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

+86新增论文
+61其中 AI 相关
+14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 10:40各信源进度 →

统计口径与数据新鲜度

统计 2026-11-15 11:35 — 2026-11-16 11:35(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 10:40库内论文最新更新时间:2026-11-13 16:48

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。

23,434 已收录论文19,641 AI 相关6,765 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 23,434 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-16 01:33(北京时间)
新论文 · v1arXiv:2610.37295

A Linear Kernel for Planar Semitotal Domination

Paloma T. de Lima, Lukas Retschmeier

原文摘要

A set of vertices $S$ in a graph $G$ is a semitotal dominating set if $S$ is a dominating set and every vertex in $S$ has a witness, that is, another vertex in $S$ within distance at most two. The Semitotal Domination problem asks whether $G$ admits such a set of size at most $k$. We study this problem parameterized by the solution size. We provide a linear kernel of size $358k$ on planar graphs, a result that adds to several existing linear kernels for other domination variants on planar graphs. Additionally, we show Semitotal Domination is $W[2]$-hard on split graphs, on bipartite graphs and on $t$-claw-free graphs, it is $W[1]$-hard on circle graphs.

cs.DS

新论文 · v1arXiv:2610.37292

Multi-Label Agreement: A Flexible Framework for Inter-Annotator Reliability

Tim Menzner, Jochen L. Leidner

原文摘要

Reliable evaluation of inter-annotator agreement (IAA) is important for assessing the consistency of annotation processes. While established IAA metrics such as Cohen's kappa, Fleiss' kappa, and Krippendorff's alpha are commonly applied in single-label settings, multi-label tasks require additional decisions about how full label sets, joint selections, and joint omissions should be compared. In this work, we present Multi-Label Agreement (MLA), a flexible framework for evaluating agreement in multi-label annotation tasks. MLA preserves the full binary label vectors assigned to each item and uses average pairwise Hamming agreement, thereby accounting for both joint selections and joint omissions. Its pooled-marginal form is not a mathematically independent coefficient: it is a chance-disagreement-weighted average of label-wise Fleiss/Scott-type coefficients and is closely related to Krippendorff's alpha with normalized Hamming distance. The framework supports pooled-marginal, Gwet AC1, and fixed-baseline normalizations, yields item-level, label-level, and corpus-level results, and includes a conditional minimum-agreement diagnostic. Through a worked example and Monte Carlo simulations, we show how the resulting values depend on label prevalence, the declared label inventory, and the selected model of expected agreement. We also provide a Python implementation. MLA thus offers a transparent and interpretable framework for multi-label agreement analysis without claiming that one normalization is universally preferable.

cs.CL

新论文 · v1arXiv:2610.37290

Taming Noise Initialization for Zero-shot Video Restoration with Image Diffusion Priors

Chong Wang, Zixuan Fu, Hao Cheng, Siyuan Yang, Alex C. Kot, Bihan Wen

原文摘要

Recent advances in diffusion models have achieved remarkable success in restoring high-quality images in a zero-shot manner. Unfortunately, extending this success to video restoration is challenging due to the substantial computational resources required to pre-train video diffusion models. A rising trend seeks to address video restoration by utilizing a pre-trained image diffusion model, initiating restoration from either frame-wise independent or identical Gaussian noise. Yet, these approaches often fall short, as such simple noise initiations fail to capture and utilize the inherent temporal correlations within degraded video frames. In this work, we propose taming noise initialization for zero-shot video restoration, which preserves the intrinsic temporal correlations by generating initial noises directly using DDIM inversion on the corrupted video frames themselves. Building on this, we introduce an adaptive noise blending strategy that suppresses degradation patterns encoded during DDIM inversion while gradually steering the noise toward a Gaussian distribution. To further emphasize temporal consistency, we propose measurement-guided trajectory attention to better align features across frames. Extensive experiments on multiple video restoration tasks demonstrate that our method outperforms existing zero-shot approaches, consistently achieving superior results on the DAVIS, REDS4, and Set8 datasets.

cs.CV

版本更新 · v2arXiv:2605.19511

Are Watermarked Images Editable? SafeMark for Watermark-Preserving Text-Guided Image Editing

Xiaodong Wu, Qi Li, Xiangman Li, Zelin Zhang, Lingshuang Liu, Jianbing Ni

原文摘要

This paper investigates a fundamental yet underexplored question: can watermarked images remain editable without compromising watermark integrity? We propose SafeMark, a framework for watermark-preserving text-guided image manipulation that explicitly integrates watermark integrity into the editing process. Specifically, SafeMark adds a thresholded watermark-decoding loss directly to the diffusion editor's training objective, fine-tuning the editor so that semantically valid edits also preserve the embedded watermark at the final output. This design admits a clean information-theoretic justification: maintaining high bit-accuracy on the edited image lower-bounds the mutual information that the editor channel preserves between watermark and edited output, the quantity that fundamentally controls watermark recoverability. SafeMark is compatible with differentiable diffusion-based editors, and requires no architectural modification. Extensive evaluations across multiple datasets, text-guided editing methods, and post-edit distortion settings demonstrate that SafeMark achieves high watermark bit accuracy across diverse editing settings while maintaining high-quality semantic edits, without sacrificing robustness to common post-edit distortions. These results demonstrate that semantic editability and watermark integrity are fundamentally compatible, enabling trustworthy image provenance in generative editing pipelines.

cs.CV

版本更新 · v2arXiv:2509.18396

Development of Deep Learning Optimizers: Approaches, Concepts, and Update Rules

Doğay Altınel

原文摘要

Deep learning optimizers are optimization algorithms that enable deep neural networks to learn. The effectiveness of learning is highly dependent on the optimizer employed in the training process. Alongside the rapid advancement of deep learning, a wide range of optimizers with different approaches have been developed. This study aims to provide a review of various optimizers that have been proposed and received attention in the literature. From Stochastic gradient descent to the most recent ones such as Momentum, AdamW, Sophia, and Muon in chronological order, optimizers are examined individually, and their distinctive features are highlighted in the study. The update rule of each optimizer is presented in detail, with an explanation of the associated concepts and variables. The techniques applied by these optimizers, their contributions to the optimization process, and their default hyperparameter settings are also discussed. In addition, insights are offered into the open challenges encountered in the optimization of deep learning models. Thus, a comprehensive resource is provided both for understanding the current state of optimizers and for identifying potential areas of future development.

cs.LG

新论文 · v1arXiv:2610.37286

LESSRec: Level-Specific History Modeling for Semantic ID-Based Recommendation

Shangxin Yang, Zongwei Wang, Jing Long, Junliang Yu, Min Gao

原文摘要

Semantic ID-based recommendation represents each item as a sequence of semantic tokens obtained through residual quantization. This paradigm generates the next item's tokens autoregressively from coarse to fine, entailing each prediction attending to historical tokens at all semantic levels. However, our inference-time analysis reveals that historical tokens at the target-token's semantic level tend to be more informative, whereas other levels can introduce interference. Motivated by these findings, we propose LESSRec that separately encodes the historical token sequence at each semantic level and restricts attention over historical tokens to the sequence at the target token's semantic level during prediction. To complement these level-specific histories, LESSRec explicitly provides an item-level semantic sequence that represents each historical item's overall semantics in chronological order. The decoder accesses the level-aligned token sequence and the item-level semantic sequence through two separate cross-attention branches and fuses their contexts. We further introduce LESSRec+, which uses separate encoders for different semantic-level histories with the same total parameter count to reduce encoder computation. Extensive experiments across three public datasets and three tokenizers demonstrate the recommendation effectiveness of LESSRec and LESSRec+, with efficiency analyses highlighting the computational benefits of LESSRec+.

cs.IR

版本更新 · v2arXiv:2610.33437

Combinatorial Lock for Trojan-Resilient AI Engines via Hash-Assisted Spectral Filtering

Soumita Chatterjee, Sudip Ghosh, Tamal Ghosh, Bhargab B. Bhattacharya, Hafizur Rahaman

原文摘要

Multi-trigger backdoor attacks, in which heterogeneous trigger mechanisms (e.g., patch, blend, warping, and the latent-domain Spy-Watermark) coexist within a single poisoned model, cannot be addressed by existing shortcut-based defenses that assume a single, static attack mechanism. Current multi-trigger remedies (BU+FT, BU+ANP, and BU+ABL) rely on backdoor unlearning, which incurs high training costs and loses effectiveness at low poisoning ratios. This paper proposes Combinatorial Lock, a training-free, reference-calibrated defense that reduces multi-trigger identification to a combinatorial problem over binary activation signatures. This formulation is the key novelty: it yields a multi-trigger defense that is training-free, trigger-oblivious, and directly implementable in hardware, since its decision rules can be evaluated with integer and logic operations. The framework combines anomaly-gated spectral scrubbing, which removes the malicious subspace only from inputs identified as anomalous, with a hash-compressed combinatorial signature verified by an ensemble of detection experts, including a compound-attack-aware expert for multi-trigger inputs. A joint threshold-shrinkage search identifies an operating point ($τ$ at the 97.1st percentile, $γ= 0.78$) that reduces the attack success rate (ASR) to as low as 0.1% while preserving 97.8% clean accuracy. Evaluation on six models (ResNet18, VGG16, MobileNet, AlexNet, ViT-Small, ViT-Base) shows strong generalization: near-100% ASR drops to single digits across poisoning rates of 1-10% and 1-9 simultaneous triggers, with only gradual degradation in clean accuracy. ASIC and FPGA implementations confirm practicality, adding a consistent 19-20% latency overhead across all evaluated architectures and establishing Combinatorial Lock as a hardware-native approach to multi-trigger backdoor mitigation.

cs.CR · cs.AR · cs.LG

新论文 · v1arXiv:2610.37284

Bayesian Inference of Expensive Simulators: Survey and Comparison of Design Choices

Šimon Soldát, Václav Šmídl

原文摘要

We present a survey of approaches to Bayesian inference with simulator forward models, focusing on settings with prohibitively expensive simulators. In this domain, Bayesian optimization-based methods have emerged as the most promising approach. We unify existing methods into a general framework, enabling consistent reasoning about shared algorithmic structure across the fragmented literature. Within this framework, we identify the primary design choices and perform a systematic empirical comparison of their effects on inference efficiency in terms of required simulation budget. A key result of our study is that inference efficiency is often dominated by the choice of surrogate-model response variable, as it directly governs the complexity of the modeled function. Specifically, we demonstrate that the prevalent scalar log-likelihood is a poor response variable, as it discards crucial information. Based on this insight, we introduce the concept of custom \emph{proxy variables}: transformations of simulator outputs engineered to retain more information and provide smoother response surfaces, substantially improving inference efficiency over standard response variables. We provide actionable guidance and a numerically robust Julia package to facilitate practical adoption of Bayesian optimization for simulator inverse problems.

cs.LG

新论文 · v1arXiv:2610.37283

BenchMeUp: Building Software Engineering Benchmarks from Natural-Language Specifications

Islem Bouzenia, Michael Pradel

原文摘要

Software-engineering research relies on benchmarks that evaluate new techniques on a set of problem instances. Unfortunately, manually constructing benchmarks is labor-intensive, as researchers must find suitable instances, prepare execution environments, establish expected outcomes, and validate correctness. This paper presents BenchMeUp, an approach for automatically creating software-engineering benchmarks from natural-language specifications. Given a specification defining the desired instances, data sources, and evaluation procedures, BenchMeUp generates search rules and a construction plan, invokes parallel LLM agents that identify candidate instances and construct executable instances, validates the results in fresh execution environments, and packages the instances behind a unified command-line interface. We evaluate the approach on four tasks: program repair, issue reproduction, compiler autotuning, and fixing static-analysis warnings. Targeting 50 instances per task (200 in total), BenchMeUp constructs 198 instances, of which 196 (99\%) are successfully packaged. Search and construction take 36 minutes and \$0.79 per instance, on average. Evaluating eight existing techniques on the generated benchmarks, we find that 189 of 196 packaged instances (96\%) support end-to-end evaluation, allowing users to study the effectiveness of the techniques. Checking every constructed instance against its source, the specification, and its expected outcome, we find that 180 of 198 (91\%) meet all criteria, compared with 10 of 200 instances delivered by Codex (general-purpose coding agent). Overall, we show that LLM-based agents can automate benchmark construction across diverse software-engineering tasks and produce executable instances that existing techniques can use, while validity beyond execution still needs to be checked.

cs.SE

版本更新 · v2arXiv:2510.00051

Latent Representation Learning from 3D Brain MRI for Latent Analysis and Prediction in Multiple Sclerosis

Trinh Ngoc Huynh, Nguyen Duc Kien, Nguyen Hai Anh, Dinh Tran Hiep, Manuela Vaneckova, Tomas Uher, Jeroen Van Schependom, Stijn Denissen 等 11 位作者

原文摘要

Neurological diseases can cause significant cognitive impairment, yet linking brain structure to cognitive function remains challenging due to the limitations of conventional methods and the black-box nature of deep learning. We propose InfoVAE-Med3D, an adaptation of InfoVAE for three-dimensional brain MRI that learns informative latent representations by relaxing the mutual information regularization penalty between inputs and latent representations. We evaluated the method on a healthy control (HC) dataset (\(n=6{,}503\)) with age and sex information and a multiple sclerosis (MS) dataset (\(n=916\)) with age, sex, and Symbol Digit Modalities Test (SDMT) scores. Two-dimensional visualizations revealed sex-related clustering and smooth transitions in grey and white matter volumes. Removing the mutual information regularization penalty generally improved MRI reconstruction and brain age and SDMT prediction using support vector regression, outperforming other variational autoencoder variants and achieving competitive performance with deep learning predictors, particularly on the MS dataset. InfoVAE-Med3D provides informative latent representations for investigating brain-related characteristics and supports latent-space analysis and imaging biomarker discovery for cognitive impairment, particularly in MS.

eess.IV · cs.CV · q-bio.QM

新论文 · v1arXiv:2610.37281

RPSD: Retrieval-Privileged On-Policy Self-Distillation with Optimal Transport

Dongyue Li, Zebang Cheng, Zhongyi Deng, Hongboxu, Yi Bin, Fei Ma

原文摘要

Sequential recommendation predicts a user's next interaction from historical behavior. Recent LLM-based methods recast this task as generative recommendation and increasingly adopt reinforcement learning such as GRPO for post-training. However, these methods suffer from two limitations, namely credit-blind optimization, where a sequence-level reward is shared across all generated tokens, and collaborative-blind supervision, where each training signal is derived from a single user and ignores behavioral patterns shared across similar users. To address both issues, we propose Retrieval-Privileged on-policy Self-Distillation (RPSD). For credit-blind optimization, we introduce on-policy self-distillation (OPSD), in which a teacher with privileged knowledge re-evaluates the student's on-policy response, and the token-level confidence difference between the student and teacher reshapes the shared sequence-level advantage into token-specific credit. However, the privileged knowledge in vanilla OPSD is still derived from a single user, leaving collaborative-blind supervision unresolved. We therefore ground the teacher in collaborative behavioral evidence from similar users. Specifically, we use temporally aware optimal transport (OT) to compare interaction trajectories across users by jointly considering item similarity and temporal structure, and further apply diversity-aware selection to retain complementary trajectories as privileged evidence. In this way, on-policy self-distillation provides fine-grained token-level credit, while OT enriches the teacher with structured cross-user evidence. To the best of our knowledge, this is the first work to bring on-policy self-distillation to sequential recommendation and to use cross-user behavior as its privileged signal. Extensive experiments across multiple real-world datasets demonstrate that RPSD achieves state-of-the-art performance.

cs.AI

新论文 · v1arXiv:2610.37280

Modeling Preference Dependencies with Directed Acyclic Graphs for Narrative-Driven Recommendation

Mingzhe Lu, Jian Qin, Ruize Qin, Jinhao Liu, Yunpeng Li, Hang Su

原文摘要

Narrative-driven recommendation allows users to express multifaceted needs through free-form text where stated preferences naturally qualify and condition one another. Existing methods typically treat narratives as flat keyword combinations or unconstrained generative queries, failing to capture how complex preferences hierarchically refine and contextualize each other. We propose the Preference Dependency Graph Framework (PDG-F), a narrative-driven recommendation framework centered on explicit preference dependencies. Specifically, PDG-A (PDG-Agent) first parses unstructured requests to organize user preferences and their mutual qualifications into a directed acyclic Preference Dependency Graph (PDG). Through this graph, candidate evidence from the open Web is acquired via directed path retrieval, and final recommendations are determined by topological path ranking. Comprehensive experiments across three diverse domains spanning English and Chinese contexts confirm that PDG-F consistently achieves superior recommendation performance over competitive baselines, open-domain retrieval agents, and frontier language models. Further diagnostic analyses show that our dependency-guided retrieval markedly raises the attainable candidate-pool ceiling, demonstrating the fundamental value of modeling preference dependencies in narrative-driven recommendation.

cs.IR · cs.CL

新论文 · v1arXiv:2610.37276

Where Should the Evaluation Budget Go in LLM-Driven Agent Scaffold Evolution?

Sichun Luo, Yi Huang, Mukai Li, Haochen Luo, Guanzhi Deng, Haibo Wang, Jian Xu, Zefa Hu 等 10 位作者

原文摘要

Large language model (LLM)-driven agent scaffold evolution improves agent workflows through iterative candidate generation and evaluation. Evaluation both guides subsequent search and determines the final scaffold, but evaluating every candidate on the full task set incurs substantial execution costs. We investigate how evaluation budgets can be allocated across these two roles. Our experiments show that sparse feedback can sustain productive evolution, while additional targeted evaluation improves final selection. Replay analyses further show that shared informative items and a common scoring reference support comparisons among closely matched candidates. Motivated by these findings, we propose \method, an evaluation allocation framework that combines sparse search-time feedback with targeted final confirmation. A short fully evaluated warm-up establishes a shared informative core and calibrates a response model whose item parameters remain fixed during search. After search, \method refits the model and applies paired successive halving, reusing accumulated observations and executing only missing evaluations. Across four benchmarks and two evolution frameworks, \method achieves higher mean performance than full evaluation in most settings while using approximately half as many evaluation cells.

cs.LG · cs.AI · cs.CL · cs.NE

新论文 · v1arXiv:2610.37272

Low-degree polynomials lower bounds for clustering in small dimension

Alexandra Carpentier, Nicolas Verzelen

原文摘要

We study the computational limits of clustering $n$ observations drawn from a mixture of $K$ isotropic distributions in $\mathbb R^d$, in the regime where the number $K$ of groups is much larger than the dimension $d$. In this regime, tensor-based procedures recover the partition with a polylogarithmic separation between the centers, but they require a sample size that is a large and non-explicit polynomial of $dK$, whereas the existing low-degree lower bounds only show that $n$ must be larger than $dK^2$. We introduce a mixture of $2K$ product Bernoulli distributions on $\{0,1\}^d$, with $K=(d+1)^m$, whose centers are built from a dual BCH code. This construction ensures that the moment tensors of the observations coincide with those of the uniform distribution on $\{-1,1\}^d$ up to the order $2m+1$. For any fixed $m$, we establish a low-degree polynomial lower bound showing that clustering is hard as long as the separation $Δ$ satisfies $Δ^2\ll(K^2d^{3/2}/n)^{1/(2m+2)}\wedge\sqrt d$, up to polylogarithmic factors. In particular, with a polylogarithmic separation, low-degree polynomials require $n\gtrsim K^2d^{3/2}$ observations, up to polylogarithmic factors. Through a Gaussianization argument, this hardness carries over, in the sense of reductions, to isotropic Gaussian mixtures. Our proof relies on a family of polynomials of the observations, indexed by bipartite graphs, which is almost orthonormal. The moments of these polynomials are governed by the number of solutions of polynomial systems over the finite field $\mathbb F\_{d+1}$ that are induced by the BCH code, and the crux of our analysis is to connect the combinatorial structure of the bipartite graphs with the structure of the solution sets of these systems.

stat.ML · cs.LG

新论文 · v1arXiv:2610.37271

An Interactive Mobile Augmented Reality System for Efficient Virtual Model-to-Patient Registration in Thoracic Surgery

Emmanuel Ajaero, Pascal Spiegler, George Rakovich, Marta Kersten-Oertal, Yiming Xiao

原文摘要

Video-Assisted Thoracoscopic Surgery (VATS) is a minimally invasive procedure, where precise surgical port placement is vital, yet it relies heavily on surgeon experience and mental mapping of pre-operative imaging in the operating room. To address this challenge, we present an accessible, interactive mobile augmented reality (AR) framework, HILMARTS, to enable accurate and efficient pre-operative virtual model-to-patient registration for AR-guided surgical navigation. Our system runs on a commercially available LiDAR-equipped iPad and supports a user-in-the-loop workflow through a two-stage coarse-to-fine registration process. First, the user performs a manual alignment using the AR view on the iPad. This initial maneuver is then refined through automatic point-cloud registration leveraging the LiDAR sensor. We further introduce a novel occupancy-grid-based Surface Coverage Score to provide real-time, actionable feedback to the operator on the geometric completeness of LiDAR data capture for reliable point-cloud-based alignment. In a phantom study with 16 participants, the system achieved a 3.31+/-1.26mm registration accuracy in ~4 min with a mean System Usability Scale (SUS) of 84.1. These findings highlight the system's accuracy, efficiency, robustness, and potential clinical usability, and could support its applicability to other AR-based surgical navigation tasks.

cs.HC

新论文 · v1arXiv:2610.37270

Understanding Everyday Communication Patterns, Stress, and Productivity in Hybrid Work through Egocentric Wearable Audio Sensing

Tiantian Feng, Aditya Kommineni, Emily Zhou, Burcin Becerik-Gerber, Gale Lucas, Shawn C. Roll, Shrikanth Narayanan

原文摘要

The hybrid work trend in the post-COVID period has transformed how people communicate while at work. However, there is a lack of quantitative understanding of how home and office environments shape communicative behavior and affective well-being. To study this, as a part of a larger study of the role of work environment on stress, we designed an egocentric wearable audio sensing system that captured interpersonal communication across both working locations. The system extracts real-time acoustic features on a wearable audio sensor and performs offline foreground speaker diarization to derive speaking load and activeness features. To improve diarization performance under low-dimensional feature constraints, we apply a teacher-student knowledge distillation framework that transfers knowledge from large-scale speech foundation models into a compact ResNet-based model, achieving consistent improvements in diarization performance over the baseline across three public egocentric speech datasets. In a four-month longitudinal deployment with 16 participants, our system revealed location-dependent differences in work communication patterns. Moreover, the mixed linear model analyses showed that office-based speaking load was significantly associated with higher self-reported stress and lower self-reported productivity, while speaking activeness during home-based work amplified both productivity and affective load in this cohort.

cs.SD

版本更新 · v2arXiv:1909.12353

Interactive Particle Systems on Hypergraphs, Drift Analysis and the WalkSAT algorithm

Gabriel Istrate, Cosmin Bonchis, Mircea Marin

原文摘要

We analyze the expected running time of WalkSAT, a well-known local search procedure for satisfiability solving, on satisfiable instances of the k-XOR SAT problem. We obtain estimates of this expected running time by reducing the problem to a setting amenable to classical techniques from drift analysis. A crucial ingredient of this reduction is the definition of (new, explosive) hypergraph versions of interacting particle systems, notably of coalescing and annihilating random walks as well as the voter model. The use of these tools allows to show that the expected running time of WalkSAT depends on structural parameter (we call odd Cheeger drift) of the dual of the formula hypergraph.

cs.DS · cs.DM · math.CO · math.PR

新论文 · v1arXiv:2610.37267

GradCO: Behavior-Aware Gradient-Conflict Offloading for Text-Based Person Anomaly Search

Zhiheng Fu, Zixu Li, Zhiwei Chen, Jiale Huang, Fangxu Liu, Jinhe Bi, Yupeng Hu

原文摘要

Text-based Person Anomaly Search (TPAS) retrieves a target pedestrian using natural-language descriptions of appearance and normal or anomalous behavior. Unlike conventional text-based person retrieval, TPAS must preserve identity cues while distinguishing fine-grained behaviors. It presents two challenges: same-identity, different-behavior hard negatives cause gradient conflict during granular alignment, while strong appearance cues can obscure weak behavioral evidence during aggregation. We propose GradCO (behavior-aware Gradient-Conflict Offloading), comprising three complementary components. Behavior-Aware Mixture-of-Experts (B-MoE) forms appearance, normal-behavior, and anomalous-behavior streams whose roles are learned from retrieval objectives without expert-specific semantic labels. Conflict Offload Learning (COL) uses pair-conditioned offload anchors in similarity computation to reduce the conflicting-gradient burden on the main text representations. Hierarchical Intent Alignment (HIA) aggregates expert similarities and features using query-conditioned weights. Experiments on five TPAS/TIPR benchmarks show GradCO significantly surpasses SOTA methods and validate our design.

cs.CV · cs.IR

新论文 · v1arXiv:2610.37266

Watermark Basins: Black-Box Detection of Distilled LLMs

Hongyan Chang, Hady Elsahar, Tom Sander, Pierre Fernandez, Saeed Mahloujifar, Sylvestre-Alvise Rebuffi, Tomáš Souček, Tuan Tran 等 13 位作者

原文摘要

Proprietary language models and their reasoning traces are vulnerable to API-based distillation, where an adversary trains a student model on the teacher model's outputs. To obtain evidence of distillation, model providers can watermark the teacher's outputs, aiming to leave a radioactive signal in the student's outputs. Existing black-box detectors search for such radioactivity using token-level statistics of the suspect model's outputs. However, token-level signals are not always detectable, for instance when the distillation traces are sampled at a low temperature. In this work, we discover the watermark basin, a persistent signal that enables more reliable watermark detection: during fine-tuning, watermarked teacher traces embed a distinct, key-specific geometric signal in parameter space that lies orthogonal to the ordinary task-specific fine-tuning subspace. Building on this, we introduce Watermark Basin Alignment (WM-Basin), a black-box watermark detector that queries the suspect model through its API, without access to its weights or logits. WM-Basin maps generated text to gradient representations using a fixed clean probe model, projects out the ordinary fine-tuning task directions, and tests whether the residual gradient aligns with the watermark basin induced by the watermark key. We evaluate WM-Basin extensively across diverse teacher models and student architectures (from 135M to 8.2B parameters) distilled on mathematical reasoning. At a strict 0.1% false-positive rate, WM-Basin detects 79% of distilled models at n-gram=1 and 45% at n-gram=3, substantially improving over the state-of-the-art token-level baseline (29% and 1.3%, respectively). Because the watermark signal resides in a persistent basin, it survives post-distillation modifications including quantization, pruning, and reinforcement-learning post-training.

cs.CR · cs.CL · cs.LG

新论文 · v1arXiv:2610.37265

REGLAT at ArGuard Shared Tasks: An Ensemble-Based Model Integrating NER for Harmful Content Detection in Arabic

Ahmed M. Fetouh, Mariam Labib, Nsrin Ashraf, Omer Dawood, Hamada Nayel

原文摘要

Detecting harmful content in Arabic is challenging because of dialectal variations and the semantic overlap between different harm categories. This paper presents a two-stage approach for classifying Arabic user prompts into seven categories of harmful content. First, GLiNER is used to extract harm-related entities from each prompt. The extracted entities are then added to the original text and passed to a fine-tuned MARBERT classifier for final classification. The approach combines explicit entity information with the contextual understanding of a pretrained Arabic language model. The system was evaluated on the development set of the ArGuard 2026 shared task. The results achieved a macro-F1 score of 0.886 and an accuracy of 0.897, demonstrating promising performance in fine-grained harmful content detection. The system reported an accuracy of 0.793 and Macro-F score of 0.735 on a blind test set for subtask 1. For subtask 2, it achieved an accuracy of 0.770 and Macro-F score of 0.754. The analysis also showed that distinguishing between related categories remains challenging. These findings suggest that integrating NER with Arabic language models is a promising approach to harmful content detection.

cs.CL

版本更新 · v4arXiv:2603.09813

Prismatoid Band-Unfolding Revisited

Joseph O'Rourke

原文摘要

It remains unknown if every prismatoid has a nonoverlapping edge-unfolding, a special case of the long-unsolved "Dürer's problem." Recently nested prismatoids have been settled [Rad24] by mixing (in some sense) the two natural unfoldings, petal-unfolding and band-unfolding. Band-unfolding fails due to a specific counterexample [O'R13b]. The main contribution of this paper is a characterization when a band-unfolding of a nested prismatoid does in fact result in a nonoverlapping unfolding. In particular, we show that the mentioned counterexample is in a sense the only possible counterexample. Although this result does not expand the class of shapes known to have an edge-unfolding, its proof expands our understanding in several ways, developing tools that may help resolve the non-nested case.

cs.CG · math.MG

新论文 · v1arXiv:2610.37256

Fast Approximate Line Nearest Neighbor Search

Jiadong Xie, Jeffrey Xu Yu, Yingfan Liu

原文摘要

Approximate nearest neighbor (ANN) search, which retrieves vectors close to a given query vector, is a fundamental operation in vector databases. However, emerging applications, such as selecting source images for photo-based animation and video synthesis, may require matching content while allowing a query-specified aspect contrast, such as an illumination change, to vary; a single query point does not directly express this requirement. In this paper, we study approximate line nearest neighbor (LANN) search, where an infinite query line removes the distance contribution along a specified direction while database records remain points. Prior approaches focus on top-$1$ search only for LANN and can incur high construction costs. Converting LANN into ordinary point ANN search through dimension lifting substantially increases index construction and query costs, while direct search on a proximity graph built for ordinary point ANN search can miss distinct regions close to a line. To address these issues, we propose LinePG, which enhances an existing proximity graph with pair edges to facilitate navigation between separated near-line regions. To find these pair edges efficiently, we first generate region pairs with spatial or graph separation, and near a line. We then score edges between the selected region pairs to guide the point endpoint selections. We conduct extensive performance studies and confirm the accuracy and efficiency of LinePG in comparison with the baseline approaches.

cs.DB

版本更新 · v3arXiv:2605.06993

Optimal Experiments for Partial Causal Effect Identification

Tobias Maringgele, Jalal Etesami

原文摘要

Causal queries are often only partially identifiable from observational data, and experiments that could tighten the resulting bounds are typically costly. We study the problem of selecting, prior to observing experimental outcomes, a cost-constrained subset of experiments that maximally tightens bounds on a target query. We formalize this as the max-potency problem, where epistemic potency measures the worst-case reduction in bound width guaranteed by an experiment, and show that this problem is NP-hard via a reduction from 0-1 knapsack. Building on the polynomial-programming framework of Duarte et al. (2023), we give a general procedure for evaluating epistemic potency in discrete settings. To control the super-exponential search space, we introduce two graphical pruning criteria that depend only on the causal graph and the query: a novel path-interception rule that exploits district structure to certify zero potency in linear time, and an identifiability check based on the ID algorithm. On Erdos-Renyi random graphs and 11 bnlearn benchmark networks, the two criteria together prune 50-88% of candidate experiments on average without solving a single polynomial program. For the general subset search, we show that ID-pruned experiments are combinatorially inert, yielding a super-exponential reduction in the number of subsets evaluated. We close with an end-to-end demonstration on observational NHANES data, selecting optimal experiments for estimating the effect of physical activity on diabetes.

cs.AI · stat.ML

版本更新 · v2arXiv:2610.23364

Power of Conditional Sampling on Hypergraphs

Debarshi Chanda, Buddha Dev Das, Arijit Ghosh, Gopinath Mishra

原文摘要

Let $G=(V,E)$ be a $d$-uniform hypergraph with $|V|=n$ and $|E|=m$. Estimating $m$ from uniformly random hyperedge samples requires $Θ(\sqrt{m})$ samples by a birthday-paradox argument. We investigate the power of conditional sampling through a hierarchy of oracles: for an integer $1\le s\le d$, given pairwise disjoint subsets $X_1,\ldots,X_s\subseteq V$, the $s$-colorful oracle returns a hyperedge chosen uniformly at random from all hyperedges contained in $X_1\cup\cdots\cup X_s$ that intersect every $X_i$, provided one exists. For $s=1$, this samples a uniformly random hyperedge induced by $X_1$. For every $1\le s\le d$, we give a randomized algorithm that outputs $\widehat{m}\in[(1-\varepsilon)m,(1+\varepsilon)m]$ with probability at least $2/3$ using $O_{s,d}(\operatorname{poly}(1/\varepsilon,\log n))$ conditional samples, where the exponent of $\log n$ is an absolute constant independent of both $s$ and $d$. Conditional sampling thus yields an exponential separation over uniform hyperedge sampling. We also study the decision version, in which the oracle only reports whether a qualifying hyperedge exists. For every $1\le s<d$, we prove that any algorithm using the $s$-colorful decision oracle requires $\widetildeΩ_{s,d}(n^{\frac{d-s}{d-s+1}})$ queries. Hence, for $s<d$, access to uniformly random witness hyperedges (random certificates) is exponentially more powerful than existence queries. For $s=d$, decision queries alone achieve $\operatorname{poly}(1/\varepsilon,\log n)$ query complexity, but the exponent of $\log n$ is known to be $Θ(d)$. The colorful hierarchy thus exhibits a phase transition at $s=d$: for $s<d$, random certificates are essential for polylogarithmic-query estimation, whereas at $s=d$ decision queries suffice, yet random certificates still provably reduce the exponent of $\log n$ from $Θ(d)$ to an absolute constant.

cs.DS

版本更新 · v3arXiv:2610.16925

Comparing GenAI to Machine Learning and Manual Review for eDiscovery

Gordon V. Cormack, Maura R. Grossman

原文摘要

Keeling et al. [Keeling2026Generative] report on a case study recently conducted by Redgrave LLP in which they assert that Relativity's Generative AI Review tool (aiR) achieved 88% recall while Relativity Assisted Learning (RAL), its machine-learning tool, achieved 64% recall. These results are not comparable because the methods employed have different objectives, because of inter-assessor disagreement, and because they represent different recall-precision and cost-benefit trade-offs. Our analysis of the Redgrave data indicates that, when these differences are taken into account, aiR and manual review are comparable. Furthermore, established machine-learning models employing Continuous Active Learning (CAL) and Scalable Continuous Active Learning (S-CAL) show state-of-the-art effectiveness, and superior efficiency, when trained only on a sample of 2,000 first-pass-reviewer responsiveness determinations.

cs.LG · cs.AI · cs.IR

版本更新 · v2arXiv:2610.21536

It Takes Two Moments: Rigidity and Limits of Continuous Encoders for Over-the-Air Computation

Saeed Razavikia

原文摘要

We study over-the-air computation of functions, such as empirical variance, formed by combining two separately postprocessed sums of locally transformed observations. We consider continuous encoders subject to pointwise peak-power constraints over a single use of a complex multiple-access channel. With four or more transmitters, we identify conditions under which exact noiseless recovery forces every continuous encoder collection into a common affine structure that preserves both sums, reducing infinite-dimensional encoder design to selecting a finite set of coefficients. To quantify resilience against channel noise, we introduce a robustness score that measures the separation of noiseless received aggregates relative to variations in the desired function value. Within this characterized encoder family, we formulate robustness maximization as an exact convex semi-infinite program, eliminating rank constraints without a relaxation gap, and construct a decoder that attains the minimum uniform noise-amplification constant. For several function classes, including empirical variance, we derive closed-form robustness-optimal encoders and scores. Under mild regularity conditions, we also establish sharp limits on the Gaussian mean squared error at high signal-to-noise ratios and show how using the input distribution reduces average error at the expense of uniform robustness.

cs.IT · eess.SP · math.OC

版本更新 · v4arXiv:2605.24585

Word-Class and Construction-Like Structure Emerges in Neural Successor Representations Trained on Natural Language

Mathis Immertreu, Achim Schilling, Thomas Kinfe, Patrick Krauss

原文摘要

Neural language models are typically trained on next-token prediction, although linguistic structure spans multiple temporal scales. Successor representations (SRs) make this horizon explicit by encoding discounted distributions over future states. Here, we ask whether such predictive representations can recover not only word classes, but also finer functional and construction-like structure from natural language. A residual network trained on WikiText-103 predicts SR distributions at three horizons without part-of-speech supervision. At the shortest horizon, unsupervised clustering robustly recovers nouns, verbs, and adjectives, while directed inter-cluster transitions reproduce familiar syntactic asymmetries. At finer resolutions and across 13 part-of-speech categories, the same geometry reveals semantic-functional groupings that cross category boundaries and directed relations tracing candidate date, measurement, and title-name constructions. Part-of-speech agreement declines as the predictive horizon lengthens. These results suggest that word classes are coarse regions within a richer predictive geometry in which categorical and construction-like linguistic structure emerge from future-word distributions.

cs.CL · q-bio.NC

新论文 · v1arXiv:2610.37245

Aligning Large Language Models for Safety in African Languages: A Case Study of Hausa

Valdini Douglace Lemofouet, Blessing Ngozi Uzor, Paula Chikaodinaka Anyanwu, Danielle Blanche Kapsa, Saminu Mohammad Aliyu, Seid Muhie Yimam, Shamsuddeen Hassan Muhammad

原文摘要

Safety alignment research for large language models (LLMs) remains concentrated on high-resource languages, leaving open how existing alignment methods perform in low-resource, culturally distinct settings. We study this question for Hausa, a language spoken by more than 200 million people across West Africa. We introduce HausaSafeLM, one of the first Hausa safety preference dataset, built from 10,000 prompts derived from PKU-SafeRLHF: 3,000 human-corrected (gold) and 7,000 machine-translated (silver) examples spanning six harm macro-categories. Using Qwen2.5-7B-Instruct, we compare supervised fine-tuning (SFT) and SFT followed by Direct Preference Optimization (DPO) under both data regimes, evaluating on 500 harmful and 200 benign Hausa prompts.We find that the untuned base model appears highly safe by refusal-rate metrics alone, but this reflects limited Hausa generation ability rather than genuine alignment: its refusals are almost uniformly low quality. SFT improves both refusal fluency and precision and benefits substantially from the larger, noisier silver-tier data, while DPO sharpens refusal precision but comes at a steep, largely data-invariant cost to linguistic quality. No single configuration jointly maximizes safety, helpfulness, and fluency. Our results suggest that current alignment techniques teach models when to refuse more readily than how to do so fluently in underrepresented languages, and that refusal-rate metrics alone are an unreliable signal of safety in low-resource settings.

cs.CL · cs.AI

新论文 · v1arXiv:2610.37244

Preserving Separation Logic Specifications through Compilation

Carmine Abate, Kleio Liotati, František Farka, Sebastian Ertel

原文摘要

Program specifications in separation logic describe ownership of resources and serve as logical interfaces for local reasoning. Compiler correctness, expressed as semantics preservation, does not by itself supply such an interface for compiled code, because it does not explicitly relate source and target resources and assertions. We investigate WP-preserving compilation: when a compiler translates a source program, the weakest preconditions that the program satisfies in a separation logic carry over to the compiled program. Our proof technique consists of a resource-aware simulation over interaction trees: it relates the resources required by corresponding source and target events, and tracks ownership through target operations, such as register accesses, that have no source counterpart. We apply the approach to a compiler from a structured imperative language to an assembly-like language, first for closed programs and then extended with modules and function calls. In the extended setting, each module can be verified in the source logic and compiled separately; its specifications carry over to the compiled module and are preserved when compiled modules are linked. All results are mechanized in Rocq.

cs.PL

新论文 · v1arXiv:2610.37243

TCM-DiagCommit: A TCM-SD-Derived Benchmark for Evidence-Conditioned Syndrome Selection and Commitment

Erwei Hou, Yue Hu

原文摘要

Traditional Chinese Medicine (TCM) syndrome differentiation is usually evaluated as static final-label selection over complete clinical records. This setting hides three diagnostic behaviors: whether a model distinguishes semantic-neighbor syndrome labels from easy random distractors, whether it updates predictions as evidence fields are revealed, and whether it should commit under uncertainty. We introduce TCM-DiagCommit, a benchmark derived from the public TCM-SD/ZY-BERT resource while retaining its source syndrome labels; it converts 1,834 source cases into 23,842 task rows over 148 syndrome labels. The benchmark combines random, profile-neighbor, and full-vocabulary candidate ladders with staged t1/t2/t3 evidence. It also includes fixed-label tongue/pulse perturbations and insufficient-evidence variants. A benchmark-defined action contract scores commit, acquire, defer, and abstain. Across five zero-shot DirectLLM calibrations, random10 top-1 accuracy is 63.2% to 66.4%, but hard20 falls to 24.7% to 30.3% and full148 to 14.8% to 22.3%; on hard20, WT(all) wrong-terminal commits remain 62.2% to 74.3%. These results show that final-answer accuracy alone is insufficient for diagnostic benchmark evaluation: answer selection, evidence use, and benchmark commitment scoring should be measured separately.

cs.AI