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

+1673新增论文
+1257其中 AI 相关
+198已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-14 04:53 · 全站最近入库：2026-11-13 20:44各信源进度 →

统计口径与数据新鲜度

统计 2026-11-13 05:29 — 2026-11-14 05:29（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：2026-11-14 04:53最近发现新增版本：2026-11-13 20:44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6,727 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 17,362 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-14 04:52（北京时间）
新论文 · v1arXiv:2611.06762

U.S. State Guidance on AI in K-12 Education: A Comparative Content and Citation Analysis

Shahan Ali Memon, Anna-Maria Gueorguieva, Anukriti Kumar, Lucy Lu Wang, Jevin D. West, Nic Weber

原文摘要

In the years following the public release of ChatGPT in late 2022, more than half of U.S. states have published formal guidelines around AI usage in K-12 education, creating a record of largely independent state education departments responding to a shared technological disruption. In this work, we analyze publicly available AI usage guidance documents from 35 states in the U.S. and Puerto Rico. We compare the guidance in these documents across various dimensions, including pedagogy and instruction, audience, actionability, workforce and career readiness, responsible use and equity, and alignment with state-level demographics and administrative capacity. Finally, we investigate who authored these documents and their cited sources, identifying epistemic foundations underlying their claims. We find that guidance priorities converge on topics anchored in laws such as data privacy and academic integrity, each addressed in 97% of documents. While most documents mention equity of access (86%) and algorithmic bias (97%), fewer discuss specific marginalized populations. Across documents, there is a common framing of urgency around AI integration to prepare students for workforce readiness (86%) and promote loosely-defined personalized learning (86%), which is not matched by specific guidance for capacity-building, actionability, or accountability. State priorities show no relationship to state demographics, capacity, or partisanship. Instead, we identify notable interdependencies between states with shared citations to non-profit organizations like TeachAI and Code.org, with some states reproducing TeachAI's model guidance near-verbatim, and peer citations concentrating on a few early states such as Oregon and Washington. No state includes parents as contributors on these documents, and only five include students.

cs.CY · cs.DL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06759

Continual Classification Beyond the Kernel Regime: Harnessing the Sparsity Bias of L2 Regularization in Diagonal Linear Networks

Gilad Karpel, Itay Evron, Ron Meir, Daniel Soudry

原文摘要

We study logistic regression for continual learning with linear predictors in a high-dimensional statistical setting. Existing theoretical work has largely focused on continual linear regression with variants of L2 regularization, motivated by their analytical simplicity and connection to the kernel regime of neural networks. We first derive the optimal L2 regularization strength for continual linear classification and characterize its generalization performance, recovering behavior analogous to prior results for continual linear regression. Next, we examine the effect of L2 regularization in deeper models using a minimal two-layer diagonal linear network. In the single-task setting, L2 regularization on the weights of such models is known to promote sparsity in the resulting predictor, yielding a rich, sparse feature-learning regime beyond the kernel regime (a similar effect arises in two-layer ReLU networks). However, in continual learning, where L2 regularization is typically centered on previous-task weights, this sparsity bias is no longer preserved. We therefore propose a weighted variant of L2 regularization that extends this beneficial sparsity bias to continual learning. We show theoretically and empirically that, for a sufficiently sparse teacher, our variant converges substantially faster than directly learning a linear predictor with conventional continual L2 or L1 regularization, trading some long-horizon bias for markedly improved performance over moderate task horizons.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2511.17747

AEGIS: Preserving Privacy of 3D Facial Avatars with Adversarial Perturbations

Dawid Wolkiewicz, Anastasiya Pechko, Przemysław Spurek, Piotr Syga

原文摘要

The growing adoption of photorealistic 3D facial avatars, particularly those utilizing efficient 3D Gaussian Splatting representations, introduces new risks of online identity theft, especially in systems that rely on biometric authentication. While effective adversarial masking methods have been developed for 2D images, a significant gap remains in achieving robust, viewpoint-consistent identity protection for dynamic 3D avatars. To address this, we present AEGIS, the first privacy-preserving identity masking framework for 3D Gaussian avatars, concealing identity from automated face recognition while preserving the avatar's perceptual realism and animation usability. AEGIS applies adversarial perturbations to the base (DC) color coefficients of the Gaussian primitives, guided by an ensemble of pre-trained face verification networks, embedding the protection directly in the 3D representation so that it applies across viewpoints and animations, without retraining or modifying the avatar's geometry. Evaluated against black-box recognizers, AEGIS reduces face retrieval and verification accuracy to near-zero while maintaining high perceptual fidelity. It also preserves key facial attributes such as age, gender, and emotion, demonstrating strong privacy protection with minimal visual distortion. We further introduce a viewpoint-robust leakage metric that quantifies residual identity leakage across an avatar's rendered viewpoints, which single-view evaluation cannot capture.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.10795

Factual recall in linear associative memories: sharp asymptotics and mechanistic insights

Alessio Giorlandino, Sebastian Goldt, Antoine Maillard

原文摘要

Large language models excel at factual recall, yet the fundamental limits of storing input--output associations with neural networks remain unclear. We study these limits in a minimal setting: a linear associative memory that maps $p$ input embeddings in $\mathbb{R}^d$ to their $d$-dimensional targets via a linear layer, requiring each mapped input to score its own target above all other outputs. Since all inputs compete for the same outputs, these constraints are strongly correlated, which makes the storage capacity $p_c$ --- the largest number of associations that can be stored --- hard to characterise. We address this in three steps. First, we introduce a decoupled model, in which each input competes with its own independent set of outputs, and provide numerical and analytical evidence that it is equivalent to the original model, both in capacity and in the structure of the learnt solution. Second, using tools from statistical physics, we show that the decoupled model has capacity $p_c \log p_c / d^2 = 1/2$, extend this computation to linear two-layer networks, and go beyond the capacity by predicting the spectrum of the learnt weights and the storage mechanism. The latter explains how the optimal solution outperforms a naïve Hebbian rule: rather than boosting input--output alignments with broad fluctuations, it raises the correct scores just above the extreme-value threshold set by the competing outputs. Third, we prove the decoupled model's capacity thresholds rigorously, including in the non-convex two-layer case; combined with a recent proof for the original model, this shows that both models have the same capacity for full-rank weights. These findings give a sharp characterisation of factual storage in linear networks, and suggest decoupling as a general tool for memorisation and learning problems in which each input must be matched to one of an extensive number of outputs.

stat.ML · cond-mat.dis-nn · cond-mat.stat-mech · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2607.14106

Token Time Continuous Diffusion for Language Modeling

Parikshit Bansal, Sujay Sanghavi

原文摘要

In this paper we introduce token time continuous diffusion (TTCD), a new diffusion language model which (a) operates in continuous space, deterministically mapping Gaussian noise to a final token canvas with no further sampling, and crucially (b) incorporates a new notion of per-token times, with some tokens proceeding from noise to token at a faster rate than others. Continuous space modeling helps TTCD avoid the parallel sampling of multiple tokens, which is a key source of inaccuracy at high speedups for models that iterate purely in discrete space. The notion of per-token times helps TTCD to better model conditional generation, allows for more sure tokens to proceed at a faster rate, and allows for differentiated inter-token influences during refinement. TTCD outperforms discrete models at high speedups. We train a 160M parameter TTCD model on OpenWebText, and then self-distill it; we find that at high speedups we are comparable in unconditional generation quality, and outperform in conditional generation, several existing models of similar size trained, on the same data, and self-distilled. We achieve similar gains in Sudoku solving as well.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.03633

Pretraining Data Scale Reverses the Muon-AdamW Fine-Tuning Gap

Catherine Li, Jingchu Gai, Andrej Risteski, Jacob Mitchell Springer, Aditi Raghunathan

原文摘要

Muon has recently emerged as a promising optimizer for pretraining large language models, offering a speedup over AdamW in minimizing pretraining loss. However, it remains unclear whether Muon's advantage persists after fine-tuning. In this paper, we study the downstream behavior of Muon and AdamW and uncover a surprising trend: beyond a sufficiently large pretraining data budget, AdamW outperforms Muon after fine-tuning. Moreover, as model size increases, AdamW overtakes Muon at progressively smaller pretraining token-parameter ratios. To explain this reversal, we view fine-tuning as a perturbation of the outputs and introduce the margin-to-spread ratio, which measures how far the correct logit lies above the wrong ones relative to how widely the wrong logits are spread. In language models, Muon has the larger margin-to-spread ratio at small data budgets and AdamW at large ones, mirroring the fine-tuning trend. In a linear associative memory, we prove that after one update the margin-to-spread ratio of gradient descent gains on that of Muon as the data budget grows, and simulations show that this trend persists after extended training.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06751

A Quantum Lower Bound for Triangle Finding

Arjan Cornelissen, Amin Shiraz Gilani, Xingyu Zhou

原文摘要

Triangle finding is a fundamental problem in graph theory that has played a central role in the development of quantum algorithmic techniques. For $N$-vertex graphs given by their adjacency matrices, a long line of work has improved the quantum query upper bound from $O(N^{3/2})$ to $O(N^{5/4})$. However, the best known lower bound has remained the elementary $Ω(N)$ bound obtained from unstructured search. We prove the first superlinear quantum query lower bound for triangle finding, showing that $Ω(N^{13/12})$ queries are necessary. Our result also implies the same lower bound for triangle detection and for detecting every fixed connected non-bipartite graph. The proof builds on the compressed oracle approach of Zhandry and the transfer approaches of Belovs. It compares the computation on graphs with a planted triangle to the computation on random graphs conditioned to be triangle-free, through a map on the input registers that almost commutes with every query. We average over local changes to the input while preserving its distribution, through a procedure known as conditional resampling. Our main technical contribution is a set of estimates that let us control the query error under this averaging, despite the dependence introduced by conditioning a dense graph to be triangle-free.

quant-ph · cs.DS

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.06598

SimForcing: Distilling Simulation Motion Priors into Real-Domain Robot World Models

Xiaodong Wang, Tianle Li, Chuanxin Song, Junliang Xie, Zhanmi Zhong, Suiying Wu, Peixi Peng

原文摘要

Action-conditioned robot world models must respond precisely to robot trajectories while preserving realistic visual dynamics, yet learning both from heterogeneous robot videos remains challenging. Simulation offers structured motion supervision, but appearance differences hinder direct transfer, and inaccurate simulation predictions can misguide real-video generation. We present SimForcing, a simulation-guided framework that uses simulation both as a source of transferable motion knowledge and as a controllable reference for prediction. First, we transfer motion knowledge from a simulation teacher through latent-motion distillation, aligning temporal changes in latent space to internalize motion priors while mitigating the influence of appearance differences. Second, we introduce multi-block simulation conditioning with condition dropout to exploit predicted simulation trajectories without relying excessively on their accuracy. Our simulation-conditioning classifier-free guidance scheme unifies these two ideas by balancing predictions based on internalized motion knowledge with those additionally guided by simulation latents. The jointly trained student generates both simulation conditions and real-domain videos, requiring no additional world model at inference. On Bridge, SimForcing achieves the best PSNR, SSIM, LPIPS, and FVD among the compared methods without external embodied pretraining. Evaluation on InternData-A1 further supports its applicability across robot datasets. Moreover, using our trained world model to initialize a vision-language-action model improves LIBERO success, suggesting its utility for downstream policy learning. https://github.com/Wang-Xiaodong1899/SimForcing

cs.RO · cs.AI · cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2609.17655

Efficient Robust Learning at the Information-Theoretic Limit

Adam R. Klivans, Konstantinos Stavropoulos, Sergei Tikhonov, Arsen Vasilyan

原文摘要

In an important recent work, Blanc (2026) gave an algorithm for robustly learning Boolean concept classes with respect to a fixed distribution that outputs a (randomized) classifier achieving the optimal error of $η+ \varepsilon$ where $η$ is the noise rate. In contrast, it is well known that deterministic hypotheses cannot achieve error less than $2η+ \varepsilon$. Blanc's algorithm is computationally inefficient, and the main problem left open in his work is to find a polynomial-time algorithm given access to an oracle for empirical risk minimization (ERM). Here we resolve this problem and give such an algorithm. Additionally, we give an efficient algorithm (no ERM oracle required) for robustly learning any function class that admits low-degree polynomial approximators with respect to hypercontractive distributions. This captures basic settings including halfspaces with respect to Gaussian marginals. Our techniques make new connections to various types of online convex optimization algorithms. As a surprising consequence, we show that efficient SQ learnability in the agnostic setting implies efficient learning with contamination (with respect to Gaussians or uniform over the hypercube).

cs.DS · cs.LG · stat.ML

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.03771

ISAC-Assisted Proactive Handover in mmWave Networks: Value of Foresight and Localization Requirements

Seyed Bagher Hashemi Natanzi, Bo Tang

原文摘要

Millimeter-wave (mmWave) links can lose tens of decibels within milliseconds when a person or vehicle crosses the line of sight, and reactive handover recovers only after the outage has begun. Integrated sensing and communication (ISAC) promises to let the network see blockers coming and move users to another cell in advance. This paper asks how much such foresight is worth relative to the best reactive handover, and what sensing accuracy is needed to harvest it. We formulate cost-aware cell selection with knowledge of the future signal-to- noise ratio as a sequential decision problem, define the value of foresight through a policy-independent bound, and develop an ISAC-assisted handover framework in which a radio unit senses blockers with its own communication waveform and a simulated Open RAN xApp plans handovers. Ray-traced experiments in a 28 GHz street canyon, reported on held-out scenarios, show that, with a short look-ahead, perfect foresight closes most of the gap between service-aware (Layer-3) reactive handover and an instantaneous oracle. Harvesting this value, however, requires the user and nearby blockers to be localized to about a decimeter, well beyond what our radar tracker and meter- level user positioning provide; with realistic errors, even an uncertainty-aware planner largely defers to reactive handover.

eess.SY · cs.NI · eess.SP

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06738

Coupled Scene Graph Anticipation: When With-Constraint Recall Hides Structural Inconsistency

Zeno Nongmaithem, Anushttha Srivastava, Anshit Sinha, Apoorv Sisodia, Suman Chowdhury, Prerana Mukherjee, Rajesh P. Barnwal

原文摘要

Scene Graph Anticipation (SGA) predicts object relationships in future video frames. Continuous-time SGA models evolve each subject-object pair with an independent Neural ODE, so relationships sharing an entity cannot influence one another during integration, and nothing prevents mutually exclusive predictions, such as "sitting on" and "standing on", for the same pair. We introduce CoupledSGA, which links such relationships through a Relationship Interaction Graph with graph attention inside the ODE vector field, and adds a Structural Consistency Loss ($\mathcal{L}_{SC}$) based on a matrix of mutually exclusive predicates. Developing CoupledSGA revealed a limitation of the evaluation protocol. With-Constraint evaluation keeps one predicate per group for each subject-object pair, so its R@K and mR@K cannot capture the within-group violations targeted by $\mathcal{L}_{SC}$: we prove they are unchanged whenever each group's winning predicate and its score are held fixed. We further show that the gradient of $\mathcal{L}_{SC}$ depends on predicate scores rather than ground-truth labels: for two-predicate rules it amplifies the ordering the model already holds, and when all scores in a group are equal it suppresses predicates in more exclusion rules more strongly, explaining why the penalty can lower recall while improving consistency. On Action Genome, activating $\mathcal{L}_{SC}$ after two warm-up epochs reduces R@20 from 42.21% to 35.18% while lowering the No-Constraint contradiction rate from 45.92% to 4.07% (matched-budget R@20: 40.48% CoupledSGA vs. 44.78% SceneSayerODE). CoupledSGA is a testbed, not a state-of-the-art claim: With-Constraint recall captures the cost of enforcing structural consistency but not the improvement. We recommend reporting No-Constraint results alongside a contradiction rate for methods that constrain predicate co-activation.

cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06737

Data Center Agglomeration and Power Infrastructure Capacity in the United States

Yutong Ma

原文摘要

The continuous expansion of digital infrastructure, especially data centers, has imposed unprecedented, geographically concentrated stress on existing power grids. However, rigorous causal evidence quantifying how these facilities reshape local power-infrastructure supply remains limited. This study builds a comprehensive county-level US panel dataset spanning 2010-2024, uniquely integrating individual data center building footprints and power-plant additions. To mitigate endogeneity and high-dimensional confounding, this study deploys Double Machine Learning with five-fold cross-fitting, conditioning on county and year fixed effects alongside regional socioeconomic covariates. Baseline estimation identifies a significant positive causal effect robust across multiple rigorous specifications. The result holds following 1%-99% winsorization that downweights mega-clusters including Loudoun County: growth in data-center floor area drives meaningful increases in nearby power-generation capacity (ATE=1.982, P=0.000, CI: [1.25, 2.72]). Outcomes remain statistically significant using a one-year lagged treatment to address reverse causality, and are stable under state-level fixed-effect alternatives. An event-study framework augmented with historical agglomeration controls validates clear parallel trends and detects a sharp causal spike at t = 3, matching typical utility-scale grid-construction lead times. A placebo test further verifies these causal estimates cannot emerge from random chance. Substantial regional heterogeneity emerges: strong positive impacts concentrate in the West, while significant negative displacement-related effects appear within resource-constrained Northeastern counties. These results deliver timely insights for urban planners and energy regulators, stressing the importance of forward-looking grid-capacity investment to support ongoing digital transformation.

cs.AR

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2605.00121

Predictive Spatio-Temporal Scene Graphs for Semi-Static Scenes

Miguel Saavedra-Ruiz, Charlie Gauthier, Kumaraditya Gupta, Shima Shahfar, Kirsty Ellis, Steven Parkison, Liam Paull

原文摘要

We have seen tremendous recent progress in our ability to build "spatio-semantic" representations that enable robots to perform complex reasoning across geometry and semantics. However, the vast majority of these methods lack any ability to perform reasoning across time. This is a desirable property in situations where a robot repeatedly observes an environment where instances may change in between observations, but in a structured way. Consider as an example a home environment where the location of a mug typically moves from the cupboard to a countertop to the sink and then back to the cupboard on a daily basis. We should be able to learn this cyclic behavior and use it to predict the state of the mug in the future. In this work, we propose a method that is able to perform this type of tempo-spatio-semantic reasoning. Underpinning the method is a filter, Perpetua*, that performs Bayesian reasoning on the states of the environment that are observed over time. This filter is integrated within a 3D scene graph structure that we call PredictiveGraphs, where nodes represent objects and edges function as Perpetua* filters encoding spatio-semantic relationships. We validate the method in both simulation and real-world dynamic navigation tasks, where our real-world experiments consist of an environment that is undergoing semi-static changes at a bi-hourly frequency over a period of three weeks. In both settings, we demonstrate that our method outperforms baselines in predicting future environment states, even in the presence of distributional shifts.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06728

Turns Matter: Advancing Streaming Video RL via Turn-Level Credit

Shuai Dong, Kanghui Tian, Linghan Chen, Wenqi Shao, Hongrui Wu, Haowen Hou, Yongfu Zhu, Xuehui Wang 等 23 位作者

原文摘要

Streaming video understanding requires models to repeatedly decide whether to respond or continue observing. Recently, Group Relative Policy Optimization (GRPO) has been applied to this setting, with existing approaches emphasizing reward design while retaining a single trajectory-level advantage across turns. Such shared credit can reinforce redundant replies after earlier successes and discourage useful follow-ups after earlier failures. We propose TurnWise, a turn-level GRPO framework that aligns learning with individual streaming decisions. TurnWise addresses the mismatch between trajectory-level feedback and turn-level interaction, promoting informative responses and reducing redundancy. Specifically, turn-level credit assignment uses silence-completed prefix scoring to construct group-relative advantages from each decision's remaining return, separating its learning signal from earlier rewards. Turn-mean policy optimization averages token losses within each turn and then across turns, giving response and waiting decisions equal weight regardless of output length. These complementary designs improve streaming policy learning without a learned critic or additional rollouts. Extensive experiments show our method outperforms prior RL approaches for streaming video understanding.

cs.CV · cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06727

Airlock: Bounding the Multi-Agent Blast Radius via Selective Online Containment

Zhonghao Zhan, Javad Forough, Yefan Zhang, Krinos Li, Xiao Ma, Hamed Haddadi

原文摘要

When multi-agent systems act on the external world, a single agent's faulty output can spread across tasks before detection, creating a system-wide blast radius. Single-agent guardrails are confined to individual harnesses, while existing multi-agent controls either cancel only the faulty source and miss downstream consumers or halt and roll back the entire workflow at the cost of healthy work. We present Airlock, a multi-agent runtime and guardrail for selective post-alert fault containment. Its tree-structured runtime, EdgeCitadel, narrows permissions vertically from parent to child agents to establish node boundaries and control switches. Meanwhile, an append-only provenance DAG records cross-agent data consumption horizontally. Upon an alert, Airlock traces forward on this DAG to isolate tainted executions and pending actions, and backward to narrow root causes. At the site switches, a default full quarantine tier freezes affected branches without a solver, while an assured optimized cut tier uses fence-then-prune to enforce a deadline-aware minimum cut minimizing collateral disruption. Across 1,832 testbed runs, 161 physical smart-home LLM runs, and 24,266 simulation records, Airlock blocks all post-alert faulty actuations on our main testbed and smart-home grids with zero post-convergence leaks. Whereas native controls in A2A and LangGraph either contain at most 33.3% of faults or retain at most 16% of work without redo, Airlock retains +68 pp to +96 pp more healthy work, and its optimized cut retains +46 pp more than full quarantine under dense spread. These results show that co-designing runtime authority boundaries with online provenance enables surgical fault containment without sacrificing healthy work (code: https://github.com/EdgeCitadelTeam/EdgeCitadel).

cs.MA

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06725

Drowning in Noise: On Signal Saliency in Self-Supervised Learning for Ocean Acoustics

Shikhar Bharadwaj, Samuele Cornell, Shinji Watanabe, Malcolm Slaney

原文摘要

Self-supervised learning (SSL) for audio typically benefits from larger pre-training corpora, but this relationship assumes that training data carries meaningful learning signal. In ocean acoustics, this assumption is often violated: passive recordings are dominated by waves, wind, and silence, with biological vocalizations occupying a small fraction of the total duration. We show that this overrepresentation of noise causes SSL models to allocate representational capacity to acoustically trivial structure, degrading downstream performance. Using BEATs as a testbed, we demonstrate that pre-training on 30 hours of salient recordings (segments containing animal vocalizations) outperforms 1,240 hours of unfiltered data on a 31-class marine mammal classification benchmark. Under linear probing, the manually curated salient set achieves markedly better accuracy than the full corpus, despite using 41 times less data. Automatic saliency-based filtering improves over unfiltered pre-training, but still falls well short of the manually curated salient set. Our findings suggest that, in domains where informative content is temporally sparse, data curation matters more than data scale for SSL pre-training.

cs.SD

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06724

Dexterous Robotic Hands in the Foundation-Model Era: A Full-Stack Survey of Hardware, Data, Cross-Embodiment Transfer, Learning, and Evaluation

Ji Pei

原文摘要

Dexterous robotic hands are increasingly coupled to large-scale human data and foundation models, yet progress in hardware, representation learning and evaluation is often assessed separately. This survey reviews work from January 2024 to early November 2026, with earlier studies included to establish technical lineages. We organize the literature into five interdependent layers: hardware; data collection and curation; cross-embodiment transfer; learning and foundation models; and evaluation and applications. Human hand-object understanding and tactile sensing provide two cross-cutting perspectives. A system-level architecture, comparative tables and five case analyses connect design choices across these layers. We distinguish within-study experimental comparisons from heterogeneous corpus statistics, vendor specifications and company-reported results. Three conclusions emerge. First, the value of human data depends on kinematic, visual and contact alignment, not recording volume alone. Second, shared action representations and foundation policies do not remove embodiment-specific constraints on force, latency and contact. Third, task completion is insufficient to establish physical correctness or deployment readiness. Evidence remains limited for zero-shot transfer of contact-rich skills between morphologically different hands, long-duration reliability, and cross-sensor tactile generalization. We identify eleven open problems and propose reporting interfaces and controlled comparisons that can make full-stack progress more measurable. The review is a structured narrative synthesis rather than a pooled performance ranking or an exhaustive systematic review.

cs.RO · cs.AI · cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06718

Symmetry Breaking at the Edge of Stability via Central Flow Analysis

Naima Elosegui Borras, Georgios Arvanitidis

原文摘要

Continuous symmetries in neural networks lead to conserved quantities that are invariant under gradient flow, such as layer balancedness in linear and ReLU networks. Finite-step gradient descent need not preserve these laws, particularly at the edge of stability (EOS), where the iterates oscillate around a smoother trajectory, which can be described by the central flow dynamics (Cohen et al., 2025). We study how gradient flow conservation laws evolve under the central flow description of this regime. We show that the curvature correction induces a finite-dimensional drift determined by the oscillation covariance along critical parameter directions. We thus take the first steps to analyse which conservation laws remain and are broken at the EOS according to the central flow dynamics by analysing a scalar two-layer model, two-layer matrix factorisation, and a two-layer ReLU network, where the known conservation laws are shown to be complete (Marcotte et al., 2023).

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06715

Reasoning over Non-Parametric Memory in Multilingual LLMs: A Cognitive-Based Analysis of Relational Knowledge

Zohreh Abbasi Liasi, Batoul Hammoud, Anas Madkoor, Ehsaneddin Asgari

原文摘要

Retrieval-augmented generation (RAG) assumes that language models can reason over relations stated in their context rather than fall back on associations memorized during pretraining. We study this evidence-conditioned relational reasoning in isolation, with the facts supplied directly in the prompt rather than retrieved. \textsc{Rel-Bloom} is a controlled multilingual diagnostic of 450 multiple-choice questions built from 30 Wikidata relations; the same source relations are instantiated at five Bloom-inspired levels (Remember, Understand, Apply, Analyze, Evaluate) and under three veracity conditions (Factual, Counterfactual, Neutralized). Across 43 models, six languages, and two multilingual settings (226,800 predictions), three findings stand out. First, accuracy drops sharply from Apply to Analyze in every evaluated open-weight model series, reaching 47.2 percentage points for the Large Granite bucket, but not for either Gemini model. Second, Evaluate items remain a bottleneck even for models near ceiling on the other task types: Gemini~3.1 Pro averages 99.5\% on the other four levels but 60.7\% on Evaluate. Third, item- and relation-level difficulty rankings are consistently preserved across languages, indicating a difficulty structure partly shared across languages within this benchmark. Across knowledge conditions, Counterfactual contexts are generally harder than Factual ones, while removing entity identities can improve higher-level performance in some model regimes. Greater model capability therefore does not by itself ensure reliable reasoning over supplied relational evidence. Relevant resources are available at: https://huggingface.co/spaces/QCRI/non-parametric-memory-relational-reasoning.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v5arXiv:2410.23187

Explorable Parity Automata

Emile Hazard, Olivier Idir, Denis Kuperberg

原文摘要

We define the class of explorable automata on finite or infinite words. This is a generalization of History-Deterministic (HD) automata, where this time non-deterministic choices can be resolved by building finitely many simultaneous runs instead of just one. We show that recognizing HD parity automata of fixed index among explorable ones is in PTime, thereby giving a strong link between the two notions. We then show that recognizing explorable automata is ExpTime-complete, in the case of finite words or parity automata up to index [0, 2]. Additionally, we define the notion of ω-explorable automata on infinite words, where countably many runs can be used to resolve the non-deterministic choices. We show ExpTime-completeness for ω-explorability of automata on infinite words for the safety and coBüchi acceptance conditions. We finally characterize the expressivity of (ω-)explorable automata with respect to the parity index hierarchy.

cs.FL

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2610.07844

GPU-accelerated wind farm layout search with a distilled endogenous wake model (EndoWake)

Martina Fischetti, Matteo Fischetti

原文摘要

We build on EndoWake, an endogenous wake model that links the wind speed at every grid cell to its upwind neighbors by linear constraints, so that wake field, siting decisions and project constraints share one mixed-integer model. Its four parameters are calibrated once on the single wake of a Reynolds-averaged Navier-Stokes (RANS) simulation, and a graphics processing unit (GPU) scores over a million layouts per second per wind direction. At Lillgrund, we compare searches guided by EndoWake and by PyWake under a RANS judge that no search calls: the fidelity of a wake model is not the quality of the layouts optimized under it. Two diagnostics separate a directional quadrature error between the sampled wind directions from a spatially localized surrogate bias off each wake edge, not reported before to our knowledge; at random directions, five paired starts detect no difference between the pipelines. The main result puts the speed to use: EndoWake ranks the moves of a local search on the GPU, and PyWake confirms every accepted move. On twenty unseen starts, with one GPU and thirty CPU processes, screen-and-confirm reaches similar mean gains to a search on PyWake alone, 7.9 times faster at one wind speed and 14.9 times faster on the annual energy (3.0 and 4.7 with a proof of local optimality charged to the timed search); on a second site it keeps its speed, and its local optima fall slightly short of those of PyWake alone. Code and data are deposited on Zenodo.

math.OC · cs.CE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06711

Energy-Guided Transport for Projection-Free Physics-Informed Flow Matching

Giuliano Galadini, Aurelio Uncini, Danilo Comminiello

原文摘要

Deep generative models, particularly Flow Matching frameworks, have emerged as powerful tools for synthesizing complex physical systems. However, standard architectures remain purely statistically driven and agnostic to the underlying governing equations, often violating fundamental physical constraints during inference. Existing zero-shot approaches designed to enforce these constraints typically rely on rigid algebraic projections. While effective for sparse boundary conditions, applying such discrete geometric corrections to dense, full-domain PDEs may disrupt the probability path, \rev{potentially deviating from the learned manifold and introducing substantial computational overhead}. To address these challenges, we introduce Energy-Guided Transport, a novel training-free framework that formulates non-linear physical constraints as a smooth potential energy landscape. Rather than interrupting the ODE integration, our method applies a continuous dissipative force directly to the intermediate generative states, steering them toward the physical manifold. By evaluating this force implicitly via reverse-mode automatic differentiation, our framework preserves the natural dynamics of the flow while maintaining an efficient $\mathcal{O}(N)$ algorithmic complexity. We extensively evaluate our framework across various 1D and 2D physical systems, including the chaotic Navier-Stokes equations. Our method achieves stable generation without structural divergence, significantly improves the stability-accuracy trade-off compared to state-of-the-art methods, and substantially accelerates inference with respect to exact projection strategies. Code available at: https://github.com/ispamm/Projection-free-energy-guided-flow-matching.

cs.LG · physics.comp-ph

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06710

Where Is VLA Inference Time Spent? Bottlenecks and Optimization Interactions Across GPUs

Muhammad Danish Waseem, Ahmed Ali-Eldin Hassan

原文摘要

Vision-language-action (VLA) models map camera observations and language instructions to robot actions. However, their large backbones and repeated action generation can make inference take longer than the robot's real-time requirements for its next action. To reduce the load of VLA computations, researchers have proposed multiple optimization approaches, including quantization and pruning. These optimizations can be combined with other general optimizations such as better kernel compilation or using CUDA graphs instead of the eager mode. However, most of these optimization results are usually reported on a single GPU type, typically for a few VLA models, with no analysis of what the real bottlenecks are for a model on a particular hardware or how these optimizations would generalize beyond the reported results. In this paper, we provide a comprehensive measurement study of seven families of inference optimization methods, from CUDA graphs and compilation to token pruning and quantization, on seven state-of-the-art VLAs evaluated on four GPU families ranging from a datacenter H100 to an embedded Jetson Thor. We analyse how CPU launch overhead, memory bandwidth, and kernel efficiency jointly shape optimization gains, and how applying one method changes the benefit of another. From this analysis, we derive VLA-Triage, guidelines for stacking optimizations under latency budgets. The guidelines identify which stages can provide the required savings and which combinations need testing in the deployed execution mode.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06701

Agent-Driven Generative Priors for Pathology Image Synthesis and Segmentation

Sicheng Yang, Rui Tang, Haipeng Zhou, Hongqiu Wang, Zhaohu Xing, Jianda Ma, Lie Dai, Guang Yang 等 9 位作者

原文摘要

Deep learning methods for pathology are constrained by the limited availability and high cost of large-scale pixel-level annotations. Synthetic data can alleviate this limitation, but existing pipelines often lack reliable quality control and remain weakly connected to downstream analysis. To address these issues, we propose a three-stage framework that integrates automated data screening, generative representation learning, and efficient adaptation to downstream tasks. First, we develop a pathology agent system to assess image quality and filter samples, resulting in TCGA-200K, a dataset containing 217,030 pathology patches selected from the public TCGA repository. Second, we train a generative model on the screened data. In addition to image synthesis, its backbone learns structural and semantic representations that can be transferred to downstream tasks. Third, we adapt the pretrained generative backbone to semantic segmentation using a lightweight task-specific head. We further introduce PathSeg-380K, a semantic segmentation dataset with expert annotations for approximately 380,000 cells across 12 cell types. Experiments on multiple pathology datasets show that the proposed framework achieves state-of-the-art segmentation performance. Our code is publicly available at https://github.com/script-Yang/Agent-GenPath.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2607.16097

Understanding Reasoning from Pretraining to Post-Training

Jingyan Shen, Ang Li, Salman Rahman, Yifan Sun, Micah Goldblum, Matus Telgarsky, Pavel Izmailov

原文摘要

Reinforcement learning (RL) has become central to improving large language models (LLMs) on complex reasoning tasks, yet RL post-training is largely studied in isolation from the pretraining that precedes it. As a result, two basic questions remain open: (1) how do pretraining choices (model size, data) shape the returns to RL compute, and (2) what does RL actually do to the model? These questions are difficult to study in the standard LLM setting: pretraining corpora are vast and uncontrolled, making it hard to attribute behaviors to pretraining versus RL, and systematic compute sweeps across both stages are prohibitively expensive. To address these challenges, we use chess as a controlled testbed for studying reasoning across the full pretraining-to-post-training pipeline. We follow the standard LLM training pipeline by pretraining language models from 5M to 1B parameters on human chess games, supervised fine-tuning on synthetic reasoning traces, and running RL on chess puzzles with verifiable rewards. Using this framework, we find that the post-RL performance at given RL compute level is well-predicted from the pretraining loss, and slope of the RL reward curves improves approximately linearly with the pretraining tokens. Beyond scaling, we find that RL does not simply sharpen the SFT policy: on easy puzzles it amplifies correct moves the SFT policy already preferred, while on hard puzzles it surfaces correct moves that were nearly absent under SFT. We further test whether our findings transfer beyond chess by training a 1B language model on math-domain text, where the same predictive pattern emerges: longer-pretrained checkpoints reach higher post-RL performance and improve faster under RL. In sum, we provide a quantitative account of the pretraining-to-RL interface and a controlled testbed for studying the science of reasoning across the full pretraining-to-post-training pipeline.

cs.LG · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2607.02131

AbsoluteDegradation: A Physics-Inspired Synthetic Film-Degradation Pipeline and Archival Film Restoration Benchmark

Mikołaj Jastrzębski, Dawid Glinkowski, Dawid Zieliński, Daniel Borkowski, Wojciech Kozłowski, Kamil Adamczewski

原文摘要

Restoring archival film remains a fundamentally challenging problem due to the absence of paired training data and the lack of standardized evaluation benchmarks. Pristine versions of deteriorated footage are physically unrecoverable, requiring supervised methods to rely on synthetic data that often fail to capture the complex, temporally coherent nature of real film degradation. At the same time, existing real-world datasets are limited in scale, quality, and accessibility, hindering reliable evaluation and fair comparison across methods. We address both limitations with AbsoluteDegradation, a physics-inspired, modular pipeline for synthesizing realistic film degradations, and a new large-scale archival benchmark. The proposed pipeline models the analog-to-digital process as a structured composition of artifact families, incorporating signal-dependent grain, parametric scratches, and temporally coherent camera motion, enabling controlled generation of diverse degradation regimes. In parallel, we introduce a curated dataset of 81,576 high-resolution frames sourced from real archival footage, designed for consistent evaluation under real-world conditions. Together, these contributions provide a unified framework for training and benchmarking restoration models. Experiments across six restoration architectures, evaluated with no-reference image quality metrics, clip-level temporal quality assessment, and a blinded human preference study (93 raters, 1,395 trials), show that models trained with AbsoluteDegradation generalize better to real-world footage: human raters preferred them in 64.7% of comparisons and for every evaluated architecture. The proposed benchmark also reveals systematic failure modes of current methods and of no-reference metrics. We hope this work establishes a foundation for reproducible and domain-authentic evaluation in archival film restoration.

cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2607.20757

GaugeQuant: Online Learning of Quantization-Optimal Bases from LLM Symmetries

Miguel P. Bento, João F. Seabra

原文摘要

Transformers are known to have internal continuous symmetries that leave outputs invariant while altering how activations are distributed across coordinates, and hence how well they quantize. GaugeQuant leverages this in-training by introducing a LogSumExp term to the loss that breaks the symmetries, thus selecting a basis that minimizes activation outliers. A stop-gradient operator ensures that only rotation matrices are updated, yielding the language modeling objective completely unaltered. Our quantization strategy requires no specific calibration data, no quantization simulation, and adds a small inference overhead. As a proof of concept, we evaluate on WikiText-2 perplexity and zero-shot reasoning. On Qwen-2.5 0.5B, GaugeQuant reduces perplexity (e.g. $25.62 \to 16.76$ under W4A16) and improves zero-shot accuracy. On LLaMA-2 7B, perplexity improves but downstream accuracy does not. The code is available at: https://github.com/MPedraBento/gauge-quant.

cs.LG · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.35160

AutoEnergyDesign: An LLM-Driven Agent for Automatic Energy System Design Optimization

Amedeo Buonanno, Salvatore Fabozzi, Maria Valenti

原文摘要

The design optimization of building energy systems represents a complex, high-dimensional search problem involving discrete technology selections, continuous sizing parameters, and intricate economic trade-offs in which every candidate must be evaluated by a year-long simulation. This paper presents AutoEnergyDesign, in which a Large Language Model (LLM) agent reasons over past simulation results, proposes configuration changes and learns in context from each outcome, while a git-based mechanism reverts changes that do not improve the design. The agent couples a reasoning model with explicit memories, a constrained action interface, and an environment-grounded keep/revert feedback signal. The simulator covers eight technologies and computes the 25-year Net Present Cost (NPC). On a case study with measured building loads, the agent, instantiated with three Claude models (Haiku 5.5, Sonnet 5.5 and Opus 5.5; ten runs of 50 simulations each), is compared with random search, Tree-structured Parzen Estimator (TPE) Bayesian optimization and a (1+1) evolution strategy that shares the agent's acceptance rule (ten seeds of 300 evaluations). With all three models the agent reaches an NPC of 3.53MEUR, 1.20% and 0.23% below the best results of TPE and of the evolution strategy, and comes within 1% of it after a median of 18 to 27.5 simulations; among the baselines, only the evolution strategy does so, after a median of 192 evaluations. Every decision is recorded, making the search auditable.

cs.AI · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06688

Don't Replace, Complement: A Detector-Agnostic Subspace Signal for Near-OOD Detection

Wonseok Shin, Songkuk Kim

原文摘要

Post-hoc out-of-distribution (OOD) detection is mature on far-OOD yet remains weak on near-OOD. These two settings differ in their use of class-characteristic feature directions: far-OOD inputs largely fail to activate those of their predicted class, whereas near-OOD inputs activate them much as in-distribution samples do. Because the axis separating far-OOD leaves near-OOD almost indistinguishable from ID, a score optimized for one setting is misaligned with the other; where a detector already saturates far-OOD, added near-OOD sensitivity is bought partly against it. This divergence motivates a targeted near-OOD signal designed to complement existing scores. We propose PLUS (Per-class Low-dimensional sUbspace Signal). For each class, PLUS selects the $m$ most class-active neurons from a sparse autoencoder, orthonormalizes the corresponding decoder directions to form a low-dimensional subspace, and scores an input by its per-class whitened squared Mahalanobis distance $z$ within the subspace of its predicted class. Designed as a dedicated complement rather than a standalone detector, the signal $z$ is fused additively with any calibrated base score at a single, fixed weight. This weight is a single global constant: no value is adjusted per backbone, per OOD dataset, or per deployment, and all calibration statistics are estimated from ID validation data alone. When applied to 18 existing detectors spanning diverse method families, $z$ consistently improves near-OOD AUROC in all 126 detector--backbone combinations. Far-OOD performance is broadly maintained or improved, with only marginal declines where the base score is near-optimal, making $z$ a robust, detector-agnostic complement across backbones.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06687

LifeVal: Evaluating AI Model Performance on Personalized Agentic Consumer Tasks

Jenny Yang, Elizabeth Proehl, Anjan Bharadwaj, Emily Fan, Charlotte Cole, James Kim, Noam Brown, Phoebe Thacker 等 10 位作者

原文摘要

We introduce LifeVal, a benchmark evaluating AI model performance on personalized agentic consumer tasks. LifeVal covers the most valuable life tasks that a personalized digital superassistant could automate, representing over 1.7 trillion US dollars in annual willingness-to-pay across 148 consumer task categories (e.g., managing finances, moving apartments, searching for a job, finding childcare). To construct our activity distribution, we conducted a new survey of willingness-to-pay for a digital superassistant across a demographically representative sample of over 3,800 consumers, cross-referencing our results against the American Time Use Survey (Bureau of Labor Statistics, 2025) and the Multinational Time Use Study (Fisher et al., 2025). For the most valuable consumer activities, we recruited task creators to create AI evaluation tasks personalized using real ChatGPT conversations and memories, reference files, and personal context. Task creators had to pass our expertise threshold (including personally completing the task multiple times and seeing the results through in their real lives for over a year) and also write a rubric, ensuring that our evaluation measured the best personalized completion for that task. All tasks had to pass at least three rounds of human quality-control before acceptance into our final evaluation sets.

cs.AI

查看论文
arXiv ↗PDF ↗