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

+479新增论文
+361其中 AI 相关
+64已有论文修订
+95新增 AI 导读

arXiv 最近完成扫描:2026-11-16 01:34 · 全站最近入库:2026-11-16 21:56各信源进度 →

统计口径与数据新鲜度

统计 2026-11-16 04:19 — 2026-11-17 04:19(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:2026-11-16 21:56库内论文最新更新时间:2026-11-14 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。

23,827 已收录论文19,941 AI 相关6,922 有修订112 HF 社区发现

浏览论文库

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 23,827 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:2611.03465

HIVE-Diff: High Frame Rate HDR Video Reconstruction from a Single LDR Frame and Events

Caixin Wang, Qingrui Wang, Jie Zhang, Ralph Etienne-Cummings

原文摘要

High frame rate HDR video is important in applications such as autonomous driving and scientific imaging, where rapid motion and extreme illumination often occur simultaneously. Conventional frame cameras face a trade-off between temporal resolution and dynamic range, while event cameras provide complementary high-speed brightness-change measurements over a wide illumination range. These properties have motivated event-based HDR reconstruction, with existing methods broadly following event-only and hybrid event-frame paradigms. Event-only HDR reconstruction, however, suffers from brightness and color drift due to the lack of absolute intensity references. Hybrid event-frame methods alleviate this ambiguity using low-dynamic-range (LDR) frames as anchors, but most perform one-to-one HDR reconstruction at available LDR timestamps. In this work, we investigate single-reference HDR temporal expansion, reconstructing N HDR frames from one LDR reference and events instead of N aligned LDR observations. We develop HIVE-Diff, an event-conditioned video diffusion framework that decomposes the task into event-guided temporal generation and HDR content completion. Because paired real HDR-event data are scarce, we train on synthetic data and adapt the model to real event domains using LDR-event sequences as proxy supervision with teacher-student distillation. Experiments on synthetic and multiple real-world datasets demonstrate strong reconstruction quality and robust real-data adaptation.

eess.IV · cs.CV

版本更新 · v2arXiv:2512.21412

A Survey of Freshness-Aware Wireless Networking with Reinforcement Learning

Alimu Alibotaiken, Suyang Wang, Oluwaseun T. Ajayi, Mushu Li, Yu Cheng

原文摘要

The age of information (AoI) has become a central measure of data freshness in modern wireless systems. Reinforcement learning (RL) has emerged as a promising approach to AoI optimization, enabling adaptive decision-making in dynamic and stochastic wireless environments without requiring precise system models. Yet existing surveys either focus on classical AoI formulations or provide broad discussions of RL in wireless networks without addressing freshness as a unified learning problem. Motivated by this gap, this survey examines RL specifically through the lens of AoI and generalized freshness optimization. Motivated by this gap, this survey examines RL specifically through the lens of AoI and generalized freshness optimization. We organize AoI and its variants into native, function-based, and application-oriented families, providing a clearer view of how freshness should be modeled in B5G and 6G systems. Building on this foundation, we introduce a policy-centric taxonomy that reflects the decisions most relevant to freshness, consisting of update-control RL, medium-access RL, risk-sensitive RL, and multi-agent RL. This structure provides a coherent framework for understanding how learning can support important wireless networking problems, including sampling, scheduling, UAV trajectory planning, medium access, and distributed coordination. We further synthesize recent progress in RL-driven freshness control and highlight open challenges. The goal is to establish a unified foundation for learning-based freshness optimization in next-generation wireless networks.

cs.LG · eess.SY

版本更新 · v2arXiv:2609.21009

Robustness Analysis via Horofunction Compactification

Harrison Bennett, Amin Farjudian

原文摘要

Robustness analysis plays a central role in the verification and design of computational and hybrid systems, particularly when system behaviour depends continuously on parameters subject to perturbation. Existing domain-theoretic frameworks provide a principled foundation for reasoning about such perturbations via monotone maps on lattices of closed sets. However, these frameworks face significant limitations when the underlying state space is not locally compact, as is the case for the infinite-dimensional spaces that arise in analysis, machine learning, and control theory (e.g., $\ell_p$ and $L_p$ spaces). In these settings, the lattice of closed subsets fails to be continuous, and classical compactifications either sacrifice precision or lack computable structure. We propose Gromov's horofunction compactification as a new tool for robustness analysis over a class of separable metric spaces of practical importance, including separable reflexive Banach spaces. Given a metric space $\mathbb{S}$, we show that its horofunction extension yields a compact metric space together with a Lipschitz embedding, which enables robust approximations of monotone maps via Scott-continuous maps on the compactified domain. For separable spaces, the horofunction compactification is metrizable, which provides a path toward effective domain-theoretic constructions.

cs.LO

版本更新 · v2arXiv:2610.16358

NP-hardness of additive approximation for generalized Turán problems

Yihan Chen, Jialin He, Xihe Li, Jie Ma, Tianying Xie

原文摘要

Given a graph $T$ and a nonempty family $\mathcal{F}$ of graphs, let $\operatorname{ex}(G, T, \mathcal{F})$ denote the maximum number of copies of $T$ in an $\mathcal{F}$-free subgraph of a host graph $G$. Alon and Shikhelman [Algorithmica, 2022] conjectured that if $e(T)> 0$ and no member of $\mathcal{F}$ is a subgraph of a blow-up of $T$, then for every $\varepsilon>0$, approximating $\operatorname{ex}(G, T, \mathcal{F})$ within an additive error of $n^{v(T)-\varepsilon}$ is NP-hard for an input graph $G$ on $n$ vertices. Previous advances toward this conjecture include the resolution of the canonical case $T=K_2$ by Alon, Shapira, and Sudakov [Ann. of Math., 2009], as well as the case of $\operatorname{ex}(G,K_m,K_k)$ by Alon and Shikhelman. In this paper, we confirm this conjecture for every bipartite graph $T$ and every clique $T$. Our proof reductions combine several techniques, including iterative leaf additions, symmetric rooted extensions, and random transversals. Together, they encode the optimal value of the NP-hard Max $r$-Colorable Subgraph problem into the objectives $\operatorname{ex}(G, T, \mathcal{F})$ for a suitably constructed graph $G$.

cs.CC · math.CO

版本更新 · v2arXiv:2610.39189

Provably Secure Diffusion Watermarking Against Removal Adversaries with Batched Detector Access

De Zhang Lee, Ee-Chien Chang

原文摘要

Recent latent-based watermarking methods can embed undetectable watermarks into AI-generated content. However, these approaches are vulnerable to removal attacks as their watermark detection boundaries are exposed, prompting the use of secret long-term transformations to hide these boundaries. We show that such defenses are insecure under a stronger threat model motivated by publicly reachable detectors: an adversary with batched detector access can reconstruct the transformations, permanently re-exposing the decision boundary. To address this, we propose a watermarking scheme based on a hybrid of long-term and one-time secret transformations, which prevents the reuse of structure across samples and keeps the long-term secret hidden. Besides undetectability, we show that this scheme is provably secure against removal adversaries with batched detector access, in the sense that no probabilistic polynomial-time adversary can achieve a non-negligible advantage over an adversary restricted to adding isotropic white-noise with a $\sqrt{2}\times$ larger perturbation budget, and we show this $\sqrt{2}$ factor to be tight. Evaluations on Stable Diffusion 2.1 and XL demonstrate the attack against the existing defense, and show that our scheme preserves generation quality and withstands common perturbations and targeted removal attacks.

cs.CR

新论文 · v1arXiv:2611.03461

Unrolled gradients in disguise: bridging interpolation-based and Jacobian regularization for stable neural dynamics

Maya Janvier, Etienne Meunier

原文摘要

Hybrid models and neural differential equations (NDEs) are becoming increasingly important for modelling physical systems; however, they often encounter stability and accuracy issues during long-term integration. Training on unrolled trajectories is known to limit these divergences but quickly becomes too computationally expensive due to the need to compute gradients over an iterative process, making this method impractical for large-scale physical systems (e.g. weather and climate forecasting). Two popular paradigms for improving the stability of learned dynamics are to train on interpolated or noisy samples or to regularize the Jacobian of the learned representation. In this work, we demonstrate that these paradigms can be understood under a common lens and that they both correspond to an approximation of the gradients obtained in an unrolled learning strategy. Building on this understanding, we derive a principled and complete approach to regularize training and demonstrate its impact on the stability of learned dynamical systems.

cs.LG · math.NA

版本更新 · v3arXiv:2511.07646

Distributed Adaptive Estimation with ISS Guarantees for Sensor Networks with Partially Unknown Source Dynamics

Moh Kamalul Wafi, Hamidreza Montazeri Hedesh, Milad Siami

原文摘要

This paper studies distributed adaptive estimation over sensor networks with partially unknown source dynamics. We present parallel continuous-time and discrete-time designs in which each node runs a local adaptive observer and exchanges information over a directed graph. For both time scales, we establish stability of the network coupling operators, prove boundedness of all internal signals, and show convergence of each node's estimate to the source despite model uncertainty and disturbances. We further derive input-to-state stability (ISS) bounds that quantify robustness to bounded process noise. A key distinction is that the discrete-time design uses constant adaptive gains and per-step regressor normalization to handle sampling effects, whereas the continuous-time design does not. A unified Lyapunov framework links local observer dynamics with graph topology. Simulations on star, cyclic, and path networks corroborate the analysis, demonstrating accurate tracking, robustness, and scalability with the number of sensing nodes.

eess.SY · cs.MA · math.DS

新论文 · v1arXiv:2611.03457

Expander Routing under Adversarial Deletions via Temporal Aggregation

Bernhard Haeupler, Anton Paramonov

原文摘要

In expander routing, we seek to establish paths in the expander graph between given source-target pairs while minimizing both dilation (maximum path length) and congestion (maximum edge load). We study this problem in a decremental dynamic setting where the underlying graph remains an expander despite ongoing edge deletions, and source-target pairs can be added or removed. Our goal is to maintain paths under these updates while keeping dilation and congestion low and performing low computation per update. We present a randomized algorithm that maintains paths with polylogarithmic dilation and congestion against an adaptive adversary, while incurring only polylogarithmic amortized computation per update, all with high probability. Our approach leverages a recent technique called Temporal Aggregation to maintain a collection of low-congestion, low-dilation random walks resilient to adaptive adversaries.

cs.DS

新论文 · v1arXiv:2611.03454

Online Class Posteriors for Interpretable and Controllable Discrete Diffusion

Felix Koulischer, Gianni Van De Velde, François Remy, Chris Develder, Thomas Demeester

原文摘要

Discrete diffusion models remain far less understood than their continuous counterparts, despite recent breakthroughs across modalities, most notably in text. Leveraging tools from continuous diffusion, we formulate a theoretical framework to track the class-conditional posterior in an online manner by combining conditional and unconditional model predictions. In masked language modeling, this posterior offers highly interpretable dynamics: tokens aligned with a class boost the posterior, while contradictory ones suppress it. We also show that the posterior can be used for logical guidance operations (AND, OR, NOT) in discrete diffusion. These operations enable precise control over generation, such as avoiding specific classes. In addition, we discuss a mismatch in the formulation of classifier-free guidance between discrete and continuous settings: discrete models mix the data distributions, while continuous models mix the marginals. We validate our methods and discuss their potential applications on synthetic data, with all quantities analytically tractable, as well as on MNIST, text, and antibody sequences.

cs.LG

新论文 · v1arXiv:2611.03452

Parity Decision Trees of Depth $O(4^d \log\|\widehat f\|_1)$ for Boolean Functions $f$ of $F_2$-Degree $d$

Shengyu Zhang

原文摘要

Let $f\colon F_2^n\to\{-1,+1\}$ have $F_2$-degree $d\ge2$. We prove that its deterministic parity decision tree depth satisfies \[ D_{\oplus} (f)= O(4^d \log_2\|\widehat f\|_1) = O(4^d \log_2 s(f)), \] where $\|\widehat f\|_1=\sum_ξ|\widehat f(ξ)|$ is the Fourier spectral norm and $s(f)$ is the Fourier sparsity. The bound is linear in the logarithm of the spectral norm for every fixed degree, with singly exponential dependence on $d$. This improves the previously best known bound of $O(2^{d^2/2} \log^{d-2} \|\widehat f\|_1)$ due to Tsang, Wong, Xie and Zhang (FOCS 2013). Our result establishes the log-rank conjecture for $\mathrm{XOR}$ functions of $F_2$-degree $O(\log\log s(f))$, extending the previously accessible range $d=O(1)$. The proof combines field lifting, multiplicative derivatives, a multiplicity-based generic-rank comparison, a Schur-complement vanishing argument, and dimension-preserving descent to $F_2$ to lower the degree on every coset of a common subspace.

cs.CC

新论文 · v1arXiv:2611.03451

Improving Hamiltonian Learning through Local Energy Decomposition

Yaojun Li, Yulong Yang, Christine Allen-Blanchette

原文摘要

Hamiltonian neural networks provide a principled framework for learning conservative dynamics. A scalar Hamiltonian is parameterized by a neural network and the vector field is derived using Hamilton's equations. However, preserving Hamiltonian structure does not guarantee that the energy function itself is represented accurately. When modeled by a conventional multilayer perceptron, the Hamiltonian inherits the spectral bias of coordinate-based neural representations, favoring smooth over fine-scale structure. These fine-scale errors can be amplified by differentiation when computing the dynamics. To address this limitation, we introduce Local Multiscale Hamiltonian Neural Network (LM-HNN), which restructures the Hamiltonian according to its physical interaction structure. LM-HNN decomposes the energy into kinetic and potential components and represents them as sums of shared local functions over multiple interaction neighborhoods. This replaces a single high-dimensional approximation problem with lower-dimensional, reusable interaction laws, making fine-scale energy structure easier to resolve while preserving Hamiltonian dynamics. Across low-dimensional, interacting, and fast--slow systems, LM-HNN consistently achieves more accurate Hamiltonian derivatives and long-horizon rollouts than competing structure-preserving models, while substantially extending the effective spectral range of the learned energy. The same structured representation also generalizes more reliably to energy levels not observed during training. These results show that accuracy depends on the Hamiltonian representation as well as its structure, and that incorporating locality, decomposition, and shared interaction laws provides a simple and effective route to more accurate and generalizable Hamiltonian learning.

cs.LG

新论文 · v1arXiv:2611.03449

Intent2CAD: How Semantic-Parametric Supervision Shapes Text-to-CAD Generation

Jinbo Yang, Mingyue Yuan, Shikai Jing

原文摘要

Text-to-CAD generation aims to make CAD modeling more accessible by generating executable CAD programs from natural-language descriptions. However, practical CAD workflows require more than executable geometry: generated programs should also expose reusable structure that supports later modification. We introduce intent-oriented text-to-CAD generation, where design intent is expressed as recoverable code-level signals: semantic features, reusable parameters, and lightweight parametric relations. Rather than changing the model architecture or decoding procedure, we investigate how supervision representation granularity affects both CAD generation and zero-shot intent-preserving editing. To enable this study, we construct IntentCAD-100K, a 100K paired text--code dataset built by converting low-level CAD construction traces into executable CadQuery programs. We further construct IntentCAD-Edit-1K to evaluate zero-shot intent-preserving editing from the same representation perspective. Intent2CAD uses a two-stage conservative lifting pipeline: semantic lifting rewrites reliable primitive groups into feature-level operations, while parametric lifting exposes lightweight parametric relations. Under controlled fine-tuning, semantic lifting mainly improves generation reliability and feature recovery, reducing IR from 2.39% to 0.22% and achieving 99.96% API Recovery, while parametric lifting makes reusable relation structure explicit and further improves relation-aware zero-shot editing. Datasets and code are available at https://github.com/JinboYang94/Intent2CAD.

cs.CV

版本更新 · v3arXiv:2601.06514

Inference-Time Alignment for Diffusion Models via Variationally Stable Doob's Matching

Jinyuan Chang, Chenguang Duan, Yuling Jiao, Ruoxuan Li, Yi Xu, Jerry Zhijian Yang

原文摘要

Inference-time alignment for diffusion models aims to adapt a pre-trained reference diffusion model toward a target distribution without retraining the reference score network, thereby preserving the generative capacity of the reference model while enforcing desired properties at inference time. A central mechanism for achieving such alignment is guidance, which modifies the sampling dynamics through an additional drift term. In this work, we introduce variationally stable Doob's matching, a novel framework for provable guidance estimation grounded in Doob's $h$-transform. Our approach formulates guidance as the gradient of the logarithm of an underlying Doob's $h$-function and employs gradient-regularized regression to simultaneously estimate both the $h$-function and its gradient, resulting in a consistent estimator of the guidance. Theoretically, we establish non-asymptotic convergence rates for the estimated guidance. Moreover, we analyze the resulting controllable diffusion processes and prove non-asymptotic convergence guarantees for the generated distributions in the Wasserstein-2 distance. Finally, we show that variationally stable guidance estimators are adaptive to unknown low dimensionality, effectively mitigating the curse of dimensionality under low-dimensional linear subspace assumptions. Numerical experiments demonstrate the effectiveness of our proposed method and show the advantages compared to the baselines.

stat.ML · cs.LG · math.NA · math.OC · math.ST

新论文 · v1arXiv:2611.03445

Error Accumulation in Second-Order Sequential Machine Unlearning

Chen Shang, Haolin Zou, Binghe Zhu, Arian Maleki

原文摘要

Machine unlearning seeks to remove the influence of deleted training data without full retraining. In the sequential setting, deletion requests arrive over time, and repeated updates can accumulate approximation errors. In this paper, we study error accumulation in high dimensions, where parameter count $p$ is proportional to sample size $n$, for second-order unlearning methods under two privacy settings: (i) \emph{partial unlearning}, which allows unpublished internal states to be retained while certified versions of the model are released; and (ii) \emph{perfect unlearning}, which retains only published models and no hidden states. We also distinguish pointwise and pathwise certification, depending on whether the certification guarantee applies to each released model or the whole released sequence. We analyze conjugate gradient (CG) as an efficient solver for the inverse Hessian-vector product (IHVP) in Newton iterations. Our theory shows that a maximum of 1/2/2/3 Newton--CG updates suffice for successful certification and vanishing population-risk degradation of the published model, for pointwise partial, pathwise partial, pointwise perfect and pathwise perfect certification, respectively. Numerical experiments demonstrate accurate sequential tracking and substantial computational gains of Newton-based methods combined with conjugate gradient, over gradient-based updates, especially for ill-conditioned problems.

stat.ML · cs.LG

版本更新 · v2arXiv:2609.22551

The category of nominal sets is locally monoidal closed

Fahimeh Bayeh, Peng Fu, Peter Selinger

原文摘要

The category Nom of nominal sets was proposed by Pitts and Gabbay as a setting for the semantics of abstract syntax with variable bindings. It is well-known that Nom is a topos, also known as the Schanuel topos, and in particular it follows that Nom is locally closed, i.e., every slice category Nom/X is cartesian-closed. In this paper, we show that Nom has a much stronger property: every monoidal (closed) structure on Nom induces a monoidal (closed) structure on all slice categories Nom/X. One monoidal closed structure of particular interest on Nom is the separated product A * B, whose right adjoint A -* B is called the separated function space. In particular, it follows that Nom is locally separatedly closed.

math.CT · cs.LO

新论文 · v1arXiv:2611.03442

Subpolynomial-Query Proximal Sampling Beyond Log-Concavity

Wei Guo, Bo Yuan, Ye He, Jiaming Liang, Molei Tao, Yongxin Chen

原文摘要

We study the gradient query complexity of sampling from a density $π(x)\propto\mathrm{e}^{-V(x)}$ on $\mathbb{R}^d$, where $V$ has a $β$-Lipschitz gradient but need not be convex. Our approach uses the proximal sampler, which alternates Gaussian perturbation with sampling a position conditional on the noisy observation. We implement its observation chain using the high-order noisy conditional sampler of [OpenAI 2026], obtaining improved dimension dependence under functional inequalities. If $π$ satisfies a log-Sobolev inequality (LSI) with constant $α$, then for every fixed $ν>0$, there is a finite constant $C_ν$ depending only on $ν$ such that the algorithm returns a sample within total-variation distance $\varepsilon$ using at most $C_νκ(d+κ+\varepsilon^{-1}+\|\nabla V(x_0)\|^2/β)^ν$ queries, where $κ=β/α$ and $x_0$ is an arbitrary reference point for initialization. The analysis controls center-dependent local errors along exact proximal histories and removes the final observation noise by conditional decoding. Under a Poincaré inequality (PI), we obtain a corresponding guarantee from a warm start with a known bound on its Rényi divergence. An oracle lower bound shows that a stationary point alone, which suffices under LSI, is insufficient under PI.

stat.ML · cs.CC · cs.LG · math.ST

新论文 · v1arXiv:2611.03440

Beyond GNSS: Leveraging LEO Satellite Signals of Opportunity for Doppler Positioning

Md. Ali Hasan, M. Humayun Kabir, Sangmin Han, Wonjae Shin, H. Vincent Poor

原文摘要

Large constellations of low Earth orbit (LEO) satellites provide ubiquitous global connectivity; yet, their rapid motion introduces significant Doppler shift effects. While challenging for communication, these effects can be leveraged for precise user terminal (UT) positioning, particularly in GNSS-denied environments where traditional satellite-based navigation struggles. Unlike GNSS, most LEO satellites lack dedicated navigation signals, motivating signals-of-opportunity (SOPs) approaches that repurpose existing LEO signals and use publicly available two-line element (TLE) files for orbital information, although ephemeris errors can limit accuracy. This article explores the fundamental principles, challenges, and enabling technologies for LEO-based Doppler shift positioning, highlighting its advantages over conventional non-Doppler methods, and discussing future research directions. Furthermore, to facilitate realistic and reproducible performance evaluation beyond stochastic modeling, we propose SionnaNTN-RT, a ray tracing framework for non-terrestrial network (NTN) built upon Sionna, enabling end-to-end simulation of Doppler-based positioning. Simulation results demonstrate that Doppler-based positioning can achieve high positioning accuracy in both urban and open-sky environments, highlighting its promise for next-generation positioning systems.

cs.IT · eess.SY

新论文 · v1arXiv:2611.03439

Playing Dumb: How a Chess Transformer Simulates Users Across Skill Levels

Difan Jiao, George Eilender, Zhenwei Tang, Ashton Anderson

原文摘要

Generative models increasingly simulate users at different skill levels in education and AI evaluation. Yet it remains unclear whether lower-skill behavior reflects less internal knowledge or a different use of retained knowledge. This distinction is difficult to study in natural language, where proficiency and relevant knowledge are hard to measure. In this work, we study Maia-2, a chess transformer that predicts human moves conditioned on player skill, using quantitative skill ratings and deterministically labeled chess concepts. We hold board positions and model weights fixed and analyze positions where skill conditioning changes the prediction from a blunder to the best move. First, we measure encoded knowledge by training probes to predict the presence of 172 chess concepts from Maia-2's internal states. Probe accuracy remains nearly constant across skill conditions, and probes trained at one level transfer accurately to the others. To test whether stronger decisions can be recovered from this retained knowledge, we fine-tune only Maia-2's final output layer, raising best-move accuracy in the lowest skill band from 14.4% to 82.8%. Training this layer only on highest-skill representations retains most of the improvement at lower levels, showing that recovery does not require direct training on lower-skill states. Steering concept-relevant features learned by a sparse autoencoder also improves lower-skill decisions while leaving probe-measured concept encoding practically unchanged. These results support an account in which skill conditioning changes how retained concept knowledge influences move selection, showing that weaker behavior can understate the knowledge available within a model.

cs.AI · cs.LG

新论文 · v1arXiv:2611.03438

Align Once to Explain: Feature Alignment for Scalable B-cosification of Foundational Vision Transformers

Raphael Maser, Siddhartha Gairola, Sukrut Rao, Bernt Schiele

原文摘要

Foundational vision models have become the de facto standard for many vision tasks due to their strong performance. However, they are notoriously opaque and remain hard to interpret. We present ALOE (ALign Once to Explain), a one-time, label-free feature alignment approach that efficiently converts foundational vision models into inherently interpretable B-cos variants. Once aligned, the B-cos backbone is used as a drop-in replacement across several downstream tasks-amortizing the cost of interpretability. ALOE is robust across pre-training paradigms (supervised, self-supervised, vision-language) and can preserve teacher-level generalization with orders of magnitude less data than training from scratch. On classification, it strongly outperforms vanilla B-cosification (e.g., +10.5 p.p. top-1 on ImageNet for DINOv3 ViT-B/16), retains strong linear probing, k-NN, and zero-shot transfer competitive with foundational backbones (DINOv3, SigLIP2) across diverse downstream datasets. It also preserves spatially structured features useful for dense prediction, while yielding well-localized and highly human-interpretable explanations by design.

cs.CV

新论文 · v1arXiv:2611.03435

Bridging Neural Tangent Kernel Analysis and Reinforcement Learning for Deep Function Approximation

William St-Arnaud, Margarida Carvalho, Golnoosh Farnadi

原文摘要

Despite their widespread success across machine learning, the learning dynamics and generalization properties of neural networks remain poorly understood. The neural tangent kernel (NTK) provides an analytical characterization of the learning dynamics of infinitely wide neural networks and serves as a useful proxy for finite-width networks in supervised learning. In this work, we extend the NTK framework to reinforcement learning (RL) by introducing a temporal-difference (TD) flow formulation that accommodates time-varying mini-batches and TD targets, yielding a closed-form solution for value function evolution in an overparametrized setting. We also devise an optimization-based state-space exploration method that leverages the closed-form solution, coupled with constraints on the environment, to model the set of feasible states. On a deterministic grid environment, we validate that the proposed RL-based NTK formulation is indeed learning efficiently and adapting to the distribution shift in the training data distribution, and we demonstrate that the resulting exploration strategy improves sample efficiency. To our knowledge, this is the first work to extend NTK theory to characterize the learning dynamics of RL training with time-varying mini-batches and TD updates.

cs.LG

新论文 · v1arXiv:2611.03434

Optimize the Harness, Not the Model: Fitting a Minimal Agent to a Self-Hostable LLM for Investigative Analysis

Shai Nahum Gefen, Vered Chassida, Dmitry Basin, Guy Feigenblat

原文摘要

Government intelligence teams need LLM agents that can analyze large, messy evidence collections, but security and cost constraints often rule out hosted frontier models and broad, hard-to-audit tool surfaces. We report CLEO: Constrained Loop for Environment Optimization, a method for fitting a minimal agent harness to a fixed, self-hostable LLM. Given an expert-validated dataset, CLEO admits only the tools, guardrails, memory policies, and loop components that improve accuracy while remaining general and auditable. On our held-out dataset, the CLEO harness reaches an 83.8% pass rate, within 1.2 points of the strongest out-of-the-box Claude Code SDK baseline, while being two orders of magnitude smaller.

cs.AI · cs.CL · cs.MA

新论文 · v1arXiv:2611.03433

A Living Leaderboard for Graph Machine Learning

Martin Ritzert

原文摘要

Graph machine learning benchmarking results are scattered across papers that use quite different sets of datasets and baseline methods, making it difficult to tell whether a reported gain reflects architectural progress or merely an outdated comparison or weakly tuned baseline. We introduce a living, graph-learning-specific leaderboard that organizes reported results by dataset, putting new results into context. As of 15 October 2026 our LLM-based extraction pipeline extracted 27,723 eligible results across 111 datasets from 885 peer-reviewed papers. Our analysis of these results quantifies concerns about graph-learning benchmarking: legacy datasets are still actively used and many result tables contain baseline results that are drastically lower than those already available in the literature, e.g. 45% Amazon-ratings tables and 37% for Peptides-struct. The leaderboard allows to quickly compare new results against compatible prior results, aiming to improve the overall quality of graph learning benchmarking.

cs.LG

新论文 · v1arXiv:2611.03431

IAMRAGBENCH: Benchmarking Authorization Expansions in LLM-Generated AWS IAM Policies under RAG Poisoning

Hasan Kaplan, Indika Kumara, Willem-Jan van den Heuvel, Damian Andrew Tamburri

原文摘要

Large language models (LLMs) using retrieval-augmented generation (RAG) can synthesize Amazon Web Services (AWS) Identity and Access Management (IAM) policies from tasks and operational documents. Attacker-controlled context may induce provider-valid policies that exceed trusted authorization requirements. We present IAMRAGBENCH, a 60-case benchmark spanning scope, conditions, explicit denies, trust, permissions boundaries, and role delegation. It combines deterministic authorization-envelope scoring with case-specific validation, including request-level checks where supported. An attack requires a provider-valid clean policy that satisfies the task and a provider-valid treatment policy that violates the envelope, matches a predeclared goal, preserves an intended request, and newly authorizes a forbidden request. Across five endpoints, included-context exposure produces 49 exact authorization deltas, including 46 goal-matched attacks (46/292; 15.75\%). End-to-end BM25 over 720 documents retrieves the designated poison for all 60 tasks at \(k=5\) but produces 7/294 goal-matched attacks (2.38\%). Presenting the same weakening as a final security architecture exception produces 74/116 attacks in a frozen two-endpoint stress test (63.79\%) and 115/294 in a post hoc all-five extension using the same frozen prompts (39.12\%). In a replay of 194 provider-valid treatment policies that violate task requirements, AWS \texttt{CheckNoNewAccess} reports no new access for four of 168 goal-matched exact attacks. The full pre-deployment rule rejects all 171 exact deltas and routes five unresolved cases to review. These findings support treating IAM copilots as untrusted proposal generators whose outputs require independent authorization checks before deployment.

cs.CR

新论文 · v1arXiv:2611.03430

Evaluating Depth-Augmented Visual Features for Cross-Dataset Lunar Traversability Estimation

Jan Baturo, Bartosz Ptak

原文摘要

Autonomous mobility is essential for sustained lunar surface operations, as communication delays and line-of-sight occlusions limit continuous teleoperation. Although recent traversability estimation methods increasingly rely on deep learning, the domain gap between terrestrial analogue environments and real lunar terrain can limit their generalisation, and real lunar traversability labels are scarce, making fully supervised training difficult. To address these challenges, we build a weakly supervised framework trained on sparse pairwise annotations and study whether augmenting visual features with depth-derived geometric information: depth, surface normals, and combined geometric descriptors. We evaluate the models in both in-domain and cross-domain settings using two terrestrial analogue datasets and the real lunar Chang'E PCAM dataset. Contrary to expectations, we find that naive geometric augmentation yields no consistent improvement over a strong visual-only baseline in either setting, with effects small relative to seed-to-seed variance. Instead, the choice of training source emerges as the dominant factor in transfer quality: models trained on domain-relevant sources transfer substantially better to real lunar imagery than the geometric fusion strategy improves any single model. Our evaluation runs onboard a resource-constrained edge device and provides a controlled baseline for designing more expressive multimodal fusion architectures in future lunar perception systems.

cs.CV · cs.RO

版本更新 · v3arXiv:2603.18321

A Simple Categorical Calculus of Interacting Processes

Chad Nester, Niels Voorneveld

原文摘要

We present a calculus that models a simple sort of process interaction. Our calculus consists of a collection of terms together with a rewrite relation, parameterised by an arbitrary multicategory whose morphisms we understand as non-interactive processes. We show that our calculus is confluent and terminating, and that terms modulo the induced convertibility relation form a virtual double category. We relate our calculus to the free cornering of a monoidal category, which is a double-categorical model of process interaction that is similar in spirit to the calculus presented herein. Precisely, we construct a functor from the virtual double category given by our calculus into the underlying virtual double category of the free cornering of the free monoidal category on the multicategory of non-interacting processes. If we think of the terms of our calculus as programs and the rewriting system as an operational semantics for these programs, this functor gives a sound denotational semantics for our calculus in terms of the free cornering.

math.CT · cs.LO

新论文 · v1arXiv:2611.03428

Toward Uncertainty-Aware, Physics-Grounded Human World Models

Yufei Zhang, Zijun Cui

原文摘要

A robot that acts around people needs a world model of the human: a belief over the person's body state and a dynamics model that predicts where that state goes next. This abstract argues that two published components form exactly these two halves, and specifies how to couple them. KNOWN [1] reconstructs the 3D human body while estimating both aleatoric and epistemic uncertainty in real time (11.6 ms per frame); its aleatoric term identifies unreliable observations, its epistemic term identifies inputs from low-density regions of the training data, and refinement driven by the epistemic term reduces the error on such inputs from 81.3 to 70.3 mm. PhysMoP [2] predicts future body configuration by solving the Euler-Lagrange equations of the body with learned dynamics terms, reducing the 80 ms prediction error from 9.6 to 2.1 mm on Human3.6M and from 12.1 to 0.7 mm on 3DPW. We define the interface between the two, propose three mechanisms by which KNOWN's uncertainty enters PhysMoP, and specify an evaluation protocol on in-the-wild video. No new experimental results are reported here.

cs.RO

版本更新 · v2arXiv:2609.18724

Second-Best Gains from Trade in Matching Markets

Xiaohui Bei, Bo Li, Wenhao Wu, Shengwei Zhou

原文摘要

We study gains from trade (GFT) in two-sided matching markets with independent private types and arbitrary downward-closed feasibility constraints. The second-best benchmark is the maximum expected GFT achievable by a Bayesian incentive-compatible, interim individually rational mechanism that is strongly budget balanced at every report profile. These constraints generally preclude attaining the first-best GFT and raise the question of how much efficiency must be lost. We prove that the second-best GFT is at least one half of the first-best GFT in every such matching market. This recovers and generalizes the recent $1/2$ guarantee for bilateral trade by Liu, Qin, Ren, and Wang to markets with multiple buyers and sellers and arbitrary downward-closed feasibility constraints. Together with their matching upper bound for bilateral trade, our result establishes a tight worst-case ratio of $1/2$ for this general class of matching markets. Our proof builds on the virtual-GFT framework of Brüstle, Cai, Wu, and Zhao to reduce the problem to a one-parameter Lagrangian. The main step is a geometric, edge-by-edge analysis based on first-best edge-selection regions, combined with a randomized contraction in rank space. The same analysis also determines the exact worst-case efficiency for every level of outside subsidy. In particular, even a small outside subsidy can significantly improve the worst-case guarantee.

cs.GT

版本更新 · v2arXiv:2605.23138

Classical State Preparation for Variational Quantum Algorithms via Reinforcement Learning

Gino Kwun, Dhanvi Bharadwaj, Gokul Subramanian Ravi

原文摘要

Variational Quantum Algorithms (VQAs) potentially offer a pathway to practical quantum advantage, but their optimization is heavily hindered by barren plateaus and numerous local minima. While classically simulable Clifford circuits can warm-start VQAs to accelerate convergence, existing heuristic-based initialization methods struggle to scale within vast combinatorial search spaces. We address this bottleneck with CRiSP (a Clifford Reinforcement Learning agent for State Preparation), which casts Clifford prefix selection as a sequential decision-making problem. CRiSP utilizes Neural-Guided Monte Carlo Tree Search, driven by a Transformer-based policy trained via self-play, to insert learned Clifford gates before fixed parameterized rotations. This enables the construction of high-quality initial states entirely through polynomial-time classical stabilizer simulation. By integrating a curriculum learning strategy that progressively expands the search horizon, the agent efficiently scales to deep circuits. Evaluated on QAOA benchmarks of up to $22$ qubits and $1{,}370$ parameters, CRiSP outperforms state-of-the-art Clifford initialization methods by a mean of $3.19\times$ (max $45.02\times$) in average energy accuracy and $2.41\times$ (max $16.01\times$) in best-achieved energy accuracy. Assessments on VQE tasks further demonstrate the framework's robustness and generalizability.

quant-ph · cs.AI · cs.ET · cs.LG

版本更新 · v2arXiv:2609.24823

G-NAC: Graph Neural Automata Clustering via Emergent Domain Formation

Keith Miller, Tristan Crawford, Ronald J. Stanley

原文摘要

We introduce Graph Neural Automata Clustering (G-NAC), an unsupervised clustering method in which observations interact as cells on a fixed neighborhood graph. A shared recurrent graph-neural cellular rule evolves latent domain states through local interactions, which are converted into a rank-based spectral affinity for partitioning. Across 73 clustering tasks from 57 benchmark datasets, G-NAC achieved a mean adjusted Rand index (ARI) of 0.7951, comparable to Genie at 0.7941 and higher than the other evaluated baselines. Empirical training time and GPU memory scaled approximately linearly from 5,000 to 100,000 nodes. Learned transition rules also transferred from smaller source graphs to independent 100,000-node samples generated under matched conditions. These results demonstrate a recurrent graph-clustering formulation while identifying dependencies on graph quality, readout design, and source-target similarity.

cs.LG · eess.SP

版本更新 · v2arXiv:2610.32888

When Human Corrections Travel: Safety in Federated VLA Adaptation

Vigneshwaran Subbaraju, Obaidullah Zaland, Monowar Bhuyan

原文摘要

Vision-language-action (VLA) policies can adapt to local human intervention, while federated learning can combine distributed robot experience without pooling raw records. We examine their prospective intersection: sharing adaptations derived from diverse human corrections across tasks, environments, people, and robot embodiments. Corrections differ in modality, safety semantics(urgency, behavioral scope, etc.), and privacy sensitivity. A shared update that improves mean task success may suppress a rare safety intervention or produce an unsafe response on another robot. We argue for three requirements: preserve the context and uncertainty of multimodal corrections when deciding what to share; assess candidate updates in each receiving robot's closed loop before deployment; and evaluate leakage alongside retention of safety-critical evidence. Immediate, legible defensive behavior remains necessary during human interaction. We offer counterexamples and a falsifiable evaluation agenda, not experimental results.

cs.RO · cs.LG