跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

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

部分采集异常
正在读取账号与研究记录…

全站更新概况

+0新增论文
+0其中 AI 相关
+2已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-08 10:17 · 全站最近入库：2026-11-08 06:02各信源进度 →

统计口径与数据新鲜度

统计 2026-11-07 12:31 — 2026-11-08 12:31（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：2026-11-08 10:17最近发现新增版本：2026-11-08 06:02库内论文最新更新时间：2026-11-06 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。

17,100 已收录论文14,661 AI 相关4,057 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 17,100 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-08 10:15（北京时间）
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

查看论文
arXiv ↗PDF ↗
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

查看论文
arXiv ↗PDF ↗
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

查看论文
arXiv ↗PDF ↗
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

查看论文
arXiv ↗PDF ↗
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

查看论文
arXiv ↗PDF ↗
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

查看论文
arXiv ↗PDF ↗
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

查看论文
arXiv ↗PDF ↗
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

查看论文
arXiv ↗PDF ↗
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

查看论文
arXiv ↗PDF ↗
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

查看论文
arXiv ↗PDF ↗
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

查看论文
arXiv ↗PDF ↗
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

查看论文
arXiv ↗PDF ↗
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

查看论文
arXiv ↗PDF ↗
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

查看论文
arXiv ↗PDF ↗
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

查看论文
arXiv ↗PDF ↗
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

查看论文
arXiv ↗PDF ↗
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

查看论文
arXiv ↗PDF ↗
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

查看论文
arXiv ↗PDF ↗
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

查看论文
arXiv ↗PDF ↗
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

查看论文
arXiv ↗PDF ↗
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

查看论文
arXiv ↗PDF ↗
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

查看论文
arXiv ↗PDF ↗
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

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.08370

Programmable Silicon Retina on Pixel Processor Array

Maciej Lewandowski, Prince Philip, Alexandre Marcireau, Chetan Singh Thakur, André van Schaik, Piotr Dudek

原文摘要

Standard dynamic vision sensors approximate retinal processing by detecting temporal contrast changes, offering high speed and high dynamic range. In this work, we explore whether incorporating additional biologically inspired processing stages - specifically spatial filtering and gain control - can offer advantages for certain downstream tasks such as saliency prediction. We present the first implementation of a multi-stage Silicon Retina model on the SCAMP-5 Pixel Processor Array, along with a GPU-based simulation framework. We evaluate the performance of our model on Video Intensity Reconstruction and Video Saliency Prediction. While the bio-inspired model is less effective at reconstructing absolute intensity frames, it achieves a 13\% reduction in saliency prediction loss in comparison to standard DVS event representation, while reducing the event rate by approximately 47\%. These experiments are obtained using a lightweight $\approx 100$k-parameter FireNet-style network, adapted from event-based reconstruction to saliency prediction. These results suggest that the silicon retina's "information distillation" mechanism can achieve a more efficient representation for downstream neural networks, particularly in bandwidth-constrained edge applications.

eess.IV · cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03424

IdeaTaste: Do LLMs Share the Research Taste of Human Researchers?

Shanshan Zhong, Chen Xu, Jingjie Ning, Zhengzhong Liu, Aviral Kumar, Chenyan Xiong

原文摘要

Research taste, the judgment of what to read, which problems to pursue, and which methods to try, increasingly shapes the work of AI scientists, yet it remains far less understood than their ability to execute research. We introduce IdeaTaste, a benchmark that scores an LLM by how closely the research proposals it writes from a literature snapshot frozen at 2025 match the work the same communities published in 2026. Our experiments span six contemporary language models and four research areas from established to emerging fields, covering more than 90{,}000 proposals in total. LLM agents fall well short of human communities in both the literature they cite and the ideas they state, reaching about 26\% of the human level on citation matching and only 18\% on idea matching. Their populations can cite as diversely as a community and take up its tasks and methods, yet rarely arrive at the concrete approaches and research plans it pursues. Neither richer field context nor larger populations substantially close this gap. In blinded expert review, AI proposals trail the 2026 papers least in presentation and most in expected success, echoing their gap in concrete approaches, and those whose ideas no human paper shares fare worst, suggesting weaker directions rather than overlooked opportunities. These results indicate that the main bottleneck in AI research taste lies less in finding the directions a community works on than in turning them into the concrete approaches it goes on to pursue. We release IdeaTaste as an open, continuously updated leaderboard (https://cxcscmu.github.io/IdeaTaste) that benchmarks contemporary AI proposals against future publication cycles.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03421

Circumventing Magnitude Collapse via Modular Two-Stage Open-Set Recognition

Laurin van den Bergh, Halil Bisgin, Andres Palechor, Mike Suter, Manuel Günther

原文摘要

Open-set recognition (OSR) requires neural networks to classify known classes while rejecting unknown samples, which is critical for real-world deployment. So far, OSR research studied and developed representation learning and postprocessing methods independently and their interactions remain unexplored. In this paper, we reconsider OSR as a modular two-stage pipeline and present the first systematic study of interactions between representation learning and postprocessing methods across dataset scales and usage of known unknown data. First, we discover a failure mode we term \emph{magnitude collapse}, where representation learning methods that utilize known unknown data can suffer performance degradation at large scale and irreversibly destroy discriminative information, despite excelling at small scale. Second, we study the modular interactions and reveal when they can be leveraged for modular performance gains via two-stage processing and where interaction effects amplify performance degradation due to magnitude collapse. Third, we show how these findings can be used to achieve state-of-the-art performance with a simple $K+1$ class classifier baseline and magnitude-aware postprocessing while circumventing magnitude collapse. Finally, our results demonstrate that small-scale evaluations with known unknown data are not predictive of large-scale performance, invalidating current best practices in OSR research. Code available at https://github.com/TwoDigitsOneNumber/Two-Stage-OSR.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2603.16375

Monoidal categories graded by partial commutative monoids

Matthew Earnshaw, Chad Nester, Mario Román

原文摘要

Effectful categories have two classes of morphisms: pure morphisms, which form a monoidal category; and effectful morphisms, which can only be combined monoidally with central morphisms (such as the pure ones), forming a premonoidal category. This suggests seeing morphisms of an effectful category as carrying a grade that combines under the monoidal product in a partially defined manner. We axiomatize this idea with the notion of monoidal category graded by a partial commutative monoid (PCM). Monoidal categories arise as the special case of grading by the singleton PCM, and effectful categories arise from grading by a two-element PCM. Further examples include grading by powerset PCMs, modelling non-interfering parallelism for programs accessing shared resources, and grading by intervals, modelling bounded resource usage. We show that effectful categories form a coreflective subcategory of PCM-graded monoidal categories; introduce cartesian structure, recovering Freyd categories; and describe PCM-graded monoidal categories as monoids by viewing a PCM as a thin promonoidal category.

cs.LO · math.CT

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03420

Temporal Island Sparse Autoencoders for Interpreting Clinical Time-Series Models

Muhan Yeo, Bong Gyun Kang, HyunGi Kim, Sungroh Yoon

原文摘要

Deep learning models for electronic health records achieve strong predictive performance but provide little insight into what clinical concepts they represent internally. Post-hoc attribution methods produce per-cell importance scores that lack temporal coherence, cross-variable structure, and reusability across patients. We introduce the Temporal Island Sparse Autoencoder (TI-SAE), which learns a backbone-specific, patient-shared clinical concept dictionary from a frozen predictive model's representations. Each dictionary entry (latent) is defined by learned temporal Gaussian islands (specifying when the concept is active) and a sparse variable-composition vector (specifying which variables are involved). A decoupled selector then identifies which dictionary entries drive each patient's prediction, separating representation learning from attribution. We evaluate TI-SAE across five backbone architectures spanning different representation strategies on MIMIC-III and MIMIC-IV (three prediction tasks each). TI-SAE produces structured clinical concepts that go beyond transient attribution heatmaps while achieving strong performance on standard faithfulness benchmarks.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v8arXiv:2501.06044

Beyond Optimal Fault Tolerance

Andrew Lewis-Pye, Tim Roughgarden

原文摘要

The optimal fault-tolerance achievable by any protocol has been characterized in a wide range of settings. For example, for state machine replication (SMR) protocols operating in the partially synchronous setting, it is possible to simultaneously guarantee consistency against $α$-bounded adversaries (i.e., adversaries that control less than an $α$ fraction of the participants) and liveness against $β$-bounded adversaries if and only if $α+ 2β\leq 1$. This paper characterizes to what extent "better-than-optimal" fault-tolerance guarantees are possible for SMR protocols when the standard consistency requirement is relaxed to allow a bounded number $r$ of consistency violations. We prove that bounding rollback is impossible without additional timing assumptions and investigate protocols that tolerate and recover from consistency violations whenever message delays around the time of an attack are bounded by a parameter $Δ^*$ (which may be arbitrarily larger than the parameter $Δ$ that bounds post-GST message delays in the partially synchronous model). Here, a protocol's fault-tolerance can be a non-constant function of $r$, and we prove, for each $r$, matching upper and lower bounds on the optimal "recoverable fault-tolerance" achievable by any SMR protocol. For example, for protocols that guarantee liveness against 1/3-bounded adversaries in the partially synchronous setting, a 5/9-bounded adversary can always cause one consistency violation but not two, and a 2/3-bounded adversary can always cause two consistency violations but not three. Our positive results are achieved through a generic "recovery procedure" that can be grafted on to any accountable SMR protocol and restores consistency following a violation while rolling back only transactions that were finalized in the previous $2Δ^*$ timesteps.

cs.DC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03419

Scaling global tractography with ExaTract: from large cohorts to ultra-high-resolution datasets

Simon Legeay, Felix Matuschke, Bastien Herlin, Jan André Reuter, Christophe Destrieux, Markus Axer, Ivy Uszynski, Cyril Poupon

原文摘要

Global tractography offers a theoretical framework for reconstructing white matter connectivity from diffusion MRI by jointly inferring all streamlines and their consistency with the diffusion signal and underlying anatomical priors. However, its sequential nature and log-linear complexity make it computationally prohibitive at the scales demanded by neuroimaging, from large population cohorts such as the Human Connectome Project (HCP) to ex vivo ultra-high-field acquisitions at mesoscopic resolution. In this work, we present ExaTract, a parallelized spin-glass tractography framework designed for high-performance computing (HPC) architectures. Implemented as an open-source MPI+Kokkos application, ExaTract partitions the tractography domain into spatially overlapping regions processed across distributed memory nodes, with regular synchronization of boundary modifications to preserve global convergence guarantees. We validate ExaTract on both in vivo and ex vivo diffusion MRI data: the complete HCP dataset demonstrates population-scale throughput, while the high-resolution Chenonceau dataset provides the first mesoscopic structural connectome derived from global tractography.

eess.IV · cs.DC · math.NA

查看论文
arXiv ↗PDF ↗