跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+197新增论文
+151其中 AI 相关
+16已有论文修订
+91新增 AI 导读

arXiv 最近完成扫描:2026-11-21 12:19 · 全站最近入库:2026-11-21 12:19各信源进度 →

统计口径与数据新鲜度

统计 2026-11-21 04:40 — 2026-11-22 04:40(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:2026-11-21 12:19最近发现新增版本:2026-11-21 12:19库内论文最新更新时间:2026-11-20 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。

29,158 已收录论文24,181 AI 相关8,992 有修订112 HF 社区发现

浏览论文库

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

找到 21,490 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-21 12:17(北京时间)
新论文 · v1arXiv:2611.21517

Lazy-MOSAIC:利用学习到的技能效果世界模型加速以技能为中心的操控规划

Lazy-MOSAIC: Accelerating Skill-Centric Manipulation Planning with Learned Skill-Effect World Models

Itamar Mishani, Mukund Krishnakumar, Oren Salzman, Maxim Likhachev

AI 速读 基于摘要

Lazy-MOSAIC 通过廉价的学习技能效果世界模型预测技能可行性与结果,将昂贵仿真集中在有希望的候选技能上,从而加速以技能为中心的长时程操控规划。

cs.RO · cs.AI

查看原文摘要

Long-horizon manipulation tasks require a robot to perform a sequence of physical interactions with its environment, typically combining several different skills. Planning such behaviors efficiently is challenging: given a library of parameterized skills, solutions lie in a vast hybrid space of skill sequences and their parameters, and evaluating each candidate skill's feasibility and effect with a high-fidelity world model such as a physics simulator is computationally expensive. MOSAIC, a recent skill-centric approach, lets the skills guide a non-sequential search toward the regions of this space where they are likely to succeed; however, it pays the full cost of simulation for every parameterized skill it considers. In this work, we introduce Lazy-MOSAIC, a lazy planning framework that instead searches over hypothesized skill outcomes. A cheap learned skill-effect world model predicts, in a fraction of a millisecond, a skill's feasibility and the world state it produces. Lazy-MOSAIC then uses these predictions to focus expensive simulation on promising candidate skills and, when a hypothesis is invalidated, repairs only the affected part of the search, while ensuring that every skill in a returned plan is validated in simulation. We evaluate Lazy-MOSAIC on cluttered-shelf retrieval tasks of increasing difficulty and demonstrate it on a physical robot, showing that it plans substantially faster than baselines with fewer simulator queries, while matching or exceeding their success rate in every setting. Visit skill-mosaic.github.io.

版本更新 · v2arXiv:2610.13597

A Systematic Study of Security Enforcement at Android Inter-Component Boundaries

Sandiyo Christan A

原文摘要

Android's inter-process communication (IPC) mechanisms (Activities, Services, BroadcastReceivers, ContentProviders, and URI scheme handlers) form the primary interface between applications and between applications and the system. We present a systematic study of security enforcement comprising 120 evaluations (99 inter-component interface evaluations across five interface categories, 10 platform security-control evaluations, and 11 dedicated positive controls) in over 30 Google and AOSP packages on Android 17 (API 37). Using an expected-versus-observed framework under a zero-permission attacker model, we evaluate whether each boundary's enforcement mechanism functions as designed. We find 97 enforcement gaps (80.8%) and 23 enforcement holds (19.2%). From these observations, we derive a 14-category enforcement gap taxonomy organized across manifest, code, platform, and architectural layers. Within our purposively selected corpus, observed enforcement outcomes differ substantially across interface categories: evaluated Activities and BroadcastReceivers exhibit a 100% gap rate, while ContentProviders, which benefit from framework-provided defenses such as setStrict(), achieve a 27.6% holds rate. We find that all seven evaluated platform compatibility changes with security intent are either disabled or gated at a targetSdkVersion that none of the applications in our evaluated corpus targets. We document 18 custom URI scheme registrations handling sensitive data (authentication tokens, payment credentials, medical information) despite the known unverifiability of custom schemes (RFC 8252 Section 8.1). Our study includes 23 positive controls, calibration cases demonstrating that the evaluation procedure distinguishes functioning enforcement from observed enforcement failures.

cs.CR

新论文 · v1arXiv:2611.21514

Tensorized Automata: Algebraically Informed Representation Learning for Sequential Decision Making

Anand Balakrishnan, Dweep Trivedi, Swarat Chaudhuri

原文摘要

Task representations for sequential decision making should describe both an objective and progress toward it. We present an algebraically informed pipeline that uses the relational structure and language semantics of alternating finite automata (AFAs) to learn control features and compile compact execution operators. AND-OR message passing learns task and state vectors; selected configurations define an event-driven Boolean matrix operator. We prove that initial and successor language coverage make its carrier represent the exact residual after every prefix, with a sufficient capacity bound in terms of reachable configurations. Conjunction and disjunction use the same pipeline. Fidelity and composition audits evaluate copied formulas and learned disjunct assignments. In five-policy-seed XLand experiments with larger training pools, pooled execution-state vectors outperform raw carrier bits and task-blind conditioning across three task pools under two rejection rewards. They achieve 77.3\% success on multi-event tasks and 99.4\% on a four-task stratum with 33--128-state minimal DFAs, using 16 operator slots. LetterWorld results show useful residual conditioning alongside a remaining gap to RAD. These results connect algebraically informed representation learning to compact task execution and useful policy conditioning.

cs.FL · cs.LG

版本更新 · v2arXiv:2605.13487

Path-independent Flow Matching for Multi-parameter Generative Dynamics

Francisco Téllez, AmirHossein Zamani, Philippe Martin, Shuang Ni, Guy Wolf, Eugene Belilovsky, Sina Sanjari, Yanlei Zhang

原文摘要

Flow Matching is a powerful framework for learning transport maps between probability distributions. Yet its standard single-parameter formulation is not designed to capture multi-parameter variations where the resulting transport should be path-independent. Path independence is crucial because it ensures that transformations depend only on the initial and target distributions, not on the specific path. In this work, we introduce Path-independent Flow Matching (PiFM), a method for learning vector fields whose induced flows yield path-independent transport between distributions. We show that PiFM generalizes Flow Matching to higher-dimensional parameter domains while enforcing structural conditions that ensure consistency of composed transformations. In addition, we show that, under suitable assumptions, PiFM approximates the Wasserstein barycenter, linking the framework to a notion of distributional interpolation. To enable practical training, we propose a tractable, simulation-free objective that regresses onto multi-parameter conditional probability paths. We showcase empirically that PiFM outperforms other approaches on both synthetic and real world data in interpolating path-independent trajectories and generating desired out of distribution samples.

cs.LG

新论文 · v1arXiv:2611.21511

退化性与k-核的分布式计算下界

Lower Bounds for the Distributed Computation of Degeneracy and k-Core

Lélia Blin, Yan S. Couto, Cristina G. Fernandes, Pierre Fraigniaud, Marcos Kiwi, Pedro Montealegre, Ivan Rapaport

AI 速读 基于摘要

该论文证明在CONGEST模型中,近似计算图的退化性(或判定2-退化性)需要显著超过直径D的轮数,从而排除了O(D)+o(n)轮算法的可能性。

cs.DC

查看原文摘要

The degeneracy of a graph $G$ is the maximum integer $k$ such that $G$ has a non-empty $k$-core, where the $k$-core is the largest induced subgraph with minimum degree $k$. Computing the $k$-core of a graph $G$ is P-complete. In the decentralized setting, the sequential peeling algorithm can be distributed so that the core value of every node, i.e., the largest integer $k$ for which the node belongs to the $k$-core, is computed in $O(n)$ rounds in $n$-node networks, where adjacent nodes exchange only $O(\log n)$ bits at each round, i.e., in the standard CONGEST model. However, while $Ω(D)$ rounds is a trivial lower bound for these problems in networks of diameter $D$, this does not rule out the existence of an algorithm running in $O(D)+o(n)$ rounds in CONGEST, as it is the case for many very important graph problems, including MST. We show that it is unlikely that such an algorithm exists, or, if it does exist, then it requires $\tildeΩ(\sqrt{n})$ rounds. Specifically, our first main result states that, for any $ε>0$, approximating the degeneracy up to a multiplicative factor $2-ε$ requires $\tildeΩ(\sqrt{n})$ rounds in CONGEST even in networks of diameter $O(\log n)$, and still $\tildeΩ(n^{1/3})$ rounds in networks of constant diameter. We also show that improving this lower bound seems challenging, as we demonstrate that the newer frameworks cannot be used as black boxes to obtain a better lower bound for degeneracy. Our second main result provides a better bound, albeit conditional. It states that, unless the well-known circuit value problem (CVP) admits a parallel polynomial speedup -- an outcome considered unlikely -- it holds that, for every $ε>δ>0$, deciding whether a graph is 2-degenerate cannot be solved in $O(D+ n^{1-ε})$ rounds with $O(n^δ)$-time parallel local computation per round at each node.

新论文 · v1arXiv:2611.21509

几乎受控:加权保形p值上Benjamini-Hochberg方法的FDR

Almost Controlled: The FDR of Benjamini-Hochberg on Weighted Conformal p-Values

Ryan Lim

AI 速读 基于摘要

作者证明加权保形p值下BH的FDR在有限样本中可能超过目标水平,并给出超额上界与实用调整规则。

stat.ME · cs.LG · math.ST · stat.ML

查看原文摘要

Weighted conformal p-values generalize conformal inference to cases with covariate shift. One way to use them is to pass them to the Benjamini-Hochberg (BH) procedure, either to decide which test units to select or to detect outliers. But weighted conformal p-values may not be positively dependent, so we want to know: does BH still control the false discovery rate (FDR) in finite samples? Based on experiments, it appears to, but we prove it doesn't. We give two counterexamples, certified in exact rational arithmetic, where the FDR exceeds its target level $q$. We also identify how large the difference between the FDR and $q$ can be. With $n$ calibration points, $m$ test units and weight ratio $B$, the relative excess $\mathrm{FDR}/q-1$ is bounded by a function of $n$, $m$, $B$ and $q$ that is of order $\sqrt{Bm/(nq)}$ when $Bm/(nq)$ is small. The bound holds for every configuration with $B\le n$ and every $n$. This order can be reached when multiple non-null test units share a common threshold: in a Poisson-limit model, that configuration's excess is $c(q)\sqrt{Bm/(nq)}$ to first order as $B/n\to0$ and then $m\to\infty$. For some fixed distributions with this structure, the excess decreases only like $n^{-1/2}$ as $n$ grows. If every test unit is null, the excess is $O(B/n)$ at fixed $m$, and in certain configurations it grows linearly with $m$. To assist practitioners in judging how large the FDR can be, we turn that bound, which depends only on $n$, $m$, $q$ and $B$, into a lowered BH level with proved finite-sample control, and give a much less conservative rule of thumb that covers every worst case we were able to find but provides no guarantee.

版本更新 · v2arXiv:2611.09140

SPDMX: Large-Scale Open Stem Audio From Symbolic Music

Phillip Long, Eduardo Escoto, Julian McAuley, Zachary Novack

原文摘要

Large public datasets have driven recent progress in machine learning, from text and vision to speech and general audio. Music remains an outlier, as copyright blocks redistribution of training audio, in particular for modern tasks that need individual stems rather than mixtures. Existing multitrack resources trade off realism, scale, and licensing, as synthetic alternatives rely on proprietary VSTs or naive open rendering that yields weak stems. We introduce SPDMX, an openly-licensed stem corpus rendered from the public-domain PDMX dataset. SPDMX comprises $5{,}469$ song-hours ($2{,}734$ song-hours, or $34.8\%$, of which are multitrack scores) at $44.1$ kHz under CC BY 4.0, with paired MIDI and identifiers that link our dataset to PDMX's original metadata. To our knowledge, SPDMX's multitrack subset constitutes the largest openly-licensed synthetic multitrack subset by song-hours. We then demo SPDMX as a dataset for both source separation and transcription, showing how its increased scale can enable better training of models on synthetic data. We release SPDMX, as well as the open creation pipeline for reuse on other symbolic music datasets.

cs.SD · cs.AI · cs.LG · cs.MM · eess.AS

新论文 · v1arXiv:2611.21507

GHySSeg:面向混合固态激光雷达的实时几何地面与道路分割

GHySSeg: Real-Time Geometric Ground and Road Segmentation for Hybrid Solid-State LiDAR

Martín Palos, Fernando García

AI 速读 基于摘要

提出纯几何方法GHySSeg,从单帧混合固态LiDAR数据中实时分割地面与可行驶道路,并发布首个公开基准HySoLiD-Drive。

cs.RO · cs.CV

查看原文摘要

Hybrid solid-state LiDAR sensors are making their way into production vehicles, yet the data they produce differs structurally from that of the established spinning mechanical sensors behind today's autonomous-driving datasets: it is ring-free, dense, cluttered, and concentrated in a frontal field of view. The classical geometric methods that autonomous vehicles rely on for drivable space computation and navigation assume the ordered ring-and-column structure of a 360-degree spinning LiDAR and degrade or fail on this data, while learned alternatives are computationally heavy, hard to certify, and trained almost exclusively on spinning-LiDAR data. We demonstrate that the same dense, per-curve geometry is instead an opportunity to close the divide between the industry's preferred sensors and autonomous-driving research. We present GHySSeg, a purely geometric method that segments ground and drivable road from a single hybrid solid-state LiDAR frame by tracing each scan curve and reading two geometric signatures, a step in height and a fold-back in range, with no training and no graphics processing unit. To evaluate it, we release HySoLiD-Drive, the first public benchmark dedicated to ground and road segmentation on an automotive hybrid solid-state LiDAR, comprising 100 manually labeled and 7000 unlabeled frames recorded by two vehicles in real driving. On this benchmark, GHySSeg surpasses both geometric and learned state-of-the-art baselines across ground and road segmentation, reaching an intersection-over-union of 0.907 for road and 0.896 for ground at over 0.96 precision, while running in real time at about 22 milliseconds per frame on a single core.

新论文 · v1arXiv:2611.21504

杠杆增强采样的Owen方法:面向可解释人工智能

Leverage-Enhanced Sampling Owen Method for Explainable Artificial Intelligence

Jing Liu, Elena Parilina, Chi Zhao

AI 速读 基于摘要

作者在Owen多线性扩展框架下提出一种结合分层采样与联盟杠杆分数的采样估计方法,用于高效近似Shapley值。

cs.GT · cs.LG

查看原文摘要

Recently, the Shapley value has been widely applied in machine learning for feature importance analysis and model explainability. The multilinear extension of games proposed by Owen (1972) expresses the Shapley value as the integral of partial derivatives along the main diagonal of the cube. Direct evaluation of this integral requires exponential-time computation of the partial derivatives. To improve computational efficiency, we propose a sampling-based estimation strategy within Owen's multilinear extension framework, combining stratified sampling with coalition leverage scores. Experimental results demonstrate that the proposed method significantly reduces computational costs while maintaining explanation accuracy.

新论文 · v1arXiv:2611.21501

代码是我的吗?当AI智能体编写规格说明和代码时学生的所有权

Is This Code Mine? Student Ownership When AI Agents Write the Spec and the Code

Gustavo Pinto, Enne Rebeca Silva de Freitas, Danilo Monteiro Ribeiro

AI 速读 基于摘要

在AI智能体编写大部分规格和代码的课程作业中,学生虽自认拥有想法却难以解释或修改代码,且自报贡献与提交记录不符,因此教学评估应关注学生能指定、审查和解释的内容而非交付物。

cs.SE

查看原文摘要

Software engineering courses are starting to ask students to build entire systems with AI coding agents, but little is known about what students actually do with them and whether they still own what they deliver. If the agent writes both the code and the decisions behind it, the artifacts we grade no longer show what students learned. We studied an assignment in which 18 pairs of students built applications with agents under Spec-Driven Development, combining the mined history of their repositories, the prompts they recorded, and a survey of 33 students. The agents wrote 69\% of the specifications meant to keep students in control, sometimes from a prompt of a few words. Students locate their ownership in the ideas, crediting themselves with half of them but a fifth of the code, yet most could not explain that code to a colleague or modify it without the agent, and what they report having written is unrelated to what their own commits declare. The three teams that met the 100,000-line target did so with generated code the application never uses, in one case proposed by the agent itself, and one team rewrote its history to backdate its specifications. Teaching with agents should therefore assess what students specify, review, and can explain, rather than what they ship, and enforce the engineering process with tools rather than trusting it to students or agents.

新论文 · v1arXiv:2611.21500

Exponential Quantum Memory Advantage for Late-Graph Smoothness and Spectral Estimation

Burhan Gülbahar

原文摘要

Graph signal processing tests how smoothly the decisions of next-generation massive sensor networks with $N$ nodes vary over their neighbour graph. Memory becomes the bottleneck when the neighbour graph arrives only after data erasure, a late-graph setting motivated by dispersed sensor networks and telemetry. We analyse three collection scenarios, reliable rounds, continuous broadcast and ordered capture, and test the Dirichlet energy $\mathcal E_G=\mathbf z^{\mathsf T}\mathbf L\mathbf z/N$ of the fused decision map $\mathbf z\in\{\pm1\}^N$, with late-graph Laplacian $\mathbf L$, against two thresholds. Hidden Matching uses $O(\log N)$ qubits on fused bits, but in reliable rounds and continuous broadcast, where nodes report $b$ sub-bits separately, a classical record buffer before it uses $O(N b)$ bits; classical methods need $Ω(\sqrt N)$ bits in the worst case. The recently introduced Quantum Oracle Sketching builds quantum oracles from random data streams without storing them. We combine coherent loading of separately reported sub-bits, exact in reliable rounds and by Quantum Oracle Sketching in continuous broadcast, with nonlinear fusion and Hidden Matching readout. The register count $R$ does not grow with $N$, and the memory is $O(\log N)$ logical qubits and classical bits, at fixed $b$, graph bounds, thresholds and error targets: an exponential memory advantage over every classical receiver and over Hidden Matching with that buffer. We prove unbiasedness in reliable rounds, preparation bounds in continuous broadcast, classical lower bounds and, for a planner-supplied multi-hop coefficient stream, spectral error bounds. Broadcast simulations match analytic averages at $N=1024$, without resolved bias growth up to $N=2^{20}$. Fault-tolerant hardware, gate rates and, in continuous broadcast, report counts remain open.

quant-ph · cs.IT · eess.SP

新论文 · v1arXiv:2611.21498

A Polynomial-Time Algorithm for Maximum Witness Set

Satyabrata Jana, Debabrata Pal, Sasanka Roy

原文摘要

A witness set in a polygon is a set of points whose visibility regions are pairwise disjoint. Since no point of the polygon can see more than one witness, the cardinality of a witness set provides a lower bound on the minimum number of guards required to cover the polygon. Finding a maximum witness set is therefore a natural packing counterpart to the classical Art Gallery problem. While the latter is $\exists\mathbb{R}$-complete, the computational complexity of finding a maximum witness set in a general simple polygon has remained open. In this paper, we present a polynomial-time algorithm for computing a maximum witness set in a simple polygon with $n$ vertices, of which $ρ$ are reflex, assuming that no three vertices are collinear. Our algorithm runs in $\mathcal{O}(ρ^4n^6\log n)$ time. Our approach exploits a tree structure induced by witness visibility regions and employs geometric dynamic programming over nested regions determined by visibility windows.

cs.CG

新论文 · v1arXiv:2611.21497

CYBER-BRIDGE项目:面向欧盟跨境网络安全、合规与取证的人工智能平台

The CYBER-BRIDGE project: An AI-Powered Platform for Cross-Border Cybersecurity, Compliance and Forensics in the EU

Nikolaos Kekatos, Georgios Koutidis, Charalampos Bratsas, Stefan Bucur, Alexandra-Mihaela Chirlejan, Mihaela Curcă, Angelos Fountoulakis, Michael Ioannou 等 15 位作者

AI 速读 基于摘要

CYBER-BRIDGE项目提出统一架构与哈希链证据层,将AI驱动的威胁情报共享、多框架合规评估和跨境数字取证整合,以弥合欧盟中小企业和关键基础设施运营者的网络韧性差距。

cs.CR · cs.AI · cs.CY

查看原文摘要

Cross-border cyber attacks on European SMEs and critical-infrastructure operators expose a structural cyber-resilience gap: cybersecurity (threat sharing, detection, response), compliance (framework assessment, certification) and digital forensics (cross-jurisdictional evidence) are jointly regulated by NIS2, the CRA, GDPR and the LED, yet their tooling evolved in silos and rarely interoperates across Member States. The EU-funded CYBER-BRIDGE project integrates the three domains under one architecture and a hash-chained evidence layer: AI-driven CTI sharing with ENISA-aligned notification, multi-framework assessments with retrieval-augmented advisory, and RFC 3161-anchored custody with lawful GDPR/LED exchange, all aligned with MITRE ATT&CK. A sanitised replica of the back-end image hosts a Cyber-Range for upskilling. The contribution is not the individual tools but the reconciliation mechanism that lets one incident produce, from a single evidence record, a cross-border CTI advisory, the regulatory notifications its deadlines demand and a re-verifiable forensic pack; we set out why binding three differently regulated evidence regimes onto one record is non-trivial and how the shared evidence layer resolves the resulting tensions. This paper introduces the project's scope, requirements, pilots, architecture and toolkits; quantitative KPIs follow in later deliverables.

新论文 · v1arXiv:2611.21486

Differentiable Exact Learning

Hristo Papazov, Francesco D'Angelo, Nicolas Flammarion

原文摘要

We introduce a framework for differentiable exact learning that couples an unbounded external environment to a state-tracking neural controller, which we train on policy-trajectory observations (PTOs): expert behavior traces that expose observations and actions while hiding internal states. In addition to the learning framework, we introduce Differentiable Finite-State Transducers (DFSTs) which use multilinear updates, support log-parallel training, and emulate arbitrary finite-state controllers, yielding computational universality through environmental interaction. From tiny training datasets, compact DFSTs achieve extreme length generalization on arithmetic and universal-simulation tasks. We replicate the success of DFSTs on RNNs and GRUs, thereby supporting a broader learning recipe: State-Tracking Controller + Unbounded External Environment + PTOs = Extreme Length Generalization. Beyond length generalization, our metric-extraction protocol recovers interpretable discrete controllers from trained DFSTs, which we prove equivalent to the target arithmetic and universal-simulation algorithms. Furthermore, for our Softmax DFST models, simply taking $\mathrm{argmax}$ over the transition probabilities yields discrete controllers which provably exactly perform universal Turing-machine simulation and binary arithmetic. Proving exact learning for the neural controllers requires assumptions, which we empirically support. We make our code, training recipes, model weights, and proof checkers publicly available at https://github.com/fanagor/DEL.

cs.LG · cs.AI · cs.FL · stat.ML

版本更新 · v2arXiv:2602.00092

通过宪法解释与控制模型行为:基于原子概念编辑

Interpreting and Controlling Model Behavior via Constitutions for Atomic Concept Edits

Neha Kalibhat, Zi Wang, Prasoon Bajpai, Drew Proud, Wenjun Zeng, Been Kim, Mani Malek

AI 速读 基于摘要

提出一种黑盒可解释性框架,通过原子概念编辑学习可验证的自然语言“宪法”,以解释和控制模型在多种任务中的行为。

cs.LG · cs.AI · cs.CL · cs.CV

查看原文摘要

We introduce a black-box interpretability framework that learns a verifiable constitution: a natural language summary of how changes to a prompt affect a model's specific behavior, such as its alignment, correctness, or adherence to constraints. Our method leverages atomic concept edits (ACEs), which are targeted operations that add, remove, or replace an interpretable concept in the input prompt. By systematically applying ACEs and observing the resulting effects on model behavior across various tasks, our framework learns a causal mapping from edits to predictable outcomes. This learned constitution provides deep, generalizable insights into the model. Empirically, we validate our approach across diverse tasks, including mathematical reasoning and text-to-image alignment, for controlling and understanding model behavior. We found that for text-to-image generation, GPT-Image tends to focus on grammatical adherence, while Imagen 4 prioritizes atmospheric coherence. In mathematical reasoning, distractor variables confuse GPT-5 but leave Gemini 2.5 models and o4-mini largely unaffected. Moreover, our results show that the learned constitutions are highly effective for controlling model behavior, achieving an average of 1.86 times boost in success rate over methods that do not use constitutions. Our open-sourced code can be found at https://github.com/google-deepmind/atomic_concept_edits

新论文 · v1arXiv:2611.21485

迷失在走廊:跨重访的持久空间记忆基准测试

Lost in the Hallway: Benchmarking Persistent Spatial Memory Across Revisits

Henry Zheng, Weibo Gong, Yang Yue, Rui Huang, Yang Zhang, Gao Huang

AI 速读 基于摘要

作者提出ReSpaceBench基准,用于评估具身智能体在多次重访中保持空间记忆的能力,发现现有模型与人类差距显著。

cs.CV

查看原文摘要

Persistent spatial understanding is essential for embodied agents to operate reliably in environments they repeatedly encounter. It requires recognizing revisited places despite viewpoint changes, distinguishing them from similar-looking rooms, and updating memories as environments change. Yet existing evaluations often leave physical place identity across separated visits implicit. We introduce ReSpaceBench, a benchmark comprising 3,244 questions across 590 synthetic and real-home scenes, organized into 9 tasks spanning room association, persistent state tracking, and downstream reasoning. Controlled walkthroughs define visits by physical room entry and deliberately include same-type room distractors and cross-session object changes. Our evaluation of 32 models and 3 agentic video-understanding frameworks reveals substantial limitations: the strongest evaluated zero-shot model achieves 50.5% overall accuracy and 52.2% on a 450-question subset, compared with 90.1% for human annotators. The evaluated agentic frameworks offer no overall improvement over direct inference with the same base model. Analysis of agent execution traces reveals evidence omissions and incorrect cross-visit room associations as major failure modes, suggesting that iterative evidence seeking alone does not ensure consistent spatial memory. Further analyses expose a gap between recognizing familiar rooms and identifying the correct visited room, while annotation-guided sampling highlights the importance of preserving intervening visits and transitions. We also provide RS-30K, a separate training dataset from synthetic sources with no template, scene, route, or video overlap with the benchmark. Fine-tuning Qwen3-VL-8B raises overall accuracy from 35.5% to 60.4%, with the largest gains in association and improvements extending to real-life scenes.

新论文 · v1arXiv:2611.21477

知识发酵:从共享变异中学习的小样本分类

Knowledge Fermentation: Learning from Shared Variation in Few-Shot Classification

Ali Mohammadi Ruzbahani, Abbas Yazdinejad, Hadis Karimipour

AI 速读 基于摘要

知识发酵(KF)通过让类别交换关于变异的知识,恢复二阶知识,从而提升小样本分类性能。

cs.IT

查看原文摘要

A classifier built from a handful of labeled examples knows where each class sits in feature space but not how it varies, which is why prototype rules and linear probes overfit in the low-data regime. Knowledge Fermentation (KF) recovers this second-order knowledge by letting classes exchange what they know about variation. Residuals around class prototypes act as carriers; the variance of each direction is measured on classes that took no part in estimating it, and directions above the level of the surrounding medium define a structured noise that acts on a linear classifier as a closed-form change of geometry. A convex objective trains the classifier at a noise strength calibrated on the distances between prototypes, and unlabeled examples, when available, join as carriers in repeated rounds. We prove that the held-out variances are unbiased for the directions on which they are measured, that the fermented map never expands a direction, and that damping caused by wrong assignments limits itself. On 14 datasets from vision and language and 8 frozen encoders, with all constants fixed, KF is on par with the best of six tuned inductive baselines. With unlabeled carriers it raises one-shot accuracy from 52.4% to 65.8% on average and attains the highest average accuracy among nine transductive methods, significantly so on vision encoders, while information maximization stays ahead on sentence encoders. Controlled studies attribute the gain to the task-level geometry and show that it grows with the within-class variation that the classes of a task share.

新论文 · v1arXiv:2611.21476

生成式AI与高等教育评估危机:审视大学水平评估的“防AI”策略

Generative AI and the Crisis of Higher Education Assessments: Examining 'AI-Proofing' Strategies for College-Level Assessments

Bonam Mingole, Davis Yadav, Hui Min Lee, S. Shyam Sundar, Amulya Yadav

AI 速读 基于摘要

该研究收集了17个学科、37位教师设计的75道大学评估题,测试三种先进LLM的答题表现,并分析教师“防AI”策略是否有效约束模型。

cs.AI

查看原文摘要

Higher education is confronting an academic-integrity challenge unlike any in its history. Students can now outsource homework, take-home assignments, and online examinations to large language models (LLMs) that complete them in seconds. Existing research on evaluating LLM performance on academic assessments has focused largely on standardized examinations, or on questions from college-level courses drawn from a single discipline. Far less is known about how LLMs perform on college-level assessment questions spanning multiple disciplines, that instructors have purposely designed to be AI-resistant, and about which features of such questions, if any, meaningfully constrain LLM performance. We address this gap by collecting 75 questions from authentic college coursework assessments, spanning 17 disciplines, which were contributed by 37 faculty members from ten U.S. universities and one U.K. university. Of these, 61 questions were intentionally designed by faculty members to be 'LLM-proof', while the remaining 14 questions were sourced from online courses. We then (i) evaluate three state-of-the-art LLMs' ability to correctly answer these questions with and without supplementary course materials; (ii) identify five strategies, through thematic analysis, that faculty used to make their questions harder for LLMs to solve; and (iii) test whether these strategies impact LLMs' ability to answer the questions accurately. Our experimental results show that the best-performing model scored approximately 83% without supplementary course materials and 85% with them, and we observed noteworthy differences across models, answer formats, and instructor tweaking strategies. We discuss implications for assessment design, academic-integrity policy, and the broader ethics of deploying LLMs in educational settings.

新论文 · v1arXiv:2611.21473

Network Intrusion Detection Adaptability under Spurious Labels: A Noise-Aware Few-Shot Class-Incremental Learning Framework

Zijian Zhao, Davide Di Monda, Domenico Ciuonzo, Yipeng Wang, Antonio Pescapè

原文摘要

Network Intrusion Detection Systems (NIDSs) must incrementally adapt to emerging attacks, even when only a limited amount of labeled network traffic is available. Consequently, Few-Shot Class-Incremental Learning (FSCIL)-based NIDSs have gained growing attention. However, existing FSCIL-based NIDSs are highly vulnerable to label noise in newly-observed attack classes. To address this limitation, we propose NAFN, a noise-aware FSCIL-based NIDS framework that reduces the impact of mislabeled data during incremental adaptation. NAFN consists of two components: (i) Noise Detection, which identifies and removes mislabeled biflows using noise-detection algorithms, and (ii) Feature Sampling, which estimates class-conditional embeddings from clean biflows, calibrates them with base-class statistics, and resamples synthetic features to recover the original biflow count. The framework follows the Rethink Few-Shot (RFS) teacher-student paradigm with lightweight nearest-neighbor or logistic regression classifiers, and various pretraining & memory selection strategies. Experiments on CSE-CIC-IDS2018, Edge-IIoT, and IoT-NID datasets show that NAFN effectively preserves prior knowledge and maintains strong incremental performance even under 50% label noise, consistently improving new-class F1-scores over non-denoised baselines, up to +52%, while being time-efficient and robust in cross-network and high-noise incremental settings. The implementation is publicly available to foster reproducibility.

cs.NI · cs.AI · cs.LG

版本更新 · v3arXiv:2602.12612

Self-EvolveRec:基于LLM方向性反馈的自演化推荐系统

Self-EvolveRec: Self-Evolving Recommender Systems with LLM-based Directional Feedback

Sein Kim, Sangwu Park, Hongseok Kang, Wonjoong Kim, Jimin Seo, Yeonjun In, Kanghoon Yoon, Hyunsik Jeon 等 9 位作者

AI 速读 基于摘要

提出Self-EvolveRec框架,通过用户模拟器提供定性批评、模型诊断工具提供定量内部验证,构建方向性反馈闭环,并让诊断工具与模型协同演化,以改进LLM驱动的推荐系统代码演化。

cs.IR · cs.AI

查看原文摘要

Traditional methods for automating recommender system design, such as Neural Architecture Search (NAS), are often constrained by a fixed search space defined by human priors, limiting innovation to pre-defined operators. While recent LLM-driven code evolution frameworks shift fixed search space target to open-ended program spaces, they primarily rely on scalar metrics (e.g., NDCG, Hit Ratio) that fail to provide qualitative insights into model failures or directional guidance for improvement. To address this, we propose Self-EvolveRec, a novel framework that establishes a directional feedback loop by integrating a User Simulator for qualitative critiques and a Model Diagnosis Tool for quantitative internal verification. Furthermore, we introduce a Diagnosis Tool - Model Co-Evolution strategy to ensure that evaluation criteria dynamically adapt as the recommendation architecture evolves. Extensive experiments demonstrate that Self-EvolveRec significantly outperforms state-of-the-art NAS and LLM-driven code evolution baselines in both recommendation performance and user satisfaction. Our code is available at https://github.com/Sein-Kim/self_evolverec.

新论文 · v1arXiv:2611.21469

变分正确的物理信息算子学习用于非线性偏微分方程

Variationally correct physics-informed operator learning for nonlinear partial differential equations

Yuan Qiu, Wolfgang Dahmen, Peng Chen

AI 速读 基于摘要

作者提出并验证了一种基于一阶系统最小二乘残差的物理信息算子学习方法,用于非线性偏微分方程,其损失在理论上等价于PDE合规范数下的误差,并在数值上优于网格基线。

math.NA · cs.LG

查看原文摘要

Physics-informed operator learning trains neural operators on the residual of a parametric partial differential equation (PDE) instead of labeled solution data, but its reliability depends on a variationally correct residual: one that is equivalent to the error in a norm dictated by the equation, the PDE-compliant norm. For nonlinear equations written as first-order systems, we prove that the first-order system least-squares residual is equivalent to the error in this norm near a solution branch if the linearized residual is stable and the residual derivative is Lipschitz continuous, possibly in a norm stronger than the error norm. We verify these conditions for monotone reaction, solution- and gradient-dependent diffusion, and compressible Neo-Hookean hyperelasticity. The stability mechanisms vary across these classes, as do the regions where the equivalence holds, from arbitrary bounded sets to a neighborhood of the branch. In a conforming finite element space, we show that the loss excess of a state near the finite element solution is equivalent to its squared distance from that solution. We use this loss to train a reduced basis neural operator with values in this space, with solution snapshots needed only for the basis and the loss and its symbolically derived gradient assembled by the finite element library. At inference, this loss estimates the error. Numerically, the square root of the loss excess tracks the error within factors comparable to those of the linear case, and the operator achieves higher accuracy in the PDE-compliant norm than grid-based baselines evaluated in the same finite element space.

版本更新 · v3arXiv:2608.26932

Contact-Aided Factor-Graph Localization for Underwater Sampling

Michele Grimaldi, Yosaku Maeda, Hitoshi Kakami, Ignacio Carlucho, Yvan R. Petillot, Tomoya Inoue

原文摘要

Accurate state estimation for autonomous underwater vehicles performing close-range seafloor sampling remains challenging. In low-altitude operation, down-looking cameras over featureless planar seabeds produce scale ambiguity, lateral degeneracy, and inconsistent feature tracking. Meanwhile, inertial-Doppler Velocity Log (DVL) fusion alone provides no mechanism for structural drift correction. We propose a Contact-Aided Factor-Graph Localization framework that treats physical interaction as an informative geometric constraint within a smoothing-based localization formulation. The method tightly fuses suction-based manipulator contact events with adaptive visual odometry, learned object detections, and on-board sensors. Visual odometry relative-pose factors and landmark bearing-range factors are uncertainty-scaled according to inlier statistics to prevent visually weak frames from destabilizing the estimator, while contact events are modeled as high-confidence factors that induce implicit loop closures without appearance-based place recognition. Furthermore, the system can fully initialize online during motion. Experimental evaluation in tanks, harbor, and simulation environments demonstrates that contact-induced constraints significantly reduce trajectory drift and improve object revisit accuracy compared to filtering-based navigation and contact-free graph formulations. These results highlight the role of embodied physical interaction as a localization primitive in perception-degraded underwater environments

cs.RO

新论文 · v1arXiv:2611.21465

用少量雅可比样本热启动神经动力学模型

Warm Starting Neural Dynamics Models From Few Jacobian Samples

Maxime Rochkoulets, Joppe De Jonghe, Mariya Ishteva

AI 速读 基于摘要

提出 TDec-Init,利用少量转移雅可比样本通过张量分解解耦出权重与非线性,从而热启动神经网络动力学模型。

cs.LG · cs.AI · eess.SY

查看原文摘要

Model-based reinforcement learning (MBRL) leverages a model of the environment, used for planning and generating samples without interacting with the real world. Motivated by evidence that informed initialization significantly improves the efficiency of MBRL, we propose TDec-Init, an algorithm to warm-start neural dynamics models using transition Jacobians. Using a decoupling algorithm based on the decomposition of a tensor of stacked Jacobian samples, we recover weights and flexible nonlinearities, and use them to initialize a feedforward neural network. In the low-data regime, we show on several benchmark environments that our approach outperforms random initialization and value training, and either matches or outperforms Sobolev training, while requiring fewer training steps between episodes.

新论文 · v1arXiv:2611.21461

ExRel:面向富文本 K-12 题目图像的可执行关系契约学习有向复用相关性

ExRel: Learning Directed Reuse Relevance between Rich-Text K-12 Question Images with Executable Relation Contracts

Xuexin Liu, Zengyi Wo, Shiyu Zhang, Suqi Cheng, Daiting Shi, Xiuyi Chen

AI 速读 基于摘要

ExRel 用可执行关系契约从真实题目合成可控、可验证的有向复用相关性监督数据,在 Medium 关系上优于规模匹配的自然数据与重放基线。

cs.IR

查看原文摘要

In K-12 education, question images combine text, mathematical expressions, diagrams, and diverse layouts. Variations in wording, conditions, answer options, or task scope can substantially alter their reuse utility despite visual similarity. We formulate this problem as directed reuse relevance, grading candidate utility as Strong, Medium, or Weak. However, generic similarity scores overlook task-specific reuse requirements, while natural supervision is dominated by Strong relations and lacks fine-grained coverage. We propose ExRel, an agentic, code-grounded framework for controllable and verifiable visual data synthesis. It reconstructs real questions into editable HTML/CSS seeds and compiles 15 relation subtypes into executable contracts specifying permitted edits, protected invariants, and query-candidate direction. Synthesized pairs undergo deterministic DOM/render validation and target-hidden, evidence-assisted review, with bounded repair before mild photographic degradation. Only rendered images are used for downstream training. Experiments show that ExRel supervision outperforms size-matched natural data and count- and class-matched replay, particularly on Medium relations, while maintaining comparable query-level ranking performance and improving robustness to visual degradation. Construction ablations demonstrate higher valid yield and fewer false admissions than less structured baselines. Human audits confirm 98.0% post-admission validity, while ExRel achieves a lower per-accepted-pair cost than outsourced annotation (0.70 vs. 1.10 RMB). Downstream answer routing further demonstrates the practical utility of the synthesized supervision.

新论文 · v1arXiv:2611.21458

面向标注任务中人口统计分歧建模的可扩展多任务学习框架

A Scalable Multi Task Learning Framework for Modeling Demographic Disagreements in Annotation Tasks

Soumyajit Gupta, Maria De-Arteaga, Matthew Lease

AI 速读 基于摘要

提出 Stakeholder-Aware Joint Multi-Task Learning(SAJ-MTL)框架,联合建模标注者群体之间与群体内部的人口统计分歧,并支持按任务定制群体权重。

cs.CL · cs.LG

查看原文摘要

Annotators from different demographic backgrounds often disagree in systematic ways due to varying lived experiences, cultural contexts, and their relationship to the content. When such disagreement occurs, one group's perspective may sometimes warrant prioritization because they hold an epistemically advantaged standpoint or bear greater stake in the outcome. For example, when assessing toxicity of posts on social media, it may be important to prioritize a targeted group's viewpoint. We propose a Stakeholder-Aware Joint Multi-Task Learning (SAJ-MTL) framework to jointly model demographic disagreement both across- and within- annotator groups. The model uses conditional gradient routing to handle sparsity induced by group-conditional labeling, and parameterization supports customized weighting of groups in different task settings. SAJ-MTL improves group-level performance in toxicity detection through better context-aware understanding of demographic-sensitive content. Only annotator group-membership information is required, which is more practical than existing methods requiring more privacy-invasive individual-level annotator details. Our scalable architecture is also computationally efficient to support large-scale deployment.

新论文 · v1arXiv:2611.21456

Expertise capture in workplace AI

Andreas Ekelhart, Ahmad Mohsin, Iqbal H. Sarker, Helge Janicke

原文摘要

AI assistants are becoming part of how knowledge workers think and perform, accumulating the prompts, exemplars, memory and interaction histories that encode a worker's professional judgment. This infrastructure typically runs under employer or platform control. We name the resulting process expertise capture, the absorption of worker-applied knowledge and judgment into AI resources under organizational control. We develop a framework of contribution forms, technical residences and transformation families, and show that how far a contribution can be attributed, separated and revoked depends on where it resides and how it has been transformed, properties fixed by system design long before any dispute arises. When a worker departs, the organization retains a capability shaped by their judgment while the worker loses access to it, and the asymmetry compounds as contributions move from inspectable artifacts into derivatives, learned components and successor systems. We outline three measures, write-time provenance, extraction of separable contributions and an executable exit procedure, that make an agreed allocation technically performable, and make explicit what cannot be separated at all.

cs.CR · cs.AI

新论文 · v1arXiv:2611.21455

Synthetic Doubt and the Integrity of Digital Proof before the International Criminal Court

Seyed Mohammad Sadegh Dashti

原文摘要

Generative artificial intelligence complicates evidentiary assessment at the International Criminal Court by enabling fabricated audiovisual material and making authentic digital evidence easier to dismiss as fake. This article calls the latter problem synthetic doubt: an objection alleging that a digital item may be AI-generated or AI-manipulated. Existing scholarship addresses digital evidence, open-source investigations and deepfakes in the ICC context. Yet the question of when synthetic doubt should trigger enhanced reliability review under the Rome Statute, without displacing the prosecution's burden under article 66 or compromising article 67 fair-trial rights, remains underdeveloped. The article proposes a three-stage framework: a baseline authenticity and provenance showing by the proponent; a case-specific articulation threshold for the objector; and proportionate reliability review by the Chamber under articles 64 and 69(4). The framework treats AI-related provenance information and synthetic-media detector outputs as contextual rather than dispositive.

cs.CY

新论文 · v1arXiv:2611.21454

Comments on "Deep Fréchet Regression"

Jianbin Tan, Anru R. Zhang

原文摘要

We discuss the Journal of the American Statistical Association (JASA) discussion paper "Deep Fréchet Regression" and explore an alternative perspective based on conditional flow matching. We propose learning covariate-dependent transport directly within the response space, avoiding separate manifold learning and reverse mapping. This perspective offers a potentially more flexible framework for incorporating geometric structure and modeling full conditional distributions.

stat.ML · cs.LG

新论文 · v1arXiv:2611.21453

Reducing Asymmetric Path TSP to Asymmetric TSP

Hong Li

原文摘要

In the Asymmetric Traveling Salesman Problem (Asymmetric TSP), we are given distances between $n$ vertices that satisfy the triangle inequality but need not be symmetric, and we seek a shortest tour through all vertices. In its path version, Asymmetric Path TSP, two vertices $s$ and $t$ are prescribed, and we seek a shortest path from $s$ to $t$ through all vertices. Both problems are equivalent to their versions with arbitrary nonnegative edge costs on a directed graph, in which vertices may be visited more than once. We show that for all constants $α\ge1$ and $\varepsilon>0$, any $α$-approximation algorithm for Asymmetric TSP yields an $(α+\varepsilon)$-approximation algorithm for Asymmetric Path TSP. The best previous reduction of this kind, due to Feige and Singh, yields an $α(2+\varepsilon)$-approximation algorithm. Our result answers an open question of Traub and Vygen. Consequently, every constant-factor approximation guarantee for Asymmetric TSP carries over to Asymmetric Path TSP up to an arbitrarily small additive error.

cs.DS

版本更新 · v2arXiv:2611.15992

The multiplicative complexity of the three-bit low-half multiplier

Bshara Alhodali, Gregory Morse

原文摘要

We prove that the multiplicative complexity of the three-bit low-half multiplier is six, giving a structural, enumeration-free lower-bound proof valid against unrestricted nonlinear reuse in Boolean XOR-AND circuits. The value was first established by SAT searches of the first author and independently confirmed by the second author. An explicit six-AND circuit supplies the upper bound. The lower bound combines derivatives, quadratic products, complementary minors, and extraction modulo a Boolean ideal. Independent finite checks accompany the arguments. $\mathrm{MC}(M_3)=6$ is fully formalized in Lean 4, using only Lean's three standard axioms (propositional extensionality, choice and quotient soundness).

cs.CC · cs.LO · math.CO