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.AI

Examining the Vulnerability of Multi-Agent Medical Systems to Human Interventions for Clinical Reasoning

Benjamin C Liu, Dillon Mehta, Rishi Malhotra, Adam Zobian, Yong Ying Tan, Samir Chopra, Daniella Rand, Natalie Pang et al.

Human interventions at fault points can alter the diagnostic accuracy of multi-agent medical systems. We defined fault points as moments in AI agent conversations, in which an agent's reasoning became most vulnerable to external influence. Using the MedQA dataset, this study analyzed simulated doctor-patient conversations to measure how interventions shifted reasoning and accuracy. Correct intervention methods showed an improvement in baseline diagnostic accuracy of up to 40%, while incorrect or…

arXiv → PDF
cs.CV

Lightweight Adaptation of General-Purpose VLMs for Multispectral and SAR Image Understanding

Shanji Liu, Kelu Yao, Junxiao Xue, Chenghui Lv, Xiangyang Miao, Yekai Huang, Yaying Chen, Chao Li et al.

General-purpose vision-language models (VLMs) now support strong visual recognition, instruction following, and generation. However, most pretrained visual encoders are built around three-channel natural images and do not directly accommodate observations such as native multispectral measurements or synthetic aperture radar (SAR). Adapting VLMs to these sensors typically requires dedicated encoders and domain pretraining, slowing the reuse of stronger general-purpose checkpoints. We show that th…

arXiv → PDF
quant-phcs.LG

Quantum MeanFlow: single-shot generative sampling on NISQ hardware

Ashish Joshi, Eshaan Mistry, Takahiko Koyama

Quantum generative models offer a promising framework for exploring whether quantum computation can enhance generative machine learning. Flow matching is a generative method in which samples are generated by transporting a simple, known distribution to the target data distribution with a learned velocity field. Its quantum counterpart, known as quantum flow matching (QFM), was introduced recently, and, like its classical counterpart, requires integrating an ordinary differential equation over ma…

arXiv → PDF
cs.CV

CC-4DGS: Computational Deformation and Point-Cloud Compression for Storage-Efficient Dynamic Gaussian Splatting

Kyungdae Park, Chae Eun Rhee

Dynamic four-dimensional (4D) Gaussian Splatting has emerged as a powerful explicit representation for high-quality view synthesis, yet existing methods still require tens to hundreds of megabytes per scene due to their heavy reliance on large multi-resolution hash tables and high-dimensional Gaussian attributes. This paper presents CC-4DGS, a storage-efficient and scalable framework that rethinks both deformation modeling and canonical attribute storage. First, we introduce a computational defo…

arXiv → PDF
cs.CRcs.LG

WeaveMark: Robust and Scalable Multi-bit LLM Watermarking via Coded Payload Spreading

Gang-Hyun Park, Ju-Hyeong Lee, Hee-Youl Kwak, Dae-Young Yun

Multi-bit watermarking for large language models (LLMs) enables content source tracing by embedding user-identifiable messages into generated text. Existing methods face a fundamental trade-off among extraction accuracy, text quality, and payload capacity. We propose WeaveMark, a robust and scalable multi-bit LLM watermarking scheme based on coded payload spreading. WeaveMark shifts this trade-off frontier by improving payload capacity through multi-bit-per-token spreading, improving extraction…

arXiv → PDF
cs.CLcs.LG

Breadth Beats Depth: Improving GCG-Based Jailbreak Optimization with Breadth-Oriented Suffix Search

Shiliang Xiao, Jingsong Wei, Yuzhi Liang, Yufan Zheng, Xia Li, Qiliang Lin

Optimization-based jailbreak attacks such as Greedy Coordinate Gradient (GCG) achieve strong effectiveness and transferability by optimizing adversarial suffixes on white-box source models. However, existing GCG-based methods rely on averaged adversarial loss and deep greedy search, which can over-emphasize easy-to-jailbreak behaviors and overlook promising regions of the suffix space. We propose BOSS, a plug-and-play framework that improves GCG-based jailbreak optimization through breadth-orien…

arXiv → PDF
cs.CV

Progressive Pseudo-Label Optimization for Point-Supervised Change Detection

Hailong Ning, Hao Wang, Yimeng Wang, Tao Lei, Renwei Dian, Asoke K. Nandi

Point-supervised change detection (PS-CD) aims to identify pixel-level changes between bi-temporal images using only sparsely annotated points. Although point annotations substantially reduce labeling costs, their limited spatial coverage often results in incomplete and noisy pseudo-labels. To address this issue, we propose a two-stage framework that introduces SAM2 priors into PS-CD and progressively adapts them to the target task. In Stage I, SAM2 generates object-aware candidate masks from po…

arXiv → PDF
cs.LG

DMRL: Document-Mediated Reinforcement Learning for Skill Optimization in Advertising Recommendation

Wei Zhang, Hongji Li, Song Sun, Peng Yu, Xue Yang, Lei Zhao, Peng Jiang

Advertising recommendation requires continuously tuning complex system parameters while balancing commercial returns and user experience. Recent work has introduced large language models (LLMs) with skill documents to assist this labor-intensive process, but skill optimization remains largely prompt-driven, lacking a principled mechanism to attribute rewards to specific document edits. To address this limitation, we propose Document-Mediated Reinforcement Learning (DMRL), a skill self-evolution…

arXiv → PDF
cs.AI

FUSE: An Evaluating Framework for Dangerous Capabilities of LLMs

Zhengyi Jin, Ru Zhang, Xiao Chen, Xinbo Liu, Jiaxuan Lin, Jia Huang, Jianyi Liu, Zhen Yang et al.

Fragmented safety evaluation undermines the governance of dangerous AI capabilities. We present a modular framework that evaluates each model through three orthogonal pipelines---Knowledge ($K$), Defense ($D$), and Harm ($H$)---under a unified protocol, aggregating results into a standardized dangerous-capability profile $φ$. Pluggable modules supply scenario seeds, knowledge banks, hazard queries, and judge rubrics, while the core evaluation engine remains unchanged across domains; the CB evalu…

arXiv → PDF
cs.CL

Do Cantonese-Adapted Language Models Better Predict Cantonese Reading? A Cross-Model Eye-Tracking Evaluation

Ziqi Zhang, Emmanuele Chersoni, Mohammad Momenian

Information-theoretic measures derived from autoregressive language models are widely used to characterize the expectations that shape human reading, but whether language-variety-specific training improves such psycholinguistic alignment remains unclear. This question is still open for Cantonese, where recent NLP evaluations reported mixed benefits from Cantonese-specific training relative to Mandarin-oriented or general-purpose models. Using naturalistic Cantonese eye-tracking data, we compare…

arXiv → PDF
cs.IRcs.LG

GenCAR: Generative Counterfactual Alignment with Risk-Controlled Selection for Out-of-Distribution Recommendation

Qianqian Wang, Yunshan Li, Jiawen Zeng, Wenwu Gong, Lili Yang

Serving useful recommendations under distribution shift is crucial for balancing utility and risk in out-of-distribution (OOD) recommendation. However, most existing OOD methods improve ranking or construct counterfactual candidates without controlling the proxy-label false discovery rate (FDR) of the served set. In this work, we formulate OOD serving as the $α$-Valid Counterfactual Recommendation ($α$-VCR) problem to retain candidate support learned from counterfactual supervision while control…

arXiv → PDF
cs.LGcs.AI

GeoSPRINT: Geometric Redundancy-Aware Step Pruning for Inference in Diffusion Trajectories

Arpita Joshi

Diffusion models achieve high sample quality but remain expensive at inference time because sampling requires many sequential neural function evaluations (NFEs). Existing acceleration methods either use fixed step-skipping schedules, adapt step sizes based on local numerical error, or require additional training. We introduce GeoSPRINT (Geometric Step Pruning for Inference in Trajectories), a training-free framework for constructing non-uniform sampling schedules from the geometry of denoising t…

arXiv → PDF
cs.CV

World-Coherent Decoding: Self-Verifying Test-Time Planning for World Action Models

Chuhan Zhang, Seiji Ito, Kenta Hoshino, Satoshi Ikehata, Ikuro Sato

World Action Models (WAMs) aim to control robots by stochastically generating visual futures and then decoding actions, but empirical observations indicate that the results can strongly depend on which future is selected. We propose World-Coherent-Decoding (WCD), a self-verifying test-time planning framework that treats WAM rollouts as falsifiable future--action hypotheses. At each decision step, WCD samples multiple candidates from a frozen WAM and ranks them using internal generative signals:…

arXiv → PDF
cs.CLcs.AI

OBJECTION! Lawyer Agents Mitigate Guilty Bias in Legal Judgment Prediction

Jaehoon Jeong, Jay-Yoon Lee

Legal Judgment Prediction (LJP) models are typically trained on documents that describe facts from a prosecutorial perspective. Existing datasets further exhibit severe label imbalance toward guilty outcomes. Consequently, these models suffer from "Guilty Bias", blindly accepting the prosecution's narrative as objective truth. Previous studies employing three-step reasoning structures or training on synthetically generated innocence data improve overall accuracy, but they still fail to mitigate…

arXiv → PDF
cs.LGcs.ITmath.NAmath.PRmath.ST

Exact Limits of Random Projections for Preserving Geometry: Distance Recovery, Nearest-Neighbor Rankings, and Covariance Shape in Gaussian Models

Piyush Sao

The Johnson-Lindenstrauss (JL) lemma guarantees that a random projection of $n$ points to $m=O(\varepsilon^{-2}\log n)$ dimensions preserves pairwise squared distances within relative error $\varepsilon$ with high probability, and this dimension order is asymptotically optimal. In high dimensions, however, distances concentrate around a baseline while key geometric information lies in much smaller fluctuations. We show that the JL bound can therefore be uninformative about retained geometry: an…

arXiv → PDF
cs.CL

A Layered Taxonomy for Chinese Learner Grammatical Error Annotation

Mengyang Qiu, Jungyeul Park

Grammatical error annotation in Chinese learner writing requires labels that are both consistent and linguistically meaningful. This paper proposes a layered scheme linking computational Chinese grammatical error correction (CGEC) with pedagogical error analysis. The scheme first identifies character- and punctuation-level orthographic errors, labeling them by edit operation and subtype. Other errors receive a three-layer core label combining edit operation, linguistic domain, and part of speech…

arXiv → PDF
cs.IRcs.AI

Beyond Modality Harmony: Orthogonal Purification and Topology-Guided MoE for Conflict-Aware Multimodal Recommendation

Jialin Liu, Zhaorui Zhang, Ray C. C. Cheung

Multimodal Recommender Systems (MRSs) typically rely on a flawed "modality harmony" assumption, presuming that multimodal features are inherently beneficial and strictly aligned with users' collaborative interaction patterns. However, modality-topology conflicts are ubiquitous in real-world scenarios due to deceptive visual clickbaits and mismatched semantics. Blindly integrating these noisy modalities inevitably pollutes the pristine collaborative space, causing severe representation distortion…

arXiv → PDF
cs.HCcs.AI

OmegaUse-SOP: SOP Engineering for Professional Computer Use from Human Demonstrations

Yixiong Xiao, Lang An, Hucheng Yang, Pinxue Ma, Yongquan Chen, Jingjia Cao, Yusai Zhao, Ting Wang et al.

Large language models (LLMs) are increasingly evolving from conversational assistants into agents capable of operating external digital environments. Graphical user interface (GUI) agents play an important role in this transition, as many real-world workflows remain accessible only through user-facing software interfaces. However, despite recent progress on general computer-use benchmarks, domain-specific professional standard operating procedures (SOPs) remain challenging for GUI agents because…

arXiv → PDF
cs.LGcs.AIcs.CCstat.ML

Online Non-Monotone DR-Submodular Maximization Matching the Offline $0.401$ Factor

Vaneet Aggarwal, Yiyang Lu

We study online maximization of nonnegative, non-monotone DR-submodular functions over compact convex down-closed subsets of the $d$-dimensional unit cube. The best known constructive offline approximation factor is $0.401$ under the corresponding meta-solvability assumptions, whereas comparable adversarial online guarantees had remained at $1/e$. We show that this factor is also achievable online. In the post-decision full-information value-oracle model, our algorithm attains factor $0.401$ wit…

arXiv → PDF
cs.DBcs.AIcs.IRcs.LG

A Power Law in Logarithm's Clothing: On the Scalability of Graph-Based Vector Search

Sajad Faghfoor Maghrebi, Navid Eslami, Niv Dayan

Most vector databases rely on graph-based indexes, notably HNSW and Vamana, for approximate nearest neighbor search. With embedding models widely adopted, the datasets these databases store grow rapidly. At a fixed accuracy, how does search cost scale with dataset size? The prevailing answer is poly-logarithmic growth. Yet the claim is proven only under special conditions and asserted without proof for the indexes used in practice. It is also largely untested: standard benchmarks measure cost at…

arXiv → PDF
cs.NIcs.LG

SoK: Where Do Flow Labels Come From? Auditing Label Provenance in Encrypted Traffic Benchmarks

Sizhe Huang, Shujie Yang

Encrypted traffic classification infers semantics beyond the flow record from transport-layer observables, and supervised training rests on labels that hold for the individual flow they are attached to. Recent systematizations scrutinize model in- puts and data splits; we systematize the complementary label side. Across 14 audited benchmark entries, we identify two recurring label-side strategies: coarse inheritance, which risks labelling flows the evidence does not cover, and overstrict filteri…

arXiv → PDF
stat.MLcs.LGstat.CO

HyperMC: Multi-Fidelity Hyperparameter Tuning for Stochastic Gradient MCMC

Ming Tan, Xiyun Jiao

Stochastic gradient Markov chain Monte Carlo (SGMCMC) methods enable scalable Bayesian inference, but their performance depends strongly on hyperparameters such as the step size, mini-batch size, and number of leapfrog steps. Since most SGMCMC algorithms lack a Metropolis-Hastings acceptance rate, standard acceptance-based tuning methods are not directly applicable. We propose HyperMC, a multi-fidelity tuning framework that combines Hyperband-style resource allocation with kernel Stein discrepan…

arXiv → PDF
cs.AIcs.CL

EmoStance: Response-Side Affective-Orientation Control for Empathetic Response Generation via Emoji Weak Supervision

Ziyuan Jin, Yuxuan Ge, Zheng Tian

Empathetic response generation requires models to decide not only what to say, but also how to respond to the previous speaker's affective situation. We formulate this as response-side affective-orientation control and use multi-annotator emoji distributions as weak affective--attitudinal evidence, rather than as output symbols or gold labels, to induce a latent control space that operationally approximates listener stance. We construct EmojiDialogue, an utterance-level extension of EmpatheticDi…

arXiv → PDF
cs.CLcs.AI

C$^{3}$T: Counterfactual Causal Reasoning for Sentiment Shifts in Social-Media Conversation Trees

S M Rafiuddin, Atriya Sen

Sentiment in social-media threads does not only vary across posts; it shifts as users react to claims, corrections, evidence, and hostility within a branching reply tree. We study why sentiment changes in rumor-centric conversation trees by treating discourse moves (e.g., denial/correction, evidence/link, toxicity/attack) as candidate interventions and asking (i) what sentiment a reply expresses, (ii) whether the sentiment shifts relative to its parent, and (iii) which prior message most plausib…

arXiv → PDF
cs.AIcs.IR

Beyond Context Windows: Persistent Discovery Context for Data-Centric Agents

Jalal Mahmud

Data-centric agents repeatedly perform a discovery step before planning or execution: identifying the data objects relevant to a task. Yet successful discovery outcomes are typically discarded rather than reused. We introduce persistent discovery context, a lightweight memory layer that stores prior intent-to-object mappings and reuses them to augment future retrieval. Across three structured data environments, persistent discovery context consistently improves retrieval quality over metadata-on…

arXiv → PDF
cs.LGcond-mat.mtrl-sci

Scalable Bayesian Optimization of Composite Functions for Image-Based Inverse Problems in Materials Characterization

Dasol Yoon, Poompol Buathong, Chia-Hao Lee, Yujia Zhang, David A. Muller, Peter I. Frazier

Estimating physical parameters from scientific images is a common inverse problem in materials characterization that often relies on expensive physics-based simulations. In electron microscopy, specimen thickness and crystal mistilt are critical parameters that govern how electrons scatter through the sample, and therefore the accuracy of any atomic-scale structure recovered from it. They are commonly inferred by matching experimental position-averaged convergent-beam electron diffraction (PACBE…

arXiv → PDF
cs.CLcs.CYcs.SI

AI agents reshape consensus formation in human groups

Lin Chen, Ziyi Liu, Xia Hu, Yong Li

As large language model (LLM) agents shift from tools to participants in human groups, a fundamental question for collective behavior is how their growing presence reshapes consensus formation. Here we study mixed human-AI groups in a collaborative description game, in which shared conventions emerge through repeated rounds of random pairwise communication. Varying the proportions of LLM agents, we identify three distinct regimes of consensus formation: low agent proportions facilitate human-led…

arXiv → PDF
cs.CV

Synergistic Information Disentanglement for Omni-modal Slide Representation Learning in Computational Pathology

Mingxin Liu, Chengfei Cai, Anwen Lu, Pengbo Xu, Jun Li, Jinze Li, Depin Chen, Jun Xu et al.

In computational pathology (CPath), developing omni-modal self-supervised learning (SSL) models that integrate histology, genomics, and clinical reports enables transferable representation learning for whole slide images (WSIs). Existing approaches implicitly force heterogeneous modalities into a uniform latent space by contrastive alignment, causing modality collapse where unique, synergistic diagnostic signals (termed as $\mathrmΦ$) are discarded in favor of trivial redundancy. We hypothesize…

arXiv → PDF
cs.AI

Semantic Signal-Assisted Inspection and Recovery Allocation in Reverse Logistics

Jiani He, Dingyan Shang, Yihua Xu, Shiqi Huang, Yan Lyu, Jize Li, Shangjing Tang

Reverse-logistics operators often decide how to inspect and route returned assets before their condition is fully observed, while full inspection consumes scarce labor. Semantic Signal-Assisted Decision Support converts return notes into a condition factor and a signal-quality score that guide inspection depth and recovery allocation under shared labor capacity. We evaluate the framework in three synthetic benchmark scenarios spanning information technology decommissioning, aircraft maintenance,…

arXiv → PDF
cs.CLcs.AIcs.DB

text2ql: Multi-Target Natural Language Querying via a Language-Agnostic Intermediate Representation

Ritesh Kumar

Natural language interfaces to databases have traditionally suffered from three structural limitations: exclusive targeting of relational SQL, unconditional dependence on large language model (LLM) inference at query time, and absence of any runtime signal when generated queries are semantically incorrect. This paper presents text2ql, an open-source Python framework that addresses all three limitations through a language-agnostic Intermediate Representation (QueryIR) and a pluggable renderer arc…

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 →