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

+979新增论文
+781其中 AI 相关
+119已有论文修订
+97新增 AI 导读

arXiv 最近完成扫描:2026-11-20 08:48 · 全站最近入库:2026-11-20 19:58各信源进度 →

统计口径与数据新鲜度

统计 2026-11-20 01:10 — 2026-11-21 01:10(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:2026-11-20 08:48最近发现新增版本:2026-11-20 19:58库内论文最新更新时间:2026-11-20 02:59

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

28,961 已收录论文24,030 AI 相关8,912 有修订112 HF 社区发现

浏览论文库

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

找到 21,358 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-20 08:46(北京时间)
版本更新 · v2arXiv:2609.25949

Flux: Optimal Scheduling of Optical Circuit Switches for LLM Training

Arno Troch, Seyyidahmed Lahmer, Abubakr Nada, Roger Sanchez-Vital, Jeroen Famaey, Michael Peeters

原文摘要

Optical Circuit Switching (OCS) offers high bandwidth density and energy efficiency for LLM training, but incurs a non-negligible reconfiguration delay. Prior work typically schedules optical circuit switches independently of compute, using aggregate traffic demand to determine which circuits to provision and when. We argue that this separation creates a fundamental inefficiency: reconfigurations that ignore the compute timeline can stall communication, resulting in low circuit utilization and large buffer requirements. In this paper, we present Flux, a scheduler that optimally schedules optical circuit switches based on the structure of the entire workload. Flux remains effective across a wide range of switching speeds by reusing circuits and amortizing reconfiguration delay behind compute and communication. We show that Flux reduces training iteration time by up to $10\times$ and peak NIC buffer requirements by more than three orders of magnitude compared to traditional periodic schedulers.

cs.NI · cs.DC

新论文 · v1arXiv:2611.23341

Management of Behavioral Addictions via Artificial Intelligence based Digital Technologies

Süleyman Eken, Serdar Solak, Mustafa Hikmet Bilgehan Uçar, Bahadır Geniş, Ömer Kardaş, Hande Albayrak, İsmail Emre Ak, Nesibe Sağlam

原文摘要

Behavioral addictions, such as problematic gaming, gambling, social media use, and online shopping, have emerged as a growing global concern with significant psychological, social, and economic consequences. Traditional assessment and treatment approaches, while clinically grounded, often struggle with scalability, accessibility, and long-term engagement. In recent years, advances in digital technologies and artificial intelligence (AI) have enabled the development of novel, data-driven solutions for the prevention, detection, treatment, and recovery of behavioral addictions. This book presents a comprehensive survey of the management of behavioral addictions through digital technologies, bridging clinical foundations with state-of-the-art computational approaches. This book aims to provide researchers, clinicians, and practitioners with a unified, interdisciplinary perspective on the opportunities and limitations of AI-based digital technologies in behavioral addiction management,and to highlight pathways toward more scalable, personalized, and effective intervention strategies.

cs.CY · cs.AI

新论文 · v1arXiv:2611.22352

Fair Bubble Sort: Provably Optimal Fair Ranking with Continuous Sensitive Attributes

Antonio Ferrara, Fabio Vitale, Atsushi Miyauchi, Francesco Bonchi

原文摘要

Most fair-ranking methods assume categorical protected attributes, requiring continuous attributes such as age or income to be discretized into groups. This introduces arbitrary thresholds, loses fine-grained information, and ignores the natural ordering of the attribute. In this paper, we study the problem of fair ranking with continuous protected attributes without relying on thresholding. We introduce Continuous Pairwise Parity (CPP), a fairness notion based on Kendall correlation between ranking positions and the protected attribute, and seek rankings that satisfy a prescribed CPP constraint while minimizing their Kemeny distance from an initial score-based ranking. To solve this problem, we propose Fair Bubble Sort (FBS), an efficient post-processing algorithm based on targeted adjacent swaps. We prove that FBS is exactly optimal for the unweighted Kemeny distance and provide approximation guarantees for the score-weighted setting. FBS is output-sensitive, with running time determined by the number of swaps required to meet the fairness constraint. Experiments on synthetic and real-world datasets show that FBS is scalable and consistently outperforms discretization-based baselines, achieving a superior fairness-accuracy Pareto front.

cs.LG · cs.CY · cs.DS

版本更新 · v2arXiv:2610.24026

Dynamical Kernel Attention: Estimating the Present from a Record of the Past

Peter Racioppo

原文摘要

Self-attention encodes where a past token lies, but not how its uncertainty grows with time: evidence accumulates without bound as the context grows, and nothing indicates which tokens are safe to discard. We introduce Dynamical Kernel Attention (DKA), which derives attention from robust estimation of a latent state governed by a stochastic differential equation. Under this model, each head draws bounded evidence from any context. This lets each head abstain when relevant evidence is weak, and gives each head a memory window outside which discarding tokens changes its output by a provably bounded amount. On language modeling, DKA outperforms RoPE within the training length and ALiBi far beyond it, and matches sliding-window attention with a substantially smaller key-value cache.

cs.LG

版本更新 · v2arXiv:2611.18507

Asymptotic Margins and Feature Confinement in Conic Classification Heads under Softmax Cross-Entropy

Omer Nezih Gerek

原文摘要

Classification heads built on conic functions give each class a bounded region of the feature space, and such regions are used to reject samples of unseen classes. We ask whether these regions also keep the features bounded when the head is trained with softmax cross-entropy. For a head whose class scores combine a linear term with a Euclidean norm, we first show that the region of each class is bounded by a quadric of revolution, whose eccentricity is the reciprocal of one learned ratio. We then attach to each class an asymptotic margin, which compares the growth of its score with the growth of all the other scores and can be computed by a second-order cone program. The loss of a class has infimum zero exactly when its margin is positive, and it then approaches zero only along diverging features. When the margin is negative, the loss is coercive and its minimizers lie in an explicit ball. Since softmax depends only on the differences between scores, a class with a bounded region can still have a positive margin, so bounded regions do not confine the features. The result extends to other norms, including the polyhedral conic functions. On CIFAR-10 and CIFAR-100, all 1210 cells of 67 trained conic heads have positive margins, whereas a prototype head keeps nine of its ten cells bounded, as the theory predicts.

cs.LG · eess.SP

新论文 · v1arXiv:2611.22351

Scaling Laws for Vision-Language Fusion

Seng Pei Liew, Teppei Suzuki, Seiya Tokui

原文摘要

Vision-language models (VLMs) have emerged as central foundation models combining multimodal perception with text comprehension. While VLMs are traditionally built via late fusion by continued pre-training an off-the-shelf language model on multimodal (image-text) data, mixing modalities from the start of pre-training (early fusion) has recently gained traction. However, the fundamental trade-offs between these paradigms remain poorly understood, resulting in expensive and heuristic-driven training recipes. In this paper, we systematically analyze the learning dynamics of these multimodal pre-training processes, showing that validation losses during vision-language fusion can be modeled by separating the base learning trajectory, where different data types contribute at distinct rates, from a distribution shift driven by the competition between modalities. We derive a scaling law that unifiedly describes these dynamics, enabling accurate loss predictions across mixture ratios, training steps, and model sizes. Crucially, our law characterizes the trade-off between early and late fusion: under a fixed data budget, early fusion preserves text performance while late fusion favors vision performance, yielding a trade-off that increasingly tilts toward early fusion as model size scales. Extensive experiments confirm that our scaling law reliably captures multimodal learning dynamics and governs fusion decisions.

cs.LG · cs.CV

新论文 · v1arXiv:2611.22350

An AI-Driven Assistant for Human-Centric Building Digital Twin Systems: Design, Implementation, and Comparative User Evaluation

Leonardo Messi, Erika Anneli Pärn, Juan Diego Castaño Molina, Oleksandr Anyshchenko, Dijar Selami, Peihang Luo, Borja García de Soto

原文摘要

Smart buildings generate streams of operational data, yet this richness rarely translates into accessible, decision-ready information for stakeholders who inhabit and manage them. Current Building Digital Twin Systems (BDTS) often remain oriented toward technical specialists and rely on static, one-size-fits-all interfaces. This paper presents the design, implementation, and comparative user evaluation of an AI-driven conversational assistant integrated into a human-centric BDTS for Indoor Environmental Quality monitoring, combined with adaptive information presentation and auto-suggest functionality. The prototype was deployed at New York University Abu Dhabi. A controlled, two-arm, between-subjects, quasi-experimental study with wave-based, non-randomized assignment compared the Baseline interface with the Experimental interface. Results showed significant reductions in task-completion time and perceived workload, while accuracy and usability improved but did not meet the adjusted significance criterion. The study contributes an implemented and empirically evaluated architecture that separates generative interaction from deterministic environmental assessment and coordinates conversational responses with adaptive visual presentation.

cs.HC · cs.AI

版本更新 · v3arXiv:2508.07683

TAR: Temporal Anchor-Constrained Reasoning for Video Temporal Grounding

Chaohong Guo, Xun Mo, Yongwei Nie, Fei Ma, Xuemiao Xu, Chengjiang Long

原文摘要

Video Temporal Grounding (VTG) aims to localize specific video segments corresponding to natural language queries. While recent Large Vision-Language Models (LVLMs) employ Reinforcement Learning to generate Chains-of-Thought (CoT), they typically rely solely on outcome-based supervision. Consequently, this often leads to hallucinations, where the reasoning process becomes disconnected from the visual content and the final prediction. Existing attempts to mitigate this by relying on external supervision from larger models or separate reward models are computationally expensive and prone to rigid patterns. To address these challenges, we propose TAR (Temporal Anchor-Constrained Reasoning), a framework that introduces the temporal anchor (T-anchor) as a transparent and auditable checkpoint mechanism. T-anchor enforces progressive refinement within the CoT, compelling the model to continuously ground its intermediate thoughts in visual evidence and iteratively calibrate temporal predictions, thereby significantly enhancing the faithfulness and autonomy of the reasoning process and final accuracy. Furthermore, we introduce a bootstrapping paradigm that automatically harvests high-quality CoT data using only a standard 7B model, eliminating the dependency on ultra-large models. Extensive experiments demonstrate that TAR achieves state-of-the-art performance and generates faithful, autonomous, and progressively refined reasoning traces.

cs.CV · cs.AI

版本更新 · v3arXiv:2506.17247

Recursive Learning-Based Virtual Buffering for Analytical Global Placement

Andrew B. Kahng, Yiting Liu, Zhiang Wang

原文摘要

Due to the skewed scaling of interconnect versus cell delay in modern technology nodes, placement with buffer porosity (i.e., cell density) awareness is essential for timing closure in physical synthesis flows. However, existing approaches face two key challenges: (i) traditional van Ginneken-Lillis-style buffering approaches are computationally expensive during global placement; and (ii) machine learning-based approaches, such as BufFormer, lack a thorough consideration of Electrical Rule Check (ERC) violations and fail to "close the loop" back into the physical design flow. In this work, we propose MLBuf-RePlAce, the first open-source learning-driven virtual buffering-aware analytical global placement framework, built on top of the OpenROAD infrastructure. MLBuf-RePlAce adopts an efficient recursive learning-based generative buffering approach to predict buffer types and locations, addressing ERC violations during global placement. We compare MLBuf-RePlAce against the default virtual buffering-based timing-driven global placer in OpenROAD, using open-source testcases from the TILOS MacroPlacement and OpenROAD-flow-scripts repositories. Without degradation of post-route power, MLBuf-RePlAce achieves (maximum, average) improvements of (56%, 31%) in total negative slack (TNS) within the open-source OpenROAD flow. When evaluated by completion in a commercial flow, MLBuf-RePlAce achieves (maximum, average) improvements of (53%, 28%) in TNS with an average of 0.2% improvement in post-route power.

cs.LG · cs.AI

新论文 · v1arXiv:2611.22342

Bad Apples in the Kitchen: How LLM Teams Detect, Correct, and Calibrate Against Their Misaligned Members

Dongseok Heo, Junghwan Kim, Bongwon Suh

原文摘要

What protects an LLM team when one teammate quietly goes wrong? Most multi-agent LLM work assumes cooperative partners and inspects chat between turns before acting. Real-time embodied cooperation does not allow this pause: chat runs alongside action, so a teammate whose words stay cooperative while behavior diverges can cause damage faster than the team can name what is happening. We study this case by injecting three theory-grounded misaligned agents into a custom four-player Overcooked environment, each stressing a different joint-action layer (speech-action mismatch, role invasion, and aggregate-progress disruption), and decompose robustness into three sequential gates of detection, correction, and calibration through a 3x4x2 design (n=720 episodes). Nearly all trolls are eventually named, but recovery follows only when attribution and situational diagnosis appear in the same utterance; direct source-attribution prompting improves the hardest case only by degrading the troll-free baseline by 37.5%. Robustness, then, depends less on detection alone than on whether team chat combines attribution with diagnosis in a single utterance, suggesting that sensitivity to misalignment should be targeted rather than uniformly raised.

cs.CL · cs.MA

版本更新 · v2arXiv:2607.28045

RaDiVe: Robust 4D Radar Odometry with Distance-Bounded NDT and Velocity-Discrepancy Point Uncertainty

Sangwoo Jung, Dongjae Lee, Chiyun Noh, Ayoung Kim

原文摘要

Recent advances in 4D radar enable robust perception in adverse weather; however, the inherent sparsity, noise, and limited positional precision of radar point clouds pose significant challenges for registration-based odometry. In this letter, we propose RaDiVe, a 4D radar odometry framework that improves the accuracy and robustness of radar point cloud registration. We introduce a distance-bounded Normal Distributions Transform, which improves optimization stability and computational efficiency by restricting the correspondence search to near-distance voxel pairs. To mitigate measurement ambiguity, we propose a velocity-discrepancy point uncertainty model that weights each input 4D radar point according to the discrepancy between its measured Doppler radial velocity and the radial velocity predicted from the estimated ego-velocity. We also incorporate Signed Distance Function-based surface point extraction via implicit neural mapping to construct a geometrically consistent, noise-filtered local submap. Evaluations across multiple public datasets demonstrate that RaDiVe outperforms existing 4D radar odometry baselines by 44.4% in translational and 21.3% in rotational Absolute Trajectory Error on average, while maintaining real-time performance.

cs.RO

版本更新 · v4arXiv:2607.16235

OpenMHC: Accelerating the Science of Wearable Foundation Models

Narayan Schuetz, Yuze Bai, Lianggang Pan, Edgar Eggert, Favour Nerrise, Juan Delgado-SanMartin, Max Rosenblattl, Milana Gurbanova 等 20 位作者

原文摘要

Mobile and wearable devices offer an unprecedented opportunity for continuous, passive health monitoring and active health coaching. However, the largest wearable datasets are proprietary, and leading wearable foundation models trained on them are rarely open weight or include reproducible training code. To accelerate open science in wearable health, we introduce OpenMyHeartCounts (OpenMHC), the largest and most comprehensive wearable health dataset broadly accessible to qualified researchers, alongside open-source implementations and weights for recent wearable foundation models. Derived from over a decade of data collected through the My Heart Counts study app, OpenMHC comprises over 67M participant-hours of wearable recordings across up to 19 sensor channels (e.g., step count, heart rate, sleep, workouts) and up to 170 health, lifestyle, mood, and behavioral variables from 11,894 participants. Furthermore, we establish a benchmark for standardized evaluation across three tasks: (1) health and behavioral outcome prediction, (2) multivariate data imputation, and (3) time-series forecasting. Benchmarking classical methods alongside recent wearable and time-series foundation models, we find that while foundation models perform strongly, carefully tuned classical baselines like XGBoost remain highly competitive. By uniting broad-access wearable data with open code and model weights, OpenMHC provides a framework needed to drive reproducible advances in wearable health AI.

cs.LG · cs.AI

版本更新 · v2arXiv:2611.15002

AI4Plasma I: Data-Efficient Surrogate Modeling of Capacitively Coupled Plasma Fields

Zhenyu Zou, Junjue Liao, Hao Yang, Luowei Yin, Chenyu Wang, Yufeng Wei, Chun Chen, Daniel Zhengyu Huang 等 14 位作者

原文摘要

Reference capacitively coupled plasma (CCP) simulations provide spatially resolved plasma fields but are costly to generate across operating conditions. We compare the data efficiency of five surrogate architectures--Coordinate MLP, PCA-Net, U-Net, Fourier neural operator (FNO), and Transolver--for predicting RF-cycle-averaged electron density, ion density, electric potential, and electron temperature in 1D planar and 2D axisymmetric GEC CCP benchmarks. We assess the number of reference simulations needed to achieve 1% and 2% mean relative L2 error for parameter-interior and parameter-boundary test cases, and examine architecture-specific mechanisms. FNO achieves the lowest or joint-lowest reference-case requirement in seven of eight comparisons. In 1D, FNO reaches 1% interior error with 50 training cases, compared with 100 for Transolver and 200 for U-Net. In 2D, FNO and U-Net each reach 1% interior error with 100 cases; FNO and Transolver each reach 2% parameter-boundary error with 200 cases, compared with 400 for U-Net. At the stricter 1% 2D parameter-boundary target, Transolver requires 400 cases versus 800 for FNO. Additional analyses investigate FNO spectral modes and padding, U-Net skip connections, Transolver adaptive slicing, and PCA-Net projection versus prediction error. The results support FNO as a data-efficient baseline for the tested CCP settings, while showing that the preferred architecture depends on the accuracy target and operating-parameter region.

cs.LG · physics.plasm-ph

版本更新 · v4arXiv:2604.04554

Epipolar-Constrained Graph Representation Learning for Geometric Pose Estimation

Prateeth Rao, Sachit Rao

原文摘要

We investigate geometry-aware graph representation learning for relative camera pose estimation using epipolar-constrained graph structures. Relative camera pose is commonly estimated from matched image correspondences that satisfy the epipolar constraint; however, identifying geometrically consistent correspondences under varying imaging conditions remains challenging. We employ an existing detector-free transformer architecture to establish correspondences between image pairs and construct a correspondence graph whose topology is guided by epipolar geometry. Initially, each node is connected to its (k) nearest neighbours based on spatial distance. The resulting graph is subsequently pruned using an initial estimate of the Essential Matrix, distinguishing the proposed formulation from conventional graph representations based primarily on heuristic spatial neighbourhoods. The graph learning module aggregates relational information between nodes into a graph-level representation that encodes the geometric context of the correspondences. This representation is passed to a pose regression network to estimate the relative camera rotation and translation. The model is trained across standard and wide baselines using a weighted objective that combines pose regression, scale consistency, heading consistency, and spectral properties of the pose parameters. Experimental graph analyses demonstrate that epipolar-guided edge pruning reduces graph connectivity by more than 90\% while retaining all correspondence nodes. Further spectral analyses characterize the effects of graph sparsification and injected outliers on learned graph representations.

cs.CV · cs.RO

版本更新 · v2arXiv:2611.20821

CuRSE-Bench: A Benchmark for Probing Cultural Blind Spots in Text-to-Image Safety Evaluation

Minsuk Jang, Minseok Son, KiHyun Seol, Yeongeun Shim, Changick Kim

原文摘要

Text-to-image (T2I) safety evaluation typically assigns each prompt or image a single culture-blind harm label, so content that is harmful only within a particular culture can pass as benign. We introduce CultureCraft, an agentic framework that constructs T2I prompts that appear benign under a general-purpose rubric yet carry a latent harmful meaning in a target culture, and use it to build CuRSE-Bench: 10,709 culture-specific prompts and 2,648 culture-general controls over six regions and ten harm axes, each drawn from a predefined knowledge base of documented harm vectors and traceable to at least two independent sources. Scoring every prompt under six region persona judges and a paired culture-blind judge, we find that the culture-blind judge under-rates culture-specific latent harm while matching the persona judges on the controls. Each persona judge, in turn, chiefly decodes its own region's latent harm under our instrument: a selective cultural blind spot that persists in deployed moderators.

cs.CL

版本更新 · v5arXiv:2605.12925

AgentLens: Revealing The Lucky Pass Problem in SWE-Agent Evaluation

Priyam Sahoo, Gaurav Mittal, Xiaomin Li, Shengjie Ma, Benjamin Steenhoek, Pingping Lin, Yu Hu

原文摘要

Evaluation of software engineering (SWE) agents is dominated by a binary signal: whether the final patch passes the tests. This outcome-only view treats a principled solution and a chaotic trial-and-error process as equivalent. We show that this equivalence is empirically false. We evaluate 2,614 OpenHands trajectories from eight model backends on 60 SWE-bench Verified tasks. Of these, 47 have enough passing trajectories to construct task-level process references, yielding a 1,815-trajectory evaluation subset. Among passing trajectories in this subset, 10.7% exhibit behavior we call a Lucky Pass: regression cycles, blind retries, missing verification, or temporally disordered exploration, implementation, and verification. We introduce AgentLens, a framework for process-level assessment of SWE-agent trajectories, and release AgentLens-Bench, a dataset of 1,815 trajectories annotated with quality scores, waste signals, divergence points, and 47 task-level Prefix Tree Acceptor (PTA) references. AgentLens builds PTA references by merging multiple passing solutions for the same task, and uses a context-sensitive intent labeler to assign actions to Exploration, Implementation, Verification, or Orchestration based on trajectory history rather than tool identity alone. On AgentLens-Bench, the quality score separates passing trajectories into Lucky, Solid, and Ideal tiers and further decomposes Lucky Passes into five recurring mechanisms. Across the eight model backends, Lucky rates range from 0.5% to 23.2%, and some models move by as many as five rank positions when ranked by quality score instead of pass rate. We publicly release AgentLens-Bench and the AgentLens SDK at https://github.com/agentlens-framework/agentlens, with a project page at https://agentlens-framework.github.io/agentlens/.

cs.SE · cs.AI

版本更新 · v2arXiv:2608.08368

PARAGraph: Pathology-Anatomy-Aware Hierarchical Graph for Diabetic Retinopathy Grading

Ziyang Zhang, Yuankai Huo, Yalin Zheng, He Zhao

原文摘要

Diabetic retinopathy (DR) remains a leading cause of vision loss among working-age adults worldwide, making reliable severity grading clinically important. Despite strong performance, most deep models formulate DR grading as image-level classification and do not explicitly model clinically grounded evidence, such as lesion types and spatial relations. In this paper, we propose PARAGraph, a Pathology-Anatomy-Aware Hierarchical Graph framework for DR grading. PARAGraph represents each image as a three-level hierarchical graph with lesion-level nodes, intermediate category and region nodes, and global anatomical and semantic nodes. To incorporate medical priors into nodes, we construct an optic disc-fovea-anchored coordinate frame that provides a scale- and rotation-normalized retinal reference system. Within this frame, lesion nodes are encoded with category, normalized area, and anatomical coordinates. To mitigate noisy lesion segmentation, PARAGraph uses a dual-fusion strategy that introduces global visual context into a graph semantic node and a decision-level prediction branch, improving robustness when lesion evidence is unreliable. Extensive experiments on Messidor-2, APTOS, and DDR show that PARAGraph achieves consistent DR grading performance over state-of-the-art methods. Interpretability and robustness analyses further demonstrate that its predictions are clinically grounded, closely associated with lesion evidence and robust to lesion segmentation noise.

cs.CV

版本更新 · v3arXiv:2605.08777

Measuring and Decomposing Mode Separation via the Canonical Diffusion

Shaul Tolkowsky, Ori Meidler, Or Zuk

原文摘要

Mode separation, namely how sharply a distribution fragments into barrier-separated clusters, is a fundamental geometric property of densities, difficult to quantify in high dimensions. Modes are often the meaningful alternatives in the data, such as the conformations of a molecule or the distinct semantic types among a generative model's outputs. Mode separation is distinct from dispersion, which is what standard label-free tools capture: differential entropy rises with spread regardless of fragmentation, and PCA orders directions by variance regardless of barriers. Mutual information does capture it, but only given the latent component labels, which are usually unavailable. We measure mode separation through a single stochastic process intrinsic to the density, namely the unique reversible diffusion with $f$ as its stationary distribution and a constant scalar diffusion coefficient. From its autocovariance matrix we extract two readouts. The first, SSA (Sum of Squared Autocorrelations), is a scalar barrier-sensitive measure. The second, DA (Dominant Autocorrelation directions), gives linear projections ordered by metastability rather than variance. Under an isotropic-Gaussian null, we derive the limiting spectrum of the empirical autocovariance in closed form, generalizing the Marchenko--Pastur law. Its upper edge gives a noise floor that separates metastable directions from sampling noise. Both readouts use only samples and a score function, scaling to high dimensions through pretrained score-based generative models via Tweedie's identity. We apply our framework to three settings: (i) synthetic Gaussian mixtures, where SSA tracks mutual information; (ii) SDXL text-to-image generations, where SSA and DA capture structure that entropy and PCA miss; and (iii) molecular dynamics of alanine dipeptide, where DA recovers the known slow backbone dihedrals from static samples alone.

stat.ML · cs.LG · math.PR

新论文 · v1arXiv:2611.22335

Comparing Implicit and Explicit Language Attitudes toward the Dutch multiethnolect Straattaal in Humans and Large Language Models

Hedwig Oldenhof, Laura Rosseel, Anna Wegmann, Dong Nguyen

原文摘要

While language attitudes have been extensively studied in humans, the extent to which large language models (LLMs) encode similar associations between language varieties and social attributes remains unclear. Contemporary sociolinguistic research distinguishes between explicit attitudes, which stem from deliberative processing, and implicit attitudes, which arise from automatic processing. This study investigates whether LLMs exhibit human-like implicit and explicit language attitudes toward the Dutch multiethnolect Straattaal, particularly its association with migrant communities. We use closely matched designs to assess attitudes in humans and LLMs. For humans, we use an Implicit Association Test (IAT) and an explicit rating task. For LLMs, we use the LLM Word Association Test (LLM WAT) and the same explicit rating task. Human participants strongly associate Straattaal with individuals with a migration background at both implicit and explicit levels. In the LLM WAT, Straattaal is consistently associated with individuals with a migration background, with stronger associations observed in larger and newer models. When presented with the same explicit rating task as human participants, LLMs produce comparable response patterns. Overall, the findings suggest that many LLMs encode language attitudes resembling those observed in humans, however we also highlight important questions about how concepts and measures developed to study human attitudes should be interpreted in LLMs. This highlights the relevance of incorporating sociolinguistic perspectives and language variation into NLP research to better identify and mitigate socially and linguistically embedded biases.

cs.CL

新论文 · v1arXiv:2611.22334

BQ-LoRA: Binary-Quantized Low-Rank Adapters as Implicit Regularizers for Parameter-Efficient Fine-Tuning

Juyoung Park, Heejun Lee

原文摘要

Parameter-efficient fine-tuning of quantized large language models is dominated by QLoRA, which combines 4-bit weight quantization with FP16 low-rank adapters. We ask whether the FP16 adapter precision is necessary. Replacing it with a single binary bit per adapter parameter, combined with a learned per-layer scale $s$ and a Scaled Straight-Through Estimator, reduces adapter storage by 13-16x. We introduce two variants -- NormScale, which binarizes under a norm-preserving scale with a clipped STE, and LearnThresh, which makes the binarization threshold learnable -- unified under a framework we call BQ-LoRA. Our main theoretical contribution is a tight characterization of the BQ-LoRA hypothesis class: it has bounded entrywise norm, a typical-set spectral norm bound that is $Θ(r)$ times sharper than the worst case, a full-rank, near-isotropic update, and consequently a Rademacher complexity that yields an explicit $\tilde{O}(s_{\max}α\sqrt{d_{out}/(rn)})$ generalization bound. FP16 LoRA has no comparable a priori norm or isotropy control. On Qwen2.5 (1.5B-72B), BQ-LoRA exceeds QLoRA's benchmark averages at every scale by 0.8-3.5 points; on LLaMA-2 (7B/70B) it remains competitive at the same storage reduction but does not uniformly lead the strongest FP16-adapter baselines (LoftQ at 7B, QLoRA at 70B). On Qwen2.5-7B the binary adapter preserves the 4-bit base WikiText-2 PPL within 0.06 (9.86 vs. 9.80) while QLoRA worsens it by 0.59. The reduction applies to inference-time adapter storage and serving; training memory matches QLoRA and step time rises by under 4%. We translate the storage saving into a deployment study, BQ-SGMV, by extending Punica's SGMV kernel with a binary inner-product primitive: the same A100-80GB holds 15.6x more adapters in HBM, and our research prototype eliminates cache misses under a skewed synthetic workload.

cs.LG

新论文 · v1arXiv:2611.22333

MoL-SQL: A Controlled Benchmark for Mixture-of-Language Text-to-SQL

Tianqi Luo, Boyan Li, Yuyu Luo

原文摘要

Text-to-SQL systems are usually built and evaluated under a monolingual assumption, yet in international applications users often query databases stored in a different language. Existing multilingual benchmarks mostly translate only the question without aligning schema and value entities, so they can neither locate the source of an accuracy drop nor rule out translation errors. Hence, we introduce MoL-SQL, a benchmark for mixture-of-language Text-to-SQL that switches the languages of the question, schema, and stored values independently while keeping each task fixed, and grades every cross-lingual entity mapping into four difficulty levels. We migrate five Text-to-SQL benchmarks of different domains and source languages through a unified alignment pipeline that builds a shared cross-lingual entity map, migrates each database with its constraints, rewrites the gold SQL under execution-equivalence checks, and regenerates the question from the verified SQL, keeping all language versions of a task aligned in entities, intent, and execution result. MoL-SQL provides two splits: MoL-Full (16,892 samples) for overall evaluation and MoL-Cube (3,840 samples) covering every language combination to isolate question, schema, and value effects. Experiments with eight LLMs and four families of Text-to-SQL methods show that schema and value languages have distinct effects, with stored values costing up to 23 points, and that these effects mainly stem from cross-lingual entity mapping. Neither question translation nor additional reasoning narrows the value gap, whereas access to target-database values substantially reduces it, indicating that mixture-of-language Text-to-SQL benefits most from language-aware context grounding.

cs.DB

版本更新 · v2arXiv:2611.15584

AI4Plasma II: Geometry-Aware Surrogate Modeling for Variable Electrode Gap GEC Plasmas

Hao Yang, Zhenyu Zou, Wenshuai Jie, Luowei Yin, Yufeng Wei, Daniel Zhengyu Huang, Chun Chen, Kangxin Liu 等 13 位作者

原文摘要

Industrial plasma process development requires broad exploration of operating and geometric parameters. Geometric parameters, particularly electrode spacing, affect discharge structure and processing uniformity. Exploring these parameter spaces through repeated high-fidelity simulations can be computationally expensive. Surrogate models can offer rapid predictions, but geometric variation complicates their application because the computational domain and discretization may change across samples. In this work, six geometry-aware surrogate models based on prescribed and learned geometry mappings, extended-domain representation, continuous coordinates, and geometry-native discretizations are compared in terms of their data requirements for accurate predictions of full plasma fields and ion density profiles near the wafer. The simulation dataset spans pressure, voltage, frequency, and electrode gap, with each reference case requiring an average simulation cost of 5.32 CPU h. To achieve a 2% mean error across the four plasma fields, prescribed-mapping Geo-FNO and Transolver require 100 training cases, compared with 250-1000 for the other models. Predicting ion density profiles near the wafer is more demanding and reveals larger differences among models, with prescribed-mapping Geo-FNO requiring the fewest training cases for the profile accuracy targets considered. To further reduce the data required for accurate predictions near the wafer, we introduce charge-separation weighting into the training loss, which reduces the prescribed-mapping Geo-FNO's minimum tested training requirement for a 5% profile error from 1000 to 100 cases. These results support prescribed-mapping Geo-FNO as a practical starting point for the variable-gap problem studied here when a suitable geometry mapping is available, while Transolver achieves the highest prediction accuracy with sufficient training data.

cs.LG · physics.plasm-ph

版本更新 · v2arXiv:2611.14775

DeNA-SGN: Deterministic Neighborhood Aggregation for Verified Spiking Graph Inference

Sanjay Das, Xi Zhang, Emily Herron, Prasanna Date

原文摘要

Graph learning on neuromorphic substrates requires an explicit spiking realization of neighborhood aggregation, supporting control and classification. We propose DeNA-SGN, which combines fixed OR and tie-inclusive Majority aggregation of binary node features with a learned signed-weight threshold classifier. A degree-dependent inhibitory construction implements Majority through shared control neurons, enabling a complete circuit compilation into SuperNeuroMAT. Across seven datasets and 41 mapped classifiers, native simulation matches the exported ANN on every evaluated class decision and output-spike pattern. On the new confirmatory Amazon Photo dataset, DeNA-SGN achieves 83.93+-0.93% current-readout accuracy and 71.61+-2.22% strict output-spike accuracy; Wiki-CS reaches 75.99+-0.54% over 20 public masks. In the matched Cora study, we achieve 74.90+-2.67% on current-readout and 68.57+-2.94% strict spike accuracy. Complete circuit and activity accounting supports analytical energy comparisons and identifies the cost of clocking inactive neurons in large deployments. Current argmax is decoded on the host, and energy is modeled rather than measured on hardware. These findings establish a reproducible route to useful graph classification with decision-matched spiking execution and explicit implementation costs.

cs.NE

新论文 · v1arXiv:2611.22330

Multistage Contextual Optimization for Vehicle Repositioning

Jinyu Zhang, Di Huang, Zhiyuan Liu, Nikolas Geroliminis

原文摘要

Ride-hailing platforms reposition idle vehicles to improve spatial supply-demand balances. This problem is prediction-driven and multistage: at each stage, the platform forecasts future demand, executes current decisions, and uses the resulting state to initialize the next stage. We formulate a multistage linear program (LP) with a macroscopic fundamental diagram (MFD) linking accumulation to trip completion. We then develop a multistage contextual optimization approach that uses decision performance to train the prediction model. The learning problem combines multiple coupled stages, context that depends on earlier decisions, and predictions that affect the objective, the constraint matrix, and the right-hand side of the LP. We derive the exact gradient, which has three parts: parameters change forecasts and hence decisions; earlier decisions change the current decision through the inherited state; and this state also changes forecasts as context. An equivalent adjoint uses reverse vector-Jacobian products, avoiding full solution and state-parameter Jacobians. Finally, forward propagation solves many stage LPs one after another, which makes training slow. We propose a parallel block evaluation algorithm that solves blocks of consecutive stages in parallel and repeatedly feeds each block output to the next block. We prove that the algorithm recovers the serial trajectory within a finite number of passes and that its gradient error remains bounded when it stops early. On New York City ride-hailing data, multistage contextual optimization yields 7.7% to 9.1% more business benefit than the same predictor trained by mean squared error, outperforms all compared baselines from five paradigms, and even outperforms realized demand fed to the same policy. With eight workers, parallel block evaluation shortens training by a factor of 1.86 without loss of decision performance.

cs.AI · cs.LG

新论文 · v1arXiv:2611.22321

Beyond Episodic Recall: Experience-to-Knowledge Evolution for Lifelong Embodied Navigation

Weitao An, Chenghao Xu, Xu Yang, Cheng Deng

原文摘要

Lifelong embodied navigation requires agents to accumulate experience through continuous interaction and reuse it for subsequent goal searches. Existing memory-enhanced methods typically retain historical observations or construct structured scene representations. However, storing observations or high-dimensional semantic embeddings incurs growing storage costs. Meanwhile, structured representations support retrieval and semantic reasoning but do not explicitly evolve accumulated experience into environment-specific knowledge. To address these limitations, we propose Experience-Evolving Memory (EvoNav), a novel two-timescale memory framework. It organizes semantic observations, spatial relations, and task-feedback cues into sparse experience atoms. During online operation, experience atoms continually consolidate repeated observations and form dynamic links based on transitions. At the slower timescale, EvoNav distills accumulated category co-occurrences and feedback signals into environment-specific structural knowledge without relying on predefined object--room relations. For each new goal, EvoNav combines direct goal evidence from experience atoms with learned structural knowledge to guide goal-directed search on the current traversability map. Experiments on single-goal, sequential multi-floor, and multimodal navigation demonstrate effective experience reuse and improved path efficiency with compact persistent memory, together with successful transfer to a real robot.

cs.RO

版本更新 · v3arXiv:2608.12253

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL

Simon Yu, Nicholas Tomlin, Marwa Abdulhai, Ximing Lu, Derek Chong, Abe Hou, Dilara Soylu, Sergey Levine 等 10 位作者

原文摘要

Multi-agent reinforcement learning (MARL) for human-AI interaction usually trains the agent against a single large language model (LLM) that simulates the user. We show that agents trained this way can systematically fail to generalize, and we trace the failure to simulator collapse: the simulator LLM is mode-collapsed, and a policy trained against it learns narrow strategies that exploit the simulator's mode behavior; these strategies transfer poorly to unseen simulators and to real users. We formalize the collapse and propose two solutions. Verbalized Sampling, applied at inference time, samples each simulator reply from a verbalized response distribution. Co-Training, applied during training similar to self-play, co-evolves the simulator as the policy, so the policy cannot exploit the mode behavior. A population variant samples the simulator for each rollout from a pool of recent checkpoints. We validate both solutions on three benchmarks: Persuasion for Good, tau^2-bench, and CooperBench. Verbalized Sampling improves held-out success by up to 9% over single-simulator RL, and Co-Training pushes gains further to 14%; the human study shows similar gain on real users. Both solutions also preserve the policy diversity that collapses under single-simulator RL. Overall, our findings on simulator collapse point to diverse simulators as a requirement for RL agents that serve real users. We release SCOPE, an open-source framework for Population Co-Training in multi-agent RL.

cs.CL · cs.AI · cs.LG

新论文 · v1arXiv:2611.22318

Breaking Visual Conventions: Spectrally Coupled Weight Perturbation for Creative Image Generation

Fu Feng, Ruoheng Zhou, Yucheng Xie, Xu Yang, Jing Wang, Xin Geng

原文摘要

Text-to-image (T2I) models often produce high-quality images that follow familiar visual conventions, even in response to open-ended prompts such as ``a creative [CLS]''. Existing methods encourage novelty by exploring semantic conditions or modifying features and guidance during denoising. Pretrained weights offer a complementary source of creative variation, but unstructured perturbations can have little visual effect or degrade image quality. We introduce Coupled Spectral Perturbation (CosPert), a training-free method that targets attention projections in layers identified by a one-time sensitivity analysis. For each projection, CosPert uses a shared random transformation and its transpose to couple updates to the singular-vector factors while perturbing the spectral gains. A common relative budget calibrates the magnitude of weight changes across projections, and a sigmoid schedule concentrates their influence in early denoising and gradually attenuates them during refinement. CosPert provides plug-and-play creativity enhancement at inference time. Once the perturbations are prepared, sampling requires no auxiliary networks or additional model evaluations. On both FLUX.1 and Stable Diffusion 3.5, CosPert enhances visual creativity, producing more varied object structures while preserving category identity. Across 50 object categories, CosPert achieves the highest mean CREward among the evaluated methods while maintaining strong prompt alignment.

cs.CV

新论文 · v1arXiv:2611.23339

Optimize the Cob, Then the Kernel: Optimizing Beam Search for Generative Recommendation Inference

Shing Wai Pun, Kai Wu, Pengfei Xia, Hui Zang, Wei Guo, Yong Liu

原文摘要

Generative recommendation (GR) inference differs substantially from conventional LLM serving, featuring long input sequences, wide beam search, and only a few fixed output tokens. Existing LLM serving engines such as vLLM process beams as batched independent sequences, causing redundant KV cache accesses over the shared prompt prefix. Furthermore, vLLM executes each beam search generation step as a separate engine invocation, incurring host-side beam processing overhead between decoding steps and substantial runtime KV block management in PagedAttention. Using Tree Attention, we concatenate beams along the sequence dimension to eliminate redundant KV accesses, and further optimize execution through pre-generated partial-attention masks, static KV cache allocation, loop-unrolled generation dispatch, TorchAir graph compilation, automatic operator fusion, and vocabulary-constrained decoding. Without the use of custom kernels, our approach reduces end-to-end latency by up to 25x over vLLM on Ascend NPUs, and achieves generation latency comparable to a SOTA solution using custom kernels, showing that the generation pipeline should be optimized holistically before resorting to custom kernel development.

cs.LG · cs.AI

版本更新 · v2arXiv:2611.18770

AerialOcc: Unified 3D Aerial Perception without Task-Specific Head

Fan Liu, Xiang Gu, Baoyu Lv, Chuanyi Zhang, Liang Yao, Yuye Ma, Yuhui Zheng

原文摘要

Aerial perception systems are increasingly expected to support diverse tasks, yet existing solutions remain fundamentally tied to task-specific outputs. Detection, segmentation, and other perception objectives are usually learned either by separate models or by sharing a backbone with multiple task heads, leaving the model itself unaware of the common structure underlying these tasks. We are interested in asking: can a single perception representation support different levels of understanding without being designed for any specific task? We notice that occupancy is a promising task-agnostic representation for drone perception. By modeling the spatial existence and semantics of the environment, it naturally bridges different perception granularities, from coarse scene understanding to fine-grained object localization. Therefore, we introduce AerialOcc, a unified occupancy-based perception model that enables multiple drone perception tasks from a single inference process, without maintaining task-specific prediction heads. To facilitate this direction, we construct AerialOcc-20K, a large-scale multi-class occupancy dataset for aerial environments. Extensive experiments show that AerialOcc achieves competitive performance across diverse perception tasks while preserving a unified architecture. Our findings demonstrate that occupancy can serve as a universal perception interface, offering a new perspective toward flexible and scalable visual intelligence for autonomous drones from a common 3D scene representation. Models and data are publicly available at https://github.com/guxiang2002/AerialOcc

cs.CV

新论文 · v1arXiv:2611.22314

Inertial Video World Models

Yuan Gao, Fan Xu, Yu Guo, Yuxu Lu, Zhengru Fang, Hao Wu, Xiaomeng Huang

原文摘要

The physical world has inertia: it evolves from what already exists rather than being recreated at every instant. However, many existing video world models lack an explicit mechanism for inertial state evolution, leaving the continuity of motion and structure implicit in video prediction. During autoregressive rollouts, repeated reconstruction can accumulate errors and destabilize the predicted dynamics. To address this limitation, we introduce InertialWorld, an Inertial Video World Model that makes inertia a structural prior for autoregressive prediction: existing scene evidence is carried across time rather than reconstructed at every step. Central to this formulation is Inertial Memory, which turns memory from passive predictive context into an evolving video state with two complementary views: a dense Eulerian grid preserves scene-aligned evidence, while persistent Lagrangian carriers bind local content to learned canonical coordinates. At each step, the model transports the carrier content according to action-conditioned motion, predicts the complete next video state from the transported carriers and dense grid, and uses a learned gate to combine transported and newly predicted content into the memory for the next step. Extensive experiments across multiple domains, including robot manipulation, 3D game simulation, and open-world navigation, demonstrate that InertialWorld achieves competitive autoregressive prediction performance against strong video world model baselines. Codes link: https://github.com/YuanGao-YG/InertialWorld

cs.CV