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

+1208新增论文
+950其中 AI 相关
+153已有论文修订
+59新增 AI 导读

arXiv 最近完成扫描:2026-11-18 04:28 · 全站最近入库:2026-11-18 14:10各信源进度 →

统计口径与数据新鲜度

统计 2026-11-17 14:42 — 2026-11-18 14:42(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:2026-11-18 04:28最近发现新增版本:2026-11-18 14:10库内论文最新更新时间:2026-11-18 08:00

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。

26,057 已收录论文21,704 AI 相关7,828 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 19,291 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-18 04:27(北京时间)
新论文 · v1arXiv:2611.10984

Network Contention State Aware Dynamic Optimizer for Accelerator Collective Communication Libraries

Rajat Bisht, Tevfik Kosar, Anthony Skjellum, Gene Cooperman, MD S Q Zulkar Nine

原文摘要

Collective Communication Libraries (CCL) are critical for large-scale distributed AI/ML training, yet their configurations are determined by static heuristics that do not account for real-time network conditions. Our empirical study shows that these heuristics perform near-optimally in contention-free environments, but degrade substantially under background traffic. To address this, we present a cooperative multi-agent run-time optimizer for accelerator collective communication. Our approach employs a two-agent architecture: (i) detector- a Long Short Term Memory(LSTM) recurring neural network fed classifier head with a sequential probability ratio test that distinguishes sustained contention from transient spikes; and (ii) selector- a configuration selector built on a Dueling Double DQN (D3QN) with Conservative Q-Learning that adapts configuration parameters in response. We implemented this dynamic tuner over NCCL, a widely used CCL developed by NVIDIA. When evaluated on Chameleon Cloud's isolated bare-metal cluster, this dynamic tuning approach reduces AllReduce latency by 36% over NCCL and 32% over a fully converged AutoCCL. We further evaluated it across six real AI workloads spanning convolutional networks, transformers, and recommendation architectures. Our multi-agent tuner approach delivers up to 65% speedups on Delta cluster with NVIDIA A100 GPUs and Slingshot-11 fabric internode connectivity.

cs.DC · cs.LG · cs.MA

版本更新 · v2arXiv:2606.25402

LibEvoBench: Probing Temporal Knowledge Stratification in Code Generation Models

Daniele Cipollone, Sergey Titov, Maliheh Izadi, Egor Bogomolov, Arie van Deursen

原文摘要

Large software projects often depend on older versions of libraries, even as APIs continue to evolve across releases. This creates a challenge for LLMs: they must maintain knowledge of multiple API versions, not merely the latest or most common one. However, current LLMs are trained on temporally mixed corpora and lack explicit mechanisms for such version-specific reasoning, leading to anachronistic errors - calling APIs as they exist in a different library version. To systematically evaluate this phenomenon, we introduce LibEvoBench, a multi-task benchmark spanning multiple versions of widely used Python libraries, along with a new metric, the Software Evolution Understanding Score (SEUS), to measure models' consistency when working with evolving APIs. Our results show that state-of-the-art models are largely version-oblivious: performance degrades for evolving APIs, while for stable APIs it remains the same across versions. Moreover, simply specifying the target version provides no benefit, while relevant documentation significantly boosts models' accuracy. These findings highlight a systematic limitation of current training paradigms and motivate new approaches for temporally grounded knowledge in code generation.

cs.SE · cs.AI

版本更新 · v2arXiv:2602.04131

Decoupling Time and Risk: Risk-Sensitive Reinforcement Learning with General Discounting

Mehrdad Moghimi, Anthony Coache, Hyejin Ku

原文摘要

Distributional reinforcement learning (RL) is a powerful framework increasingly adopted in safety-critical domains for its ability to optimize risk-sensitive objectives. However, the role of the discount factor is often overlooked, as it is typically treated as a fixed parameter of the Markov decision process or tunable hyperparameter, with little consideration of its effect on the learned policy. In the literature, it is well-known that the discounting function plays a major role in characterizing time preferences of an agent, which an exponential discount factor cannot fully capture. Building on this insight, we propose a novel framework that supports flexible discounting of future rewards and optimization of risk measures in distributional RL. We provide a technical analysis of the optimality of our algorithms, show that our multi-horizon extension fixes issues raised with existing methodologies, and validate the robustness of our methods through extensive experiments. Our results highlight that discounting is a cornerstone in decision-making problems for capturing more expressive temporal and risk preferences profiles, with potential implications for real-world safety-critical applications.

cs.LG

版本更新 · v3arXiv:2604.00449

Convergence of Byzantine-Resilient Gradient Tracking via Probabilistic Edge Dropout

Amirhossein Dezhboro, Fateme Maleki, Arman Adibi, Erfan Amini, Jose E. Ramirez-Marquez

原文摘要

We study distributed optimization over networks with Byzantine agents that may send arbitrary adversarial messages. We propose Gradient Tracking with Probabilistic Edge Dropout (GT-PD), which combines a universal self-centred projection that clips incoming messages to a radius-$τ$ ball around the receiver with a fully decentralized probabilistic dropout rule driven by a threshold-gated, dual-metric trust score in the decision and tracking channels. These identity-free defences bound adversarial perturbations while preserving doubly stochastic mixing. The projection preserves the honest network average exactly in every realization, even when honest messages are clipped. Under complete Byzantine isolation ($p_b=0$), GT-PD converges linearly to a neighbourhood of order $ασ^2/(μn_{\mathcal H})$ plus higher-order network terms, matching centralized stochastic gradient descent to first order in the step size. We also give a radius computable from problem data that ensures honest messages remain unclipped with high probability. Under partial isolation ($p_b>0$), a leaky variant, GT-PD-L, controls accumulated tracking perturbations and converges linearly to a bounded neighbourhood governed by stochastic variance and the clipping-to-leak ratio, under explicit conditions on the step size, leak, and aggregate Byzantine mixing weight. With two-tier dropout and $p_h=1$, Byzantine isolation adds no variance to honest consensus dynamics. MNIST experiments under Sign Flip, ALIE, and Inner Product Manipulation attacks show that GT-PD-L outperforms coordinate-wise trimmed mean by up to 4.3 percentage points under stealth attacks.

cs.LG · cs.MA · eess.SY

版本更新 · v3arXiv:2605.20555

LAPO: KL-Free Logit-Averaged Policy Optimization to Leverage RL and SFT in LLM Post-Training

Xingwei Gan, Ying Zhu

原文摘要

From a classical statistical perspective, model averaging and parameter shrinkage (e.g., Ridge regression with an $l_2$-penalty) are deeply connected mechanisms designed to reduce estimator variance and lower mean squared error. Motivated by this insight, we introduce Logit-Averaged Policy Optimization (LAPO), a KL-free and critic-free post-training framework that replaces explicit KL regularization with logit averaging inside Group Relative Policy Optimization (GRPO); in particular, averaging the logits of the trainable policy and a frozen reference policy functions as an implicit structural regularizer that stabilizes rollout trajectories. For selecting the mixing weight, we propose a compute-efficient adaptive algorithm that dynamically balances exploration and structural anchoring throughout training, evaluated against a static fixed-weight baseline. This adaptive mechanism eliminates explicit KL penalty backpropagation and expensive, fragile hyperparameter sweeps while reducing the incidence of uninformative zero-reward rollout groups. Mathematically, embedding logit averaging within the reinforcement learning loop operates as an in-training Product of Experts (PoE): the multiplicative geometric mean enables the reference anchor to act as a soft logical "AND" that vetoes non-compliant tokens, enforcing schema rigor and safety guardrails without the catastrophic forgetting typical of sequential fine-tuning. Evaluated across Qwen2.5-Instruct models (1.5B, 3B, and 7B), LAPO consistently outperforms canonical KL-regularized GRPO, achieving a 7%-15% accuracy gain on MATH and a 2%-5% gain on cn_k12 and MMLU. Finally, the resulting mixed teacher policy can be distilled back into a single student network, fully restoring standard $1\times$ inference latency.

cs.LG · cs.AI

版本更新 · v2arXiv:2606.14029

Utility-Constrained Policy Optimization

Mehrdad Moghimi, Bernardo Avila Pires

原文摘要

Constrained MDPs (CMDPs) are a widely adopted framework for incorporating safety into RL agents; however, the framework does not support risk-sensitive constraints. This can be problematic: For example, CMDPs allow for optimal solutions that, in order to satisfy the risk-neutral constraints, mix infrequent catastrophic behaviors and frequent, overly conservative ones. Moreover, prior empirical results suggest that enforcing stricter, risk-sensitive constraints can improve performance even under risk-neutral evaluation. The natural framework to incorporate risk-sensitive constraints is utility-constrained MDPs (UCMDPs), but no practical solutions for this problem existed. In this work, we introduce a simple yet powerful methodology for UCMDPs and constrained RL. Besides allowing for risk-sensitive constraints, our framework does not require us to fix constraint limits in advance of training the agent, provided that a sensible range is known. This increases policy flexibility and, in practice, allows for adjustments to these limits at no extra training cost. Besides benefiting from the generality of the framework, our agent shows strong performance in practice, consistently matching or outperforming existing baselines in several Safety Gymnasium benchmark tasks.

cs.LG

新论文 · v1arXiv:2611.10981

An Analysis of Reinforcement Learning with Function Approximation

Francisco S. Melo, Sean P. Meyn, M. Isabel Ribeiro

原文摘要

We address the problem of computing the optimal Q-function in Markov decision problems with infinite state-space. We analyze the convergence properties of several variations of Q-learning when combined with function approximation, extending the analysis of TD-learning in Tsitsiklis and Van Roy (1996) to stochastic control settings. We identify conditions under which such approximate methods converge with probability 1. We conclude with a brief discussion on the general applicability of our results and compare them with several related works.

cs.LG

版本更新 · v2arXiv:2605.30213

Faithful Embeddings of Irregular and Asynchronous Data for Online Log-NCDEs

Benjamin Walker, Alexandre Bloch, Lingyi Yang, Sam Morley, Terry Lyons

原文摘要

Continuous-time models are a natural choice for irregular and asynchronous data. A central design choice is how to embed discrete observations into continuous time. Interpolation- and imputation-based embeddings reconstruct a continuous observation path, making the model sensitive to the choice of reconstruction. We show that this reconstruction step is unnecessary; under mild conditions, compact-set universality on the model input space transfers to the data space whenever the embedding from data to input is continuous and injective. Guided by this result, and building on the rectilinear control path for Neural Controlled Differential Equations (NCDEs), we introduce a continuous and injective embedding for Log-NCDEs, a universal class of continuous-time models. Our approach records observations as increments and composes them over arbitrary query intervals to directly form log-signatures. This provides interval-level summaries without first interpolating the observed variables, while supporting online computation. Experiments on synthetic controlled dynamics and real-world time-series datasets show that the representation is accurate, efficient, and robust to irregular, asynchronous, and sparse observations.

cs.LG

版本更新 · v2arXiv:2609.24593

Polyhedral Methods for Cooperative Games: Small Lifts and Hard Faces

Michel Grabisch and. Hans Raj Tiwary

原文摘要

We study the computational complexity of fundamental algorithmic problems -- membership testing, separation, valid-inequality testing, and linear optimization -- over polytopes and cones arising from cooperative games (also known as pseudo-Boolean functions). A central obstacle in the study of such problems is that a general cooperative game on $n$ players requires $2^n$ values, so the input size is $2^n$ for a game with $n$ players, making these computational tasks theoretically trivial. Restricting to $k$-additive games reduces the input size to $O(n^k)$, making such games a natural target for meaningful questions about the existence of efficient algorithms. On the positive side, we give an explicit extended formulation of size $O(n^k)$ for the core of $k$-additive $k$-monotone games, allowing all four problems to be solved by a single polynomial-size linear program -- in particular, circumventing the ellipsoid method that is needed when building from earlier tractability results of Deng and Papadimitriou, or of Edmonds. For the cone of $k$-additive $(k{-}1)$-monotone games, we give a complete characterization of its extreme rays and derive the same $O(n^k)$ bound on extension complexity, yielding a geometry-based proof and generalization of a result of Billionnet and Minoux. On the negative side, we show that for $l \leq k-2$ the cone of $k$-additive $l$-monotone games is computationally intractable: membership testing is not in NP (unless NP\,=\,coNP), valid-inequality testing is NP-complete, and extension complexity is at least $1.5^n$. Our hardness results yield, as a special case, a result of Crama and of Gallo and Simone. Furthermore, our hardness results also explain the lack of any good characterization of the extreme rays of the cone of $k$-additive $(k{-}2)$-monotone games.

cs.GT · cs.CC · math.CO · math.OC

新论文 · v1arXiv:2611.10977

DM-Call: Decision-Model-Guided Function Calling with Cumulative Verification Feedback

Minhyeong Yu, Wonduk Seo, Seunghyun Lee

原文摘要

Reliable function calling requires Large Language Models (LLMs) to select appropriate functions and generate arguments consistent with user intent. However, syntactically valid calls may still be semantically incorrect due to inappropriate function selection or mismatched arguments. In this paper, we propose Decision-Model-Guided Function Calling (DM-Call), a framework that combines local schema validation with separate decision-model verification of function selection and argument correctness. For rejected candidates, DM-Call accumulates verification probabilities, binary judgments, and schema errors across attempts. A hybrid feedback representation further combines numerical probabilities with verbal correctness labels to guide iterative refinement without executing external tools. Extensive evaluation across BFCL and API-Bank (first-call) demonstrates DM-Call boosts function-calling accuracy versus direct generation, at modest additional cost.

cs.IR · cs.AI · cs.CL · cs.LG · cs.SE

版本更新 · v2arXiv:2606.03199

Fast Organic Crystal Structure Prediction with Unit Cell Flow Matching

Alston Lo, Luka Mucko, Austin H. Cheng, Andy Cai, Alastair J. A. Price, Wojciech Matusik, Alán Aspuru-Guzik

原文摘要

Organic crystal structure prediction (CSP) is a requirement for computational modelling of organic solids, but traditionally costs several CPU-years per molecule. Generative models such as OXtal dramatically reduce this cost by sampling stable organic crystal structures directly. However, OXtal forgoes explicit lattice parametrization in favour of modelling large crops of the bulk material with expensive triangle layers, which can incur a computational cost of minutes per molecule. In this paper, we reduce this to seconds with Clari, a large-scale flow matching model that generates redundancy-free unit cells and replaces triangle layers with pair-bias attention. Clari requires only atom types and bonds as input and does not need an RDKit-sanitizable input molecule, which expands its applicability to challenging chemistries such as fullerenes, metal complexes, and atom clusters. We further ablate key design choices such as auxiliary losses, timestep distributions, noise priors, and self-conditioning. On OXtal's test sets, we surpass OXtal's solve rate while obtaining a speedup of 15-30$\times$. Because Clari also models explicit hydrogens, it supports inference-time scaling via direct energy ranking, without any decoration or relaxation step. When generating 150 crystals and selecting the top-30 by energy, we further improve solve rate while maintaining a speedup of 5-8$\times$. We also introduce the CSD Teaching Subset as a new test split of diverse and complex molecules for future benchmarking. Our contributions enable CSP within seconds, making large-scale virtual screening of organic solids practical. Code is available at https://github.com/the-matter-lab/clari.

cs.LG · physics.chem-ph

新论文 · v1arXiv:2611.10973

Patchbay: a block model for the sonification of ADS-B aircraft data

Arquimedes Canedo

原文摘要

Patchbay is a design for turning the data that an ADS-B receiver collects into sound by wiring typed blocks together. ADS-B reports are the position and altitude messages that aircraft broadcast and that a small ground receiver can collect. We first describe what such a receiver reports: signals that differ in shape (continuous, stepped, circular, categorical), in resolution, in who produces them, and in how long they stay put, which runs from about ten seconds to the whole time an aircraft is in view. From this we derive a small model. Four kinds of connection carry an aircraft set, a value, an event or audio, and 27 blocks select aircraft, read fields, decide when a note starts, shape values and make sound. One of these blocks makes the receiver act as a radar: scanning by bearing it is a line that rotates about the receiver, and scanning by range it is a ring that grows from the centre or shrinks inward. Each aircraft sounds at the moment the scan reaches it, and the scan's period is set in bars of a beat clock. The model does not depend on a browser. Our reference implementation is a browser editor, contained in one HTML file, that replays two recorded captures and records both an audio take and a MIDI take, a file of the notes played rather than of the sound. We say what is not built and place the work beside the closest systems we found, among them a radar-sweep sequencer for tangible objects from 2006 and a range-ring sonification of ADS-B aircraft published in 2026. Sweeps that trigger sound, and typed connections, both exist in earlier systems. To our knowledge, none of the sources we reached carries the aircraft in view, with every field attached, as one kind of connection in an editor.

cs.SD · cs.HC

新论文 · v1arXiv:2611.10969

Rule-table structure of life-like cellular automata: activity, asymmetry, sensitivity, and the propagation storage factorisation

Yair Cohen

原文摘要

What structure on the rule space of a cellular-automaton family exposes which rules can support which behaviours? For the 262,144 life-like rules -- the two-dimensional outer-totalistic family containing Conway's Game of Life -- the standard coordinate, Langton's activity parameter, is long known to be too coarse. I organise the family by three symmetry-derived rule-table coordinates: an unweighted activity, a birth-survival asymmetry (odd under the swap of birth and survival), and the Vichniac-Binder Boolean-derivative sensitivity in closed form, whose centre-bit component vanishes exactly on the centre-blind (B=S) submanifold. The cardinality coordinates lambda, delta are necessary but never sufficient to certify behaviour; the centre-bit sensitivity labels the B=S submanifold on which the paper's one exact exclusion holds. Combined with an exhaustive enumeration of every rule's compact gliders, still lifes and oscillators (three-by-three seed, period at most sixteen), they expose a hierarchical factorisation: the birth condition is a narrow gate deciding whether anything can propagate, the survival condition tunes storage, and every compact-glider-supporting rule is birth-light and survival-rich. One exclusion is exact: no B=S rule supports a compact glider at that footprint, proven by exhaustive enumeration and closing only for compact-footprint patterns -- 36 B=S rules ship at four-by-four seed and 40 at five-by-five. Two dynamical results frame the whole: glider-capable rules that random sampling never expresses show that capability is certifiable from the table while its expression is only estimable from dynamics; and every uncatalogued rule producing a richly Life-like ecology turns out to be a Conway or HighLife variant on the neighbour counts its trajectories actually visit.

q-bio.PE · cs.LG

版本更新 · v2arXiv:2501.00087

High-Dimensional Markov-Switching Ordinary Differential Processes

Katherine Tsai, Mladen Kolar, Sanmi Koyejo

原文摘要

Complex systems often evolve in continuous time but are observed only at discrete time points with measurement noise. When the interactions can change across unobserved states, recovering both the state transitions and the differential equations is important for mechanistic insight and for identifying time-varying directed graphs. However, this recovery is challenging in high dimensions. In this paper, we study estimation and graph recovery for high-dimensional Markov-switching ordinary differential equation models from noisy discrete observations. We model the switching between states by a latent continuous-time Markov chain, and within each state the drift is a sparse additive function with unknown nonlinear components. We approximate each component by a finite basis expansion and estimate the parameters under group sparsity. Our procedure estimates the latent trajectories by wavelet smoothing and then runs a penalized surrogate expectation-maximization algorithm. Under stationarity and geometric $β$-mixing, given a sufficiently accurate estimated trajectory and other local regularity conditions, we show that the algorithm converges geometrically to a neighborhood of the true parameters. Finally, in an application to resting-state fMRI data, the procedure identifies multiple connectivity states, whose occupation times we compare descriptively between the children with combined-type ADHD and the typically developing children used in the fit.

stat.ME · cs.LG · math.ST · stat.AP

新论文 · v1arXiv:2611.10967

BAT-WAM: Bridging Action and Touch in World-Action Models for Dexterous Hands

Dong Fang, Feixuan Huang, Yuanxin Zhong, Yuxiang Gao, Qi Song, Yunlong Wang, Xiaosong Jia, Yu-Gang Jiang

原文摘要

Dexterous manipulation with world action models (WAMs) relies on hand configuration and contact information, yet joint-state and whole-hand tactile observations may be partially or entirely missing. RGB images provide scene context and hand-object geometry but are insufficient to reliably recover these missing modalities. We further observe a correlation between hand state and tactile information. Motivated by this observation, we introduce BAT-WAM, a framework that bridges visual, joint-state, and tactile representations for WAMs. BAT-WAM learns separate codebooks and decoders for the tactile and action streams. An RGB-conditioned continuous latent bridge connects the two streams for bidirectional learning, while visual information serves as continuous context. Under the HTBench evaluation protocol, BAT-WAM reduces the root mean squared error (RMSE) of tactile reconstruction by 34.73% under fully masked conditions and 38.84% under partially masked conditions, relative to an image-conditioned HandTouch checkpoint. For future tactile prediction conditioned on target-time RGB and historical actions, it reduces mean RMSE by 85.56% relative to OpenWAM with HandTouch. Real-robot experiments further show that BAT-WAM consistently outperforms related WAM baselines in dexterous manipulation. Generalization experiments on unseen objects and scenes also demonstrate substantial improvements over baseline models. These findings support joint modeling of visual context, hand state, and touch as a representation approach for multimodal WAMs.

cs.RO

新论文 · v1arXiv:2611.10966

PQC-Corpus: A Dataset of Linked Development Histories for Post-Quantum Cryptography

Souhardya Saha Dip, Moshood A. Fakorede, Umar Farooq

原文摘要

As post-quantum cryptography (PQC) standards evolve, developers must adapt implementations, tests, and protocols. Studying this work requires connecting code changes to problem reports and developer reviews. We present PQC-Corpus, a dataset of linked development histories from 179 public GitHub repositories, spanning cryptographic libraries and general-purpose projects. It connects issues and closing pull requests to commits and full patches, with comments and reviews. We combine Git histories with GitHub threads, reconstruct 23 pull-request commit lists truncated at 250 entries, and check file integrity, schemas, and links. Two annotators independently assessed sampled commits and issues ($κ=0.86$ and $0.93$), labeling about seven in ten commits and two in three issues PQC-related within these samples. We provide full and filtered views with removal ledgers, and quantify how filtering reduces links from issues to commits. A patch-free view supports inspection before downloading patches, while traversal scripts follow issues to code changes. We make the dataset and collector publicly available for studies of specification changes, hybrid interoperability, cryptographic review, and migration assistance.

cs.CR · cs.SE

新论文 · v1arXiv:2611.10965

Bayesian transfer for offline Q-learning with multi-task Gaussian processes

Wenxing Guo

原文摘要

Offline reinforcement learning can benefit from data collected in related tasks, yet indiscriminate knowledge transfer may lead to negative transfer under task mismatch and limited target-data coverage. We propose a target-aware Bayesian transfer framework for offline Q-learning based on multi-task Gaussian processes that jointly model task-specific Q-functions. Source tasks are assessed using target predictive evidence and maximum mean discrepancy (MMD), while posterior uncertainty and behavior-supported action sets guide conservative Bellman updates and policy extraction. To account for the dependence induced by Bellman bootstrapping, we distinguish Bellman innovations from bootstrap errors and establish stability and predictive source-selection results under explicit regularity conditions. We further derive selection-adaptive posterior contraction and offline policy-performance bounds, identifying the structural conditions under which source information can be pooled to achieve minimax-optimal rates in a shared-function Gaussian sequence experiment. Simulation studies with heterogeneous source tasks demonstrate improved target Q-function estimation and reduced material negative transfer compared with indiscriminate source pooling. An application to human decision-making data further shows higher average expected immediate payoff than both target-only learning and matched-size random source selection. These results highlight the benefits of combining target-aware source selection with uncertainty-aware conservative learning for reliable and sample-efficient offline reinforcement learning.

stat.ML · cs.LG

版本更新 · v2arXiv:2602.06208

Emergent Low-Rank Training Dynamics in MLPs with Smooth Activations

Alec S. Xu, Can Yaras, Matthew Asato, Qing Qu, Laura Balzano

原文摘要

Recent empirical evidence has demonstrated that the training dynamics of large-scale deep neural networks occur within low-dimensional subspaces. While this has inspired new research into low-rank training, compression, and adaptation, theoretical justification for these dynamics in nonlinear networks remains limited. %compared to deep linear settings. To address this gap, this paper analyzes the learning dynamics of multi-layer perceptrons (MLPs) under gradient descent (GD). We demonstrate that the weight dynamics concentrate within invariant low-dimensional subspaces throughout training. Theoretically, we precisely characterize these invariant subspaces for two-layer networks with smooth nonlinear activations, providing insight into their emergence. Experimentally, we validate that this phenomenon extends beyond our theoretical assumptions. Leveraging these insights, we empirically show there exists a low-rank MLP parameterization that, when initialized within the appropriate subspaces, matches the classification performance of fully-parameterized counterparts on a variety of classification tasks.

cs.LG · cs.AI

新论文 · v1arXiv:2611.10960

Anatomy-Activated Mixture-of-Experts for 3D Medical Vision-Language Pre-training

Szymon Płotka, Gizem Mert, Pedro R. A. S. Bassi, Wenxuan Li, Zongwei Zhou, Anna Marcinkiewicz, Wiktoria Romańczyk, Jarosław B. Ćwikła 等 12 位作者

原文摘要

Medical Vision-Language Pre-training (VLP) leverages the semantic richness of radiology reports to learn 3D representations, yet current architectures remain fundamentally anatomy-agnostic. While clinical diagnostics rely on organ-specific context, standard encoders apply a uniform, dense parameterization to all volumetric patches, and existing Mixture-of-Experts (MoE) routers gate on isolated local features without explicit access to the organ composition of the scan or crop. We propose Anatomy-Activated Mixture-of-Experts (A$^{2}$MoE), a framework that incorporates anatomical inductive biases within the model's computational path. A$^{2}$MoE introduces two key components: (1) a Histogram Representation Router (HRR) that conditions expert selection on global visual context and a predicted anatomical composition histogram, encouraging anatomy-dependent expert weighting; and (2) an Organ-Query Multi-Scale Projector (OQMSP) that utilizes learnable queries to extract organ-level embeddings for fine-grained alignment without requiring manual annotations at inference. By routing at the patch level rather than the token level, A$^{2}$MoE reduces routing complexity by orders of magnitude while satisfying load balancing by construction. Pre-trained on over 60,000 multi-phase CT scans, A$^{2}$MoE achieves state-of-the-art performance across segmentation, classification, and detection benchmarks. Furthermore, we demonstrate that our anatomically grounded inductive biases support robust generalization to MRI and ultrasound, establishing a scalable foundation for medical representation learning. The code is available at https://github.com/gmum/A2MoE.

cs.CV · cs.AI

版本更新 · v2arXiv:2605.26302

Your Agents Are Aging Too: Agent Lifespan Engineering for Deployed Systems

Jianing Zhu, Yeonju Ro, John Robertson, Kevin Wang, Junbo Li, Haris Vikalo, Aditya Akella, Zhangyang Wang

原文摘要

Long-lived AI agents are increasingly deployed as persistent operational systems, yet they are still mostly evaluated like freshly initialized models. Day-one benchmarks miss a basic systems question: how does an agent's reliability change after deployment? Even when model weights are frozen, an agent's effective state keeps changing as it compresses interaction history, retrieves from a growing memory store, revises facts after updates, and undergoes routine maintenance. Reliability therefore becomes a lifespan property of the full agent harness, not only a snapshot property of the base model. We introduce AgingBench, a longitudinal reliability benchmark for agent lifespan engineering: measuring not only whether deployed agents degrade, but what form the degradation takes and where repair should target. AgingBench organizes agent aging into four mechanisms: compression aging, where writing and rewriting drops future-relevant details; interference aging, where accumulated similar memories crowd out the target fact; revision aging, where changed or derived state is not updated correctly; and maintenance aging, where lifecycle events such as model swapping trigger regressions. To diagnose these failures, AgingBench uses temporal dependency graphs and counterfactual probes that produce diagnostic profiles for the write, retrieval, and utilization stages of the memory pipeline. Across 6 scenarios, 10 memory systems and 6 models from two families, we find that agent aging is not one-dimensional over 400 runs spanning 50-200 sessions: a well-formed reply can hide a value the memory no longer supplies; derived state collapses as updates accumulate; and the same wrong answer can require different repairs depending on what the diagnostic profile points to.

cs.AI · cs.CL · cs.MA

版本更新 · v2arXiv:2605.08553

VeriContest: A Competitive-Programming Benchmark for Verifiable Code Generation

Zichen Xie, Mrigank Pawagi, Yuxin Liu, Aaditi Rai, Lize Shao, John Berberian, Sicong Che, Wenxi Wang

原文摘要

Large language models can generate useful code from natural language, but their outputs come without correctness guarantees. Verifiable code generation offers a path beyond testing by requiring models to produce not only executable code, but also formal specifications and machine-checkable proofs. Progress in this direction, however, is difficult to measure: existing benchmarks are often small, cover only part of the pipeline, lack ground-truth proofs or rigorous specification validation, or target verification settings far from mainstream software development. We present VeriContest, a benchmark of 1,006 competitive-programming problems from LeetCode and Codeforces for verifiable code generation in Rust with Verus. Each problem includes a natural language description, expert-validated formal specifications, judge-accepted Rust code, Verus-checked proofs, and positive and negative test suites. VeriContest is constructed through a three-phase pipeline that scales from manually verified seed problems to semi-automated expansion with human-in-the-loop review. To strengthen benchmark quality, we also use testing to validate postcondition completeness. VeriContest supports both isolated and compositional evaluation of specification, code, and proof generation, and end-to-end verified program synthesis. Evaluating ten state-of-the-art models reveals a sharp gap between ordinary coding and verifiable code generation: the strongest model reaches 97.51% on natural-language-to-code generation, but only 57.16% on specification generation, 13.82% on proof generation, and 6.76% end-to-end. These results identify proof and specification generation as the central bottlenecks for current models and establish VeriContest as a rigorous platform for evaluating and training future systems that generate code with machine-checkable correctness.

cs.SE · cs.AI · cs.LG

版本更新 · v3arXiv:2602.13415

The Rise of AI Search: Implications for Information Markets and Human Judgement at Scale

Sinan Aral, Haiwen Li, Rui Zuo

原文摘要

We analyzed global, longitudinal AI and traditional search data to spark a conversation about the growth and impact of AI search, and discuss its policy implications for platforms, regulators, scientists and citizens. We executed 24,000 search queries in 243 countries, generating 2.8 million AI and traditional search results in 2024 and 2025. We found a rapid global expansion of AI search and key trends that reflect important, previously hidden, policy decisions by AI companies that impact human exposure to AI search worldwide. From 2024 to 2025, overall exposure to Google AI Overviews (AIO) expanded from 7 to 229 countries, with surprising exclusions like France, Turkey, China and Cuba, which did not receive AI search results. While only 1% of Covid search queries were answered by AI in 2024, over 66% of Covid queries were answered by AI in 2025---a 5600% increase signaling a policy shift on this critical health topic. Our results also show AI search surfaces significantly fewer long tail information sources, lower response variety, and significantly more low credibility and right- and center-leaning information sources, compared to traditional search, impacting the economic incentives to produce new information, market concentration in information production, and human judgment and decision-making at scale. The social and economic implications of these rapid changes in our information ecosystem necessitate a global debate about corporate and governmental policy related to AI search. We hope this discussion and the dataset released with this paper elevate the global dialogue on AI search and its impact.

cs.CY

新论文 · v1arXiv:2611.10958

Hybrid Source Code Change Impact Analysis

Katharina Stengg, Christian Macho, Martin Pinzger

原文摘要

Change impact analysis (CIA) helps developers identify code entities impacted by their initial changes. While several approaches for CIA were proposed, they still struggle with either low precision or low recall, thereby increasing manual effort for developers to verify the results. Furthermore, limitations in the used datasets and experimental setups can bias the results reported by many CIA approaches. In this paper, we first address the dataset limitations by manually labeling 1,931 changed code entities stemming from 263 commits of 22 open-source Java projects. Next, we introduce two variants of katIA, our code change impact analysis approach that combines static impact analysis with the reasoning capabilities of large language models (LLMs). The first variant uses a single prompt (katIA-SP) for refining an initial static impact set while the second variant uses three specialized agents (katIA-MA). The evaluation with our curated dataset shows that katIA-SP with Gemini 2.5 Flash achieved an F1-score of 22.4% when matching impacted entities by their fully qualified names (FQN) and 27.0% when matching them by their class and entity names (CE). The latter shows an improvement of 2.0 percentage points over the state-of-the-art. This score is further improved by katIA-MA which, using Gemini 2.5 Flash, yields an FQN-matching F1-score of 29.1% and a CE-matching F1-score of 33.3%. While these improvements come at the cost of increased median generation time from 0.570 s to 11.214 s and median token usage from 1,235 to 6,462 tokens, the improved performance justifies the additional cost. The comparison of three LLMs using katIA-SP finds that Gemini 2.5 Flash is the most consistent model. These results indicate that combining static impact analysis with LLM-based refinement, particularly with the multi-agent variant, can improve code change impact analysis.

cs.SE · cs.AI

新论文 · v1arXiv:2611.10956

Risk-Sensitive Reinforcement Learning for an Options Market Maker: An Empirical Study with Real S&P 500 Options

Jacky Chen, Ing-Haw Cheng, John Hull, Landis Li, Zissis Poulos, Justin Shi, Andreas Veneris, Zeyu Wang

原文摘要

Options market makers absorb client order flow and must hedge the resulting inventory risk under trading frictions. We study whether an option hedging reinforcement learning (RL) agent trained on historical market data outperforms three alternatives in tail-risk protection: (i) traditional delta hedging, (ii) simple hedge-ratio rules, and (iii) the same agent trained in simulated markets. Most RL hedging agents are trained in model-generated markets that do not capture the crashes and volatility regimes present in real data. We introduce an empirical replay environment using S&P 500 option data from 1996 to 2017 and compare against a matched geometric Brownian motion (GBM) environment, a stochastic-volatility (SABR) simulator, and a hybrid that values historical paths with Black-Scholes, all sharing the same portfolio mechanics, stochastic arrivals, costs, and test period. We train a distributional Twin Delayed Deep Deterministic Policy Gradient (TD3) agent and evaluate it out of sample over 2018-2023. The agent trained on empirical data reduces Conditional Value-at-Risk (CVaR) tail loss by 3.1% compared to delta hedging and outperforms every hedge-ratio rule chosen during the training period and every alternative training environment. The reduction reaches 8.9% in volatile and falling markets, but reverses to a cost of 7-10% in rising markets. Empirical training induces a state-dependent short net delta: the policy under-hedges negative-delta books, most strongly after prices have fallen. This tilt disappears with GBM training and is weaker with SABR or hybrid training. These findings suggest that exposure to historical market dynamics can materially change a tail-risk hedging policy, although the evidence rests on a single test path and the edge is regime-conditional.

q-fin.RM · cs.LG · q-fin.CP

版本更新 · v3arXiv:2603.29264

Linear Generator Networks for Nonlinear Partial Differential Equations

Shafayeth Jamil, Rehan Kapadia

原文摘要

Most physical systems are governed by nonlinear partial differential equations, yet the analytical tools that make linear systems transparent, such as eigenspectra, dispersion relations and modal decomposition, remain unavailable in nonlinear settings. We introduce Linear Generator Network-Koopman (LGN-KM), a neural operator that learns a nonlinear lift and a continuous-time linear generator for the lifted dynamics through the decomposition $L_k = S - D_k$, where $S$ is skew-symmetric (conservative coupling) and $D_k$ is positive-definite diagonal (mode-selective dissipation). The decomposition guarantees stability by construction and exposes the eigenstructure directly, making linear-systems analysis available on a nonlinear PDE. On 2D Navier-Stokes turbulence, the generator yields a complete multi-branch dispersion relation and models trained independently at viscosities $100\times$ apart learn the same coupling spectrum ($R^2 = 0.87$). The same architecture shows the corresponding diffusive damping on FitzHugh-Nagumo reaction-diffusion, and for pulse propagation in optical fibers, the oscillation frequencies of the learned generator match the fiber's dispersion relation, giving the group-velocity dispersion to within $3.1\%$ with no fitted constant. The architecture additionally enables long-horizon stability, $O(1)$ continuous-time evaluation, and physics-informed cross-regime model transfer.

cs.LG · physics.flu-dyn

版本更新 · v2arXiv:2610.39869

Incorporating Machine-Others: An Enactive Exploration of Human-LLM Interactions

Elena C. Cuffari, Marta Pérez-Verdugo, Xabier E. Barandiaran

原文摘要

New concepts based in interactional thinking are required to understand how humans are changed by relating to LLMs. Standard theories of technological impact upon users' autonomy are inadequate here, because this technology is capable of inducing linguistic interactions with humans in an unprecedented manner. Traditional theories of social cognition also fall short, because LLMs have neither autonomy nor minds nor sociality as such. And yet, humans interact, talk, and create with them. We base ourselves on enactive theory, particularly on the theory of Linguistic Bodies and recent developments of enactive accounts of AI, to explore how we make sense with machines. We argue that we incorporate machine-others in two ways: in the tool-like sense of incorporation as enabling particular skills, but also in the more linguistic and identity-tied sense of incorporating (and incarnating) LLMs' ways of languaging. However, LLMs are themselves excorporated and excarnated phantoms of our own languaging; we give a (machinic) body to our language. As such, we are not just incorporating machinic others; we are incorporating excorporated others. These conceptual advances draw a new map of our linguistic relation to LLMs, putting them in continuation with other forms of languaging involving other linguistic artifacts (e.g., religious books). We attend to some particular forms that this relation takes today, and how they may be impacting the autonomy and becoming of LLM-engaged humans. We introduce the idea of "susceptive sense-making" to characterize increased semiotic labour that is carried by the lack of friction that we sometimes encounter within these services.

cs.HC · cs.AI · cs.CY

新论文 · v1arXiv:2611.10952

Optimal Sampling and Transmission Policy for Information Freshness in Gossip Networks

Irtiza Hasan, Ahmed Arafa

原文摘要

We study the optimal sampling and transmission policies for a transmitter communicating with n gossiping receivers with the objective of tracking a source's status over time using a semantic freshness metric: Version Age of Information (VAoI). The transmitter observes the version changes in the source, and can acquire a new information version by paying a sampling cost. The receivers gossip, allowing information exchange among each other without direct transmission. Gossiping can save on transmission cost, but it may propagate stale version information, necessitating transmitter intervention. With imperfect communication links, we formulate an infinite horizon average cost Markov Decision Process (MDP) in order to jointly optimize receivers' VAoIs, sampling and transmission costs in a time slotted fully connected (FC) gossip network. We first solve the MDP using Relative Value Iteration (RVI) algorithm. Then, we prove that the sampling decision has a threshold structure in the transmitter VAoI. Further, under reliable gossiping links, we show that transmission and idling has an VAoI-difference threshold structure with minimum VAoI activation. Numerical results obtained using RVI show that the optimal policy consistently outperforms natural baselines. These results characterize how source sampling, direct transmission, and receiver gossip should be jointly coordinated for cost-aware semantic freshness in gossip networks.

cs.IT · cs.NI · eess.SP

新论文 · v1arXiv:2611.10950

Interpretable Cyber-Physical Attack Detection in Smart Grids: A Leakage-Controlled Multi-Testbed Evaluation of Fusion, Robustness, and Observability Limits

Muhammad Ridwanul Hoquea, Sarah Sharif, Reza Saeed Kandezy, Yaser Banad

原文摘要

Cyber-physical smart-grid detectors are typically treated as black boxes and validated exclusively on clean, temporally shuffled datasets, which risk overly optimistic performance claims. This work presents a multi-testbed evaluation study built around an interpretable, time-windowed fusion Random Forest, adopting the pessimistic result whenever evaluation protocols disagree. (i) On a public paired cyber-physical dataset, shuffled cross-validation is optimistic: macro-F1 falls from 0.96 to 0.88 +/- 0.06 under rolling-origin temporal evaluation. A topology-free graph convolutional network (GCN) serving as a control confirms that this lightweight model is competitive on these splits. (ii) The adaptive and adaptive-joint feature-space attacks, which are infeasible as realistic grid manipulations, degrade macro-F1 to 0.67 and 0.34, respectively. Adversarial training and randomized smoothing partially restore performance, and a physics-constrained evolution-strategy evasion on the IEEE 14-Bus testbed shows the same vulnerability pattern. (iii) On real IEC-104 traffic, the cyber view reliably catches structural attacks (recall of 0.87 to 0.98) but largely fails on semantic value manipulation (recall of 0.11 to 0.35). An observability taxonomy on the IEEE 14-Bus system reveals that stealthy false data injection defeats all three observation views. (iv) On a full AC weighted least-squares state-estimation testbed, a forecasting-aided temporal test is evaded by slow ramps precisely where a rate-invariant physics-manifold test sustains detection at a common 5% false-alarm target. A full end-to-end evaluation on IEEE 118-Bus confirms the ordering but bounds its strength: the manifold test detects every trial down to 0.05 degree/step and 0.48 at 0.02 degree/step, against 0.14 for the temporal test. All code and benchmarks are released.

cs.LG · cs.AI · cs.CR

新论文 · v1arXiv:2611.10949

Explicitly capturing demonstrator multi-modality for distillation into diffusion policies

Shao Yuan Chew Chia, Rebecca H. Jiang, Abhinav Agarwal, Andreas Hofmann, Leslie Pack Kaelbling, Russ Tedrake

原文摘要

The diversity of a distilled diffusion policy's outputs matters beyond how it impacts the policy's success rate. In particular, downstream applications like test-time search and policy improvement require exploration. Thus, we want to distill multi-modal demonstrators into diffusion policies which reproduce their conditional action distributions. Standard data collection for behavior cloning applies a sliding window to demonstration episodes, which pairs unique observation histories with actions. These datasets can be fit by a policy that is either multi-modal, or unimodal with high Lipschitz constant to capture a diversity of actions seen at nearby observation samples. Prior work finds that diffusion policies trained on sparse data learn the latter, memorizing one action per observation. We adapt vine sampling to behavior cloning data collection to resolve this ambiguity: at some states the demonstrator visits, query it $k$ times from exactly the same observation. On a synthetic task, we study how the number of actions per observation, $k$, affects the learned policy, and find that larger $k$ yields a policy that better matches the demonstrator's conditional distribution, including its multi-modality and diversity. On a 2D truck unloading task, vine sampling likewise leads to a policy closer to the demonstrator and substantially improves both best-of-$N$ and expert iteration performance.

cs.RO

新论文 · v1arXiv:2611.10947

Validating AI-Discovered Cloud Threats on Live Infrastructure: A Multi-Model, Multi-Cloud Study

Nicholas Pecka, Lotfi Ben Othmane, Renee Bryce

原文摘要

Cloud infrastructure threat modeling lacks empirical validation of AI-discovered threats. We present a three-phase methodology of multi-agent threat discovery, automated exploit synthesis, and non-destructive live validation, and apply it to three commercial foundation models on two cloud architectures, validating each threat natively on the cloud (AWS, GCP, or Azure) it was discovered against. Of 233 AI-discovered threats, 103 were confirmed and 34 refuted (75.2\% precision, 95\% CI [67.3, 81.7]); 44 were conditional (the named mechanism refuted but an equivalent impact shown through another path) and 52 indeterminate. Multi-model discovery helped through breadth, not agreement: the three models together found 2.2$\times$ the confirmed threats of the best single model at comparable precision, while threats reported by several models were confirmed no more often than single-model ones. False positives were not architecture-specific: they asserted access or system state the deployment did not have. Threats coded in advance as observable configuration resolved cleanly more often than multi-step behavioral threats (72.5\% vs.\ 51.6\%), which were more often conditional, suggesting that models more often misidentify the exploitation mechanism than the underlying weakness. AI-assisted discovery is a practical input to security workflows when paired with empirical validation.

cs.CR