leading models in blinded expert grading, and its MCoT trajectories earned high ratings for diagnostic traceability. Furthermore, a paired review evaluation suggests that access to MCoT can aid in identifying errors within generated reports.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.14017

Personalized Memory Rubrics: Learning What to Remember per User via Rubric-Guided Credit Assignment

Yupeng Han, Kai Zhang, Shuochen Liu, Ze Liu, Xianquan Wang, Zhihong Pan, Xiangyu Zhao, Qi Liu 等 9 位作者

原文摘要

Long-horizon personalized agents maintain an evolving memory by continuously deciding what to add, modify, or discard. However, learning an optimal update policy remains challenging. Conventional training relies solely on terminal question-answering accuracy, yielding a coarse feedback signal that treats all intermediate updates identically. Furthermore, update utility is inherently user-specific, as identical memory actions may yield opposite effects across different user personas. Existing methods fail to address this heterogeneity, relying on globally shared evaluation standards with at most a single scalar intermediate reward. To address these challenges, we propose \textbf{Personalized Memory Rubrics} (\textbf{PMR}), a framework that translates terminal feedback into fine-grained, per-step, and per-user credit assignment. PMR decomposes evaluation into a universal layer capturing cross-persona failure patterns and a per-user adaptive layer modeling individual traits as a specialized delta over the universal baseline. Through \textbf{Rubric-Guided Credit Assignment}, PMR redistributes credit at the token level, selectively amplifying validated decisions on successful trajectories while falling back to standard policy optimization on failed ones to avoid unreliable attribution. The rubric and memory policy \textbf{co-evolve} in a closed loop with anti-circularity guarantees. Crucially, PMR incurs zero inference overhead, operating without any rubric or external judge during deployment. Extensive experiments across four benchmarks demonstrate consistent gains over strong memory-augmented baselines.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.14015

Margin-Guided Token Credit for Reinforcement Learning with Verifiable Rewards

Chi Liu, Xin Chen, Yuchuan Weng, Srinivasan Manoharan

原文摘要

In reinforcement learning with verifiable rewards, a language model is rewarded for a correct final answer, and GRPO passes that reward to every token of the solution in equal measure. We instead place the credit where the model hesitated, in a method we call MCPO (Margin-Credit Policy Optimization). We measure hesitation by the top-2 margin $M=p_1-p_2$ of the policy's next-token distribution, map it to a score with two fixed thresholds, and spread each solution's advantage over its tokens so that the mean stays unchanged. The margin is read from a forward pass the trainer already performs, so the method needs no extra model evaluation and no batch statistics. We train MiniCPM5-2B-Base with LoRA for 200 steps on 2,048 DAPO-Math problems and evaluate on six competition-math benchmarks. MCPO beats an unmodified GRPO baseline for all five data seeds, by 6.55 points of macro avg@32 on average (95\% CI $[4.1, 9.0]$), and a Qwen3-4B-Base replication improves for all three seeds ($+4.75$). The gain is largest on problems that GRPO solves only some of the time and grows with $k$ in pass@$k$, reaching 13.8 points at pass@32. MCPO models also write two to three times longer answers, and runs that write longer score higher; our experiments do not separate the two effects.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.14013

A Stage-Wise Explainable Pipeline for Arteriolar-to-Venular Ratio Estimation and Retinopathy Screening

Sharan Sharmeela Karuppannan, Yoga Sri Varshan, Subin Sahayam, Umarani Jayaraman

原文摘要

The arteriolar-to-venular diameter ratio (AVR) is a clinically motivated marker of retinal vascular health. We present a five-stage pipeline for AVR estimation and exploratory retinopathy screening from fundus images, with inspectable intermediate outputs at each stage. The pipeline combines vessel and artery-vein masks, optic-disc localization, vessel-calibre estimation using a minimal-chord boundary walk, and AVR computation from dominant arterial and venular branches. An explicit threshold-based rule produces the screening decision, enabling errors to be traced to individual processing stages. On an exploratory cohort of 30 HRF images, we report 96.7% accuracy, an F1-score of 0.968 and ROC-AUC of 0.978. Ablation studies and an exploratory comparison with VascX examine the effects of vessel pairing, calibre measurement and aggregation. Interpretation is limited by the small cohort, proxy disease labels and absence of independent reference calibre measurements. The pipeline provides a transparent framework for investigating retinal vascular biomarkers, with further validation needed on larger, clinically graded cohorts.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.14010

One Sequence Is Enough: Fingerprinting Language Models from Fixed-Length Integer Sequences

Fantong Meng, Chengjie Sun, Shuangjia Yang, Zhiyuan Zhao, Yansheng Pei, Xinyang Li

原文摘要

Users of model APIs and third-party platforms often rely on the declared model name to identify the model responding to their requests. However, the actual model may differ from the declared one, motivating identity verification based on observable outputs. Previous studies have shown that preferences in simple numerical-choice tasks can serve as model fingerprints. We investigate whether a single fixed-length integer sequence can combine multiple numerical observations to identify its source model. For this task, we introduce NumPrint, a benchmark of 5,036 answers from 51 models, collected using Chinese, Japanese, and English prompts that request 294 integers between 1 and 355 in one response. We propose the Shallow MLP and Causal Transformer (SMCT) to capture aggregate numerical preferences and behavioral patterns in generated sequences. In 51-class closed-set evaluation, SMCT achieves 92.72% accuracy from a single sequence, outperforming all methods compared in this study. Using two and four answers increases accuracy to 96.06% and 97.12%, respectively. These results show that a single integer sequence contains useful model fingerprints and that additional answers further improve identification.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.14009

Coding Agent Memory Post-Training II: Unlocking the Memory Potential of Pre-trained File Operations for Long-Horizon Tasks via On-Policy Distillation

Lirui Luo, Kelong Mao, Xinwei Yang, Rongqing Li, Luyu Chen, Kieran Wong, Yudong Guo, Xinrui Wang 等 12 位作者

原文摘要

Language-model agents increasingly tackle long-horizon tasks whose interaction histories exceed the model's active context. They must therefore decide what to write down and what to read back, and when to do either. Recent work has begun to use on-policy distillation (OPD) to make memory control part of the policy, relying on memory tools and compaction protocols that lie outside either model's pre-training. However, this weakens the distillation on both sides: the teacher cannot give useful guidance on an interface it has never used, and the student samples too few meaningful memory actions for that guidance to take effect. To study this problem, we introduce Coding Agent Memory Gym II (CAMG-II), a suite of long-horizon agentic-RL environments spanning Shop, Coding, AutoResearch, General, and Visual. Alongside each environment's native task interface, CAMG-II provides ordinary Bash access and an episode-persistent workspace, enabling the policy to create, revise, search, and reuse files as memory across context replacements. We also introduce Coding Agent Memory Post-Training II (CAMP-II), which trains a single policy jointly across all five environments with fully asynchronous OPD to learn this file-based memory behavior directly from a frozen teacher with a prior for file operations. On CAMG-II, CAMP-II obtains 2.97 times the gain of the strongest OPD baseline. The memory behavior CAMP-II learns generalizes to two external benchmarks, Terminal-Bench 2.1 and SWE-Bench Pro V2, with improved success rates.

cs.LG · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.09109

TransferBreaker: Breaking Adversarial Transferability in Fine-Tuned Speech Recognition

Mojtaba Nafez, Aref Mousavi, Mohammad Ebrahim Mahdavi, Mobina Poulaei, Kiarash Kiani Feriz, Mohammad Hossein Rohban

原文摘要

Many organizations fine-tune publicly available pretrained Automatic Speech Recognition (ASR) models and deploy them in black-box settings, assuming limited access provides protection. We show this assumption is fragile: adversarial perturbations crafted on the public base model transfer effectively to fine-tuned target models, severely degrading performance and posing concerns for safety-critical applications. We propose TransferBreaker, a unified fine-tuning framework that suppresses adversarial transfer by integrating Base Adversarial Fine-Tuning, which restricts adversarial training to base-effective perturbations; Latent Jacobian Regularization, which enforces latent-space invariance by suppressing adversarially sensitive directions; and HybridGrad-AFT, which improves robustness against adaptive attacks by interpolating transferable perturbations from base and target gradients. We theoretically justify all components and evaluate TransferBreaker across three languages and four large ASR models, reducing adversarial WER from 92.6 to 27.8. Our code is publicly available at https://github.com/rohban-lab/TransferBreaker.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.14006

Normalizing Flows for Classical Simulation of Quantum Circuits in Phase Space

Edward Jiang, Timothy Heightman, Marcin Płodzień

原文摘要

We present a novel framework to learn a representation of quantum circuits based on the phase space formulation of many-body systems. Given that $N$-qubit states can be represented as probability distributions on a smooth $2N$-dimensional manifold, we show how unitary gates can be parameterized as normalizing flows between these distributions, opening a new avenue for quantum circuit simulation using generative models. We evaluate our method on three common families of quantum circuits, and show that its accuracy exceeds that of current state-of-the-art neural network methods for large system sizes.

quant-ph · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.14004

LUMIR: Decoupled Multimodal Representation Learning from Heterogeneous Data for Next-POI Recommendation

Zehui Wang, Wolfram Höpken, Dietmar Jannach

原文摘要

As multimodal tourism-related information collected from heterogeneous data sources has become increasingly available, learning effective representations has attracted attention for improving recommendation performance. Existing approaches often tightly couple multimodal fusion with the architecture and optimization objective of a specific downstream model, which limits the generality and reusability of the learned representations. To address these limitations, we propose LUMIR, a decoupled multimodal representation learning framework based on contrastive learning. Multimodal information collected from heterogeneous data sources is first semantically unified into a shared textual representation space using large language models (LLMs). An interaction-aware fusion mechanism is then designed to model cross-modal interactions, while sequential signals are incorporated as a structural constraint to guide representation learning. To evaluate the learned representations, experiments are conducted on a multimodal point-of-interest (POI) dataset under the next-POI recommendation setting across multiple sequential recommendation backbones. The results show that LUMIR consistently outperforms existing multimodal fusion baselines in both accuracy-oriented and beyond-accuracy metrics, demonstrating that decoupling representation learning from downstream optimization provides an effective paradigm for learning reusable multimodal representations. The code is publicly available at https://github.com/wzehui/LUMIR.

cs.IR · cs.LG · cs.MM

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.14003

Spatio-Temporal Calibration of a Vehicle-Mounted Microphone Array for Autonomous Driving

Marvin Seegert, Richard Taupitz, Korbinian Moller, Johannes Betz

原文摘要

Microphones let an autonomous vehicle sense into areas its cameras and LiDAR cannot see, by picking up the sound that other traffic participants emit. Locating those sources and fusing them with the visual perception requires the microphone array to be calibrated and registered relative to the vehicle's other sensors. Existing calibration methods assume small, unobstructed indoor rigs, whereas a vehicle body casts an acoustic shadow that straight-line propagation cannot represent, and to our knowledge no calibration of an array distributed around a vehicle has been reported. We propose a pipeline that uses a balloon burst as a single cross-modal target, which the LiDAR locates in metric coordinates, every microphone hears as a sharp onset and a camera times. Each observation is weighted by its own timing variance, which discounts shadowed arrivals instead of discarding them and needs no model of the vehicle. On a full-size vehicle with eight microphones over a 4.9 m aperture, the held-out range residual of 6.37 cm approaches the 6.07 cm floor set by the onset timing noise, and the calibrated array tracks a moving source to within a few degrees of the vehicle's own LiDAR. A dozen bursts spread around the vehicle suffice, and spreading them matters more than adding more.

cs.SD · eess.AS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.13997

Specify Privacy Yourself: Assessing Inference-Time Personalized Privacy Preservation Ability of Large Vision-Language Models

Xingqi Wang, Xiaoyuan Yi, Xing Xie, Jia Jia

原文摘要

Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities but raise significant privacy concerns due to their abilities to infer sensitive personal information from images with high precision. While current LVLMs are relatively well aligned to protect universal privacy, e.g., credit card data, we argue that privacy is inherently personalized and context-dependent. This work pivots towards a novel task: can LVLMs achieve Inference-Time Personalized Privacy Protection (ITP$^3$), allowing users to dynamically specify privacy boundaries through language specifications? To this end, we present SPY-Bench, the first systematic assessment of ITP$^3$ ability, which comprises (1) 32,700 unique samples with image-question pairs and personalized privacy instructions across 67 categories and 24 real-world scenarios, and (2) novel metrics grounded in user specifications and context awareness. Benchmarking the ITP$^3$ ability of 21 SOTA LVLMs, we reveal that: (i) most models, even the top-performing o4-mini, perform poorly, with only $\sim$24% compliance accuracy; (ii) they show quite limited contextual privacy understanding capability. Therefore, we implemented initial ITP$^3$ alignment methods, including a novel Noise Contrastive Alignment variant which achieves 96.88% accuracy while maintaining reasonable general performance. These results mark an initial step towards the ethical deployment of more controllable LVLMs. Code and data are available at https://github.com/achernarwang/specify-privacy-yourself

cs.CV · cs.AI · cs.CL · cs.CY · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.13995

Lipschitz-Controlled Flow Matching for Robust Image Restoration

Sedjro Salomon Hotegni, Konstantin Sonntag, Paul-Christian Bürkner, Sebastian Peitz

原文摘要

Flow-matching models can produce high-quality image restorations, but their learned dynamics may amplify small input perturbations and make reconstructions unstable. We introduce LipsFlower to reduce this amplification. We derive stability bounds for Flow-from-$Y$, which initializes the ordinary differential equation from a noise-perturbed observation, as well as for observation-conditioned posterior sampling, which conditions the velocity field on the observation throughout integration. Based on this analysis, we develop LipHDiT, a Lipschitz-aware hourglass diffusion transformer that serves as the vector-field architecture of LipsFlower. LipHDiT incorporates stabilized approximate spectral normalization, bounded modulation, and convex residual mixing. We also use adversarial finite-radius gain regularization at sampled interpolation states to penalize excessive sensitivity to the state and, for conditional sampling, the observation. We test both formulations on blind face restoration, measuring adversarial robustness and the perceptual quality of the reconstructions. LipsFlower reduces perturbation amplification while keeping restoration quality competitive with the evaluated baselines. These results suggest that Lipschitz-aware flow matching can improve the stability of generative image restoration.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.13994

BioXArena-Pro: a research-grade benchmark for autonomous biomedical machine learning agents

Loka Li, Duzhen Zhang, Xingbo Du, Leonard Song, Kun Zhang, Le Song

原文摘要

Coding agents are increasingly proposed as autonomous builders of biomedical models, but existing benchmarks are small, near saturation or open to leaked information. We present BioXArena-Pro, 64 research-level modelling tasks from eight biomedical domains, each rebuilt from a published study; most hold out whole biological units such as species or cohorts. Across 22 agent configurations, the best scores 55.1 of 100, and the scaffold matters almost as much as the model. We re-ran a published method for every task: where the published recipe applies unchanged, the best agent and the methods tie; on rebuilt tasks the methods trail by 8.2 points, suggesting that agents gain by adapting to new data. Pretrained models (including biological foundation models) matter where the strongest agent uses them: forbidding them decreases its score on those tasks by 9 points. Every task was audited in several AI-assisted rounds and a final human review.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.13993

Temporal Behavior Trees for Reinforcement Learning: Specifications as Rewards, Curricula, and Diagnostics

Vladimir Krsmanovic, Bernd Finkbeiner

原文摘要

Reinforcement learning from formal specifications often separates task definition, reward shaping, curriculum design, and policy diagnostics into different mathematical objects. This fragmentation requires additional conversion steps and discards structure already present in the specification, such as subtask boundaries, ordering constraints, and quantitative measures. We introduce TBTCL (Temporal Behavior Tree Centric Learning), a framework that uses Temporal Behavior Trees (TBTs) as a unified interface for specification-guided reinforcement learning. A single TBT specifies the task, induces dense robustness-based rewards, defines a curriculum, and supports better understanding of learned policies. By adapting TBT syntax and semantics for specification-guided reinforcement learning, we provide a formalism that is more expressive than popular specification languages such as LTL and inherently hierarchical. We present algorithms to automatically extract a curriculum DAG and derive dense, robustness-based rewards directly from TBT semantics. Furthermore, we utilize TBT trace segmentation to build understandable competence profiles and automatically adapt the reward toward bottlenecks. We evaluate TBTCL on six specifications across discrete and continuous domains and show that Temporal Behavior Trees can serve as a specification, a reward, a curriculum, and a diagnostic.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.13992

Pulse or Provenance? What rPPG-Based Deepfake Detectors Learn

Othmane Harraq, Tamer Aldwairi

原文摘要

Remote photoplethysmography (rPPG) has been proposed as a physiological cue for deepfake detection, based on the premise that synthesized faces lack a genuine cardiac signal. We examine what rPPG-style detectors learn on Celeb-DF++ (22 forgery methods) and FaceForensics++ (FF++), using one identically sampled window per real and fake video. On talking-face forgeries, simple chrominance traces reach an AUC of 0.998, exceeding a dedicated rPPG extractor (0.87). Controlled experiments indicate that this signal is not physiological in origin. On fully synthesized forgeries, it is equally discriminative when extracted from background regions or from full frames without face detection, and it is concentrated above the 0.7 to 4 Hz heart-rate band. It is largely removed by shuffling frame order but persists after normalizing resolution, frame rate and encoding, and an independent reimplementation reproduces these findings. Removing high-frequency content makes most synthesized videos appear real, adding it makes real videos appear fake, and injecting a synthetic pulse has little effect. In controlled self-reenactment experiments with two generators, animating a face from a single frame introduces the same high-frequency signal, whereas reconstructing each frame from its own source does not. Face-based chrominance detectors trained on Celeb-DF++ classify over 99% of real FF++ videos as fake, indicating that they largely encode video source rather than manipulation, and a CLIP-based detector exhibits the same behavior. A frozen CLIP backbone matches or exceeds fusions of CLIP with rPPG and frequency features. Finally, we show that the official Celeb-DF and Celeb-DF++ splits share identities and source-video content between training and test, and that custom protocols reusing test videos and identities in training inflate weaker detectors by up to 0.30 AUC.

cs.CV · cs.CR · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.13991

Universal Approximation Theorem for Metaplectic Neural Operators

Ahmed Abdeljawad, Malek Yacine Rezoug

原文摘要

We prove universal approximation for metaplectic neural operators on nonempty bounded Lipschitz domains. The nonlocal branches are whole-space metaplectic multipliers with zero extension and restriction, associated with any fixed free symplectic matrix. Assuming a smooth, globally Lipschitz, nonpolynomial activation, we obtain compact-uniform approximation of continuous operators from $C^s$ to $C^r$ and from $H^s$ to $H^r$ in the respective output norms, for arbitrary nonnegative integers $s,r$ and finite input and output channel dimensions. In the Sobolev setting, compact input sets must additionally be uniformly bounded in $L^\infty$. One hidden operator layer with one nonlocal branch suffices. A single scalar symbol atom and finitely many positional features are prescribed by the transform and domain independently of the target operator, compact set and accuracy. The proof combines averaging neural operator theory with an exact chirp-conjugated averaging identity and derivative estimates. The result includes Fourier and fixed nondegenerate fractional Fourier multiplier constructions.

cs.LG · math.FA

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.17991

DORIS: Polarization Aware Multimodal Degradation Perception for Underwater Image Restoration

Wenshuo Zhang, Xiangyue Zhang, Junlin Li, Wenjie Tian, Yubo Zheng, Zhixin Dong, Hongli Xu, Jingyu Ru 等 9 位作者

原文摘要

Recovering high-quality images from degraded underwater observations is crucial for underwater exploration. Polarization observations show promise as an effective source of complementary physical cues for recovering target radiance under clear-water conditions. However, existing methods have yet to jointly model raw intensity information and polarization cues to enable image restoration driven by an understanding of mixed underwater degradations. To overcome these limitations, we propose DORIS, a unified multimodal language-driven framework that jointly uses polarization and RGB information to generate textual descriptions of degradation types and severity levels through structured semantic instructions and enhances joint restoration representations under the guidance of degradation-aware semantic features to improve restoration robustness under mixed degradations. We further construct a new benchmark named MixPolar, which contains underwater images exhibiting real degradations and the corresponding annotations. It supports systematic evaluation of degradation perception, image restoration, and downstream task performance. Extensive experiments demonstrate that our method effectively integrates polarization and RGB information, achieving competitive performance in degradation perception and image restoration.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.13990

On the information rate of phones, syllables and words

Herman Kamper

原文摘要

Which linguistic units minimise the bitrate required to encode speech content: phones, syllables, words, maybe larger units, or something in between? This question has implications for the development of speech and language systems and theories of human language processing. Using a transcribed corpus of 960 hours of English audiobooks, I compare the information rates of phones, syllables, words, multi-word combinations and intermediate tokenisations. While all units are equivalent under a perfect language model, it makes sense to compare these under limited modelling budgets; I use $n$-gram and transformer language models. The lowest bitrates are achieved using words, with slightly longer units sometimes performing best. The results show that, when modelling capacity is limited, units larger than syllables but smaller than long multi-word phrases provide the most efficient representation in terms of information rate.

cs.CL · eess.AS

查看论文
arXiv ↗PDF ↗
版本更新 · v5arXiv:2507.01835

Filter-Enhanced Smartphone Hyperspectral Imaging

Daniil Reutsky, Daniil Vladimirov, Yasin Mamedov, Georgy Perevozchikov, Nancy Mehta, Egor Ershov, Radu Timofte

原文摘要

Hyperspectral reconstruction from RGB imagery offers an affordable alternative to costly hyperspectral acquisition devices. However, its accuracy is fundamentally constrained by the limited spectral resolution of standard RGB cameras. In this paper, we propose a new approach that leverages the multi-camera systems integrated into most modern smartphones and enhances their capabilities by modulating their spectral response functions using carefully selected spectral filters, enabling a smartphone to capture richer spectral information. We propose a neural network able to exploit auxiliary RGB images with diverse spectral characteristics, enabling more accurate hyperspectral reconstruction compared to conventional single-image methods. Training is supported by a newly collected dataset, Doomer, which consists of multiple misaligned RGB images alongside corresponding hyperspectral data. We also propose a device-adaptation strategy that conditions the multi-image hyperspectral reconstruction network on camera color correction matrices available in standard DNG metadata, requiring no real images from the target device. We evaluate it on three physical smartphones, two of them unseen during training.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.13987

Communication-Learning Co-Design for Pinching-Antenna-Assisted Federated Learning in Heterogeneous Wireless Networks

Shuai Wang, Wenxuan Sun, Mingjie Shao, Wantao Jiang, Yanqing Xu, Lingxiang Li, Zhi Chen

原文摘要

Wireless federated learning (FL) suffers from two coupled bottlenecks: statistical heterogeneity across clients and communication-constrained model synchronization over unreliable wireless links. Instead of focusing on algorithmic design and/or wireless resource optimization, this paper provides a systematic study of pinching antenna (PA)-empowered FL for heterogeneous wireless networks and develops a unified communication-and-learning framework. Specifically, we integrate a segmented waveguide-enabled pinching antenna (SWAN) architecture with a heterogeneity-robust FL algorithm based on client variance reduction and dual quantization, so as to jointly mitigate communication bottlenecks and client drift. On this basis, we further develop a two-stage SWAN-assisted downlink protocol and formulate fairness-oriented uplink optimization problems for PA positioning, bandwidth allocation, and quantization design. Efficient solution frameworks are then derived for the resulting downlink and uplink optimization problems. Experimental results show the superiority of the proposed design in convergence speed and final accuracy under non-independent and identically distributed data and communication bottlenecks.

cs.IT

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.24324

Prague Dependency Treebank -- Consolidated 2.0: Enriching a Complex Annotation Scheme

Marie Mikulová, Jiří Mírovský, Milan Straka, Pavlína Synková, Jan Štěpánek, Barbora Štěpánková, Jan Hajič

原文摘要

The Prague Dependency Treebank framework is unique in its attempt to systematically include and link different layers of language, including a meaning representation with several types of inter-sentential phenomena, especially coreference and discourse relations. We present its second consolidated version (PDT-C 2.0), which concludes almost 30-years long project of sustained development of the resource to a uniformly and coherently annotated, genre-diversified, almost 4 million token language resource of Czech language, with accompanying fully compatible lexicons. In addition to continuous linguistic research, the richly linguistically annotated corpus is also widely used in international comparisons of the development of traditional and novel NLP tools as well as in conversions into other formalisms. The corpus and the trained parsers are available under the CC BY-NC-SA licence.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.13984

Bounded Weighted Edit Distance with Metric Costs

Jihan Wang

原文摘要

We give a deterministic $O(n+k^2)$-time algorithm for bounded weighted edit distance when the input costs form an integer metric on the alphabet extended by a gap symbol. Here $n$ is the total input length and $k$ is the given threshold on the distance. If the distance is at most $k$, the algorithm returns it with an optimal alignment. Otherwise, it reports that the distance exceeds $k$. The running time matches the classical unit-cost bound and is independent of the alphabet size and of the largest cost. The algorithm keeps only the farthest-reaching prefix alignment for each cost and each difference between the total gap costs of the aligned prefixes. For real metrics whose nonzero costs are at least one, scaling and upward rounding give a $(1+\varepsilon)$-approximation for the bounded problem in $\widetilde{O}(n+(k/\varepsilon)^2)$ time. If insertions and deletions have integer costs, the running time improves to $\widetilde{O}(n+k^2/\varepsilon)$.

cs.DS

查看论文
arXiv ↗PDF ↗