跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+479新增论文
+361其中 AI 相关
+64已有论文修订
+93新增 AI 导读

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

统计口径与数据新鲜度

统计 2026-11-15 23:17 — 2026-11-16 23:17(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-16 01:34最近发现新增版本:2026-11-16 21:56库内论文最新更新时间:2026-11-14 02:59

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

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

浏览论文库

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

找到 23,827 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-16 01:33(北京时间)
新论文 · v1arXiv:2611.11465

When Normality Shifts: Multi-Level WavLM Modeling for Open-World Audio Deepfake Detection

Daniel Niekurzak, Daniel Kozuch, Weronika Folwarska, Khan Muhammad, Rafał Scherer

原文摘要

Audio deepfake detectors trained with known synthesis attacks can learn generator-specific shortcuts that fail as synthesis systems and acoustic conditions evolve. We investigate an attack-free alternative: a normality model trained exclusively on bona fide speech, which scores synthetic audio by its deviation from authentic representations. We propose MLN-WavLM, a method that applies shrinkage-Mahalanobis modeling to pooled hidden states from a frozen large-scale, pre-trained speech processing WavLM Base+ architecture. Evaluated on ASVspoof 2019 LA, our best attack-free variant achieves an 8.45\% Equal Error Rate (EER), closely tracking a fully supervised WavLM-HM-Conformer baseline (7.86%). However, when subjected to the ASVspoof 2021 DF domain shift, performance drops to 22.12% EER, exposing vulnerabilities in the bona-fide-calibrated operating point. Layer-wise analysis reveals that early WavLM representations dominate the ensemble. To test real-world viability, we simulated deployment streams using unlabeled threshold adaptation. While robust median/MAD recalibration easily handles in-domain contamination up to 10%, recalibrating under the 2021 DF domain shift triggers a total collapse of low-FPR recall. We conclude that while frozen source-domain normality can effectively rank deepfakes, it does not yield a stable open-world decision rule, and downstream threshold adaptation cannot rescue upstream ranking degradation.

cs.SD · cs.LG

新论文 · v1arXiv:2611.11464

Off-Policy RL with Online Inference Tuning: My Solution to the CoRL 2026 RoboEval Challenge

Ilia Larchenko

原文摘要

The CoRL 2026 RoboEval challenge has eight bimanual tasks, and it ranks a policy not only on whether it succeeds but on how: every stage of the task, done safely, efficiently and with both arms in coordination, scored against human demonstrations. My solution has two parts. The generic part, carried over from my LeHome challenge solution, is off-policy RL on a $π_{0.5}$-based policy that is also its own value function. It is trained with AWR and RECAP on advantages of the exact official score, in a loop where every rollout is at the same time a Thompson-sampling trial of about 20 inference parameters. Out of the box, it took the policy to 0.85 RDS on held-out seeds in two days (and it was still very far from convergence). The competition-specific part adds data that local exploration cannot find: generated demonstrations that reach the full reward, and recovery episodes that start from the policy's own failures. The submitted policy reaches 0.990 RDS on held-out seeds and 0.987 on the official seeds.

cs.RO · cs.CV · cs.LG

新论文 · v1arXiv:2611.11461

Sharp Rates for Optimal Recovery of Bandlimited Functions from Localized Oversampling

Wentao Huang, Haizhang Zhang

原文摘要

It is well-known that one can recover a function $f$ bandlimited to $[-δ,δ]$ ( $0<δ<π$) from its finite sample data $f(j),-n\le j\le n$, with an approximation error exponentially decaying to zero as $n$ tends to infinity. Various regularized Shannon sampling formula have been proposed to achieve such exponential approximation. So far the best rate has been $$ O\biggl(\frac1{\sqrt{n}}\exp(-(π-δ)n)\biggr). $$ We establish that the optimal recovery algorithm in the worst-case scenario achieves an approximation error $ρ_{n,δ}$ satisfying $$ c_* \frac1{\sqrt{n}}(\tan\fracδ4)^{2n+1/2}\le ρ_{n,δ}\le C^* \frac1{\sqrt{n}}(\tan\fracδ4)^{2n+1/2}, \quad 0<δ\leqπ,\quad n\geq1, $$ where $c_*,C^*$ are positive constants independent of $n$ and $δ$. This result identifies the best possible exponential rate to reconstruct bandlimited functions from two-sided finite oversampling data. In other words, $$ ρ_{n,δ} \asymp \frac{\tan\fracδ4}{\sqrt{n}}\exp\bigl(-c_δ(π-δ)n\bigr), $$ where $c_δ$ is strictly decreasing on $(0,π]$ and $$ \lim_{δ\toπ^-}c_δ=1,\ \lim_{δ\to 0^+}c_δ=+\infty. $$ We also make the new finding that one can also reconstruct $f$ bandlimited to $[-δ,δ]$ with exponentially decaying error from one-sided sample data $f(j)$, $1\le j\le n$, and the sharp rate of approximation error $ρ_{n,δ}'$ of the optimal algorithm is $$ ρ_{n,δ}' \asymp \sqrt{δ/π}\sin^n(δ/2). $$

cs.IT · math.CA

新论文 · v1arXiv:2611.11460

Identifiable alignment of unpaired representations

Stas Syrota, Albert Lopez I Serrano, Johanne Franck, Søren Hauberg

原文摘要

Aligning two models without paired data requires a distance that both share, yet existing methods use Euclidean or spherical geometry. This is either an arbitrary choice or imposed by their loss function. We show that, under a precise form of the manifold hypothesis, the pullback of the data metric gives such a distance for any two models of one data-generating process. This holds whether the models are encoders, decoders or both, and whatever their architecture, loss, prior or training data. The alignment map preserves this distance and the distribution of representations, and is identifiable if and only if the data distribution breaks every symmetry of the data manifold. We show that this symmetry breaking holds generically. Identifiability makes the alignment coupling the unique optimum of Gromov--Wasserstein and of its weighted combinations with a linear program. The linear program alone has the same optimum if almost every data point has a distinct distribution of distances. The coupling, and with it the alignment map, is recovered exactly from permuted samples, even without identifiability, and consistently from independent ones. Our method, Neural Gromov--Monge Alignment (NGMA), uses no pairs or labels and outperforms every unpaired and label-informed baseline. It relies on pullback distances to align image models with different priors and single-cell models trained on disjoint cells, where Euclidean distances fail.

stat.ML · cs.AI · cs.LG · stat.ME

版本更新 · v3arXiv:2502.04058

Explanation Design in Strategic Learning: Sufficient Explanations That Induce Non-harmful Responses

Kiet Q. H. Vo, Siu Lun Chau, Masahiro Kato, Yixin Wang, Krikamol Muandet

原文摘要

We study the design of explanations in algorithmic decision-making with strategic agents, individuals who may modify their inputs in response to explanations of a decision maker's (DM's) predictive model. While the demand for algorithmic transparency has led much prior work to assume full model disclosure, in practice DMs typically provide only partial information via explanations, which can cause agents to misinterpret the model and take actions that unintentionally reduce their own utility. A central open question is therefore how DMs should communicate explanations that avoid harming strategic agents while still supporting their own goals, e.g., minimising predictive error. In this work, we analyse widely used explanation methods and establish a necessary condition to prevent explanations from inducing self-harming responses. Furthermore, we show that action recommendation-based explanations (ARexes), which encompass counterfactual explanations, are sufficient to induce all non-harmful responses. Under a conditional homogeneity assumption, this sufficiency extends to ARex-generating methods, echoing the revelation principle in information design. To demonstrate their practical utility, we introduce a simple learning procedure that jointly optimises the predictive model and the explanation-generating policy. Experiments on both synthetic and real-world tasks show that ARexes enable DMs to achieve high predictive performance while preserving agents' utility, offering a principled strategy for safe and effective partial model disclosure.

cs.AI

版本更新 · v2arXiv:2609.30212

Anchored Extra-Proximal Methods: Optimal Higher-Order Methods for Monotone Inclusion Problems

Ruichen Jiang, TaeHo Yoon

原文摘要

We characterize, up to logarithmic factors, the optimal higher-order oracle complexity of finding approximate solutions to composite monotone inclusion problems, formed by the sum of a smooth single-valued monotone operator and a maximal monotone set-valued operator. We introduce the Anchored Extra-Proximal (AEP) framework, which combines an anchored extrapolation step with an inexact anchored proximal update satisfying a relative-error condition. This framework recovers the composite Fast Extragradient method in the first-order setting and yields natural higher-order extensions through Taylor approximations of the smooth operator at the extrapolated point. For every $p\geq 2$, assuming that the $(p-1)$th derivative of the single-valued operator is $L_p$-Lipschitz continuous and the initial distance to a solution is at most $R$, we combine AEP with a bisection line search to obtain a $p$th-order method that attains a tangent residual of at most $\varepsilon$ in $\widetilde{O}((L_p R^{p}/\varepsilon)^{\frac{2}{3p-1}})$ oracle calls. We complement this result with a worst-case lower bound of $Ω((L_p R^p/\varepsilon)^{\frac{2}{3p-1}})$ for every deterministic algorithm in the $p$th-order oracle model, without imposing any prescribed update structure. For the subclass of smooth nonexpansive fixed-point problems, we further establish a lower bound of $Ω(\min\{R/\varepsilon, {(L_p R^{p}/\varepsilon)}^{\frac{2}{3p-1}}\})$. By choosing between AEP and Halpern iteration, we match this lower bound up to logarithmic factors, thereby also settling the deterministic oracle complexity of smooth nonexpansive fixed-point problems.

math.OC · cs.LG · stat.ML

新论文 · v1arXiv:2611.11457

MOMENT-DP: Momentum Aware Evaluation of Correlated Noise for Differentially Private Training

Sunny Gupta, Raja Viswanadha

原文摘要

Temporally correlated noise can substantially improve the utility of differentially private optimization, yet candidate mechanisms are commonly designed or evaluated using only partial information about the optimization process, such as workload structure, learning-rate schedules, or local curvature. We study whether persistent optimizer state provides additional information that can change the relative utility of privacy-valid correlated-noise mechanisms. We introduce MOMENT-DP, an optimizer-state-aware framework that models how temporally correlated privacy noise propagates through momentum-based optimization. For locally quadratic objectives, MOMENT-DP expresses privacy-induced final loss through an optimizer transfer operator that jointly captures curvature, learning-rate scheduling, momentum, and temporal noise covariance. NoiseCurve's curvature-aware quadratic criterion is recovered exactly as the zero-momentum, constant-learning-rate special case. Changing only momentum while holding curvature, schedule, privacy calibration, and candidate mechanisms fixed induces genuine mechanism-ranking reversals. The effect persists outside exact quadratic dynamics in per-example-clipped private logistic regression, while remaining unresolved in the neural regime we study. These results establish optimizer state as an under-modeled, decision-relevant axis in evaluating temporally correlated privacy noise.

cs.LG · cs.AI · cs.DC

新论文 · v1arXiv:2611.11455

Coding Agents Propagate Vulnerabilities in Code Bases

Chenhao Sun, Niels Mündler-Sasahara, Mark Vero, Martin Vechev

原文摘要

LLM-based coding agents are widely used to develop critical production software. Even though coding agents are known to occasionally write vulnerable code, there has not been any investigation into how code base vulnerabilities evolve over time under coding agent contributions. In this work, we close this gap by investigating whether and how vulnerabilities in existing code lead coding agents to introduce similar vulnerabilities in the code they write. We first evaluate coding agents on 96 tasks that require implementing a new backend application in a repository where other applications already exist. Second, we investigate repository-level code generation on 20 pairs of tasks in real C/C++ projects. In each task, the agent is asked to complete code critical to memory safety. We find that in both settings, insecure existing code leads to agents writing vulnerable code more often. In backend generation, insecure neighbors reduce the share of correct and secure implementations by 3.4% on average, and in C/C++ repository-level coding, the average gap between secure and insecure contexts reaches 35.4%. Prompting to follow existing code-style or to be careful about security increases, respectively decreases, how strongly agents propagate vulnerabilities, but neither stops them. When asked to explain their implementation choices, coding agents attribute them to following another code site in 76.5% of cases, even though they recognize the introduced vulnerability in 69.9% of cases. These findings show that agents use existing vulnerabilities as templates for new ones indiscriminatorily, turning each contribution into an opportunity to introduce more vulnerabilities. As such, as agents write a growing share of production code under decreasing human review, code bases can increasingly degrade in security if security vulnerabilities are not thoroughly fixed continuously.

cs.CR

版本更新 · v3arXiv:2611.06194

Cross-Asset Knowledge Transfer for Early Fault Detection of Data-Scarce Assets Without Target Fault Data

Zekai Wang, Yuxuan Li, Zhangyue Shi

原文摘要

Reliability management of industrial fleets depends on early fault warnings, yet lifecycle data across similar assets are highly imbalanced. A few assets accumulate run-to-failure histories, while newly installed or rarely failing assets provide only normal-condition data. This paper asks how diagnostic knowledge can be transferred from a data-rich source asset to a data-scarce target asset when no fault data have been observed on the target. We formulate cross-asset early fault detection as a zero-shot domain adaptation problem, in which zero-shot refers to the absence of target fault samples, and propose a framework that requires only normal data from the target. The framework comprises (1) a statistical process control step that labels the source asset run-to-failure data with an exponentially weighted moving average chart, reducing manual annotation to verifying flagged segments, (2) an Adapted Domain-Adversarial Neural Network (ADANN) that combines domain-adversarial training and a Maximum Mean Discrepancy penalty with an Adapted Classification-Domain (ACD) loss, which anchors the classifier normal region to the target own normal data, and (3) an ahead-of-time labeling scheme with a prediction horizon that targets incipient faults. Under an exact-classification assumption, a theoretical analysis characterizes the domain-adversarial term for a normal-only target and the alignment state in which source fault features remain separated from target normal features. On a public run-to-failure bearing dataset, ADANN attains the highest mean F1-score among four transfer baselines, with a nominally significant precision gain over the strongest baseline, and its robustness is examined under synthetic noise.

cs.LG

版本更新 · v5arXiv:2607.11976

LiteTopK: Exploiting the Curse of Dimensionality for a Fused Indexer-TopK Kernel in Long-Context Sparse Attention

Ziqi Yin, Jianyang Gao, Peiqi Yin, Jiangneng Li, Gao Cong

原文摘要

Indexer-TopK, which computes scores and selects the top-$k$ candidates, is a key primitive in long-context sparse attention for large language models, vector retrieval for recommendation systems, and vector databases. However, existing GPU-based Indexer-TopK kernels like DeepSeek Sparse Attention (DSA) typically separate scoring from selection and materialize the full score matrix in high-bandwidth memory. This strategy is inefficient for large score matrices, such as those encountered in long-context sparse attention, due to excessive global-memory traffic, costly synchronization, and prohibitive memory overhead. In this study, motivated by the curse of dimensionality, we observe that sparse attention scores exhibit a score concentration phenomenon, with scores falling within a narrow range. Based on this observation, we propose LiteTopK, a sample-filter-select framework that estimates query-data score ranges from a small subset of the data. It uses these estimates to filter scores as they are computed, materializes only the candidates that pass the filter, and selects from the surviving candidates. In particular, we develop two implementations of LiteTopK. The first uses a conservative threshold estimate, while the second pairs a predicted threshold with a fallback strategy. Building on LiteTopK, we further propose LiteDSA, which reuses overlapping key/value entries across neighboring queries to accelerate attention computation. We integrate LiteTopK into vLLM, SGLang, and Megatron-LM. Our evaluation on eight B200 GPUs demonstrates prefill speedups of up to 1.49$\times$ across GLM-5.2, DeepSeek-V4-Flash, and Hy-4-Preview at a context length of 1M tokens, without compromising model capabilities.

cs.LG

新论文 · v1arXiv:2611.11452

Semantically Aligned KV Cache Compression for Efficient Agentic Autoregressive Video Generation

Weizhong Huang, Huaijia Kou, Tianyu Xie, Xiawu Zheng, Liujuan Cao

原文摘要

Agentic autoregressive video generation combines semantic planning, sequential generation, and visual verification for controllable synthesis. Growing visual histories enlarge the key-value (KV) cache, increasing memory use and attention costs across candidate rollouts. Existing compression methods primarily optimize individual generators without the planner's semantic constraints, risking low priority for states supporting requested attributes or actions. We introduce SemanticKV, a training-free method for semantically aligned KV cache compression. To our knowledge, SemanticKV is the first KV cache compression method for agentic autoregressive video generation that explicitly uses planner-extracted semantic constraints to guide retention. Text cross-attention identifies constraint-related video positions, whose self-attention queries are collected into separate groups. Attention weights are averaged within each group and maximized across groups, giving each cached entry a high score when strongly used by any represented constraint. A single top-k selection retains high-scoring entries under the memory budget, leaving their keys, values, and positions unchanged. For fixed query groups and equal entry costs, this selection minimizes an additive upper bound on worst-group discarded attention. The method operates independently within each candidate without retraining or additional video generations. We evaluate four AR video backbones on three benchmarks for 5-, 30-, and 60-second generation. On Causal Forcing at a compression ratio of 0.7, SemanticKV obtains a VBench Total Score of 84.10, compared with 84.05 for the strongest compressed baseline and 83.99 for Full KV. It achieves a 1.22x speedup over Full KV and reduces KV-cache memory from 6.04 GB to 1.81 GB, a 3.35x reduction.

cs.CV · cs.LG

版本更新 · v2arXiv:2604.00858

Statistical Physics of Coding for the Integers

Neri Merhav

原文摘要

We study a paradigm of coding for compression of the natural numbers via the zeta distribution and develop a statistical-mechanical interpretation, both in terms of Hagedorn systems and a Bose gas with energy levels given by logarithms of prime numbers. We also propose a simple coding scheme for the zeta distribution that nearly achieves the ideal code length. For block coding of vectors of natural numbers, we derive the micro-canonical entropy function and demonstrate its asymptotic linearity implying that its behavior is analogous to that of a Hagedorn system. We also derive the large deviations rate function, and provide a formula for the best coding parameter in the large deviations sense. We show that due the Hagedorn-type phase transition there is only partial equivalence of ensembles, due to the degeneration of the domain of the partition function.

cond-mat.stat-mech · cs.IT

版本更新 · v2arXiv:2610.41558

A complete analytical characterization of optimal collision-free motion for two robots

Jan Kamm, Antonio Terpin, Raffaello D'Andrea

原文摘要

Collision-free motion planning for multi-agent robotic systems remains an active research area because of the complexity of coordinating robot trajectories, with applications ranging from coordinated drone shows to autonomous operations on land, in the air, and on water. Importantly, the analytical difficulty of nonconvex collision-avoidance constraints has so far driven the development of exclusively numerical methods. We derive a complete analytical characterization of the optimal trajectories for two robots with zero initial and final velocities, under double-integrator dynamics and a squared-acceleration objective. We prove that these trajectories belong to eight distinct contact families and determine which family applies for each configuration of initial and final positions. We analyze the geometrical properties of the optimal trajectories and provide a numerical algorithm for computing them. These insights have already been adopted to improve the performance of numerical methods for multi-agent motion planning by several orders of magnitude.

cs.RO · eess.SY · math.OC

新论文 · v1arXiv:2611.11450

How Much Training-Inference Mismatch Can On-Policy Distillation Tolerate?

Cong Yu, Ziting Wang, Songlin Jiang, Sitong Zhang, Chengliang Chai, Youhe Jiang, Eiko Yoneki, Tuo Shi

原文摘要

On-policy distillation (OPD) trains a student language model on its own responses, guided by a fixed teacher. Generating these responses is expensive, so systems use quantized inference and asynchronous rollouts to reduce the cost. Both, however, introduce training-inference mismatch between the rollout engine and the model being trained. Such mismatch can destabilize reinforcement learning (RL), but its effects on OPD remain unclear. This paper investigates how much mismatch OPD tolerates, where its effects arise, and how training systems can use this tolerance. Measuring all mismatch sources on one scale, we examine quantization across three student-teacher pairs, with additional tests of weight staleness and injected noise on one pair. OPD tolerates substantial mismatch without meaningful loss of training quality but degrades at higher levels, revealing an empirical mismatch budget. Both the quality cost of mismatch and the mismatch introduced by quantization depend on the model, with some layers particularly sensitive to reduced precision. In controlled comparisons, OPD remains stable under rollout configurations that destabilize RL methods. Under weight noise, mismatch also shifts the prefixes reached during generation, introducing errors that per-token corrections cannot address. To put these findings into practice, we introduce a lightweight admission check that screens rollout configurations against a calibrated budget without requiring a full training run for each candidate. Model-specific FP8 recipes preserve training quality while providing capacity for at least $1.93\times$ as many KV-cache tokens as BF16. Combining FP8 with asynchronous rollouts reaches the same training quality $1.62\times$ sooner than synchronous BF16 training. Code is available at https://github.com/benyucong/train-inference-mismatch-opd

cs.LG · cs.AI

新论文 · v1arXiv:2611.11447

Learning to Rank Propagators in Constraint Programming

Matija Lojović, Mladen Nikolić

原文摘要

The order in which propagators are executed can substantially affect the performance of constraint programming solvers, yet propagator priorities are typically determined by fixed, manually designed heuristics. In this work, we explore learning instance-dependent propagator priorities from static problem features. We formulate the task as a learning-to-rank problem, addressing the challenge that the quality of a priority assignment can be measured through solver runtime, while the desired priorities of individual propagators are not directly observable. A self-attention-based model jointly scores the propagators present in an instance and is trained using pairwise preferences derived from solver runtimes measured under randomized propagator priority assignments, with a Plackett-Luce-based ranking objective. Predicted rankings are mapped to the discrete priority levels of the Choco solver before search begins, without modifying its propagation or search procedures. We evaluate the approach on XCSP3 instances and demonstrate that propagator ordering can have a substantial impact on solving time. On a test set of 698 instances, picked out as most difficult by problem class, the learned priorities increase the number of solved instances from 634 to 654, reduce median solver runtime by 27.93%, and reduce aggregate penalized runtime (PAR1) by 12.65% compared with Choco's default priorities. We further observe that improvements vary across problem classes and show that a simple policy selecting between learned and default priorities further increases the number of solved instances. These results demonstrate the potential of learning instance-dependent propagator priorities to improve constraint programming performance, particularly on difficult instances.

cs.LG · cs.AI

新论文 · v1arXiv:2611.11444

Tight B-Trees for Adjacency Labeling

Noy Rotbart

原文摘要

We show that planar graphs admit adjacency labels of size $\log n+O(\log\log n)$: every vertex gets a label of this many bits, and the adjacency of two vertices is decided from their labels alone, in constant time. This improves the $\log n+O(\sqrt{\log n\log\log n})$ of Dujmović et al. (J. ACM 2021) and the $\log n+O(\sqrt{\log n})$ of Gawrychowski and Janczewski (SOSA 2022). Equivalently, $n$-vertex planar graphs have an induced-universal graph with $n(\log n)^{O(1)}$ vertices, down from $n2^{O(\sqrt{\log n})}$. The same holds for graphs of bounded genus, apex-minor-free graphs and $k$-planar graphs. For every proper minor-closed class we get $\log n+O(\sqrt{\log n\log\log n})$, down from the $\log n+O((\log n)^{3/4})$ of Dujmović et al. (2026). Both results come from tight B-trees: nodes are split into parts of nearly equal size, so every node but the topmost stays within a factor $1\pm O(1/\log n)$ of its target size, and a root-to-leaf path loses only $O(\log\log n)$ bits.

cs.DS · cs.DM

版本更新 · v3arXiv:2610.33465

LegoSR: A Unified Framework for Self-improving Agent-Guided Scientific Discovery

Hao Mao, Xu T. Liu, Hao Xu, Peng Zhao, Qian Li, Dongxiao Zhang, Jinyue Yan, Yuntian Chen

原文摘要

Discovering equations from data provides governing laws, constitutive relations and closure models for scientific understanding and prediction. Yet a method that succeeds on one system may fail on another or on noisy data, so discovery depends on expert trial and error. Unsuccessful searches can still reveal useful parts of an equation, but these clues must be recognized and combined. We present LegoSR, a unified framework for agent-guided equation discovery built on composable discovery and cumulative experience. Seven complementary equation discovery methods and shared computational modules form reusable building blocks, connected through a common equation representation. Researchers can launch discovery with one command and guide it with partially known equations. LegoSR Agent selects methods, revises searches using feedback and combines partial findings into new hypotheses. Its Experience Library consolidates graded outcomes into lessons that guide later tasks across equation families. Evaluation covers 134 algebraic regression problems, 40 ordinary differential equation targets and 17 partial differential equation problems at several noise levels, together with three case studies. On noisy differential equation benchmarks, LegoSR Agent nearly matches the recovery coverage of seven expert-tuned methods combined and exceeds a generic agent with the same model, tools and budget by up to 29.4 percentage points, with 51-61% shorter median wall-clock time.

cs.AI · cs.LG

版本更新 · v4arXiv:2601.12203

Embryonic Exposure to VPA Influences Chick Vocalisations: A Computational Study

Antonella M. C. Torrisi, Inês Nolasco, Paola Sgadò, Elisabetta Versace, Emmanouil Benetos

原文摘要

In young animals like poultry chicks (Gallus gallus), vocalisations convey information about affective and behavioural states. Traditional approaches to vocalisation analysis, relying on manual annotation and predefined categories, introduce biases, limit scalability, and fail to capture the full complexity of vocal repertoires. We introduce a computational framework for the automated detection, acoustic feature extraction, and unsupervised learning of chick vocalisations. Applying this framework to a dataset of newly hatched chicks, we identified two primary vocal clusters. We then tested our computational framework on an independent dataset of chicks exposed during embryonic development to vehicle or Valproic Acid (VPA), a compound that disrupts neural development and is linked to autistic-like symptoms. Clustering analysis on the experimental dataset confirmed two primary vocal clusters and revealed systematic differences between groups. VPA-exposed chicks showed an altered repertoire, with a relative increase in softer calls. VPA differentially affected call clusters, modulating temporal, frequency, and energy domain features. Overall, VPA-exposed chicks produced vocalisations with shorter duration, reduced pitch variability, and modified energy profiles, with the strongest alterations observed in louder calls. This study provides a computational framework for analysing chick vocalisations, advancing knowledge of early-life communication in typical and atypical vocal development.

cs.SD

新论文 · v1arXiv:2611.11439

SWHForest: A Structural Curation and Search Layer for Large-Scale Code Corpora

Federico Pennino, Andrea Gurioli, Maurizio Gabbrielli, Paolo Ferragina

原文摘要

Pre-training code language models relies on massive code corpora usually streamed over the internet. However, researchers rarely need a multi-terabyte archive in its entirety; instead, their workflow centers on curated subsets: selecting well-documented files, filtering out repetitive boilerplate, auditing for benchmark contamination, or retrieving specific code patterns. Yet, because modern corpora are typically published as file pointers and basic attributes rather than source text, no general structural layer exists to select which files to download: curating a subset requires downloading and parsing millions of files first just to discard most of them. We present SWHForest, an open-source framework and public dataset that provides this missing structural layer for any pointer-based corpus without redistributing source code. A single pass over the archive parses each file into an AST and immediately discards the source text, keeping only its structural summary. Queried locally or exposed by archive providers as a server-side filtering API, SWHForest selects matching files first (via SQL or index intersection) and downloads only surviving candidates. Across the ten largest languages of Stack-Edu (52.1M unique files, 341M definitions), SWHForest answers curation queries in milliseconds while cutting downloads by 46-72%, reducing live structural searches from hours of per-language streaming to seconds or minutes.

cs.SE · cs.LG

新论文 · v1arXiv:2611.11438

When Coding Agents Get Arms: Safety Risks Across the Digital-Physical Boundary

Yiming Sun, Mi Zhang

原文摘要

Advances in spatial understanding have enabled frontier models to power coding agents that control a real robot arm zero-shot and end-to-end, without task-specific demonstrations or retraining. This brings two new safety challenges. First, the extensive knowledge of frontier models lets these agents perform tasks that earlier VLA and WAM paradigms could not, opening the door to new forms of capability misuse. Second, coding agents can access digital resources such as web pages and emails. Threats in these resources, such as indirect prompt injection, can carry over into the physical world when the agent controls a robot. We therefore introduce ArmedAgent, the first systematic benchmark to evaluate both risks for coding agents performing zero-shot robot control. It covers robustness, malicious use, and indirect injection across 36 tasks in 5 scenarios, evaluated in simulation and validated on a physical robot arm. A distinctive portion of the tasks target harmful behaviors that earlier VLA paradigms could not perform. Testing several frontier models, including GPT-6-Astra, under widely used agent frameworks, we find substantial safety risks in current systems.

cs.RO · cs.CR · cs.MM

新论文 · v1arXiv:2611.11437

How to "train" a surgeon? Benchmarking generalist agents in surgical scene understanding

Gengyuan Zhang, Xiao Han, Shijie Zhou, Abdullah Koukash, Jingpei Wu, Jindong Gu, Yuqicheng Zhu, Nassir Navab 等 10 位作者

原文摘要

Evaluating general-purpose multimodal large language models (MLLMs) for surgical scene understanding remains limited due to scarce surgical data and fragmented evaluation protocols. We address these challenges through a two-stage evaluation framework for surgical scene understanding. In Stage I, we introduce SurgKnowBench, a diagnostic benchmark that harmonizes public surgical datasets across procedures and tasks and evaluates proprietary and open-source MLLMs to map the boundary of pretrained surgical competence. SurgKnowBench reveals that current models retain partial visual priors but remain weak on relational and procedural understanding and workflow assessment. Building on this failure frontier and motivated by the scaffolded nature of surgical training, we introduce SurgAgentGym, an agentic environment where general-purpose MLLM agents can use bounded knowledge search over SurgWiki and general-purpose visual grounding for surgical tasks. SurgAgentGym evaluates whether generalist agents can improve surgical understanding at inference time through tool-mediated evidence use, without additional surgical training. Our results show that agentic inference narrows the gap mainly for perception-heavy tasks, while fine-grained localization and expert-style assessment remain persistent bottlenecks. This opens a path toward future studies of agentic surgical understanding.

cs.CV · cs.AI

新论文 · v1arXiv:2611.11436

Retrospective Analysis of Team-Following Trading Profitability in Pumpfun Meme Coins Using Funding Networks

Fail Gafarov

原文摘要

If the right token-creation teams had been known, how much could following them have returned, and what is left when only information available before each launch is used? We study ten separately recorded Pumpfun windows (April 2024 to September 2026), each reconstructed independently from real-SOL reserve states and finite-capital accounts that start with one SOL. Teams are directed funding groups ranked in hindsight. When every team exits at its own best reserve threshold, chosen in hindsight, the main account ends above one SOL in all 8 windows that have a qualifying team (1.10 to 11.32 SOL), but free cash exceeds one SOL in only 5, and marks of positions that never reached their threshold make up 17--94% of equity. If teams are recognised online, from tokens whose first hour has completed, 9 of 19 teams become identifiable only after their last launch; the remaining 10 end above one SOL in 10 cases, with free cash above one SOL in 7; funding links in this step still come from the full window, so even these results are not a fully realisable signal. A large model balance, a result above random cohorts that repeat the threshold search, and a statistical rejection in the selection-matched nulls (3 of 40 tests after Holm adjustment) are three different statements, and these nulls condition on the discovered funding graph, so they do not calibrate the whole selection procedure. Midpoint tests describe a further source of apparent opportunity. A detailed analysis of the best and the worst window, with every analysis parameter varied, shows that the worst result, which is close to break-even, rises several-fold with a stop rule or another funding-graph construction. The results are conditional retrospective model accounts, not executable profits, and not evidence of a causal effect of the SOL price.

physics.soc-ph · cs.SI · q-fin.TR

新论文 · v1arXiv:2611.11435

From Dialogue to Task: How Cognitive Engagement With Generative Artificial Intelligence Relates to Post-Dialogue Activity and Task Outcomes

Xiaoyu Zhuang, Aneesha Bakharia, Dragan Gašević, Hassan Khosravi

原文摘要

Generative AI is increasingly embedded within learning tasks, yet interaction frequency reveals little about cognitive engagement in student-AI dialogue. Little is known about how such engagement is situated within task workflows or how dialogue characteristics and subsequent task activity relate to students' behaviour and task outcomes. This study examined cognitive engagement in student-AI dialogue, its position within task workflows, and associations of dialogue and task-process characteristics with post-dialogue activity and task outcomes. Data were collected from 1,681 students across 40 university courses using three AI companions embedded in resource creation, peer moderation, and practice. Cognitive engagement in 829 conversation threads was coded with a dialogue-oriented Interactive-Constructive-Active-Passive (ICAP) framework, and 2,969 task sequences were modelled with first-order Markov models. Regression models linked dialogue and task-process characteristics to behavioural re-engagement, peer-rated artefact quality, and practice performance. Passive and Active engagement predominated, although resource creation involved more Constructive and Interactive dialogue, peer moderation more Passive, and practice more Active, while higher-engagement dialogue was less often followed by session termination. In resource creation, student-composed messages were associated with more dialogue-to-task returns than template-only requests at the same Passive level, whereas deeper cognitive engagement was associated with higher final artefact quality independent of return frequency; in practice, AI dialogue after an incorrect attempt was associated with fewer further attempts but higher next-attempt correctness among continuers. Post-dialogue activity and task outcomes are distinct aspects of AI use that interaction frequency cannot capture and evaluations should assess separately.

cs.CY · cs.HC

新论文 · v1arXiv:2611.11433

Unlearning at Speed: Rapid Activation Dampening for Efficient Machine Unlearning in Real-World Face Recognition

Rouqaiah Al-Refai, Leo Scheubel, Philipp Terhörst

原文摘要

Machine unlearning has become increasingly important in face recognition, where regulations like the GDPR empower users to request the removal of their personal data from deployed models. However, most existing unlearning methods are designed for closed-set classification with small-scale models and training data, and therefore do not generalize to real-world face recognition systems, which operate in an open-set setting with large-scale models and data. In this work, we propose Rapid Activation Dampening (RAD), a fast and targeted unlearning method tailored specifically for large-scale open-set face recognition. RAD approximates differences in average neuron activations between forget and retain identities, identifying and selectively suppressing neurons that are most associated with the targeted identity through a sensitivity-controlled dampening mechanism. We further propose the Forget Score (FS), which addresses the mismatch between existing unlearning metrics and open-set problems by providing a probabilistic interpretation of forgetting directly in the representation space. Experiments across several recent large-scale face recognition architectures and datasets show that RAD achieves strong forgetting while preserving overall model utility and substantially improving unlearning speed. These findings establish RAD as a scalable and practical approach to machine unlearning in face recognition systems.

cs.CV

版本更新 · v2arXiv:2609.05762

AAMBERS-UAV: Acquisition-Aware Multimodal Backbone Evaluation and Ranking for UAV Weedy Rice Segmentation

Tarek Rahman, Nazim-E-Alam, Md Kishor Morol, Jannatun Noor

原文摘要

UAV image collections contain spatially and temporally related frames, yet semantic-segmentation benchmarks commonly split them at image level. Such splitting can place samples from one acquisition in both model development and testing, obscuring transfer to a genuinely new survey. Using the 734-sample WeedyRice-RGBMS-DB, we fix a 124-image target-acquisition test set and compare two protocols with identical train, validation, and test counts: target-held-out, which excludes the target acquisition from development, and target-exposed, which admits its remaining images. SegFormer-B0 is evaluated with RGB, four-band multispectral (MS), and seven-channel RGB+MS input over two fixed-split seeds. RGB is strongest under complete acquisition holdout ($0.7317\pm0.0201$ IoU), whereas RGB+MS becomes strongest after target exposure ($0.7822\pm0.0269$). A fixed-split U-Net/ResNet18 replication confirms positive exposure gains for all three inputs, but retains RGB as the best modality under both protocols. Acquisition exposure therefore increases measured performance across both evaluated backbones, while its effect on modality ranking is architecture-dependent. A supplied-split audit reveals strong near-sequential dependence, and corruption tests show that early fusion is substantially more sensitive to RGB--MS displacement than to moderate radiometric scaling. These results support acquisition-aware same-test evaluation as a necessary complement to ordinary image-level splitting in multimodal UAV benchmarks. The code and supporting the findings of this study will be publicly released upon acceptance of the paper.

cs.CV · cs.LG

版本更新 · v5arXiv:2610.09471

When Should an In-Context Learner Expand Its Hypothesis Space?

Weihan Li, Xinlei Chen, Junhao Wu, Tianshi Zheng

原文摘要

Learning systems adapt quickly within a familiar family of models. The harder step is deciding, from a prediction failure, whether opening a richer family is worth its cost. We cast this as a costly sequential decision and introduce the Structural Revision Environment (SRE), which produces matched failures from noise, exceptions, change within the family or structure outside it, varies the price of expansion and the remaining horizon independently of the evidence, and admits an exact normative solution of the one-shot decision. The solution shows that revision is a value boundary, not an evidence threshold: except at the lowest prices, the richer family becomes the more probable explanation long before expanding becomes optimal. Small Transformers trained in SRE reproduce the expansion boundary from utility alone. Pretrained 7B and 8B language models fail at a definite point: their predictions carry a failure-sensitive signal that their decisions do not reflect. Told the gain of expanding, they weigh it against price and horizon only when they reason, and the one model that finishes its reasoning on the history alone still does not estimate that gain. Controlled post-training of the small Transformers moves the prior and the sharpness of predictions, and neither moves the criterion.

cs.LG

版本更新 · v2arXiv:2603.03667

ORION: Intent-Aware Orchestration in Open RAN for SLA-Driven Network Management

Gabriela da Silva Machado, Gustavo Z. Bruno, Alexandre Huff, José Marcos Camara Brito, Cristiano B. Both

原文摘要

The disaggregation of the Radio Access Network (RAN) introduces architectural flexibility but significant operational complexity, necessitating automated management frameworks. For instance, current Open RAN (O-RAN) orchestration relies on fragmented manual policies, lacking end-to-end intent assurance from high-level requirements to low-level configurations. In this article, we propose ORION, an intent orchestration framework that integrates Large Language Models (LLMs) through the Model Context Protocol (MCP). It translates natural language slice requests into network policies aligned with O-RAN interfaces, supporting the AI-RAN agentic orchestration and AI-for-RAN paradigms. ORION combines an MCP-based Service Management and Orchestration (SMO) layer with a Non-Real-Time RIC rApp and a Near-Real-Time RIC xApp to enforce Physical Resource Block (PRB) quotas over E2. We evaluate eight LLM configurations across proprietary and open-weight models on a 100-intent workload. Claude Opus 4.5 and GPT-5 achieve 100% policy-creation success with 99% and 96% slice-type classification accuracy, while GPT-5 Nano achieves 97% policy-creation success. The evaluation also assesses MCP tool-use quality, cost-performance trade-offs, resource consumption, and end-to-end control-path latency.

cs.NI

新论文 · v1arXiv:2611.11428

CHANNELS4WORLD: An Environment-Scale Dataset for Wireless Foundation Models

Joonkyu Jang, Hyung-Joo Moon, Kwang Soon Kim, Seong-Lyun Kim, Jakob Hoydis, Robert W. Heath,, Chan-Byoung Chae

原文摘要

Wireless foundation models learn reusable representations across tasks, configurations, and deployment environments. Their pretraining requires environmental breadth, yet wireless datasets often sample few sites densely. We introduce Channels4World, a scene-centered dataset of 100,000 distinct outdoor RF scenes and a procedural method for generating them. Each scene links a generated environment and RF material assignments to 32 base-station (BS) positions, 16,384 UE positions, and aligned variable-length multipath and ordered interaction records at 3.5 and 7~GHz. The corpus comprises 52.43 billion physical BS-UE pairs, 104.86 billion frequency-specific evaluations, and a 29.14-TB packaged payload. Scene identity aligns geometry, placements, channels, and interactions across frequencies, allowing environmental breadth and within-scene observation density to vary independently. The public release offers predefined subsets at multiple scales and separate access to corpus components. A deterministic 90K/10K scene-level train-test split keeps both frequencies and all scene components together. We characterize morphology, RF materials, and transceiver placement across three generation profiles. Controlled propagation and path-retention analyses show that diffraction materially affects retained-link availability and multipath structure, while the retention policy reduces storage substantially with little loss in represented aggregate power. Under matched training exposure, models trained on broader scene collections perform better on held-out scenes, although an equal-episode control shows that scene count alone cannot explain the gain. By making environmental breadth explicit and controllable, Channels4World supports the development and evaluation of wireless foundation models for generalization across deployment environments.

cs.LG · cs.IT · eess.SP

新论文 · v1arXiv:2611.11427

Flex-DDCM: Zero-Shot Task-Oriented Image Compression via Diffusion Trajectory Guidance

Yixin Gao, Runsen Feng, Xin Li, Zhibo Chen

原文摘要

Recent zero-shot image compression methods exploit the powerful priors of pretrained diffusion models to produce perceptually pleasing reconstructions without compression-specific training. However, image compression serves not only human viewing but also machine analysis, while existing zero-shot codecs have limited flexibility in meeting the diverse reconstruction requirements of these applications. In this paper, we propose Flex-DDCM, a framework for zero-shot task-oriented image compression via diffusion trajectory guidance. Building on Turbo-DDCM, we adapt the coded diffusion trajectory through task-guided noise selection, embedding the effects of task guidance into the compressed representation. Guidance terms can be applied individually or combined, with timestep-dependent strengths controlling their influence throughout denoising. This design enables task adaptation without introducing additional decoding complexity. Experiments demonstrate flexible trade-offs among pixel fidelity, perceptual quality, and downstream task performance, with competitive performance against trained task-oriented codecs and faster decoding than Diff-ICMH.

cs.CV · cs.LG

新论文 · v1arXiv:2611.11426

Vietnamese Legal Ontology: Every legal answer, traced to the article that grounds it

Khac-Hoai Nam Bui, Quan Tran Minh

原文摘要

A legal answer is only as good as the article it rests on. Vietnam's largest open legal corpus pairs 109,543 published questions and answers with 573,851 legal documents, yet its citations are free text: "Khoan 3 Dieu 101 cua Bo luat nay" ("Clause 3, Article 101 of this Code") names neither the code nor its version. Following the five stages of NVIDIA Auto Ontology, Discover, Ground, Validate, Expose and Learn, we turn four open datasets into a knowledge graph of 11.5 M nodes and 16.0 M edges in which every node and edge carries its source record and method, with no duplicate keys, dangling edges or schema violations. Of 67,868 cited provisions, 61,487 resolve to a dated law version, 51,694 to a parsed article, clause or point, and 19,012 are confirmed word for word. The ontology then shows what flat records hide. 36% of the 78,361 answers whose citations resolve now cite a law that is no longer in force; 2,525 verified citations point to an article number that says something else in the current law; 2,520 citations were re-versioned because their words match a different version than their date suggests; and 5,575 document numbers are shared by several local authorities, one of them by 72. Every number in this paper is computed from the graph.

cs.CL · cs.AI