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

+406新增论文
+306其中 AI 相关
+55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 11:42各信源进度 →

统计口径与数据新鲜度

统计 2026-11-15 13:40 — 2026-11-16 13:40(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-16 01:34最近发现新增版本:2026-11-16 11:42库内论文最新更新时间:2026-11-14 01:29

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。

23,754 已收录论文19,886 AI 相关6,892 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 23,754 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)
版本更新 · v3arXiv:2510.21615

Epipolar Geometry Improves Video Generation Models

Orest Kupyn, Théo Uscidda, Marta Tintore Gazulla, Fabian Manhardt, Federico Tombari, Christian Rupprecht

原文摘要

Video generation models have advanced significantly through the latent diffusion transformers trained with rectified flow techniques. Yet these models still struggle with geometric inconsistencies, unstable motion, and visual artifacts that break the illusion of realistic 3D scenes. 3D-consistent video generation could significantly impact numerous downstream applications in generation and reconstruction tasks. We explore how epipolar geometry constraints improve modern video diffusion models. Despite using massive training data, these models fail to capture fundamental geometric principles. We align diffusion models using pairwise epipolar geometry constraints via preference-based optimization, directly addressing unstable trajectories and geometric artifacts through mathematically principled geometric enforcement. Our approach efficiently enforces geometric principles without requiring end-to-end differentiability. Evaluation demonstrates that classical geometric constraints provide more reliable preference signals than the video-quality and geometry metrics based on foundational models. We construct preferences from static scenes with camera motion, where the epipolar metric is most reliable, while the aligned model generalizes to dynamic scenes. By bridging data-driven learning with classical computer vision, we reduce epipolar error by 31% and improve human-rated consistency from 54% to 72% without compromising visual quality.

cs.CV

新论文 · v1arXiv:2611.14209

Breakdown of Autoregressive Multi-Step Reasoning Under Concentrated vs. Diffuse Attention Head Dropout

Karol Struniawski

原文摘要

During extended wakefulness, mammalian neocortical networks experience localized periods of transient neuronal silence termed off-states. Here, we examine how analogous spatiotemporally concentrated disruptions affect sequential reasoning in autoregressive Large Language Models (LLMs). Evaluating 250 paired derivations on the GSM8K benchmark across two 8B models (Qwen3-8B and LLaMA-3.1-8B-Instruct), we contrast clustered bursts of attention head masking against budget-matched diffuse i.i.d. dropout. Concentrated bursts induce substantial reasoning degradation: at onset parameter $\mathcal{B}=0.10$ (scheduling $\sim 5.7\%$ of vulnerable head-token volume), Qwen3-8B accuracy drops from $91.2\%$ under diffuse noise to $78.8\%$ under burst dropout ($Δ= -12.4$ percentage points [pp], exact McNemar $p = 5.5 \times 10^{-6}$), while LLaMA-3.1-8B-Instruct drops from $84.0\%$ to $76.8\%$ ($Δ= -7.2$ pp, $p = 0.0198$). Conversely, dispersing the identical cumulative budget uniformly across generation steps via stratified quintile matching yields substantially milder degradation (retaining $91.2\%$ in Qwen and $84.0\%$ in LLaMA). In an exploratory factorial dissociation ($N=100$), single-step dropout density is associated with an acute drop in a single schedule draw ($-10.0$ pp on Qwen, $p_{\text{holm}} = 0.0425$), while multi-token continuity exhibits an inconclusive compounding trend ($-7.0$ pp, $p_{\text{holm}} = 0.1892$). Error analysis reveals that Qwen failures reflect derivation errors within formatted responses (conditional accuracy drop of $-11.4$ pp), whereas in LLaMA $22.2\%$ of discordant losses lack a final answer format line (conditional gap narrows to $-5.0$ pp). These findings demonstrate that autoregressive reasoning chains are particularly vulnerable to concentrated structural disruptions, providing empirical benchmarks for fault tolerance in transformer architectures.

cs.AI · cs.CL

新论文 · v1arXiv:2611.14207

DailyWildfireCAN: A Dataset and Benchmark for Next-Day Wildfire Spread Prediction in Canada

Mahacine Ettahri, Hager Radi Abdelwahed, Toluwaleke Olutayo, Daniel Aloise, Gaétan Marceau Caron

原文摘要

Wildfires represent a critical ecological and socio-economic challenge in Canada, where vast boreal forests and a warming climate have amplified the frequency and severity of extreme fire seasons. Predicting next-day wildfire spread can support fire management, but requires capturing complex interactions among weather, fuels, and terrain. Deep learning has emerged as a promising approach to learning these relationships from heterogeneous environmental data, yet its development and evaluation depend on representative datasets. Existing deep learning research on wildfire spread relies predominantly on US-focused datasets, leaving Canadian fire environments underrepresented. To address this gap, we present DailyWildfireCAN, a multi-modal, multi-temporal dataset and benchmark for predicting next-day wildfire spread across Canada. The dataset tracks continuous fire progression over multi-day events at a high spatial and temporal resolution of 90-m and 24-hour, respectively. This resolution preserves fine-scale information relevant to fire-edge geometry, local fuel variations, and terrain effects, supporting research toward improved daily wildfire spread forecasting. DailyWildfireCAN covers 2,440 wildfire events across eight fire seasons 2017-2024 and integrates 33 features across diverse modalities, including topography, meteorology, land cover, vegetation and forest structure, human influence indices, and satellite imagery. We establish a comprehensive benchmark comparing mono-temporal and multi-temporal prediction models, accompanied by a multi-dimensional evaluation framework assessing robustness across wildfire characteristics, geographic regions, and temporal conditions, spatial prediction quality, and sensitivity to reference label variations.

cs.CV

版本更新 · v2arXiv:2606.24969

Frequency Domain Reservoir Computing

Klaus Schertler, Xiomara Runge, Andrea Ceni, David Kappel, Claudio Gallicchio

原文摘要

While the quadratic sequence-length bottleneck of transformers has fueled a resurgence in recurrent models, effectively capturing complex dynamics requires architectures that balance efficient training with highly expressive latent states. Echo State Networks (ESNs) offer a compelling approach by utilizing fixed recurrent weights to circumvent backpropagation through time, enabling a closed-form training solution. However, achieving the expressivity needed for complex tasks demands large reservoirs, exposing an $\mathcal{O}(N^2)$ state-update bottleneck that prevents ESNs from matching the scale of contemporary recurrent models. To address this limitation, we introduce Frequency Domain Reservoir Computing (FRESCO), an ESN architecture operating entirely in the frequency domain while avoiding domain-shift overheads to achieve $\mathcal{O}(N)$ complexity for dense, non-linear updates via structured circulant recurrence. By employing a novel dimensional zero-padding input embedding, a packed frequency-domain readout, and a natively applied frequency-domain non-linearity, FRESCO drastically reduces computational costs and energy consumption of training and inference. Furthermore, FRESCO achieves competitive predictive performance on memory benchmarks, sequential classification, and multivariate long-horizon forecasting, offering a scalable and energy-efficient path forward for dense recurrent architectures.

cs.LG

版本更新 · v2arXiv:2609.27932

Binary Quantized Neural Network Training Is W[1]-Hard Parameterized by Input and Output Dimensions

Tao Jiang, Minbo Gao, Shaowei Cai

原文摘要

When the weights and biases of a neural network range over a fixed finite alphabet, training the network to fit a data set exactly becomes a finite combinatorial problem, and parameterized complexity asks which structural quantities of an instance make this problem tractable. Ganian, Sommer, and Sorge (ICLR 2026) showed that training quantized networks is fixed-parameter tractable when parameterized jointly by the input dimension $α$, the output dimension $ω$, and the treewidth of the architecture, and they asked whether $α+ω$ alone suffices. We show that it does not: training binary quantized networks is W[1]-hard parameterized by $α+ω$, so it admits no algorithm with running time $f(α+ω)\cdot|I|^{O(1)}$ for any computable $f$ unless FPT = W[1]. Hardness holds already for exact fitting of $k+1$ examples whose inputs equal their targets and form a coordinatewise prefix chain, and also when all biases are fixed to zero. The proof rests on a one-flip routing equivalence. On such data, nonnegative binary weights force every neuron to switch on at most once, and a network fits the data exactly if and only if the architecture contains vertex-disjoint paths that link each changing input to the corresponding output. Every neuron therefore has one of only $k+1$ activation profiles, yet deciding whether these profiles can be realized simultaneously is as hard as disjoint-path routing. Small input and output dimensions thus limit what each neuron can do locally, but not how the architecture forces neurons to share resources globally.

cs.LG

版本更新 · v2arXiv:2611.10595

Design and Evaluation of Secure Distributed Chaotic Image Encryption on ESP32-S3

Mohammed Almozaini, Fazal Noor, Sohail Alhazmi

原文摘要

The limited computational resources of Internet of Things (IoT) devices present challenges for secure image processing. This paper presents a distributed chaotic image encryption system using independent Wi-Fi-connected ESP32-S3 microcontrollers. A master-worker architecture distributes image blocks through master-coordinated chaotic sequence management, maintaining one logically continuous chaotic sequence by assigning block-specific starting states independently of worker assignments. The implemented system uses reversible chaotic substitution (SUBSTITUTE), while Elliptic Curve Digital Signature Algorithm (ECDSA)-signed discovery messages and Transport Layer Security (TLS) 1.3 with mutual authentication secure device communication. Experimental evaluation using one, two, and four workers demonstrates a reduction in execution time from 43.215 to 15.878 seconds, achieving a speed-up of 2.72 times. The encrypted image achieves a Shannon entropy of 7.999940 bits/byte and near-zero adjacent-pixel correlation. Exact image recovery is verified through matching Secure Hash Algorithm 256-bit (SHA-256) hashes and a Structural Similarity Index (SSIM) value of 1.0. Additional experiments demonstrate successful encryption and decryption using different worker counts and block sizes, automatic task reassignment following worker failure, and rejection of a mismatched private key during TLS authentication. These findings demonstrate the feasibility of secure, flexible, and distributed chaotic image processing across independent resource-constrained IoT devices.

cs.CR

版本更新 · v2arXiv:2607.09767

Listen to the Features: Voice Anonymization Driven by Content Embedding Matching over Signal Reconstruction

Adrien Schneider, Kacper Zabkowski, Anderson Augusma, Fr{é}d{é}rique Letu{é}, Maria Camila Pinzon, Dominique Vaufreydaz

原文摘要

The paper presents a voice anonymization model focusing on preserving content rather than producing realistic speech. It relies on content embeddings extracted from a frozen pretrained wav2vec2 encoder. These embeddings are decoded into an anonymized signal using vector quantization and a HiFi-GAN vocoder, both trained on LibriTTS without any waveform reconstruction loss or speaker embedding mapping. The training objective enforces that embeddings of the anonymized signal match those of the original one. While training, an auxiliary speaker classification branch with a gradient reversal layer is used to discard speakerspecific information. Results show that this straightforward embedding-based approach achieves very low WER (2.53) with an anonymization performance (EER 13.39) ranking within first level for VPC. Notably, emotions are partially preserved (UAR 43.91), even without a supporting training objective, while the anonymized voice is audible without reconstruction loss.

eess.SP · cs.AI

版本更新 · v2arXiv:2605.06466

Diversity Curves for Graph Representation Learning

Katharina Limbeck, Nadja Häusermann, Martin Carrasco, Guy Wolf, Bastian Rieck

原文摘要

Graph-level representations are crucial tools for characterising structural differences between graphs. However, comparing graphs with different cardinalities, even when sampled from the same underlying distribution, remains challenging. Unsupervised tasks in particular require interpretable, scalable, and reliable size-aware graph representations. Our work addresses these issues by tracking the structural diversity of a graph across coarsening levels. The resulting graph embeddings, which we denote diversity curves, are interpretable by construction, efficient, and directly comparable across coarsening hierarchies. Specifically, we track the spread of graphs, a novel isometry invariant that is inherently well-suited for encoding the metric diversity and geometry of graphs. We utilise edge contraction coarsening and prove that this improves expressivity, thus leading to more powerful graph-level representations than structural descriptors alone. Demonstrating their utility over a range of baseline methods in practice, we use diversity curves to (i) cluster and visualise simulated graphs across varying sizes, (ii) distinguish the geometry of single-cell graphs, (iii) compare the structure of molecular graph datasets, and (iv) characterise geometric shapes.

cs.LG

新论文 · v1arXiv:2611.14204

Performance Portability Explained: Insights from accelerating ICON microphysics

Faveo Hörold, Georgiana Mania, Panagiotis Adamidis, Harshada Balasubramanian, Jörg Behrens, Yakup Budanaz, Alexandru Calotoiu, Nicoletta Farabullini 等 18 位作者

原文摘要

Scientific computing is under increasing pressure to adapt to HPC hardware that is shaped by AI workloads. In these modern ecosystems, extracting reasonable performance without investing major engineering effort is a central issue for domain scientists. Correctness constraints and intricate reference implementations represent further impediments to development. Instead of using a double-precision implementation as a reference, considering the underlying scientific problem directly opens more opportunities for performance improvements when updating and rewriting applications. We take seven different portability frameworks---covering pragma-based, DSL, and data-centric approaches---and evaluate them on a microphysics kernel of the ICON climate model. Our performance benchmarks show that each different HPC system benefits from a different combination of optimizations, so we develop the measure of framework expressivity to gauge how easily each framework can customize portable implementations in this way.

cs.DC · cs.PF · cs.PL

版本更新 · v2arXiv:2611.07342

Selective Retrieval Routing for Multi-Violation Knowledge Graph Repair

Tung-Wei Lin, Gabe Fierro, Han Li, Tianzhen Hong, Pierluigi Nuzzo, Alberto Sangiovanni-Vincentelli

原文摘要

Knowledge graphs often contain missing or inconsistent facts that undermine the applications built on them. Schema validation detects such violations but does not identify which of several valid repairs recovers the intended graph. External corpora can supply the evidence needed to identify the intended repair, but retrieving from them is costly and not always successful. We propose a framework for selective retrieval in iterative graph repair. An LLM repair agent explores and edits the graph, while a router controls its access to a researcher agent that retrieves external evidence. We extend a violation-injection framework to generate cases with multiple compatible violations and known reference repairs. The agent's repair outcomes on these cases provide supervision for training the deployment-specific router. On two building-automation datasets, researcher access improves repairs for some violations and degrades them for others, with effects differing across deployments. The router uses fewer repair-time tokens than always enabling access in all six evaluation suites. It achieves higher repair $F_1$ than always disabling access in five of six suites.

cs.DB · cs.AI

版本更新 · v3arXiv:2504.01551

Identifying Macro Causal Effects in a C-DMG over ADMGs

Simon Ferreira, Charles K. Assaad

原文摘要

Causal effect identification using causal graphs is a fundamental challenge in causal inference. While extensive research has been conducted in this area, most existing methods assume the availability of fully specified directed acyclic graphs or acyclic directed mixed graphs. However, in complex domains such as medicine and epidemiology, complete causal knowledge is often unavailable, and only partial information about the system is accessible. This paper focuses on causal effect identification within partially specified causal graphs, with particular emphasis on cluster-directed mixed graphs (C-DMGs) which can represent many different acyclic directed mixed graphs (ADMGs). These graphs provide a higher-level representation of causal relationships by grouping variables into clusters, offering a more practical approach for handling complex systems. Unlike fully specified ADMGs, C-DMGs can contain cycles, which complicate their analysis and interpretation. Furthermore, their cluster-based nature introduces new challenges, as it gives rise to two distinct types of causal effects: macro causal effects and micro causal effects, each with different properties. In this work, we focus on macro causal effects, which describe the effects of entire clusters on other clusters. We establish that the do-calculus is both sound and complete for identifying these effects in C-DMGs over ADMGs when the cluster sizes are either unknown or of size greater than one. Additionally, we provide a graphical characterization of non-identifiability for macro causal effects in these graphs.

cs.AI

新论文 · v1arXiv:2611.14201

CFGKAT: A Complete Calculus for Non-Local Control Flow

Spencer Van Koevering, Alexandra Silva, Cheng Zhang, Tobias Kappé

原文摘要

CFGKAT is an extension of guarded Kleene Algebra with Tests (GKAT) that adds non-local control flow (e.g., break, goto) while maintaining an efficient decision procedure. An axiomatization of equivalence for CFGKAT presents unique barriers created by the presence of non-local control flow and contextual semantics of goto which compromises compositional reasoning. In this paper, we overcome these barriers and present a sound and complete axiomatization of program equivalence in CFGKAT. We verify the loop case of the Erosa-Hendren goto elimination algorithm, a difficult syntactic metatheorem which requires reasoning about fixpoints, control-flow contexts, and mutable state. We mechanize the metatheory and case study in Rocq.

cs.PL

版本更新 · v2arXiv:2605.14786

Known By Their Actions: Fingerprinting LLM Browser Agents via UI Traces

William Lugoloobi, Samuele Marro, Jabez Magomere, Joss Wright, Chris Russell

原文摘要

As LLM-based agents increasingly browse the web on users' behalf, a natural question arises: can websites passively identify which underlying model powers an agent? Doing so would represent a significant security risk, enabling targeted attacks tailored to known model vulnerabilities. Across 14 frontier LLMs and four web environments spanning information retrieval and shopping tasks, we show that an agent's actions and interaction timings, captured via a passive JavaScript tracker, are sufficient to identify the underlying model with up to 96\% F1 within a fixed harness. Although fingerprints are harness-specific, with cross-harness transfer falling to near chance, pooling traces across harnesses recovers model identification at 0.74 to 0.81 Macro-F1. We further show that strong classifiers can be trained from roughly one third of the available traces, and that identification improves steadily as more events are observed. Injecting randomised timing delays between actions substantially degrades classifier performance, but does not provide robust protection: a classifier retrained on delayed traces largely recovers performance. We release our code and a labelled corpus of agent traces at https://github.com/KabakaWilliam/known_actions.

cs.CR · cs.AI · cs.HC · cs.LG

新论文 · v1arXiv:2611.14196

Joint Quantization and Dynamic Partitioning for Context-Aware Edge Vision Transformers

Zhu Jiaqi, Jain Prakriti, Katare Dewant, Kumar Saurabh

原文摘要

Deploying vision transformer models across connected and automated vehicles (CAVs) requires joint management of computation and Vehicle-to-Vehicle (V2V) communication. Static split-inference methods use fixed partition points and cannot adapt to time-varying link bandwidth, processing load, and concurrent multi-stream traffic. This paper proposes an edge orchestration framework that jointly selects model partition points, per-layer quantization bitwidths, and execution placement across heterogeneous vehicular compute nodes. The joint partitioning and mixed-precision allocation problem is formulated as a Mixed-Integer Linear Program (MILP) that minimizes compute and communication energy subject to end-to-end latency and task-quality constraints. The framework is evaluated on Jetson Orin Nano (8~GB), Jetson Orin NX (16~GB), and Jetson AGX Orin (32~GB) nodes using OPV2V-driven multi-stream workloads with $K \in \{2,4,6,8\}$. Across the evaluated configurations, the proposed formulation reduces V2V communication energy by $33.3$--$36.0\%$ relative to a Uniform INT8 split. At $K=8$, end-to-end task completion latency is reduced by $34.0\%$ on the Orin Nano and $33.1\%$ on the Orin NX relative to the same baseline, while limiting the reduction in 3D detection accuracy to $3.1$--$4.1$ percentage points in $\mathrm{mAP}_{50}$ relative to FP16 execution.

cs.AI

版本更新 · v2arXiv:2602.03623

Self-supervised Physics-Informed Manipulation of Deformable Linear Objects with Non-negligible Dynamics

Youyuan Long, Gokhan Solak, Sara Zeynalpour, Heng Zhang, Arash Ajoudani

原文摘要

We address dynamic manipulation of deformable linear objects by presenting SPiD, a physics-informed self-supervised learning framework that couples an accurate deformable object model with an augmented self-supervised training strategy. On the modeling side, we extend a mass-spring model to more accurately capture object dynamics while remaining lightweight enough for high-throughput rollouts during self-supervised learning. On the learning side, we train a neural controller using a task-oriented cost, enabling end-to-end optimization through interaction with the differentiable object model. In addition, we propose a self-supervised DAgger variant that detects distribution shift during deployment and performs offline self-correction to further enhance robustness without expert supervision. We evaluate our method primarily on the rope stabilization task, where a robot must bring a swinging rope to rest as quickly and smoothly as possible. Extensive experiments in both simulation and the real world demonstrate that the proposed controller achieves fast and smooth rope stabilization, generalizing across unseen initial states, rope lengths, masses, non-uniform mass distributions, and external disturbances. Additionally, we develop an affordable markerless rope perception method and demonstrate that our controller maintains performance with noisy and low-frequency state updates. Furthermore, we demonstrate the generality of the framework by extending it to the rope trajectory tracking task. Overall, SPiD offers a data-efficient, robust, and physically grounded framework for dynamic manipulation of deformable linear objects, featuring strong sim-to-real generalization.

cs.RO

版本更新 · v2arXiv:2610.19013

Data Density Scaling Laws for Image Self-Distillation

Alvard Barseghyan, Ani Vanyan, Hakob Tamazyan, Hrant Khachatrian

原文摘要

Current scaling law formulations suggest that increasing the number of unique samples in a dataset consistently improves model performance, while repeated exposure to the same samples provides diminishing value. In this work, we challenge this assumption for image self-distillation models. We train iBOT models on random subsets of seven datasets spanning satellite imagery, driving scenes, egocentric video, and natural images, and evaluate their frozen representations on downstream tasks. We propose a density-interaction scaling law that combines unique-image count $U$ and repetition $R$, fitting it on runs with at most 50 million image presentations and testing it at larger budgets $C$. On Maxar dataset, a random subset containing approximately 1.5% of the training pool improves average nearest-neighbor classification accuracy by 3.11 percentage points over training on the full pool at the same budget of 200 million image presentations. Smaller subsets also outperform the full pool on SATLAS and Ego4D, whereas ImageNet favors larger pools at higher budgets. At a fixed subset size, further training can improve performance, lead to a plateau, or reduce performance. Our law captures smaller-subset advantages that the compared baselines cannot represent and improves prediction at higher budgets on Maxar, SATLAS, and Ego4D under nearest-neighbor evaluation. These findings show that both the number of unique images and how often they are repeated matter when allocating a training budget.

cs.LG

新论文 · v1arXiv:2611.14194

You Can Have It All: Small sparse induced-universal graphs for minor-closed classes

Vida Dujmović, Cyril Gavoille, Gwenaël Joret, Piotr Micek, Pat Morin, David R. Wood

原文摘要

We show that, for every fixed proper minor-closed graph class $\mathcal{G}$ and every positive integer $n$, there exists a graph $U_n$ with $n^{1+o(1)}$ vertices and edges such that every $n$-vertex graph in $\mathcal{G}$ is isomorphic to an induced subgraph of $U_n$. This result generalizes and unifies the results of Dujmović et al. (J. ACM 2021) on induced-universal graphs and the results of Esperet, Joret, and Morin (J. London Math. Soc. 2023) on sparse induced-universal graphs from planar graphs to all proper minor-closed graph classes. It simultaneously improves the previous bounds for the number of vertices in induced-universal graphs (previously $O(n^2)$ obtained as a corollary of a result of DeVos et al. (J. Comb. Theory, Ser. {B} 2004) and a result of Gavoille and Labourel (ESA 2007)) and the number of edges in subgraph-universal graphs (previously $O(n^{3/2})$ by Babai et al. (Theory and Practice of Combinatorics 1982)).

math.CO · cs.DM

新论文 · v1arXiv:2611.14191

The Monophonic Directed Convexities

Júlio Araújo, Ana Karolinna Maia, Thiago Marcilon, Nicolas Nisse, Rudini M. Sampaio

原文摘要

Graph Convexity is a topic with many papers in the literature, especially on the $P_3$, geodesic, and monophonic convexities in undirected graphs. Regarding directed graphs, Erd{\H o}s et al. in 1972 and Chartrand and Zhang in 2000 obtained the first results on the $P_3$ and geodesic convexities for directed graphs, respectively. In this paper, we start the investigation of monophonic convexity on directed graphs. We define two convexities, the monophonic and the strong monophonic directed convexities, related to the minimal and the induced directed paths, respectively. We show that deciding whether a set is convex is polynomial-time solvable in the monophonic convexity, but coNP-complete in the strong monophonic convexity. For both convexities, we prove that the hull number is NP-complete even in DAGs. Regarding the monophonic convexity, we prove that the hull number is polynomial time solvable in tournaments, but the interval number is NP-complete in tournaments and also in bipartite oriented graphs.

cs.CC · math.CO

新论文 · v1arXiv:2611.14186

Koopman Model-Based Reinforcement Learning

Wenjian Hao, Paulo C. Heredia, Shaoshuai Mou

原文摘要

We propose a Koopman model-based reinforcement learning (K-MBRL) algorithm for controlling nonlinear robotic systems with unknown dynamics. The K-MBRL learns a control policy by minimizing an approximate policy objective that combines the analytical immediate cost with an estimate of the future cost evaluated at the one-step predicted state. To this end, we develop a stochastic Koopman operator-based learning method to approximate the unknown nonlinear dynamics in a linear representation, while a critic function estimates the remaining future cost. This formulation offers two key advantages. First, the linear Koopman dynamics simplify the model-dependent policy gradient computation to a constant matrix product, enabling computationally efficient policy improvement. Second, one-step model propagation mitigates the accumulation of prediction errors associated with long-horizon rollouts while retaining long-term cost information through the critic. The learned policy enables real-time control through feedforward evaluation without online optimization. We establish policy learning convergence guarantees under standard stochastic approximation assumptions. Simulations on HalfCheetah and quadruped four-legged locomotion tasks demonstrate strong sample efficiency and improved performance compared with classical model-free and model-based reinforcement learning baselines. A pendulum swing-up task is used to assess policy gradient approximation accuracy and conduct ablation studies on the learning mechanism and key hyperparameters. The proposed K-MBRL is further validated on a physical quadruped robot performing a challenging sequence of maneuvers: rising to an upright posture supported by two rounded rear feet, maintaining balance during bipedal walking, and safely returning to the ground, as shown in Fig.1.

cs.RO · eess.SY

版本更新 · v3arXiv:2505.04005

Iterative Orthogonalization Scaling Laws

Devan Selvaraj

原文摘要

The muon optimizer has picked up much attention as of late as a possible replacement to the seemingly omnipresent Adam optimizer. Recently, care has been taken to document the scaling laws of hyper-parameters under muon such as weight decay and learning rate. However, at much larger scales the iterative orthogonalization procedure present in muon may suffer a possible issue as the singular values of random matrices shrink with scale. This paper shows this scaling behavior theoretically and empirically on random matrices but does not suggest what to do about it.

cs.LG

版本更新 · v2arXiv:2611.08982

Stabilizing Vector Approximate Message Passing with Circuit-Designed Lag-Lead Damping

Mohamed Akrout

原文摘要

Vector approximate message passing (VAMP) often fails to converge on ill-conditioned matrices, and its damping factor is tuned either manually or adaptively. Using the fact that VAMP iterations are the discretization of an electric circuit, we show that the denoiser and the likelihood act as nonlinear resistors, the Onsager correction is a mirror resistor and damping is a lag filter. This circuit gives a closed-form loop gain whose spectrum can predict when VAMP fails. Because a lag filter cannot isolate the oscillating modes, we add a lead capacitor whose design often results in a negative capacitance. Across a wide range of condition numbers, our proposed damping strategy achieves a higher convergence rate than adaptive damping and Anderson acceleration at a lower mean iteration cost. On ill-conditioned multipath channels, across ranks and sparsity levels, it also converges more reliably than existing damping baselines.

cs.IT

新论文 · v1arXiv:2611.14183

An Augmented Lagrangian Approach to Lifted Bellman Linear Programming

Jongchan Park, Hyukjun Yang, Narim Jeong, Donghwan Lee

原文摘要

Temporal-difference critics regress onto a bootstrapped target and usually need a target network. Lifted Bellman Linear Programming (LBLP) instead expresses the in-sample optimal values of offline RL as the solution to a linear program over the dataset. Its neural solver ALBUM relaxes the constraints into hinge penalties with fixed coefficients, and its guarantees are conditions on coefficients chosen in advance. We solve the same program with the method of multipliers: the coefficients become multipliers learned by dual ascent, with one penalty parameter $ρ$. In the convex case the fixed points are the KKT pairs of LBLP, and at every stationary point the applied constraint weights balance the objective exactly. The critic can serve a Gaussian actor, a flow actor, and best-of-N sampling, and for the Gaussian actor we propose an advantage-normalized DDPG+BC objective. With a single $Q$ and $V$ and no target network, our AL-LBLP with best-of-N reaches 60.1\% average success on the 50 state-based OGBench tasks. On long-horizon tasks, it reaches 81.5% on humanoidmaze-giant and 79.8% on antmaze-giant. It does not collapse up to batch size 8192.

cs.AI

版本更新 · v3arXiv:2610.18039

Prune-and-Merge: Training-Free Scaling of Vision Transformers

Vatsal, Soumil Malhotra, Priyanshu Chahal, Sanjeev Kumar

原文摘要

Vision Transformers achieve strong performance but incur high computational costs from quadratic token interactions. Training-free token reduction methods improve efficiency, but their robustness remains underexplored. We propose Prune-and Merge ViT, a training-free framework for off-the-shelf models. It combines class attention-based pruning with similarity-based merging to reduce redundancy while preserving semantic information. To evaluate robustness we introduce two metrics. Relative Accuracy Drop (RAD) measures relative accuracy degradation under transformations, and Prediction Flip Rate (PFR) quantifies prediction consistency. On pretrained ViT and DeiT, Prune-and-Merge reduces computation competitively while maintaining robustness and better accuracy than existing token reduction methods. Our analysis suggests that hybrid token reduction does not introduce hallucination-like behavior and preserves prediction stability for common image transformations.

cs.CV · cs.AI

新论文 · v1arXiv:2611.14176

SpecValley: Aggregation as Spectral Valley in Dense Heterophilic Graphs

Christoph Jahn, Delvin Bacho, Urs Waldmann, Bastian Goldluecke

原文摘要

Node classification in heterophilic graphs remains an open problem: aggregating over neighbourhoods can damp precisely the part of the signal that carries the labels. The field has answered with ever more expressive propagation operators, leaving the aggregation step that precedes them fixed by degree normalisation. However, degree normalisation acts as a spectral valley in its own right, attenuating a fixed middle band whose position at lambda equal 1 is set by the normalisation rather than by the data, exactly where the eigenvalues of dense graphs accumulate. We therefore begin with the representations rather than the propagation, in two stages: a learnable aggregation followed by an ordinary spectral filter. The first, SpecValley learns the position, sharpness and flank gains of the valley for every graph. We show formally how the aggregation operator and downstream filter interact. We establish that the response 1 minus lambda of degree normalisation vanishes exactly at that accumulation point. A spectral energy budget shows that what aggregation removes from a band, no linear spectral filter can recover. Crowding alone says nothing about the benefit. That is decided by how much label energy the valley removes, which we measure for every graph. SpecValley achieves strong results across heterophilic benchmarks, and a controlled ablation over aggregation operators and downstream filters attributes the gain to aggregation rather than the filter.

cs.CV · cs.LG

新论文 · v1arXiv:2611.14174

Cross-Border Fulfillment Center Selection via Doubly Robust Estimation and Linear Programming

Kriti Mahajan, Patrick Bloebaum

原文摘要

We introduce the cross-border (XB) fulfillment center (FC) Selection Model: a multi-stage optimization framework combining forecasting, doubly robust estimation, and linear programming to select optimal source FCs. For each source-destination shipping arc, the objective is to choose a subset of source-country FCs that minimize delivery time and cost while maximizing profit and shipped units under a fixed domestic network. We evaluate the model on three production-scale international shipping corridors for a large e-commerce company using 12 months of shipment data, employing both aggregate offline replay and shipment-level counterfactual nearest-neighbor matching. Across all shipping corridors, the XB FC Selection Model achieves 8.5-51.1% reductions in delivery time and 4.4-48.3% reductions in logistics cost relative to human expert-defined FC selection policies, with up to 6.5 percentage-point improvements in 5/5 target compliance (5 days, $5 USD). Pareto analysis shows the model consistently dominates single-objective ranking strategies and unconstrained LP on the efficiency-reallocation frontier, with all results statistically significant.

cs.AI

新论文 · v1arXiv:2611.14171

BARS: Budget-Aware Sequential Sampling with Refusal for Majority Identification under Unknown Distributions

Shenxi Liu, Yiwei Li, Mingyang Zhao, Yuhang Tian, Kan Li

原文摘要

Repeated sampling with majority selection is an effective means of enforcing self-consistency in large language models. Recently, a variant has also been introduced that terminates early to save costs when the output distribution is favorable. But it still cannot yield a correct confidence estimate from the answer distribution. For this issue, we formalize this as majority identification under an unknown distribution with a budget and a target error rate, and propose BARS, a sequential rule certifying the top-two gap and returning an early stop, a budgeted majority vote, or a refusal when feasibility cannot be established. A refusal is a statement about the rule and its budget, not a claim that a question is unanswerable, and it tells practitioners when to widen the budget or switch models. A certified mode carries proven bounds on the joint answering error and on refusing an instance the budget could handle, while a practical mode, used in our experiments, replaces them with empirical calibration. On synthetic instances drawn from known distributions over thousands of seeds, the difficulty-driven behavior is recovered and the price of the certified mode is measured.On GSM8K the practical mode draws 22.3\% fewer samples than fixed-8 sampling over the same pool, refused questions included, at the cost of declining 18.8\% of the questions. On MATH, it greatly improves the accuracy of its output answers into 82.5\% at the cost of honestly refusing to answer half of the difficult questions that the model itself is unable to solve.

cs.AI

版本更新 · v2arXiv:2607.09553

Writing Bug Reports for Software Repair Agents: What Information Matters Most?

Vincenzo Luigi Bruno, Alessandro Giagnorio, Daniele Bifolco, Leon Wienges, Massimiliano Di Penta, Gabriele Bavota

原文摘要

Software development is increasingly moving toward agentic-first workflows. This includes AI agents responsible for generating initial fixes for submitted issue reports. In this setting, issue reports are no longer merely documentation for human maintainers; they become the primary task specification for the agent. However, little is known about how such reports should be written to maximize the agent's chances of producing a correct fix. We study what makes a bug report agent-ready. Starting from the SWE-Bench Verified benchmark (i.e. a collection of 500 real repository issues with human-written gold patches and test suites for evaluating generated fixes) we manually classify each issue by change type (e.g. bug fix vs refactoring) and annotate each sentence with its information type, such as observed behavior, expected behavior, reproduction steps, localization cues, and suggested fixes. We focus on the 441 issues representing bug reports, and we run on them mini-swe-agent using three LLM backbones (i.e. GPT-5-mini, MiniMax M2.5, and Gemini 3 Flash). We then fit a binomial regression model to estimate the incremental association between each information type and agent success, controlling for confounding factors. Our results suggest that agentic-first reports benefit most from information that narrows the agent's search and repair space. Suggested fixes, expressed either in code or natural language, show the strongest positive associations with pass probability, while localization cues show positive but non-significant associations. An ablation study removing selected information types confirms that agents benefit less from information traditionally useful to humans, such as reproduction steps, and more from sentences that expose a repair direction.

cs.SE

版本更新 · v2arXiv:2502.18733

Cross-Modality Investigation on WESAD Stress Classification

Eric Oliver, Sagnik Dakshit

原文摘要

Deep learning's growing prevalence has driven its widespread use in healthcare, where AI and sensor advancements enhance diagnosis, treatment, and monitoring. In mobile health, AI-powered tools enable early diagnosis and continuous monitoring of conditions like stress. Wearable technologies and multimodal physiological data have made stress detection increasingly viable, but model efficacy depends on data quality, quantity, and modality. This study develops transformer models for stress detection using the WESAD dataset, training on electrocardiograms (ECG), electrodermal activity (EDA), electromyography (EMG), respiration rate (RESP), temperature (TEMP), and 3-axis accelerometer (ACC) signals. The results demonstrate the effectiveness of single-modality transformers in analyzing physiological signals, achieving state-of-the-art performance with accuracy, precision and recall values in the range of $99.73\%$ to $99.95\%$ for stress detection. Furthermore, this study explores cross-modal performance and also explains the same using 2D visualization of the learned embedding space and quantitative analysis based on data variance. Despite the large body of work on stress detection and monitoring, the robustness and generalization of these models across different modalities has not been explored. This research represents one of the initial efforts to interpret embedding spaces for stress detection, providing valuable information on cross-modal performance.

cs.LG · cs.AI

版本更新 · v3arXiv:2605.06749

A Statistical Framework for Algorithmic Collective Action with Multiple Collectives

Claudio Battiloro, Pietro Greiner, Dario Rancati, Bret Nestor, Oumaima Amezgar, Francesca Dominici

原文摘要

As learning systems increasingly shape everyday decisions, Algorithmic Collective Action (ACA), i.e., users coordinating changes to shared data to steer model behavior, offers a complement to regulator-side policy and corporate model design. Real-world collective actions have traditionally been decentralized and fragmented into multiple collectives, despite sharing overarching objectives, with each collective differing in size, strategy, and actionable goals. However, most of the ACA literature focuses on single collective settings. To address this, we propose the first comprehensive statistical framework for ACA with multiple collectives acting on the same system. In particular, we focus on collective action in classification, studying how multiple collectives can influence a classifier's behavior. We provide quantitative statistical bounds on the success of the collectives, considering the role and the interplay of the collectives' sizes and the alignment of their goals. We make such bounds computable by each collective with only partial knowledge of other collectives' sizes and strategies. Finally, we numerically illustrate our framework on simulations inspired by interventions for climate adaptation in smart cities, demonstrating the usefulness of our bounds.

stat.ME · cs.AI

新论文 · v1arXiv:2611.14168

Representational Atoms in Neural Networks

Chenhui Hu, Pengfei Cao, Kang Liu, Jun Zhao

原文摘要

Understanding the internal representations of neural networks and characterizing their relationship with human conceptual structure are two critical questions for elucidating model mechanisms. The former reveals how learned knowledge is organized in internal representations, whereas the latter provides a basis for interpreting these representations through human conceptual structure. Here, we formally define fundamental representational units (FRUs) and establish two evaluation criteria: fidelity and stability. We further prove that threshold-activated sparse autoencoders (TSAEs) can identify FRUs with high fidelity and stability under appropriate conditions, and validate this result through large-scale experiments. Further analyses reveal that FRUs with higher stability exhibit greater monosemanticity and can be composed across layers to recover semantic organization corresponding to human conceptual structure. These results provide a unified framework for defining, evaluating and identifying FRUs in neural networks, and establish a foundation for characterizing the relationship between neural network representations and human conceptual structure.

cs.CL · cs.AI