跳到正文
研踪PaperTrail

论文库

检索计算机领域论文，按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+0新增论文
+0其中 AI 相关
+0已有论文修订
+93新增 AI 导读

arXiv 最近完成扫描：2026-11-16 01:34 · 全站最近入库：2026-11-14 15:09各信源进度 →

统计口径与数据新鲜度

统计 2026-11-15 05:02 — 2026-11-16 05:02（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：2026-11-16 01:34最近发现新增版本：2026-11-14 15:09库内论文最新更新时间：2026-11-13 02:59

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

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

浏览论文库

研究日报 / 周报 →按信源浏览 →

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

找到 23,348 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-16 01:33（北京时间）
新论文 · v1arXiv:2611.16188

PERA: Plug-in Experts for Robotic Actions in Continual Whole-Body Control

Shangchao Hu, Yadan Sun, Xibo Yu, Wei Huang

原文摘要

Motion imitation enables humanoid robots to acquire whole-body skills such as walking and dancing. However, fine-tuning an entire policy for a new skill can affect existing behaviors, while training a separate policy for each skill increases training and maintenance costs. We present PERA, a method for learning new skills by reusing existing motion capabilities. PERA freezes a pretrained mixture-of-experts policy and trains an additional task expert and its routing score using task rewards or teacher-action supervision. In Unitree G1 simulation, each added task module contains approximately 1.03% of the parameters of the base actor. Built on our pretrained policy, PERA successfully completes all ten new tasks. Disabling the expert restores the original computation path of the base policy, which still fully executes all 126 original motions. Enabling the expert also improves the execution of some dance motions not used to train that expert, indicating that its benefits extend beyond its training motions. Experiments with HoloMotion further demonstrate the applicability of PERA to different base policies.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2511.03398

A Class of Self-Orthogonal, NMDS, or LCD MDS $(\mathcal{L}, \mathcal{P})$-Twisted Generalized Reed-Solomon Codes

Zhonghao Liang, Chenlu Jia, Dongmei Huang, Qunying Liao, Chunming Tang

原文摘要

Maximum distance separable (in short, MDS), near MDS (in short, NMDS), linear complementary dual codes (in short, LCD) and self-orthogonal codes play a pivotal role in algebraic coding theory, particularly in applications such as quantum communications and secret sharing schemes. Recently, the construction of non-generalized Reed-Solomon (in short, non-GRS) codes has emerged as a significant research frontier. This paper focuses on a class of $(\mathcal{L}, \mathcal{P})$-twisted generalized Reed-Solomon (TGRS) codes $\mathcal{C}_{k-1}\left(\boldsymbolα,\boldsymbol{v},\boldsymbolη\right)$ characterized by $\ell+1$ twists. By considering a special class of parity-check matrices derived from existing results, we derive the corresponding necessary and sufficient conditions or sufficient conditions for $\mathcal{C}_{k-1}\left(\boldsymbolα,\boldsymbol{v},\boldsymbolη\right)$ to be self-orthogonal, and then generalize the corresponding results given by Liu et al. (2021), Sui et al. (2021), and Zhang et al. (2025). As applications, leveraging these self-orthogonal structures, we can obtain several families of LCD MDS codes. Secondly, we provide a characterization of the NMDS property for the codes $\mathcal{C}_{k-1}\left(\boldsymbolα,\boldsymbol{v},\boldsymbolη\right)$, offering a partial solution to the open problem concerning general $(\mathcal{L}, \mathcal{P})$-TGRS codes posed by Hu et al. (2025). Finally, we rigorously prove that the codes $\mathcal{C}_{k-1}\left(\boldsymbolα,\boldsymbol{v},\boldsymbolη\right)$ are of non-GRS type when $2k > n>k+\ell+2$.

cs.IT

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16184

Flow-CAD: Flow Matching for Contextual Anomaly Detection and Explanation in Tabular Data

Zhong Li, Qi Huang, Yuhang Wang, Yang Cao, Thomas Bäck, Niki van Stein, Matthijs van Leeuwen, Lincen Yang

原文摘要

Contextual anomaly detection in tabular data aims to identify objects whose behavior is unexpected under their contextual conditions. In data-engineering pipelines, this task screens table rows whose measurements violate context-dependent integrity relationships. Most existing approaches rely on either shallow conditional models with limited distributional expressiveness or localized estimators that require per-context modeling, making it difficult to capture complex conditional relationships and scale to high-dimensional settings. We propose Flow-CAD, a new framework for contextual anomaly detection based on Flow Matching. Flow-CAD learns a single global and amortized conditional generative model that flexibly represents behavioral distributions conditioned on context, without assuming simple parametric forms or retraining local models. To enable robust and interpretable anomaly scoring, we introduce a scale-normalized and truncated residual energy derived from the learned conditional flow, which stabilizes anomaly scores, mitigates domination by extreme deviations, and supports feature-wise attribution. We further provide theoretical insights showing that the proposed residual-based anomaly score is stable under velocity estimation error, and that its Monte Carlo estimator satisfies concentration bounds. Experiments on 20 benchmark datasets with 13 competitors demonstrate that Flow-CAD has the best average rank for PR AUC, ROC AUC, and P@n, highlighting its effectiveness and practicality for contextual anomaly detection in tabular data. We provide the source code at https://github.com/ZhongLIFR/FlowCAD.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2506.03874

On a class of generalized Roth-Lempel codes

Zhonghao Liang, Yongkang Wan, Qunying Liao

原文摘要

Maximum distance separable (MDS), almost MDS (AMDS), and self-dual codes have applications in communications, data storage, and quantum coding. The construction and structural study of MDS codes that are not equivalent to generalized Reed-Solomon (GRS) codes are important problems in coding theory and finite geometry. In this paper, we investigate the generalized Roth-Lempel (GRL) codes \(GRL_k(α, v, A_{3\times 3})\) introduced by Li et al. [28] in the case of a \(3\times 3\) appended matrix. Using the Cauchy matrix method of Roth and Lempel, we derive a sufficient condition under which these codes are not equivalent to GRS codes. We also establish necessary and sufficient conditions for their duals to be AMDS and for the codes to be self-dual. The self-duality criterion extends the corresponding result in [28], and we provide examples illustrating our results. Under suitable parameter assumptions and an explicit rank condition, we show that the Schur square of an \([n, k]_q\) GRL code \(GRL_k(α, v, A_{3\times 3})\) has dimension \(2k + 2\). Using this invariant, we show that, under certain conditions, these GRL codes are not equivalent to codes from several known non-GRS families.

cs.IT

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16183

Data-Efficient LLM Safety Alignment Guided by Interpretable Features

Hongyu Li, Zhan Yu, Zhe Zhao, Kimmo Yan, Xiong Kuang, Renfen Hu

原文摘要

Existing large language models typically rely on massive fine-tuning datasets for safety alignment, which results in higher costs for safety alignment and often leads to the problem of over-refusal. We propose Less is Safer (LIS), a compact yet highly effective dataset for safety alignment, constructed through interpretable feature-guided selection and adversarial synthesis. Specifically, we leverage Sparse Autoencoder (SAE) activations to efficiently select prompts that cover diverse and interpretable safety features. Then, we employ a multi-agent adversarial synthesis framework to generate harmless prompts that nevertheless elicit unnecessary refusals. LIS contains only 2.4K samples, yet outperforms much larger datasets, e.g., TRIDENT-Core (26K), TRIDENT-Edge (19K) and WildJailbreak (262K), in overall performance on four safety and five over-refusal benchmarks. Through ablation experiments, we demonstrate that neither safety data nor over-refusal data alone can achieve optimal results. We also used safety features from SAE, annotated by an LLM, for data filtering, but the results were inferior to those obtained using the pipeline proposed in this paper.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16182

Same-State Pairs Make One JEPA Proof of the Platonic Representation Hypothesis Vacuous

Xin Li

原文摘要

In a Joint-Embedding Predictive Architecture (JEPA), the JEPA proof of the Platonic Representation Hypothesis (PRH) assumes that every observation determines the world state and that a spectral gap makes minimizers unique up to rotation. Under the hard-whitening population objective, same-state positive pairs make the induced world kernel the identity: every centered whitened state function is a global minimizer, and, when $d_z-1\ge 2k$, two minimizers can have best-rotation squared residual $2k$. The uniqueness claim is conditional; for $k<d_z-1$, where $d_z$ is the number of world states, this limit makes its premise unsatisfiable, so the claim has no content there. The experiments that motivate it leave the assumption: a caption sees only part of an image, and the paper states no experiment meets its hypotheses exactly. The theorem does not reach those experiments, and for $k<d_z-1$ its idealized same-state limit is vacuous. One of the paper's four quantitative results survives: a gap-free lower bound. Its bound vanishes only at perfect scene-explained fraction; it bounds alignment error but cannot certify good-view alignment. A canonical frame is determined only up to a rotation and a latent permutation. Paired samples fix the relative frame at effective rank $k$; a global rotation remains. Component semantics fix the relative permutation only up to signs; value anchors fix it once the mixing frame is pinned. A resource--gauge ledger records which resource fixes which gauge.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16180

Fast Serverless LLM Cold Starts by Sharing and Prewarming Startup Work

Hongjin Kim, Igjae Kim, Kwanghoon Choi, Minho Ha, Jaehyuk Huh

原文摘要

When a serverless LLM platform launches a model worker on demand, the cold start lasts roughly a minute, yet only 5-11% of it is spent loading weights. Most of the remainder goes to compilation, memory profiling and runtime setup, which each server performs again even though the outcome is identical across servers or independent of the model. We present Cairn. The server that is first to start a model publishes the weights and engine artifacts to a CXL memory pool shared across the cluster, and the remaining servers read them in place. Model-independent setup is completed ahead of time inside warm containers, and a template process replaces each container as soon as it is used. With ServerlessLLM on vLLM v0.20, six models from 1B to 14B, and two servers that share an emulated CXL pool, Cairn speeds up cold starts by 4.1-5.2x on servers without a checkpoint of their own and reduces median TTFT on a request stream by 64%.

cs.DC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16179

Concatenated Codes with One Inner Code: Low-Rate Gilbert-Varshamov Asymptotics from Algebraic-Geometric Codes

Yota Maeda, Ruho Kondo

原文摘要

Constructing codes that attain the Gilbert-Varshamov (GV) bound while admitting efficient encoding and decoding is a fundamental problem in coding theory. We study concatenated codes that reuse a single binary inner code across all outer coordinates. To exploit existing encoding and decoding algorithms, we restrict the outer codes to random subcodes of scaled copies of prescribed algebraic codes and investigate their minimum distance. Our first contribution is a general upper bound on the minimum-distance failure probability that separates two terms controlled by the inner code's bias moments and the dual weight distribution of the prescribed code, together with sufficient conditions for exponential decay. Our second contribution is a concrete construction satisfying these conditions using algebraic-geometric codes from the Garcia-Stichtenoth tower. For every sufficiently small $\varepsilon>0$, we construct a family of random binary codes $C_m$ whose rates approach $\varepsilon^2$ and satisfy \[ \Pr\left[δ(C_m)\geq\frac12-\sqrt{\frac{\ln 2}{2}}\left(\varepsilon+\frac{\varepsilon^3}{2}\right)\right]\geq 1-2^{-c\varepsilon^4N_m}, \] for all sufficiently large $m$, where $N_m$ is the block length and $c>0$ is independent of $\varepsilon$ and $m$. Thus, the distance guarantee matches the leading coefficient of the GV bound at low rates. For each fixed $\varepsilon$, the construction uses a single inner encoding map throughout the family and admits polynomial-time encoding and unique decoding within a guaranteed radius. This answers the question of Doron, Mosheiff, and Wootters for subcodes of scaled algebraic geometry codes at low rates.

cs.IT

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16176

A One-Sided Sublinear-Query Tester for Bounded-Degree 2SAT

Yuichi Yoshida

原文摘要

We give a one-sided tester for satisfiability of 2CNF formulas in the bounded-degree model. For every degree bound $Δ$, distance parameter $\varepsilon>0$, and $ν\in(0,1/2)$, its query complexity on $n$-variable formulas is $\widetilde O_{\varepsilon,Δ,ν}(n^{1/2+ν})$.

cs.DS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16175

Stack more levels: how to get general and human-like Mario playing

Shinichi Arimura, Yuchen Li, Julian Togelius

原文摘要

Super Mario Bros. is widely used in game AI and procedural content generation (PCG), yet it remains unclear whether a model-free agent can reliably win unseen levels. To address this question, we train Proximal Policy Optimization (PPO) agents on increasingly large sets of PCG-generated Mario levels and evaluate their generalization on 1000 held-out test levels. We then shape competent PPO policies into three gameplay archetypes---runner, killer, and collector. Finally, we fine-tune these PPO policies using Diffusion-Reward Adversarial Imitation Learning (DRAIL) with human gameplay demonstrations. We find that increasing the number of distinct PCG-generated training levels generally improves unseen-level performance, and that fine-tuning PPO policies with DRAIL increases action-level human-likeness while preserving much of the persona induced by PPO pretraining.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16174

JudgeMix: Judge-Guided Mixed-Rollout Data Synthesis for LLM Agents

Cheng-Yu Hsieh, Ting-Yao Hu, Sanjoy Chowdhury, Oncel Tuzel, Raviteja Vemulapalli

原文摘要

Supervised fine-tuning (SFT) on expert trajectories is a standard paradigm for training LLM agents. However, it suffers from a well-known training-inference distribution mismatch, calling for target-aware data synthesis strategies that ground the training data in the target model's native state distribution. To bridge this gap, emerging approaches incorporate the expert either to guide mixed rollouts alongside the target model, or to provide dense step-wise supervision. Nonetheless, existing methods apply expert assistance blind to the target model's inherent behavior: they either disrupt the rollout using sub-optimal random intervention heuristics, or they enforce indiscriminate uniform supervision that unnecessarily overwrites the model's already-correct actions. We introduce JudgeMix, a judge-guided data synthesis framework that dynamically interleaves the target model and expert based on step-wise semantic evaluations. JudgeMix queries expert guidance precisely when the target model struggles, ensuring high trajectory success rates while keeping the state distribution aligned with the target model. It additionally uses the judge evaluation to reweight expert supervision on different steps, preserving model's inherent valid behavior while correcting its errors. On two agentic tool-use benchmarks, AppWorld and AutomationBench, JudgeMix demonstrates consistent superior performance to existing methods, with improvements up to 10 pass@1 points.

cs.LG · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2604.21260

Calibeating Prediction-Powered Inference

Lars van der Laan, Mark Van Der Laan

原文摘要

We study semisupervised mean estimation with a small labeled sample, a large unlabeled sample, and a black-box prediction model whose output may be miscalibrated. A standard approach in this setting is augmented inverse-probability weighting (AIPW) [Robins et al., 1994], which protects against prediction-model misspecification but may be inefficient when the prediction score is poorly aligned with the outcome scale. We introduce Calibrated Prediction-Powered Inference, which post-hoc calibrates the prediction score on the labeled sample before using it for semisupervised estimation. This simple step requires no retraining and can calibeat the original score, improving it both as a predictor of the outcome and as a regression adjustment for semisupervised inference. We study both linear and isotonic calibration. For isotonic calibration, we establish first-order optimality guarantees: isotonic post-processing can improve predictive accuracy and estimator efficiency relative to the original score and simpler post-processing rules, while replacing the fitted isotonic score by its conditional-mean oracle yields no additional first-order variance reduction. For linear calibration, we show first-order equivalence to PPI++. We also clarify the relationship between existing estimators, showing that the original PPI estimator is a special case of AIPW and can be inefficient when the prediction model is accurate, while PPI++ is AIPW with empirical efficiency maximization [Rubin and van der Laan, 2008]. In simulations and real-data experiments, our calibrated estimators often outperform PPI and are competitive with, or outperform, AIPW and PPI++. We provide an accompanying Python package, ppi_aipw, at https://larsvanderlaan.github.io/ppi-aipw/.

stat.ML · cs.AI · cs.LG · econ.EM · q-bio.QM · stat.ME

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16173

Between Niti and Nyaya: A Society-Centered Framework for AI Governance

Snehalkumar `Neil' S. Gaikwad, Punya Aragula, Shiva Kruthi Palpanoori, Pratik Patekar

原文摘要

Governments are making decisions about AI before they can measure its public effects, and those decisions determine whether a person can learn that AI influenced an outcome, challenge it, and see it corrected. Research has documented what AI governance produces: principles, strategies, registers, and audits. However, we lack shared language for understanding AI policy while it is still being made. We introduce the Society-Centered AI Governance Framework, which gives policymakers, researchers, and the public a way to assess instruments in any jurisdiction by whether a person can get notice, challenge a decision, and see it corrected. It reads a jurisdiction's instruments together by date and binding status, separates an agency duty from a right a person can invoke, and traces which later instrument must enforce each commitment. We evaluated it in North Carolina using interviews with nine AI Leadership Council members, conducted before and after the state's 2026 AI roadmap, and a provision-level reading, with human-reviewed model-assisted coding, of 49 AI governance documents from 19 states. For the state's own AI systems, we find visibility-first governance: visibility duties are in effect, notice exists as an agency duty with no right a person can invoke, and AI-specific challenge and correction remain advisory. The roadmap assigns owners and dates to the missing protections, so the gaps are documented but not yet closed. Recent federal preemption proposals focus on AI development, so recourse for a state's own systems is likely to remain a state decision. We identify "legitimacy before protection" as a testable risk of visibility-first governance and name the milestones that would test it. More broadly, judging AI policy by who can act on what it makes visible lets the field assess recourse while policy is still forming, before harm occurs.

cs.AI · cs.CY · cs.HC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16172

Self-Supervised Attention-Based Virtual Metrology for CMP MRR Prediction

Jonathan Adam Rico, Nagarajan Raghavan, Senthilnath Jayavelu

原文摘要

Chemical mechanical planarization (CMP) is a critical semiconductor manufacturing process where material removal rate (MRR) is a key metric for process monitoring and advanced process control (APC). Virtual metrology enables MRR estimation from process time series signals, supporting run-to-run(R2R) control and process optimization while reducing reliance on physical metrology. Existing approaches typically rely on simplified linear assumptions or require handcrafted feature engineering. In this paper, we propose Global Regression Pretraining(GREP), a self-supervised, attention-based framework for CMP MRR prediction. GREP learns temporal representations from unlabeled sensor signals through global proxy-target regression, followed by supervised fine-tuning for MRR estimation. The framework is evaluated against a feature-engineered supervised baseline under three conditions: limited labeled data, sensor noise, and temporal process drift. Experiments on the PHM 2016 CMP dataset demonstrate competitive performance under limited labeled-data conditions, with improvements in selected cases and performance largely comparable to the baseline across different labeled-data fractions. Both models exhibit relatively small changes in prediction error with increasing noise, while GREP achieves a 17.0% RMSE reduction in the final temporal interval.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16171

MRxD: A Usage-Pattern Framework for Mixed-Reality Cross-Device Interaction

Yang Zhan, Yuxuan Huang, Yuchen Cai, Yichen Andy Yu, Xiaoran Yang, Ye Yuan, Qiao Jin

原文摘要

Mixed reality (MR) cross-device experiences often combine MR headsets with non-immersive devices such as laptops, tablets, and phones. Yet such cross-device design remains challenging because users must coordinate workflows across heterogeneous devices with different roles. This motivates our focus on usage patterns: recurrent ways in which people distribute and coordinate work across devices. Through a systematic analysis of 238 MR cross-device papers, we developed MRxD, a usage-pattern framework organized around three dimensions: user attention, task relatedness, and cognitive symmetry. Using these dimensions, we identified six usage patterns and synthesized the design strategies commonly used within each pattern. We further investigated the framework's application in design practice through a workshop (n=6) and the results suggest that MRxD can guide pattern-based design exploration and identify blind spots. We further discuss how usage patterns may shift or combine, and outline research gaps and design implications for future MR cross-device systems.

cs.HC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16169

Feature-Aware Edge Sampling for Approximate One-Step Laplacian Propagation

Jonathan Z. Sun, Zheng Wang, Kebin Xu

原文摘要

This paper studies how to approximate one-step combinatorial Laplacian messages in graph neural networks using edge sampling. We propose a spanning tree based hybrid sampler that combines feature-conditioned message scores and effective-resistance leverage scores, derive the expected one-step message error and obtain the optimal sampling probabilities and error frontier for a given expected edge budget. Preliminary experiments on synthetic community graphs show that message error decreases, while classification accuracy increases slightly, as the edge budget grows, and performance of the hybrid sampler is in between of optimal selection uniform random sampling. We leave multi-step propagation and evaluation on larger and real graphs for future work.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.08006

Penalty-Based First-Order Methods for Bilevel Optimization with Minimax and Constrained Lower-Level Problems

Yiyang Shen, Yutian He, Weiran Wang, Qihang Lin

原文摘要

We study a class of bilevel optimization problems in which both the upper- and lower-level problems have minimax structures. This setting captures a broad range of emerging applications. Despite the extensive literature on bilevel optimization and minimax optimization separately, existing methods mainly focus on bilevel optimization with lower-level minimization problems, often under strong convexity assumptions, and are not directly applicable to the minimax lower-level setting considered here. To address this gap, we develop penalty-based first-order methods for bilevel minimax optimization without requiring strong convexity of the lower-level problem. In the deterministic setting, we establish that the proposed method finds a lifted $ε$-KKT point with $\tilde{O}(ε^{-4})$ oracle complexity. We further show that bilevel problems with convex constrained lower-level minimization can be reformulated as special cases of our framework via Lagrangian duality, leading to an $\tilde{O}(ε^{-4})$ complexity bound that improves upon the existing $\tilde{O}(ε^{-7})$ result when the lower-level Slater's condition holds. Finally, we extend our approach to the stochastic setting, where only stochastic gradient oracles are available, and prove that the proposed stochastic method finds a nearly lifted $ε$-KKT point with $\tilde{O}(ε^{-9})$ oracle complexity.

math.OC · cs.LG · stat.ML

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2509.21172

Inverse Reinforcement Learning with Just Classification and a Few Regressions

Lars van der Laan, Nathan Kallus, Aurelien Bibaut

原文摘要

Inverse reinforcement learning (IRL) seeks to recover a reward function from observed behavior, but rewards are typically only partially identified: many reward--value pairs can induce the same behavior policy. We study this problem in the maximum-entropy, or Gumbel-shock, model under a broad class of statewise affine normalization constraints, with anchor-action constraints as a special case. This leads to Generalized Policy-to-$Q$-to-Reward (GenPQR), a modular approach to normalized reward recovery based on policy estimation and $Q$-evaluation via the Bellman equation; both components can be instantiated with off-the-shelf classification and regression methods. We establish modular finite-sample guarantees under general function approximation, with separate terms for policy-estimation and $Q$-function estimation error. We also give explicit bounds for GenPQR with fitted $Q$-evaluation. In experiments, GenPQR improves on DeepPQR in reward recovery. Our guarantees extend beyond anchor actions, accommodate large action spaces, and are not tied to a specific neural-network architecture or training procedure.

cs.LG · econ.EM · math.OC · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16164

Exact and Approximation Algorithms for Computing Smallest SESs and BMSs

Hiroki Shibata, Hideo Bannai

原文摘要

Compression schemes represent repetitive strings compactly by using repeated substrings. Computing the minimum size of a representation of a given input string is important for compression and for understanding relationships between compression schemes, although this task is NP-hard for several schemes. In this paper, we introduce exact and approximation algorithms for finding smallest substring equation systems (SESs) and bidirectional macro schemes (BMSs). Specifically, for an input string of length $n$, we give deterministic and randomized algorithms for computing a smallest SES using $O^*(4^n)$ and $O^*(2^n)$ time and space, respectively. We also give a deterministic algorithm for computing a smallest BMS using $O^*(2^n)$ time and space. We further give deterministic and randomized $(1+α)$-approximation algorithms for smallest SESs using $O^*(4^{e^{-α}n})$ and $O^*(2^{e^{-α}n})$ time and space, respectively, for every $α\ge 0$. A conversion from SESs to BMSs gives $4(1+α)$-approximation algorithms for smallest BMSs with the same time and space bounds. All time bounds hold in the worst case, and the randomized algorithms return correct answers with high probability. Our algorithms adapt several approaches to exact and approximation algorithms for combinatorial problems, such as dynamic programming over determinant expansions and a greedy algorithm for monotone submodular functions.

cs.DS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16163

Generative AI models for exploring diffusion dynamics from multi-frame particle tracking

Jianan Wei, Qiang Zhang, Hao Sun, Yi Yang, Wenguan Wang

原文摘要

Particle-based volumetric flow measurement techniques have proven their efficacy in quantitatively assessing the dynamic characteristics of unsteady flows within the realm of fluid mechanics. Despite recent advances in multi-frame particle tracking, an open challenge in this area is maintaining trajectories in temporally under-sampled 3D sequences, where inter-frame displacements are large. In this work, we develop DiffTR-Flow3D, a diffusion-based model that estimates flow motion from spatiotemporal three-dimensional particle recordings via a stochastic diffusion process. DiffTR-Flow3D conditions the diffusion process with both global and local particle dynamics and enhances flow estimation by leveraging historical particle trajectories. Extensive experiments, including numerical simulations and real-world measurements, demonstrate that DiffTR-Flow3D achieves state-of-the-art displacement estimation accuracy compared with learning-based flow estimators, and, when integrated into particle tracking pipelines, substantially improves their long-term tracking performance, while exhibiting robustness and generalization across diverse flow patterns. This work is expected to provide fluid researchers with an effective tool for the consistent and precise analysis of particle trajectories in temporally under-sampled 3D sequences with large inter-frame displacements.

physics.flu-dyn · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16162

GOOSELoc: A Multimodal Benchmark for Ground-to-Aerial Localization in Unstructured Off-Road Terrain

Fabian Deuser, Peter Mortimer, Robin-Nico Kampa, Anna Bößendörfer, Mirko Mählisch, Martin Werner, Norbert Oswald

原文摘要

Cross-view pose estimation estimates a ground camera's geographic pose by matching onboard sensor data with geo-referenced overhead imagery. This is particularly relevant when GNSS is unreliable, for example under forest canopy or in urban canyons. Existing metric cross-view benchmarks, such as VIGOR and cross-view KITTI, are dominated by urban and road scenes with strong human-made structure without off-road terrain. We introduce GOOSELoc, a multimodal benchmark for ground-to-aerial localization in unstructured environments, including forests, fields, and rural tracks. GOOSELoc comprises 9,356 scenes recorded across all four seasons around Munich, Germany, pairing geo-referenced aerial orthophotos with surround-view RGB imagery and 3D LiDAR point clouds. Paved/unpaved labels enable analyzing the impact of terrain structure, while the seasonal recordings allow studying the appearance gap to mostly summer-captured orthophotos. To assess the transferability of existing methods, we adapt and fine-tune four state-of-the-art cross-view localization baselines on GOOSELoc. Despite task-specific fine-tuning, the performance degrades substantially in off-road environments. We therefore propose a multimodal baseline combining surround-view imagery and LiDAR geometry, improving localization performance and providing a stronger reference for future work. Data and baselines are released at https://gooseloc.github.io.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2606.22673

Agent MechSuits: Mechanistic Subspace Safety Steering for Multi-Turn CLI Agents

Weidi Luo, Qiming Zhang, Yihao Quan, Mingyu Jin, Jie Cai, Chaowei Xiao, Jingcheng Niu, Zhen Xiang

原文摘要

Command-Line Interface (CLI) agents based on large language models (LLMs) demonstrate remarkable autonomous capabilities, but they also introduce significant safety and misuse risks during multi-turn interactions with external environments. Existing safety mechanisms mainly rely on external guardrails, which have a limited ability to perform fine-grained behavioral control during execution. Meanwhile, recent mechanistic interpretability methods for LLM safety are mostly confined to single-turn or jailbreak-style QA settings, limiting their ability to capture the evolving risk dynamics of multi-turn agent execution. In this paper, we investigate the safety of multi-turn CLI agents from an internal perspective. We propose Agent MechSuits (Mechanistic Subspace Intervention and Steering), a white-box defense framework that performs runtime safety detection and representation-level mitigation for CLI agents. Unlike conventional agent guardrails, Agent MechSuits detects harmful execution states from step-level hidden representations and mitigates unsafe behavior by intervening in a 10-dimensional subspace within a single layer. To support this research, we introduce the Mechanistic Agent Safety (MAS) benchmark, comprising comprehensively annotated multi-turn execution trajectories across 194 tasks using LLaMA-3.1-8B, Qwen-2.5-7B, and Gemma-2-9B. Extensive experiments show that Agent MechSuits achieves strong safety detection performance, provides preliminary evidence for lookahead risk anticipation, and substantially reduces harmful actions of the CLI agent, establishing a foundation for applying mechanistic interpretability to dynamic LLM agent safety.

cs.AI · cs.SE

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.06059

Exact Transport-Information Correspondence for Distribution-Adaptive Discretization

Koretaka Yuge

原文摘要

Discretization of continuous probability distributions is an operation on the sample space, and the structure induced by this operation cannot generally be determined solely from information geometry. In our recent work on unavoidable canonical nonlinearity (UCN), we established a non-arbitrary connection between the transport cost associated with discretization and the information-geometric indistinguishability of continuous probability distributions. Through this transport-information correspondence, UCN quantifies the information-theoretic cost associated with discretization in terms of the expected Kullback-Leibler divergence between nearby continuous distributions characterized by the discretization geometry. In the original UCN construction, discretization is implemented by transporting the probability mass within each cell to its geometric centroid. The resulting transport-information correspondence, however, is derived under specific conditions involving the cell geometry, spatial coverage, and the vanishing-cell-scale limit. In this work, we generalize the local-map discretization framework by allowing an arbitrary representative point for each cell and establish an exact decomposition of the associated transport cost into contributions from the conditional covariance of the probability distribution and the displacement of the representative point from its probability-weighted centroid. Consequently, the resulting transport cost is exactly represented by the expectation of the associated Fisher-induced quadratic form, without requiring uniform cell geometry, complete coverage of the sample space, or an infinitesimal cell-scale limit. The proposed construction thus establishes an exact transport-information correspondence for finite-scale discretization using arbitrary collections of non-overlapping bounded sets.

cs.IT · cond-mat.stat-mech

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16159

From Tokens to Behaviors: Rethinking Generative Recommendation for User Trajectory Prediction

Jiaqi Wang, Hanchen Yang, Hengyu Zhang, Hongxu Ma, Wenqi Rao, Hongyang Wang, Zhongbo Sun, Renliang Qian 等 15 位作者

原文摘要

User behavior trajectory prediction (UBTP) aims to capture how a user's needs evolve over time by predicting the sequence of future interactions from that user's interaction history. Recent generative recommendation (GR) methods address this task through autoregressive generation of semantic IDs (SIDs). However, serial SID decoding couples token generation with behavior state transitions and requires multiple dependent steps per interaction. Discrete item feedback overlooks predictive uncertainty, and teacher-forced training leaves a training-inference gap in trajectory generation. To address these limitations, we propose TraGR, a behavior-aware generative recommendation framework that aligns generation, feedback, and learning with successive user behaviors. Its behavior-level architecture predicts SID tokens in parallel within each interaction and models behavioral transitions through recurrent state updates, with joint SID and item-level supervision. Probability feedback combines the selected behavior with a probability-weighted summary of alternatives to guide subsequent predictions. Relation-aware trajectory learning incorporates collaborative transition signals and later credit assignment into training on model-generated trajectories. Experiments on four public datasets demonstrate that TraGR consistently outperforms state-of-the-art baselines across different prediction horizons. Code: https://github.com/CalmaQi/GR4UBT.

cs.IR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16158

PolicySniff: Inferring Agent Policy States through Shared-GPU Execution

Weimin Fu, Minghao Shao, Zeng Wang, Qiying Li, Yuntao Liu, Johann Knechtel, Ozgur Sinanoglu, Muhammad Shafique 等 10 位作者

原文摘要

LLM agents apply approval settings, such as whether to ask before a consequential tool call, through instructions in their system prompt, and operators keep these settings confidential by restricting access to prompts and responses. Audits check whether an agent obeys its setting, not whether a neighboring process can infer which setting is deployed. PolicySniff infers an agent's approval-policy state through shared-GPU execution. A co-resident attacker that knows the candidate settings and the task first profiles both settings, then times only its own GPU kernels while the agent processes the task. The policy prefix is cached before capture, so the attacker observes processing of a task suffix that is identical under both settings. On an eager sparse mixture-of-experts runtime, where each selected expert runs as separate work, a frozen and blinded study identified the deployed setting at 94.17% balanced accuracy on its primary estimand. Across all authorization conditions, accuracy was 88.82% on tasks for which both settings produce the same decision and 91.98% on tasks where they differ. Hardware replays of expert routing show that its temporal density and layer-and-bucket alignment carry the policy information. Behavioral compliance does not imply configuration confidentiality: deployments that keep their approval setting private should measure its distinguishability on the serving runtime and enforce authorization outside the model.

cs.CR

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2604.14689

ISAC with Backscattering RFID Tags: Beamforming and Codebook Design

Hao Luo, Umut Demirhan, Ahmed Alkhateeb

原文摘要

This paper explores an integrated sensing and communication (ISAC) system with backscattering radio frequency identification (RFID) tags. In this setup, an access point employs communication beams to serve communication users while leveraging a sensing beam to interrogate RFID tags. Under the total transmit power constraint of the system, our objective is to design a joint sensing and communication beamforming codebook by considering the tag interrogation and communication requirements. To lay a foundation for the codebook design problem, we first study the beamforming design problem in the single-tag scenario and investigate two approaches: a two-stage zero-forcing-based design with optimized power allocation and a joint beamforming design that minimizes the total transmit power. Extending our study to the multi-tag scenario, we propose a site-specific beamforming codebook design. The proposed approach partitions the region of interest into angular sectors and jointly optimizes the sensing and communication beams for each sector. The simulation results show that the proposed beamforming designs can effectively mitigate the mutual interference between sensing and communication functionalities, thus enhancing the interrogation range of the tags while minimizing transmit power. Also, the efficacy of the proposed site-specific codebook design has been demonstrated in terms of interrogation success rate, offering a promising approach for ISAC backscattering systems.

eess.SP · cs.IT

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2602.08340

Effect-Level Validation for Causal Discovery in Interactive Telemetry

Hoang Dang, Luan Pham, Minh Nguyen

原文摘要

Causal discovery is increasingly used to analyze telemetry from interactive systems, but a plausible graph does not guarantee an identifiable or reliable product decision. We study this problem for one query: whether early competitive gameplay increases Day-1 retention in a deployed Role-playing game (RPG). We propose an admissibility-first framework that treats discovered graphs as structural hypotheses, keeps only graphs that identify the target effect and have adequate treatment-control overlap, and validates admissible effects through cross-algorithm stability, placebo, subsampling, and E-value diagnostics. On real telemetry, under minimal constraints the admissible runs that return Directed Acyclic Graphs (DAGs) are those whose graphs leave player-versus-player (PvP) with no parents, so they estimate the confounded raw difference; under the full constraint set all are admissible. Runs returning Partial Ancestral Graphs (PAGs) are not evaluated by the DAG gate and are reported separately. The admissible DAGs agree on one adjustment set and return a positive, cohort-conditional risk-difference average treatment effect (ATE), down from a raw retention gap; the estimate keeps its sign under placebo and subsampling checks, but its magnitude changes with the adjustment set and the constraint specification. A known-truth simulation shows that the checks screen identification and stability given the measured variables and cannot certify the absence of unmeasured confounding, and a second game-telemetry dataset shows that identifiability rates do not transfer. Graph-level recovery is therefore a weak proxy for causal reliability; discovery pipelines for decision support should be evaluated at the query and effect level.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16155

Accelerating Distributed Variational Quantum Computing over Wireless Networks with Incentive Mechanism Design

Shaba Shaon, Dinh C. Nguyen, Octavia Dobre

原文摘要

Distributed variational quantum computing (DVQC) appears as the emerging paradigm to address the limitations of near-term quantum devices by decomposing large parameterized quantum circuits (PQCs) into smaller subcircuits executed across multiple quantum processors. In this context, how to incentivize quantum processors to participate actively is crucial for accelerating DVQC, yet remains largely unexplored in the literature. To address this significant gap, we propose a novel two-stage incentive framework for wireless DVQC. In the first stage, we minimize processor-side energy cost via a joint optimization of subcircuit parameters, number of noise measurements, and transmit power, efficiently solved using block coordinate descent (BCD) and successive convex approximation (SCA). In the second stage, we maximize aggregator-side system utility by selecting an optimal subset of processors based on their optimized energy costs derived from the first stage, formulating a non-convex combinatorial selection problem addressed using the alternating direction method of multipliers (ADMM). Extensive numerical experiments on the MNIST and CIFAR-10 datasets demonstrate that our DVQC framework achieves training and testing performance comparable to centralized quantum computing in terms of accuracy and loss, with similar convergence behavior on MNIST and slightly slower initial convergence on CIFAR-10. Moreover, our optimization approach consistently outperforms baseline schemes in energy efficiency and system utility, revealing a strong synergy between processor-level energy minimization and incentive-driven processor selection, where reduced energy costs directly enhances a processor's likelihood of selection and contributes to higher overall system utility.

cs.DC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16151

Fault Injection Attacks on Q-Learning: Analysis, Vulnerabilities, and Countermeasures

Tom Slooff, Anthony Etim, Jiaqi Yu, Francesco Regazzoni, Jakub Szefer

原文摘要

Hardware fault injection attacks threaten machine learning systems, yet their impact on reinforcement learning (RL) has received little attention despite the use of RL in safety-critical applications. This paper presents a security analysis of Q-Learning implementations under voltage and clock glitching attacks on a ChipWhisperer platform, evaluating five variants: Standard, Robust, Resilient, Linear, and Deep Q-Learning. In standard Q-Table implementations, faults corrupt reward computation, action selection, and Q-value updates during learning, and change the selected action during inference. Robust Q-Learning does not prevent these attacks: NaN and infinite values injected during learning persist in the Q-table, and its greedy policy uses the same code as standard Q-Learning. This paper also evaluates a Resilient Q-Learning variant that applies triple modular redundancy with majority voting. It corrects corruption of a single Q-table copy, but inputs shared by the copies, such as the reward, and the voting code itself remain outside its protection. The analysis extends to Linear and Deep Q-Learning, where faults corrupt stored weights during learning and change actions during inference. Moving beyond benchmark environments, this work evaluates an online traffic light controller in a microscopic traffic simulator, where a single injected infinite value degrades accumulated vehicle waiting time by 148x while corrupting under 4% of the Q-table, and where triple modular redundancy corrected the faults injected in our tests, although glitching could still halt the device. Altogether, this work provides a basis for understanding and securing RL deployments against fault injection attacks.

cs.CR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16149

HyperPage: Learned Page Layouts for Disk-Resident Graph Vector Indexes

Xinyu Zhang, Jingze Li, Baihua Zheng, Weiwei Sun

原文摘要

Disk-resident graph indexes such as DiskANN store each vector with its graph edges as one record on SSD pages. A search needs the page of every record it expands, so its page reads depend on the page layout, that is, which records share a page. Search agents trained with reinforcement learning query one such index run after run, and every graph traversal can be logged with the records it expands. We therefore use the logs of a finished run to lay out the index for a declared memory budget, so later runs read fewer pages. In contrast, existing layouts such as Starling and MARGO are computed from the graph and vectors and use no logs. Learning a layout from logs is challenging, because the logs must stay valid under every layout, the saving depends on what the budget caches, and the best layout is NP-hard to find. Our key observation is that DiskANN-style search routes on in-memory codes and the records it expands, never on their page-mates. As a result, the logged traversals price every layout by replay, and cached records add no page reads. Accordingly, we propose HyperPage, which first builds layouts for the declared budget on the logged traversals of uncached records. It then selects one layout, together with the budget split between hot records and a page cache, by replaying validation steps. In addition, a Lagrangian lower bound shows how far a layout may be from the optimum. We learn from one Search-R1 agent run and test on a later run with a different reward, over 1M and 21M passages. Across seven cache budgets, HyperPage reads 5.2% to 21.2% fewer pages than MARGO, and no compared layout reads fewer. The advantage is largest when the cache is small. For example, at 1% of the 1M index, MARGO needs nearly 3 times the budget to read as few pages. On the 21M index, HyperPage also cuts search time per step by up to 10.4%. The saving holds for a second agent model and a second corpus.

cs.DB · cs.IR

查看论文
arXiv ↗PDF ↗