跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

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

部分采集异常
正在读取账号与研究记录…

全站更新概况

+1072新增论文
+845其中 AI 相关
+94已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-10 01:54 · 全站最近入库：2026-11-09 13:22各信源进度 →

统计口径与数据新鲜度

统计 2026-11-09 01:57 — 2026-11-10 01:57（北京时间） · 点击数字查看对应简报；AI 相关包含在新增论文内。

最近完成检查：2026-11-10 01:54最近发现新增版本：2026-11-09 13:22库内论文最新更新时间：2026-11-07 02:59

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

18,172 已收录论文15,506 AI 相关4,527 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

时间范围跟随排序：版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常，查看状态 →

找到 18,172 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-10 01:52（北京时间）
新论文 · v1arXiv:2610.34825

Interpretable Brain Age Prediction Using White Matter Fiber Orientation Distributions with Rotation-Equivariant Deep Learning

Chenyang Fan, Robert D. Sanders, Elie Matar, Yixuan Yuan, Xiang Li, Sharon L. Naismith, Fernando Calamante, Jinglei Lv

原文摘要

Diffusion MRI (dMRI) provides information about white matter microstructure that can support brain age prediction. However, many existing prediction models use diffusion tensor imaging (DTI) scalar metrics that omit orientation information. Deep learning is increasingly used for brain age prediction, but conventional CNNs do not explicitly respect the geometric structure of orientation-dependent features. We present an interpretable brain age prediction framework that combines white matter fiber orientation distributions (WM-FODs) with an SE(3) (Special Euclidean group in 3 dimensions) equivariant CNN. The network operates directly on spherical harmonic (SH) coefficients of the FOD, preserving their transformation properties under rotation. Evaluation in 692 participants aged 36-90 years from the Human Connectome Project Aging dataset showed that the combined framework outperformed the evaluated DTI-based models and conventional CNNs. Averaging predictions from five cross-validation models yielded a mean absolute error of 3.54 years and Pearson's correlation of 0.958. Our results indicated that the performance advantage depended on combining WM-FODs with equivariant processing. Prediction accuracy was highest at a maximum SH order of Lmax = 2 and declined at higher orders. Tract-level occlusion, where each segmented tract was masked in turn, revealed age-dependent patterns of model sensitivity, with importance peaks in frontal projection pathways at 36-44 years, the fornix at 45-54 years, the callosal isthmus at 55-64 years, the middle cerebellar peduncle at 65-74 years, and the callosal genu at 75-90 years. These findings support rotation-equivariant processing of WM-FODs for accurate brain age prediction with anatomically interpretable model sensitivity.

cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2504.07462

Learning Universal Features for Generalizable Image Forgery Localization

Hengrun Zhao, Yunzhi Zhuge, Yifan Wang, Lijun Wang, Huchuan Lu, Yu Zeng

原文摘要

In recent years, advanced image editing and generation methods have rapidly evolved, making detecting and locating forged image content increasingly challenging. Most existing image forgery detection methods rely on identifying the edited traces left in the image. However, because the traces of different forgeries are distinct, these methods can identify familiar forgeries included in the training data but struggle to handle unseen ones. In response, we present an approach for Generalizable Image Forgery Localization (GIFL). Once trained, our model can detect both seen and unseen forgeries, providing a more practical and efficient solution to counter false information in the era of generative AI. Our method focuses on learning general features from the pristine content rather than traces of specific forgeries, which are relatively consistent across different types of forgeries and therefore can be used as universal features to locate unseen forgeries. Additionally, as existing image forgery datasets are still dominated by traditional hand-crafted forgeries, we construct a new dataset consisting of images edited by various popular deep generative image editing methods to further encourage research in detecting images manipulated by deep generative models. Extensive experimental results show that the proposed approach outperforms state-of-the-art methods in the detection of unseen forgeries and also demonstrates competitive results for seen forgeries. The code and dataset are available at https://github.com/ZhaoHengrun/GIFL.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2603.12106

Space-Efficient Approximate Spherical Range Counting in High Dimensions

Andreas Kalavas, Ioannis Psarros

原文摘要

We study the following range searching problem in high-dimensional Euclidean spaces: given a finite set $P\subset \mathbb{R}^d$, where each $p\in P$ is assigned a weight $w_p$, and radius $r>0$, we need to preprocess $P$ into a data structure such that when a new query point $q\in \mathbb{R}^d$ arrives, the data structure reports the cumulative weight of points of $P$ within Euclidean distance $r$ from $q$. Solving the problem exactly seems to require space usage that is exponential to the dimension, a phenomenon known as the curse of dimensionality. Thus, we focus on approximate solutions where points up to $(1+\varepsilon)r$ away from $q$ may be taken into account, where $\varepsilon>0$ is an input parameter known during preprocessing. We build a data structure with near-linear space usage, and query time in $n^{1-Θ(\varepsilon^4/\log(1/\varepsilon))}+t_q^{\varrho}\cdot n^{1-\varrho}$, for some $\varrho=Θ(\varepsilon^2)$, where $t_q$ is the number of points of $P$ in the ambiguity zone, i.e., at distance between $r$ and $(1+\varepsilon)r$ from the query $q$. To the best of our knowledge, this is the first data structure with efficient space usage (subquadratic or near-linear for any $\varepsilon>0$) and query time that remains sublinear for any sublinear $t_q$. We supplement our worst-case bounds with a query-driven preprocessing algorithm to build data structures that are well-adapted to the query distribution.

cs.CG

查看论文
arXiv ↗PDF ↗
版本更新 · v5arXiv:2601.00705

Rethinking Densification in Gaussian SLAM: A Stationary Sampling Perspective

Wei-Tse Cheng, Yen-Jen Chiou, Yuan-Fu Yang

原文摘要

Gaussian Splatting enables high-fidelity differentiable SLAM by representing scenes as anisotropic Gaussian primitives. Most systems rely on residual-driven densification, which couples refinement with representation growth: accuracy saturates at a moderate primitive count, yet memory grows throughout the trajectory, degrading throughput. We introduce TopoGS-SLAM, a stationary-sampling formulation that decouples refinement from capacity through coverage-triggered Gaussian initialization and bounded-topology optimization, turning mapping into a bounded-dimensional problem with stable scaling. On standard indoor benchmarks, TopoGS-SLAM matches or surpasses densification-based pipelines in localization and reconstruction accuracy while substantially improving memory scalability and throughput, showing that iterative topology mutation is not required for accurate Gaussian SLAM in bounded-area static indoor scenes with sufficient multi-view coverage. Additional details and resources are available at this URL: https://breeze1124.github.io/topogs-slam-project-page/

cs.CV · cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34819

Selective Monocular Precession Estimation under Geometric and Evaluation Ambiguity: An Auditable Synthetic Study with ORBIT-SCOUT

Carlos Eduardo Sanoja

原文摘要

Monocular observations of a tumbling object can support a precise fitted trajectory without establishing that the recovered physical axis is correct. We study this distinction for elongated, approximately cylindrical targets observed by a calibrated stationary camera. ORBIT-SCOUT couples image-derived line and rim geometry to constant-cone and torque-free triaxial trajectory families, then returns a linked momentum-axis and mean-precession-rate estimate only when numerical, geometric, temporal and competing-hypothesis checks pass. We describe the measurement objective, selection policy and limitations, and situate them within spacecraft pose estimation, unknown-target reconstruction, rigid-body identification and selective prediction. An internally preregistered population of 96 new synthetic scenes was processed in two cold passes, retaining all 192 attempts. In the primary pass, 38 scenes produced jointly correct estimates, none produced an incorrect estimate, 57 were withheld and one execution was incomplete. Correct coverage on the 64 supported scenes was 25/64. Ninety-five repeated pairs were scientifically equivalent under a frozen comparison policy; the remaining pair was incomplete. The registered coverage, failure-free execution and all-case repeatability targets were not met. Historical audits also exposed an overly permissive axis metric and motion-dependent acquisition cadence. The contribution is a documented measurement-to-decision implementation and a failure-preserving evaluation case study, not a new rigid-body theory or evidence of state-of-the-art accuracy. Zero observed errors does not establish calibrated risk, and conditional temporal checks do not remove shared image-feature bias. Real-image transfer and external reproduction remain open.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34816

Can System-1-Style Decision Models Replace Dedicated Rerankers in RAG? A Systems Evaluation

Qiaomu Li, Ying Xie

原文摘要

Retrieval-augmented generation (RAG) systems often use a dedicated reranker to choose which retrieved candidates reach the language model. Reranking improves relevance but adds latency, so teams look for faster alternatives. System-1style decision models make direct, structured predictions instead of generating long responses. Could one provide comparable reranking quality with less inference overhead? We first screen 21 open-weight models on 11 benchmarks, then compare a promising decision model with a dedicated reranker on identical candidate lists. The default decision-model setup fails on many long candidate sets, so scoring only the requests it completes gives a misleading ranking. Limiting candidate text length largely restores reliability and makes some configurations competitive. A frozen evaluation on new retrieval data supports the reliability and ranking results, but confirms the latency requirement for only one of the two selected configurations. Across workloads, which model ranks better changes, and a tuned reranker remains faster and uses far less GPU memory. A decision model can perform competitive reranking, but replacing a reranker requires weighing quality, latency and memory together, and teams should tune the reranker they already run first.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2511.08912

A Shared Control Framework for Mobile Robots with Planning-Level Intention Prediction

Jinyu Zhang, Lijun Han, Feng Jian, Lingxi Zhang, Hesheng Wang

原文摘要

In mobile robot shared control, effectively understanding human motion intention is critical for seamless human-robot collaboration. This paper presents a novel shared control framework featuring planning-level intention prediction. A path replanning algorithm is designed to adjust the robot's desired trajectory according to inferred human intentions. To represent future motion intentions, we introduce the concept of an intention domain, which serves as a constraint for path replanning. The intention-domain prediction and path replanning problems are jointly formulated as a Markov Decision Process and solved through deep reinforcement learning. In addition, a Voronoi-based human trajectory generation algorithm is developed, allowing the model to be trained entirely in simulation without human participation or demonstration data. Extensive simulations and real-world user studies demonstrate that the proposed method significantly reduces operator workload and enhances safety, without compromising task efficiency compared with existing assistive teleoperation approaches.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2610.29680

TraceForge: Distilling with Your Own Thinking

Yan Wang

原文摘要

Using an LLM to generate training data for another is among the most general ways to train one, and it remains common practice. Some frontier teams have closed that route for their own models: what comes back is an answer, or a short summary, without the detailed reasoning trace behind it. That is a little ironic: they were themselves built on distilling human knowledge, and distilling an open-source model is still entirely routine; the restriction applies to their own outputs alone. Recent work recovers the hidden reasoning by replaying encrypted blocks across models. It somehow works, but it breaks the providers' terms of service, so it is not something a product can be built on long-term. We built the alternative. We take the context and the teacher's answer as input, and generate the reasoning trace ourselves, in the style of the student's own model family. Training is two-stage, supervised and then adversarial: a generator learns to regenerate the family's own reasoning traces from their context and answer, and a critic learns how real a reasoning trace looks. Applied to a teacher's answer, the generator writes one in the family's style. An independent judge rates how likely traces are to be genuine on a scale from 0 to 1: ours average 0.68, real traces 0.66, and traces selected by the critic from four candidates 0.82. These are authenticity scores, not correctness rates. We test the idea on five benchmarks with everything else held fixed. On general tasks the five training corpora are about the same; on coding, the generated reasoning beats Fable 5's own thinking content. With the same 5,000 questions and the same teacher answers, HumanEval+ improves by 3.7 points and MBPP+ by 7.1 at the final checkpoint, and the MBPP+ lead holds at every checkpoint. We suspect that reasoning written in the student's family style is easier for it to learn from.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34812

Precedence-Aware Resource Allocation: Extending the AUTOC Framework to Multi-Level Treatments

Olin E. Gilster, Shengpu Tang

原文摘要

Many real-world decision problems require allocating limited resources across individuals to maximize total benefit often through interventions that vary in intensity rather than binary treat-or-not decisions. In these settings, higher levels treatments require first applying lower levels of treatment, inducing a precedence constraint that complicates allocation under a fixed budget. While the causal inference literature has largely emphasized accurate estimation of conditional average treatment effects (CATE), recent work has shown that estimation accuracy alone does not guarantee effective resource allocation, motivating ranking-based evaluation frameworks. The Area Under the Targeting Operating Characteristic (AUTOC) provides an effective way to evaluate prioritization rules across budget levels, but existing formulations are limited to binary treatments. We introduce Multi-Level AUTOC (ML-AUTOC), which is a generalization for AUTOC designed for multi-level treatment settings with precedence. We also propose precedence-aware policies for mapping true marginal treatment effects to feasible treatment assignments under fixed budget constraints. Our results show that in the setting of multi-level treatments, maximizing realized treatment effects may require re-allocation of treatments across individuals.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v5arXiv:2403.17382

How Quickly Do Development Teams Update Their Vulnerable Dependencies?

Imranur Rahman, Ranindya Paramitha, Nusrat Zahan, Jason Osborne, William Enck, Laurie Williams

原文摘要

Industry practitioners are increasingly concerned with software that contains vulnerable versions of third-party dependencies that are included both directly and transitively. To address this problem, projects are encouraged to both (a)~quickly update to non-vulnerable versions of dependencies and (b)~be mindful of the update practices of the dependencies they choose to use. To this end, researchers have proposed metrics to measure the responsiveness of the development teams of the packages in keeping their dependencies updated: Mean-Time-To-Update (MTTU) and Mean-Time-To-Remediate (MTTR). While MTTU covers all dependencies, MTTR quantifies the time needed for a package to update its vulnerable dependencies. However, existing metrics fail to capture important nuances, such as considering floating versions and prioritizing recent updates, leading to inaccurate reflections of a development team's update practices. \textit{The goal of this study is to aid practitioners in understanding how quickly packages update their dependencies.} We propose two novel metrics, Mean-Time-To-Update for dependencies (MTTU) and Mean-Time-To-Remediate for vulnerable dependencies (MTTR), that overcome the limitations of existing metrics. We conduct an empirical study using $163,207$ packages in npm ($117,129$), PyPI ($42,777$), and Cargo ($3,301$) and characterize how the ecosystems differ in MTTU and MTTR, as well as what package characteristics influence MTTU and MTTR. We found that most packages have a relatively fast dependency update practice. We further study whether MTTU can be used as a proxy for MTTR when sufficient vulnerability data is not available. As we did not find enough statistical evidence for a strong proxy, our findings suggest that MTTU could only be partially used (may be used but with caution) as a proxy for MTTR when vulnerability data is not available.

cs.SE · cs.CR

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2609.02847

RoGe: Novel View Synthesis via End-to-End Implicit Reconstruction and Generation

Xiaolei Lang, Ze Kang, Zehao Huang, Naiyan Wang

原文摘要

Novel view synthesis from sparse inputs requires both geometric grounding from the observed views and generative priors of unobserved regions, motivating recent hybrid methods that combine reconstruction and generation. However, existing methods bridge the two with rendered images or explicit 3D representations such as point maps or 3D Gaussians. Generation is thus conditioned on a lossy and imperfect projection of the scene, inheriting its errors, and reconstruction receives no signal from generation to correct them. We present RoGe, an end-to-end unified reconstruction and generation framework that removes this explicit bridge. It targets roaming within a scene anchored by sparse views: given a few posed images and a camera trajectory, it synthesizes a temporally coherent video along that trajectory. From the sparse input views, RoGe builds an implicit scene representation with a feed-forward reconstruction model, and queries it with camera rays to obtain per-view geometric features. These features are injected into a video diffusion model as conditioning, without any explicit 3D intermediate. Both modules are trained jointly, so the generation objective directly shapes its own geometric conditioning. We conduct extensive experiments, where RoGe outperforms reconstruction-based, generation-based, and hybrid baselines in terms of image-level quality and video-level temporal and geometric consistency. Ablations confirm that ray-queried implicit features outperform both raw reconstruction tokens and rendered RGB as conditioning, and that joint training brings further gains. Our code will be released on https://jerry-locker.github.io/roge/.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.32417

Measuring the Energy Cost of Completing Tasks with Quantized Language-Model Agents

Stephen Abkin, Aldric Yang, Alex Flesher, Nitheesh Kodarapu, Deepak Panigrahy, Aakash Tyagi, David Kebo Houngninou

原文摘要

Quantization reduces the memory and energy needed to serve large language models (LLMs) and AI agents for coding and data analysis can now run on locally hosted LLMs. In practice, this benefit is commonly benchmarked per output token. Yet an agent calls its model repeatedly, runs tools, and revises its work, and quantization can change both how much the agent generates and whether it succeeds. Existing energy studies either compare quantized models on single requests or measure agents at one fixed precision, overlooking how a change in precision plays out across a complete agent task. To address this gap, this paper presents the first characterization of the task-level energy trade-offs of model quantization in locally hosted agents. We develop 29 agent tasks with automatic pass/fail checks in six families, ranging from single-answer SQL analytics to multi-step repository bug fixing, and measure CPU and GPU energy per output token and per completed task for 4-bit and 8-bit versions of two open-weight models on bare-metal NVIDIA A100 nodes with llama$.$cpp. Our findings reveal that 4-bit precision generally saves energy per token, though whether it saves energy per completed task is task dependent and changes with the model and the execution budget (i.e., limits on turns, tokens, and time). We trace this discrepancy to the extra tokens needed to complete a task in full, which translates into using up to 3.5 times as much energy per completed task. These findings offer actionable guidance for developers and operators choosing model precision for agents, showing how tokens per completed task, set against the per-token saving, reveal whether lower precision completes the work with less energy.

cs.PF

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2408.02846

What's in a Package? Getting Visibility Into Dependencies Using Security-Sensitive API Calls

Imranur Rahman, Ranidya Paramitha, Henrik Plate, Dominik Wermke, Laurie Williams

原文摘要

The Log4Shell vulnerability occurred because the JNDI (Java Naming and Directory Interface) lookup feature was used, even though it was not needed for log4j's core functionality. This case illustrates why developers may want visibility into the sensitive capabilities available through a dependency. The presence of a call alone does not establish that the call is unnecessary or risky. Security-sensitive APIs provide access to security-sensitive resources, such as filesystem, network, or process-related resources. If developers know which types of sensitive resources a dependency can access, they can control their dependencies at a finer grain, and they can consider an alternative dependency when a dependency makes unnecessary or suspicious security-sensitive API calls. However, prior work has not provided a documented, repeatable procedure for deriving an ecosystem-specific security-sensitive API list, so developers lack systematic visibility into the sensitive capabilities of their dependencies. The goal of this study is to aid developers in understanding sensitive resources accessible to their dependencies by identifying security-sensitive APIs in packages through an empirical study of Java packages. In this study, we present a novel and repeatable methodology to construct a security-sensitive API list for an ecosystem, and we apply it to Java. We then compare the security-sensitive API calls of functionally similar Java packages. The number of security-sensitive API calls (call level) ranges from 0 to 368 in one capability and from 0 to 429 in total among packages with similar functionality. These packages also differ in capability breadth, the number of the 15 capabilities that a package reaches. For example, capability breadth ranges from 0 to 10 in the "Dependency Injection" category and from 0 to 13 in the "Web Frameworks" category.

cs.CR · cs.SE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34809

Position Matters More Than Channel: Talking a Language Model Out of a Correct Answer

Xinyi Ni

原文摘要

Language models now answer questions alongside other claims: a note in the system prompt, a message from another agent, their own earlier answer. We ask what it takes to talk a model out of an answer it gets right on its own, and separate three factors that earlier studies vary together: where the advice sits in the prompt, who is said to have written it, and what the model has already written. On Qwen3.5-27B and four-option MMLU-Pro items, with the rest of the advice held fixed in each comparison, we find three things. First, position matters far more than the API channel, in opposite directions for a bare claim and an argument: a bare "the answer is X" does most harm just before the model answers, while the same claim with a false rationale does most harm before the question, where it raises error on items the model otherwise almost never misses from 1% to 67%; moving the claim between the system message and the user message at the same position changes error by a few points. Second, attributing the note to an authority rather than to another participant, and phrasing it assertively, each raise error by 10-27 points, while the two authorities we tested differ by under two. Third, replaying a correct worked answer before the advice protects it whether the text is shown as the model's own or as someone else's, and the same replay keeps wrong answers from being corrected by a bare correct note. The position result replicates under an independently written prompt. Code, items and all result tables are released at https://github.com/coolkillercat/safety.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2603.13829

ArrayTac: A Closed-Loop Piezoelectric Tactile Platform for Continuously Tunable Rendering of Shape, Stiffness, and Friction

Tianhai Liang, Shiyi Guo, Baiye Cheng, Zhengrong Xue, Han Zhang, Huazhe Xu

原文摘要

Human touch depends on the integration of shape, stiffness, and friction, yet existing tactile displays cannot render these cues together as continuously tunable, high-fidelity signals for intuitive perception. We present ArrayTac, a closed-loop piezoelectric tactile platform that simultaneously renders these three tactile dimensions with continuous tunability on a 4 by 4 actuator array. Each unit integrates a three-stage micro-lever amplifier with end-effector Hall-effect feedback, enabling up to 5 mm displacement, an array refresh rate greater than 500 Hz, and a closed-loop bandwidth of 123 Hz. In psychophysical experiments, naive participants identified three-dimensional shapes and distinguished multiple stiffness and friction levels through touch alone without training. We further demonstrate image-to-touch rendering from an RGB image and remote palpation of a medical-grade breast tumor phantom across a distance of more than 1,000 km, in which all 11 participants correctly identified the number and type of tumors with a sub-centimeter mean localization error. Together, these results establish ArrayTac as a programmable multidimensional tactile rendering platform that bridges digital representations, physical environments, and human tactile perception, enabling intuitive tactile communication between humans and machines.

cs.RO · cs.AI · cs.HC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.05911

PREFER: Personalized Review Summarization with Online Preference Learning

Millend Roy, Agostino Capponi, Vineet Goyal

原文摘要

Product reviews significantly influence purchasing decisions on e-commerce platforms. However, the sheer volume of reviews can overwhelm users, obscuring information most relevant to their individual needs. Existing e-commerce summarization systems typically produce generic, static summaries that fail to account for the fact that (i) different users prioritize different product characteristics, and (ii) these preferences may evolve with interactions. To address these challenges, we propose an online learning framework that generates personalized summaries for each user by representing user interests in a latent aspect space and selecting preference-aligned review evidence. Our system then iteratively refines its understanding of user preferences by incorporating feedback on the generated summaries directly over time. We evaluate our framework on Amazon Reviews'23 using controlled feedback simulations and robustness checks with held-out-history, independent-embedding, and external LLM-based evaluators. These experiments show improvements in preference-aligned evidence selection under the evaluated feedback settings. A separate human-based study finds that scenario-conditioned summaries are preferred over generic (uniformly-aggregated) alternatives in 69.9% of paired comparisons.

cs.AI · cs.GT · cs.LG · eess.SY · math.OC

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2610.28402

StreamEval: Evaluating Interactive Streaming Video Generation Models

StreamEval Team

原文摘要

We introduce StreamEval with four key features: (1) First interactive streaming video generation benchmark. (2) Fully open source. Benchmark data, evaluation code, protocols, and scoring rules are publicly available. (3) Comprehensive coverage. Five tasks cover avatar dialogue, avatar performance, world generation, instruction editing, and reference editing, with 300 scripted cases lasting 15 to 300 seconds. Ten metrics assess task execution, state consistency, visual fidelity, and audiovisual coordination. (4) Monthly updates. We will evaluate new and updated models and publish leaderboard results monthly. Results from 37 models show that high visual quality and identity retention do not necessarily coincide with reliable request execution or sustained state consistency. The leaderboard is available at https://streameval.ai.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34807

ImageTTS: Repurposing Pretrained Image Diffusion Transformers for Speech Synthesis

Hanchen Pei, Shujie Liu, Yayue Deng, Fangyun Wei, Yanqing Liu, Jianwei Yu, Gongping Huang

原文摘要

Pretrained image-generation models have been successfully repurposed for various downstream visual tasks. Whether their learned representations and generative priors can transfer beyond vision to other modalities remains largely unresolved, particularly for speech synthesis, which requires linguistic fidelity and preservation of speaker identity from a short reference. We present ImageTTS, which repurposes FLUX.2 for speech synthesis by encoding pseudo-RGB log-mel spectrograms with its frozen image VAE and adapting only its pretrained Diffusion Transformer (DiT) using conditional latent flow matching. This formulation disentangles two forms of vision-to-speech transfer: representation transfer through the image VAE and generative-prior transfer through DiT initialization. The frozen image VAE largely preserves intelligibility and speaker identity with 0.99 STOI and 0.95 speaker similarity, while image-pretrained DiT initialization accelerates convergence and improves linguistic accuracy, reducing WER from 4.2\% to 2.7\% at 100k matched updates relative to random initialization. The same framework supports both zero-shot and instruction-guided TTS and, when scaled to 100K hours of speech data, achieves 1.12\% WER on Seed-TTS test-en and a Style-ACC of 0.66 on CapSpeech, outperforming speech-native baselines trained on comparable data across both tasks. These results suggest that pretrained image models can transfer beyond architectural reuse, supplying useful latent representations and generative priors for intelligible and controllable speech synthesis.

cs.SD · cs.MM

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.30729

Width and Depth Limits Commute During Training in Linear Residual Networks

Ruijia Zhang, Soufiane Hayou

原文摘要

Recent work established that the infinite-width and infinite-depth limits of residual networks commute at initialization when residual branches are scaled by $1/\sqrt{depth}$. In particular, the network output converges to the same limit whether width and depth tend to infinity sequentially or jointly. We extend this commutativity result to training in linear residual networks. Under the same $1/\sqrt{depth}$ residual-branch scaling (Depth-$μ$P) and the $μ$P width parameterization, we prove that, for any fixed number of gradient-descent steps with gradient clipping, the network output converges in $L^2$ along every joint width--depth growth path as both width and depth tend to infinity. Consequently, the infinite-width and infinite-depth limits commute throughout any finite training horizon. Without gradient clipping, the corresponding $L^2$ convergence does not hold in general, but we establish the weaker convergence in probability.

cs.LG · stat.ML

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.13700

C-MambaPose: Phase-Preserving Complex Mamba for Cross-Environment Wi-Fi Human Pose Estimation

Phuc H. Nguyen, Van-Dinh Nguyen

原文摘要

Cross-environment generalization remains a fundamental challenge for Wi-Fi-based human pose estimation (HPE), as environmental multipath can drastically alter Channel State Information (CSI) for the same human motion. Existing approaches often discard CSI phase or collapse complex signals into real-valued features early, losing motion-sensitive phase dynamics. We present C-MambaPose, a phase-preserving complex-valued state-space framework for robust cross-environment Wi-Fi 3D HPE. Our key insight is to preserve complex phase relationships throughout spatiotemporal modeling, rather than using phase only as an input feature. C-MambaPose sanitizes synchronization-induced phase errors and employs a Spatiotemporal Complex Mamba encoder with dynamic multi-scale receptive fields to capture long-range phase-amplitude dynamics. Cross-attention then maps the learned representations to human joints, followed by a skeleton-aware GraFormer decoder for anatomically coherent pose estimation. Experiments on MM-Fi show that C-MambaPose achieves strong performance across all settings, with the largest gains in unseen environments, reaching $298.5$ mm and $317.6$ mm MPJPE on the two cross-environment protocols using only $3.78$ M parameters and no pretraining. Ablations further show that prematurely discarding complex phase relationships substantially degrades performance, demonstrating their importance for cross-environment Wi-Fi HPE.

eess.SP · cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34805

On the Existence of Complete Coverings of Lee Spheres

Jing Zhang, Yue Zhou

原文摘要

Every perfect $r$-error-correcting Lee code in $\mathbb{Z}^n$ induces a finite configuration around each codeword: a family of pairwise disjoint radius-$r$ Lee spheres, all disjoint from the central sphere, that covers every lattice point at Lee distance $r+1$ from the codeword. We call such a configuration a complete covering. Under projection onto a suitable Cartesian product of cycles, a complete covering corresponds to an optimal local structure in the sense of Špacapan. The existence of a complete covering is necessary but, in general, not sufficient for the existence of a perfect Lee code, as our construction for $(n,r)=(3,2)$ shows. We prove that no complete covering exists whenever $n\ge 8$ and $r^2+\lfloor 25r/34\rfloor-3\ge 2n$. For the corresponding Cartesian products of cycles, this strengthens Špacapan's nonexistence theorem by replacing the linear radius condition $r\ge n$ with a threshold of order $\sqrt{2n}$. We also obtain an improved large-radius nonexistence bound for perfect Lee codes, strengthening the bound of Horak and Kim. Furthermore, we show that, for every $\varepsilon>0$, no complete covering exists when $n\ge 3$, $r$ is sufficiently large, and $r^2+(2/\mathrm{e}-\varepsilon)r\ge 2n$. On the positive side, we use near-optimal ternary constant-weight codes to construct almost complete coverings whose pairwise disjoint shadows cover a $1-o(1)$ proportion of the first outer Lee shell as the dimension tends to infinity, for every fixed radius.

cs.IT

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.26185HF 社区推荐

MoveBench: A Rubric-Based Benchmark for Evaluating Large Language Models in Sports and Health Coaching

Yitong Li, Jiang Bian, Jingling Wang, Pan Ding, Chengying Gu

原文摘要

Despite rapid advances in large language models (LLMs), their deployment in the sports and health domain remains high-risk due to the absence of domain-specific evaluation benchmarks. Existing general-purpose benchmarks (e.g., MMLU and HELM) primarily assess broad knowledge and reasoning capabilities, but fail to capture critical domain requirements such as exercise safety, physiological appropriateness, personalization, and actionable coaching quality. This gap is particularly concerning in fitness and health applications, where incorrect or unsafe recommendations can lead to physical harm. To address this limitation, we introduce MoveBench, the first comprehensive benchmarking framework specifically designed for evaluating LLMs in sports and health coaching. The proposed benchmark integrates heterogeneous task formats, including multiple-choice questions (MCQs) and open-ended question answering (OpenQA), grounded in real-world user scenarios and paired with structured rubrics emphasizing safety compliance, scientific validity, and training logic. Through large-scale evaluation of 15 diverse LLMs on 809 questions with 5,012 rubric-level criteria, our results reveal substantial performance variability, particularly in safety awareness, structured program design, and personalization capability, highlighting a critical gap between knowing and doing. Our work establishes a foundational evaluation standard for sports and health LLM applications and provides a reproducible framework for advancing safe, reliable, and context-aware AI-driven coaching systems. Open resources are available at https://github.com/SatoSakula/MoveBench.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34801

When Does Data Value Reduce to Class Balance? A Coverage View of Per-Point Data Valuation

Yingjie Bai, Weiming Zhi

原文摘要

Per-point data-valuation scores -- Data Shapley, influence, leverage -- are routinely used to select training data: keep the points with the top $k$ scores. We argue that top-$k$ by a fixed, mode-blind per-point score is the wrong selection rule precisely in the regime where data selection matters. The reason is that a point's value is not a fixed number but depends on what else has been selected -- a near-duplicate of an already-chosen point adds almost nothing, however high its score -- and a per-point scalar cannot express this interaction. The theory quantifies this failure exactly: in an equal latent-mode model, fixed top-$k$ selection incurs a closed-form excess risk over adaptive coverage because it repeatedly spends budget on already-covered modes. The gap is largest when the budget is tight, the learner representation is redundant, and missing a mode is costly. The practical rule is simple: use balance when the labels available at selection identify the learner's modes, and use explicit coverage when they do not. On standard classification tasks with strong pretrained features, class-balancing the same per-point scores recovers the missing coverage and matches or outperforms generic set coverage across our datasets. Without labels, label-free coverage improves accuracy by up to +0.20 while raw top-$k$ can fall below random; when labels are coarser than the modes, coverage within coarse strata performs best. We turn this distinction into a pre-specified diagnostic and validate it across both favorable and stress-test settings. The limits are part of the claim: the advantage is representation-relative. Coverage fails when the relevant modes are not expressed in the learner geometry, as with spurious subgroups, or when data quality varies independently of coverage -- exactly as the theory predicts.

cs.LG · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34800

Phantom Forgetting: How BatchNorm State Fakes Deletion in Edge Split Machine Unlearning

Anand Agrawal, Anil Kumar Chillara, Naresh Mandan

原文摘要

Split learning is a natural fit for edge intelligence: a resource-constrained edge device runs the first layers of a network and offloads the remainder to a server, so that raw data never leave the device. When such a system must unlearn revoked or sensitive data for example to honor a right-to-erasure request, the deletion is commonly assessed through changes in forget-set accuracy. However, inference on an edge-server split also depends on non-learnable model state distributed across the two parties, and this state is especially volatile on edge devices subject to data drift, over-the-air updates, and checkpoint rollback. This paper isolates a state-integrity question with direct edge-security implications: can Batch Normalization (BN) running statistics create a target-specific forgetting signal even when every learnable weight remains fixed? We define a state-only diagnostic that separates learnable-parameter change from BN- buffer change and localizes the effect to the edge (client) side, the server side, and joint placements. We also introduce a state-induced forgetting gap (SIFG) that discounts simultaneous retain-set degradation. Over all ten CIFAR-10 forget classes, centralized BN recalibration on forget data reduces mean forget accuracy by 61.50 percentage points with zero weight change; in a split model, edge-only, server-only, and joint recalibration produce mean drops of 37.27, 41.71, and 51.90 points. The server-side state yields the largest selective gap relative to retain degradation, while joint recalibration causes the largest overall prediction change. These results establish distributed normalization buffers including those held on the edge device as security and privacy-relevant inference state, and show that forget accuracy should not be interpreted, or accepted as a deletion certificate, without an explicit edge-aware state-integrity audit.

cs.CR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34799

Centralized Critics for N-Agent Ad Hoc Teamwork

Andrew McAlinden, Caroline Wang, Steven Shi, Arrasy Rahman, Elad Liebman, Peter Stone

原文摘要

Centralized training with decentralized execution (CTDE) has become the dominant paradigm in multi-agent reinforcement learning (MARL), motivating extensive study of what privileged information should be made available to the critic during training. While prior work has examined the role of global state in fully cooperative settings, the design of centralized critics for N-agent ad hoc teamwork - in which dynamically varying set of learning agents must coordinate with an arbitrary set of uncontrolled teammates drawn from an unknown distribution - remains poorly understood. We study this question by comparing two natural classes of advantage estimators: controlled history estimators, which condition only on the observation and action histories of the learner's own agents, and joint history estimators, which additionally condition on the histories of the uncontrolled teammates. We prove that both estimators are unbiased and characterize the conditions under which the joint history estimate attains strictly lower variance than its controlled counterpart. Empirically, joint history critics match or outperform controlled history critics across a range of NAHT tasks, yielding improved sample efficiency and final returns. Together, these results provide both a theoretical justification and an empirical recommendation for incorporating uncontrolled agent histories into centralized critics for N-agent ad hoc teamwork.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2510.08479

No Provenance Left Behind: Revisiting Reference Monitor Guarantees with Learned Kernel Scheduling

Jinsong Mao, Benjamin E. Ujcich, Shiqing Ma

原文摘要

Provenance plays a critical role in maintaining traceability of a system's actions for root cause analysis of security threats and impacts. Provenance collection is often incorporated into the reference monitor of systems to ensure that an audit trail exists of all events, that events are completely captured, and that logging of such events cannot be bypassed. However, recent research has questioned whether existing state-of-the-art provenance collection systems fail to ensure the security guarantees of a true reference monitor due to the 'super producer threat' in which provenance generation can overload a system to force the system to drop security-relevant events and allow an attacker to hide their actions. One approach towards solving this threat is to enforce resource isolation, but that does not fully solve the problems resulting from hardware dependencies and performance limitations. In this paper, we show how an operating system's kernel scheduler can mitigate this threat, and we introduce Aegis, a learned scheduler for Linux specifically designed for provenance. Unlike conventional schedulers that ignore provenance completeness requirements, Aegis leverages reinforcement learning to learn provenance task behavior and to dynamically optimize resource allocation. We evaluate Aegis's efficacy and show that Aegis significantly improves both the completeness and efficiency of provenance collection systems compared to traditional scheduling, while maintaining reasonable overheads and even improving overall runtime in certain cases compared to the default Linux scheduler.

cs.CR · cs.OS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34797

TimeWorld: Towards Action-Conditioned Multimodal World Models for Time Series Forecasting

Hang Ni, Weijia Zhang, Hao Liu

原文摘要

Time series forecasting supports decision-making in web applications such as online retail and network management, where planned actions can reshape future dynamics. World models provide a natural paradigm for predicting such action-dependent changes beyond extrapolating historical patterns. However, existing time series world models (TSWMs) typically rely on fixed, domain-specific covariate schemas that limit flexible intervention specification, while multimodal forecasters treat text primarily as passive predictive context. To investigate these gaps, we introduce TSWM-Bench, a cross-domain benchmark for multimodal TSWMs spanning seven real-world datasets, with textual interventions grounded in recorded action--outcome data. Our evaluation reveals that conventional multimodal forecasters underperform history-only time series foundation models (TSFMs) despite dataset-specific training, whereas simple text-prefix adaptations improve forecasting across all evaluated TSFM backbones. These findings suggest that pretrained TSFMs encode implicit world knowledge of temporal dynamics, offering a strong foundation for action-conditioned modeling beyond conventional multimodal fusion. Building on this insight, we propose TimeWorld, a plug-in framework that adapts pretrained TSFMs through explicit action-response modeling. Specifically, the Prototype-Guided Latent Modulation (PLM) module grounds textual actions in temporal dynamics by composing representative response prototypes to modulate future representations based on the action and historical patterns. The Action Contrastive Learning (ACL) component strengthens action-specific response modeling by contrasting these updates under alternative interventions sharing the same history, distinguishing action types while preserving relative intensity relationships.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34795

Towards Spatio-Temporal Intelligence Systems in Urban Space: A Twin-Agent Perspective

Zhen Dong, Haiping Wang, Wei Tu, Yuan Liu, Bing Wang, Xuan Sun, Jinzhou Cao, Ronald Clark 等 17 位作者

原文摘要

Cities must coordinate domains like infrastructure, mobility, environmental management, emergency response, and public services as conditions evolve. An urban Spatio-Temporal Intelligence (STI) system helps the city monitor citywide states, analyze problems, plan and execute interventions, and adapt through feedback, making urban governance more timely, effective, and transparent. Recent urban twinning and agentic AI techniques provide foundations for such systems. From a twin-agent perspective, this survey takes a system-level view of how these disparate techniques can be coherently integrated into an urban STI system. Specifically, we review how the twin reconstructs and represents a persistent, information-enriched urban environment, and how the agent understands the twin via interfaces, reasons over it, acts reliably, and continuously evolves with the city. Built upon this synthesis, we summarize a two-loop blueprint, where an inner agent loop for grounding, reasoning, and verification, and an outer system loop linking data, twin, agentic action, feedback, and update. We then use this to structure an STI research agenda and show how a shared prototype supports diverse urban domains.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.00326

Prompt-Induced Score Variance in Zero-Shot Binary Vision-Language Safety Classification

Charles Weng, Dingwen Li, Alexander Martin

原文摘要

Safety pipelines often block content by thresholding a model's first-token unsafe score. We show that a single prompt's score is not a reliable probability and compare two repairs: mean ensemble and calibration with development labels. Across seven vision-language models and two benchmarks, an input's unsafe probability varies across 15 task-preserving rewordings with a standard deviation of 0.16-0.30 on average; the inputs that vary most are more often misclassified. The 15-prompt mean has lower negative log-likelihood (NLL) than the best single prompt, even one chosen with evaluation labels, on 13 of 14 model-benchmark pairs. Development labels change the picture: jointly selecting and calibrating a single prompt outperforms the similarly calibrated mean for all seven models on held-out data from the development benchmark. Under cross-benchmark evaluation without refitting, however, the advantage reverses, with the calibrated mean outperforming the single prompt on six of seven models. We recommend evaluating first-token scores as a prompt family, using the mean ensemble as the label-free baseline, calibrating one prompt when development labels exist and deployment data match, and calibrating the mean when they may not.

cs.CL · cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34791

Text Is the Bottleneck: A Small-Scale Replication of LLM Game Playing in Riichi Mahjong

Mingge Xu

原文摘要

We replicate the riichi-mahjong track of "Can Large Language Models Master Complex Card Games?" (arXiv:2509.01328) under a drastically smaller budget: models of at most 2B parameters, one 16 GB consumer GPU, about five GPU-days. (1) With matched data and labels, text is the bottleneck: on the same 100k-decision training set, a 2.6M-parameter convolutional board encoder agrees with the strong AI Mortal on 80.6% of test decisions, above every text-prompt LLM we train (best 77.8%), and places better at the table (2.85 over 1,000 games vs. ~3.0 for the LLMs; paired difference at n=100 not significant). Scaled to 1.71M decisions, a 4.9M-parameter Transformer reaches 94.7% agreement, beats the 0.8B LLMs on identical seeds (-0.45 ranks, sign test p=0.005), and is statistically equivalent to parity against three Mortal champions (TOST within 0.10 ranks, p=6e-4); parity against a teacher-opponent is roughly the ceiling of pure imitation. (2) Training toward the teacher raises teacher agreement more than a 2.5x parameter increase does (+2.5 vs. +1.5 points); on human-record agreement both effects are +1.0, and neither is visible at the table. (3) Few-point agreement differences do not resolve into playing strength within a family: +2.5 agreement points coincide with a paired placement difference of +0.02 +/- 0.12 ranks (p=1.0), and +2.0 points at 2B with -0.06 (p=0.37) - both below the ~0.25-rank resolution of 100 paired games. We also document a paper-code mismatch in the original winner filter, reconstruct its two private engine patches, and show that a divide-and-conquer pipeline makes template-generated Japanese rationales 93% sentence-exact (43% without facts). Per Tenhou's terms we release no trained weights - only code, configurations, and evaluation protocols.

cs.CL

查看论文
arXiv ↗PDF ↗