AIの鬼

研究動向 (arXiv)

機械学習・自然言語処理・コンピュータビジョンの最新プレプリント。

cs.LG

Universal Semantic Enhancement for Weakly Supervised Anomaly Detection

Siyu Zhou, Yuqin Xie, Hao Yuan, Yingjie Zhou

Weakly supervised anomaly detection on tabular data is an essential task in many label-scarce applications, since tabular data is widely encountered and it is commonly observed in practice that only a limited number of labeled anomalies are available alongside abundant unlabeled samples. Most existing methods try to learn features that capture the inherent distribution patterns in the target domain. However, such features often struggle to provide a complete description of possible abnormal char…

arXiv → PDF
nlin.CDcs.LG

From Flow-Box Invariants to Global Conservation Laws: Machine Learning-Assisted Detection of Singularities and Near-Integrability

Jimmie Adriazola, Ioannis G. Kevrekidis, Panayotis G. Kevrekidis, Wei Zhu

Conservation laws reveal invariant structure in dynamical systems and constrain their evolution to lower-dimensional level sets. Locally, however, per the flow-box theorem, every $d$-dimensional system generically admits $d-1$ functionally independent conservation laws near a regular point even though, generically, only a few such laws persist globally. Data-driven methods typically learn conservation laws on a prescribed region of phase space from which training samples are drawn, leaving their…

arXiv → PDF
cs.CV

A Paired RGB-Sonar Dataset for Fish Monitoring with Consumer Sonar

Mourad Derbedrosian, Michael Hobley, Pietro Perona

Imaging sonar enables underwater observation in conditions where optical imaging is ineffective due to darkness and turbid water. However, imaging-sonar systems previously used for ecological monitoring have typically been expensive, limiting their accessibility. Consumer forward-looking sonar has the potential to make fish monitoring more accessible, but its noisy imagery makes annotation and the development of automated methods challenging. We introduce the Huntington and Caltech Koi RGB and S…

arXiv → PDF
cs.CV

MTEdit: Packed Trajectories Beat Rollouts for Multi-Turn Image Editing

Houyuan Chen, Fanzhou Wang, Xiangyu Fan, Songlin Yang, Zhitao Yang, Lvmin Zhang, Pei Yang, Hao Zhao et al.

Multi-turn image editing aims to modify an image according to a sequence of instructions, making it better aligned with human-AI collaborative creation than single-turn editing. However, constructing high-quality multi-turn training data remains challenging, as conventional sequential rollout accumulates errors and introduces visual-quality drift across editing turns. To address this challenge, we introduce MTEdit, a multi-turn image editing dataset built through a pipeline centered on packed tr…

arXiv → PDF
cs.CV

Beyond Multi-Stage Pipelines: A Label-Correlation Ensemble for Multi-Label Retinal Fundus Disease Classification

Md Asif Uddin, Jannatul Ferdous, Asif Islam, Zobaer Mahmud Zisan, Promit Ghosh, Shah Ahafik Arman, Niloy Farhan, Rafeed Rahman et al.

Retinal fundus images frequently carry more than one disease, and public fundus datasets are heterogeneous and severely long-tailed. Clinical triage suggests a staged design, in which a screening gate, a disease-group router and group-specific classifiers operate in sequence, but it is unclear whether this hierarchy earns its complexity. We present a controlled comparison of three architectures on a unified 39-target label space built from RFMiD 1.0, RFMiD 2.0 and ODIR-5K (12,652 images): (i) a…

arXiv → PDF
cs.SDcs.CL

VocalGrad: Evaluating Acoustic Perception in Audio Language Models

Koki Ryu, Hitomi Yanaka

Recent large audio language models (LALMs) have extended their capabilities beyond lexical speech understanding to tasks requiring paralinguistic and non-linguistic audio understanding, such as emotion recognition. However, these models still struggle to reliably utilize acoustic information, particularly when it co-occurs with spoken linguistic content. Existing benchmarks do not clearly distinguish acoustic perception from higher-level reasoning, making it difficult to identify the source of t…

arXiv → PDF
cs.CL

The Italian lawmaking process: a unified and structured dataset

Matilde Contestabile, Chiara Ferrara, Giovanni Parrillo, Lorenzo Emer, Andrea Vandin

The Italian legislative process is documented in detailed parliamentary records hosted in institutional websites. However, much of this information is available only as unstructured text, limiting its systematic reuse. We applied a controlled, systematic LLM-based extraction procedure, validated against manually annotated records, to convert these texts into ordered and dated events including, e.g., bill introduction, committee examination, plenary examination, and approval. The resulting datase…

arXiv → PDF
cs.LG

LagNet: Lag-Structured Operators for Long-Term Time Series Forecasting

Zhenan Yu, Guangxin Jiang, Jiuyun Jiang, Jin Yang

Long-term time series forecasting maps a finite history window to an extended future horizon. Many existing models focus primarily on the design of input representations and model structures, while paying less attention to the structural form of the history-to-future forecasting operator itself. We examine this operator directly and find that, across model families, sensitivity matrices exhibit recurring diagonal patterns whose diagonals correspond to relative temporal lags. Motivated by this ob…

arXiv → PDF
cs.CLcs.CYcs.LGcs.SIphysics.soc-ph

Bridging the Language Gap in Scholarly Data II: Enhancing Gender Inference for Chinese Names

Lisette Espín-Noboa, Mingrong She, Ana Maria Jaramillo, Liuhuaying Yang

Perceived gender inference from names is important for inclusive scientometrics research, yet existing methods perform poorly on non-Western scholars. We address this gap for Chinese names, which appear in two forms, Hanzi and Pinyin, its Romanized form (e.g., Zhang Wei, Li Na). In international bibliographic records, names are often available only in Pinyin. However, a single pinyin name can correspond to multiple distinct hanzi characters with different gender associations, so gender inference…

arXiv → PDF
cs.CV

Synthetic Image Oversampling for Rare-Class Representation Learning in Deep Facial Phenotyping

Miles Liao, Zhanliang Wang, Hongzhuo Chen, Kai Wang

Recent deep facial phenotyping methods can support the recognition of genetic syndromes, but patient images are often scarce and unevenly distributed across disorders. Synthetic facial images offer a way to supplement the training data without collecting additional patient photographs. Their usefulness, however, depends on whether they improve recognition of real patients: generated images may introduce artifacts or repeat features already represented in the training set. It is therefore necessa…

arXiv → PDF
cs.LG

Escaping Parameter Space: Tight Generalization Bounds via Representation Quality

Niclas Göring, Shuofeng Zhang, Branton DeMoss, Ard A. Louis

We derive a tight generalization bound for deterministic neural We derive a tight generalization bound for deterministic neural networks based on their last hidden layer representations. By evaluating representation quality with a parameter-free $k$-nearest-neighbor ($k$-NN) classifier, our certificate avoids traditional parameter-space complexity measures, KL divergences to a posterior, weight norms, and compression. The bound is tight: trained from scratch, it reaches an 8.0 percentage point g…

arXiv → PDF
eess.SPcs.LG

ECG-SDI: Single-lead Electrocardiogram Enables Continuous Sleep Depth Index Profiling and Scalable Digital Biomarkers for Sleep Health

Donglin Xie, Qingshuo Zhao, Songchi Zhou, Haoyu Wang, Jingyu Wang, Yuxi Zhou, Thomas Penzel, Shenda Hong et al.

Conventional sleep staging provides a coarse-grained representation that obscures within-stage depth variation. We developed ECG-SDI, a single-lead electrocardiography (ECG) framework for continuous sleep-depth profiling and digital biomarker extraction. Using 12,392 overnight polysomnographic recordings, we trained and validated a two-stage deep learning model supervised by conventional sleep-stage labels. Correlations with ordered stages excluding rapid eye movement (REM) sleep were 0.828 in t…

arXiv → PDF
cs.AI

Beyond Large Language Models: A Mental World Model Framework for Mental Modeling, Simulation, Evolution, and Interpretability

Qingshi Wang

Understanding and simulating how subjective cognition and mental states emerge, evolve, and shape behavior is essential for advancing artificial intelligence toward deeper social cognition and general intelligence. Existing large language models (LLMs) and Theory of Mind (ToM) methods primarily infer mental states from linguistic information, lacking unified mechanisms for subjective world construction, cognitive-psychological interactions, dynamic evolution, and historical dependencies. This pa…

arXiv → PDF
cs.CL

Recognizing Study Lineage Is Not Enough: Over-Crediting Same-Trial Evidence in LLM-Based Medical Verification

Mukand Krishna, Anoushka Harit, Chenghao Xiao, Zhongtian Sun

Publication count is not study count. A model can identify shared trial lineage correctly in a direct task yet over-credit a second publication from the same trial when aggregating evidence. We evaluate this behavior in medical LLM verification using 14 source-audited clinical families and five model conditions. The families span provenance, clinical applicability, result direction, and composition; the provenance families provide the direct lineage tests. Recognition and aggregation are separat…

arXiv → PDF
cs.LGcs.AI

Neural Expansion: A Unified Mechanism for How Deep Neural Networks Generalize

Chashi Mahiul Islam, Samuel Jacob Chacko, Mao Nishino, Canlin Zhang, Xiuwen Liu

Deep neural networks demonstrate remarkable generalization despite being highly over-parameterized, challenging traditional statistical learning theories. While several theoretical paradigms such as margin-based bounds, PAC-Bayesian analyses, and neural tangent kernels provide global explanations, they often lack mechanistic insight into how generalization emerges from training dynamics. We introduce Neural Expansion, a unified geometric framework that characterizes generalization through the ex…

arXiv → PDF
cs.CL

The Cognitive Cost of LLM Writing: A Reading-Time Comparison with Human Text

Kamer Cekini, Elisabetta Biondi, Chiara Boldrini, Andrea Passarella, Marco Conti

Although linguistic differences between human-written and Large Language Model (LLM)-generated texts have been extensively studied, their implications for the cognitive effort involved in reading remain less explored. In psycholinguistics, reading time is commonly used as an indirect measure of cognitive processing effort. Building on this perspective, we investigate whether human-written texts and their LLM-generated rewrites exhibit differences in predicted reading time that may reflect differ…

arXiv → PDF
cs.CLcs.AI

GLOBE: Evolving Structured Agentic Memory for E-commerce Product Optimization in Generative Search

Hyunseo Kim, Suil Choe, Sukkyoung So, Daeyeon Yi

Optimizing product listings for generative search requires language agents not only to rewrite effectively but also to continually self-improve by retaining successful strategies across diverse categories. However, existing approaches often treat structured listings as free-form text, leaving effective strategies implicit in prompts, search trajectories, or rewritten outputs rather than accumulating them as a reusable agentic memory. To address this limitation, we introduce GLOBE, an agentic fra…

arXiv → PDF
cs.LGcs.IR

Tool Recommendation for Multi-Step Agents: Finding Every Tool a Task Needs

Sam Partee, River Stevens, Thierry Damiba, Valerie Fanelle

A multi-step agent task fails when a single tool it needs is missing, yet the tools an agent may need are too many to list: the roughly 8,200 tools on the platform we study have definitions that together exceed the context window of any model we evaluate. We present Tool Recommendation, a deployed system that gives an agent all of them, hundreds of times more than a typical MCP server exposes, through a fixed interface of three tools. It runs at the gateway between agent and tools, executing eve…

arXiv → PDF
cs.CV

FedRAPP: Federated Test-Time Prompt Tuning for Vision-Language Models with Reliability-Aware Prompt Personalization

Syed Md. Ahnaf Hasan, Md Akil Raihan Iftee, Sajib Mistry, Amin Ahsan Ali, AKM Mahbubur Rahman

Federated prompt learning enables vision-language models like CLIP to collaboratively adapt lightweight soft prompts across distributed clients without sharing raw data. However, existing federated prompt learning methods are designed primarily for supervised settings with labeled client data and assumed relatively stable training distributions. At test time, source-free federated prompt tuning remains largely unexplored. Clients may receive unlabeled target samples with heterogeneous, often non…

arXiv → PDF
cs.LG

Blitz: Accelerating the Diffusion Modules of AlphaFold3 and Boltz-2

Vinay Saji Mathew, Soundar Kumara, Gretta Kellogg, William K. M. Lai

Diffusion-based protein structure prediction models produce all-atom structures in about 200 denoising steps, and that cost has driven a number of few-step samplers. We present Blitz, a few-step distillation framework that uses a geometric noise schedule to distribute steps more evenly across noise scales, then learns those updates through multistep consistency training. Physical steering and target-free candidate selection help reduce the remaining geometric defects at inference. We apply Blitz…

arXiv → PDF
cs.CL

VISTA: Steering LLMs with Latent User Values Inferred from a Few Survey Answers

Yinuo Xu, Jadie Adams, Brian Hu, Shivani Kumar, David Jurgens, Arslan Basharat

Personalizing a language model requires knowing what a person values, which stays largely consistent across tasks. Yet most methods either learn task-specific preferences or place the user's profile in the prompt, where models struggle to act on it. We introduce VISTA (Value-Informed Steering and Targeted Acquisition), which infers a latent profile from users' (full or partial) survey answers, and maps the profile through a hypernetwork to a user-specific steering intervention in a frozen LLM to…

arXiv → PDF
cs.LGstat.ML

Equivalence testing and run-count design for stochastic machine-learning experiments

Dmytro Knopov, Nadiya Shvai

Claims that two training methods perform equally well often rest on a non-significant difference between two or three runs per method. We develop a protocol, with its power theory, for certifying practical equivalence in per-run metrics such as the AUROC (area under the receiver operating characteristic curve). It rests on a two-level (seed x item) variance model separating between-run dispersion from item-level noise. Equivalence within a pre-specified margin is tested by two one-sided tests (T…

arXiv → PDF
quant-phcs.LG

Expressivity of IQP Feature-Map Quantum Kernels via Reproducing Kernel Hilbert Spaces

Valeria Repetto, Stefano Melchionna, Romina D'Aurizio

Quantum kernels are among the most promising methods in quantum machine learning, providing a natural way to embed data into high-dimensional Hilbert spaces via quantum circuits and capturing non-linear relationships in data. Their learning behaviour is governed by the function class they represent, which is formally characterized by the structure of the associated Reproducing Kernel Hilbert Space (RKHS). However, a theoretical characterization of this function class, and of how it depends on th…

arXiv → PDF
cs.CRcs.LG

HardEval: An Execution-Verified Benchmark for AI-Driven Security Hardening and Compliance Remediation

Manohar Vellala, Soumya Banerjee, Sandip Roy, Ross Gore, Sachin Shetty

Implementing Security Technical Implementation Guide (STIG) controls remains a demanding operating-system administration task. Each natural-language security requirement must be translated into a precise and persistent configuration change. These changes span Secure Shell (SSH) configuration, authentication policy, audit rules, and kernel parameters. Existing benchmarks do not measure whether a model can perform this task on a live system. Code benchmarks evaluate isolated programs without persi…

arXiv → PDF
cs.SDcs.CL

Beyond the Benchmark: Conditioning, Domains and Failure Modes of Qwen3-TTS

Séverin Baroudi, Yanis Labrak, Petr Motlicek, Hervé Bredin, Ricard Marxer

Qwen3-TTS reports state-of-the-art zero-shot voice cloning, but its technical report leaves open how the model should be conditioned, how it behaves outside read speech, and how it fails. We characterise its two cloning interfaces, in-context learning (ICL) and X-Vector, against Chatterbox, XTTS-v2 and F5-TTS on read, meeting, emotional and air-traffic-control (ATC) speech, using eighteen objective measures, an LLM judge, a spoofing countermeasure and a listening test. Neither interface dominate…

arXiv → PDF
cs.CV

Agentic Physics-Grounded Video Generation via Memory-Augmented In-Context Reasoning

Xikang Guan, Shaocong Yang, Yanqi Bao, Can Wang, Zheng Gu, Zhengqing Chen, Kai Chen, Jing Huo et al.

Physical plausibility is essential for realistic video generation. Existing methods impose physical guidance before synthesis via simulations or refined prompts, but this can limit dynamic diversity, miss errors that emerge only after generation, and require repeated regeneration when inconsistencies remain. We therefore study a generate-diagnose-repair paradigm that preserves the original generation capability and selectively repairs physical inconsistencies afterward, raising two key questions…

arXiv → PDF
math.OCcs.AIcs.MA

On the possibilities and limitations of LLM-based multi-agent systems for multi-criteria decision-making in healthcare operations management

Marco Boresta, Tommaso Giovannelli, Sepehr Namirad, Giulia Riccardi

Multi-criteria models for healthcare operations need weights that express how stakeholders trade off patient waiting time, provider workload, and operating cost, but these weights are difficult to quantify. Teams of large language model (LLM) agents, each prompted to represent a stakeholder, have been used to supply them. We propose a framework for assessing the reliability of LLM-generated preferences as inputs to multi-objective optimization and quantifying how their uncertainty affects decisi…

arXiv → PDF
cs.AI

OwlSight: A Panoramic Monitor for Chain-of-Thought Reasoning

Lewen Yan, Yanxu Zhu, Jie Zhang, Jing Shao

Chain-of-Thought (CoT) monitoring offers actionable evidence for oversight AI systems, with the potential to enable early detection and intervention. However, existing approaches are focused on specific tasks, whereas the regulation of AI, particularly reasoning models, requires monitoring a broader range of tasks. We introduce Factor for CoT monitoring, a strategy that supports customizing monitoring requirements in the prompt, which enables a single monitor to cover different tasks by relying…

arXiv → PDF
cs.CRcs.AI

TUPLE-Bench: Evaluating and Mitigating Privacy-Utility Trade-offs in Typed Decision Models

Yiqu Yang, Qiaoyuan Zheng, Yang Tian, Yu Fan, Elliott Ash

Typed decision models often return more than a selected category. They also expose probabilities for each candidate and, sometimes, a separate confidence score. These fields support downstream decisions but may reveal information beyond a recipient's authorization. We introduce TUPLE-Bench (Typed decision models' Utility and Privacy Leakage Evaluation Benchmark), a benchmark of paired synthetic cases in which recipients may learn a coarse operational category but not its fine-grained cause. Acro…

arXiv → PDF
cs.LGeess.SP

TriRouter: Sparse-to-Dense Electrode-Space Routing for Robust EEG Motor Imagery Decoding

Ying Zhou, Yaoxin, Mengting Liu

Motor imagery brain-computer interfaces require reliable decoding from multichannel EEG, but practical acquisition often yields sparse or corrupted electrode montages. We propose TriRouter, an electrode-space routing framework with discriminative-preservation, mask-robustness, and latent-compensation paths. A validation-calibrated router uses observable channel availability to allocate path contributions, preserving complete-channel discrimination while increasing representation recovery under s…

arXiv → PDF
御社でもAIを使ってみませんか
まずはここから 御社でもAIを使ってみませんか？ 御社の実際の業務を題材に、AIで何ができるかを一緒に考えます。 「ChatGPTの使い方」を教えるだけの研修ではありません。 AI研修・AI活用相談 →
AI検索で自社がどう見えるか知りたい ChatGPTやPerplexityで自社が言及されるかを実際に測ります。 引用を約束するものではなく、まず現状を測るサービスです。 AI検索可視性診断 → Webサイトを改善したい 測った結果、サイト側に原因があった場合の改善まで対応します。 Web制作25年・1000案件の実績があります。 SEO・Webサイト改善 →