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.AIcs.SE

MCPEvol-Bench: Benchmarking LLM Agent Performance Across Dynamic Evolutions of MCP Servers

Huanxi Liu, Kun Hu, Jiaqi Liao, Qiang Wang, Pengfei Qian, YuanZhao Zhai, Dawei Feng, Bo Ding et al.

As Model Context Protocol (MCP) servers emerge as the core infrastructure for connecting LLMs with external tools, existing benchmarks leverage real-world MCP servers to evaluate LLM agents' tool-using capabilities. However, these benchmarks overlook the continuous evolution of tool interfaces and functionalities within MCP servers, resulting in flawed assessments that fail to capture the agent's adaptability in changing tool landscapes. To bridge this gap, we introduce \textbf{MCPEvol-Bench}, a…

arXiv → PDF
cs.AI

Analytic Abduction: Causal Decomposition and Governed Commitment for Human--AI Coordination

Remo Pareschi

Abductive reasoning operates in two directions. The synthetic mode builds explanations from available hypotheses; the analytic mode, conversely, identifies the latent factors whose interaction accounts for a complex observed state. This paper develops the analytic mode as a non-greedy, risk-sensitive discipline of commitment, in which candidate factors coexist and interact, resolving into committed conclusions only when explicit governance conditions are met. The formal core is the $κ$-$τ$ appar…

arXiv → PDF
cs.LG

TIDE: Trustworthy and Interpretable Battery Degradation Estimation with Contextual Learning and Symbolic Distillation

Wen Yang Tan, Jiawei Li, Fang Liu, Wei Zhang, Sumei Sun, Peng Cheng Wang, Elisa Y. M. Ang

Battery health estimation is fundamental for battery management in battery-powered systems, where inaccurate health states may affect control, maintenance, and service life. It becomes even more critical in intelligent connected systems, where estimation errors can propagate across interconnected devices and downstream decisions. In this paper, we propose TIDE, a trustworthy and interpretable battery degradation estimator for reliable battery health estimation. TIDE jointly considers accuracy, t…

arXiv → PDF
cs.ROcs.CV

Image-to-Point Cloud Registration Made Easy with Rectified Flow-based LiDAR Upsampling

Reon Tabata, Kenji Koide, Shuji Oishi, Masashi Yokozuka, Taku Okawara, Aoki Takanose, Jun Miura

Image-to-Point Cloud Registration (I2P) is essential for integrating camera and LiDAR in perception and autonomous systems, yet the modality gap between images and point clouds makes it difficult to achieve both high accuracy and strong generalization. In this paper, we propose a simple yet effective I2P method that treats LiDAR as an imaging sensor: from a single sparse LiDAR scan, we generate a dense LiDAR intensity image using Conditional Rectified Flow, match it with a camera image using a p…

arXiv → PDF
cs.AIcs.CVcs.RO

Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models

Yufeng Ji, Wenhao Tang, Haoyi Niu, Koushil Sreenath, Yi Wu, Zhongyu Li

Action supervision in vision-language-action (VLA) models is often treated as a downstream objective for learning action prediction. In this paper, we study it instead as a force that shapes inherited multimodal representations. We show that this shaping has a dual effect: it is necessary for forming action-compatible representations, but when action supervision is applied too directly to the inherited multimodal pathway, it can also destabilize representations that support language-side process…

arXiv → PDF
cs.CVcs.AI

Knowing You at First Glance: Inferring Apparent Personality from Faces

Shuhuan Chen, Xiangyu Zhu, Weisong Zhao, Haichao Shi, Xiao-Yu Zhang, Zhen Lei

Inferring apparent personality from facial images is important in social scenarios for embodied agents in human-robot interaction. Unlike inferring intrinsic personality traits via conversation, this task models first-impression personality perception based solely on facial appearance before interaction begins. Existing studies mainly focus on the Big Five personality model and often rely on language or multimodal inputs. As a result, it remains unclear whether facial cues alone can support mean…

arXiv → PDF
cs.CLcs.CR

Routing Ceilings Are Domain-Independent: Structural Prior Injection in Code Security Vulnerability Detection

Manuel Israel Cázares

Large language models (LLMs) exhibit a well-documented gap between latent capability and consistent activation: the router hypothesis posits that models possess the knowledge to solve a task but lack reliable internal routing to activate it. Prior work in formal mathematical reasoning (SAIR, Cázares 2026) reports that structural priors (cheatsheets) raise in-distribution performance dramatically, yet collapse below the zero-shot baseline out-of-distribution (OOD) -- and that iterative recalibrat…

arXiv → PDF
cs.ARcs.LGcs.OS

ExaGEMM: Exploration Framework for CPU-Driven ML Inference via Associative In-Register Computing for Low-Bit GEMM

Hyunwoo Oh, Suyeon Jang, Hanning Chen, Sanggeon Yun, Ryozo Masukawa, Mohsen Imani

Low-bit GEMM is increasingly central to efficient ML inference, yet very-low-bit execution remains a poor fit for conventional CPUs. Practical deployment spans fragmented regimes-from 1/2/4-bit weights to varying activation precision-whose feasibility, reuse opportunity, and support cost differ under fixed SIMD and register-file budgets, making lightweight CPU support selection a first-class design problem. We present ExaGEMM, a workload-aware codesign and exploration framework for CPU-native lo…

arXiv → PDF
cs.LGcs.ARcs.OS

PolyQ: Codesigning End-to-End Quantization Framework for Scalable Edge CPU LLM Inference

Hyunwoo Oh, Suyeon Jang, Hanning Chen, KyungIn Nam, Sanggeon Yun, Ryozo Masukawa, Mohsen Imani

CPUs are the most universal target for on-device LLM inference, but existing low-bit quantization methods offer either coarse operating points or fine-grained mixed precision that is difficult to execute efficiently on CPUs. We present PolyQ, a CPU-oriented compiler/quantization co-design for activation-aware channel-wise bit allocation under a user-specified average-bit budget. PolyQ assigns per-channel bit-widths from $\{2,3,4,8,16\}$, then uses a compile-time model compiler to permute and clu…

arXiv → PDF
cs.AIcs.CV

SportD: Can VLMs Physically Strategize?

Jasin Cekinmez, Addison J. Wu, Haotian Xia, Akshaya Bharadhwaj, Anay Putty, Anirudh Ravishankar, Jaewoong Lee, Jinglin Xiao et al.

Vision--language models have become increasingly capable of interpreting visual scenes, but it remains unclear whether they can use information to make strategically effective decisions. We investigate this question in soccer, where models observe the seconds preceding an on-ball decision and must choose whether to shoot or pass to a specific teammate. Unlike conventional visual-understanding tasks, soccer enables decisions to be evaluated quantitatively by estimating the value of every availabl…

arXiv → PDF
cs.LGcs.AIcs.CL

Beyond Entropy: Correctness-Aware Advantage Shaping via Contrastive Policy Optimization

Weiwen Xu, Jia Liu, Hou Pong Chan, Long Li, Deng Cai, Min Chen, Hao Zhang

Reinforcement learning with verifiable rewards (RLVR) commonly uses entropy for advantage shaping. However, entropy cannot distinguish useful uncertainty from detrimental confusion, limiting its effectiveness as a correctness signal. We propose Contrastive Policy Optimization (CPO), which uses token-level contrastive disagreement between reference-guided and vanilla generation distributions for correctness-aware advantage shaping. Both theoretical and empirical results show that this disagreemen…

arXiv → PDF
cs.LGcs.AI

Angular Gaussian Supervised Contrastive Learning for Long-Tailed Electrocardiogram Arrhythmia Diagnosis

Jin Dai, Qiuzhen Zhang, Chenyun Dai, Danmei Lan, Can Han

Long-tailed label distributions reduce the reliability of deep learning for electrocardiogram (ECG) arrhythmia diagnosis, particularly for clinically important but rare abnormalities. Existing rebalancing and logit adjustment methods mainly address class frequency while overlooking direction-dependent morphological variability across ECG classes. This study proposes Angular Gaussian Supervised Contrastive Learning (AG-SCL) for long-tailed multi-label ECG diagnosis. AG-SCL integrates three compon…

arXiv → PDF
cs.CRcs.AIcs.MA

Bad Memory: Evaluating Prompt Injection Risks from Memory in Agentic Systems

Soham Gadgil, David Alexander, Sai Sunku, Franziska Roesner

A growing class of agentic systems maintain persistent state across sessions through memory files, behavioral preferences, and knowledge bases. While this makes agents more useful and self-improving, it also creates a new attack surface for prompt injections in which malicious instructions can be embedded within persistent files and influence future behavior. In this work, we study prompt injection attacks in memory-based agentic systems using a sandboxed synthetic workspace. We evaluate two age…

arXiv → PDF
cs.LGcs.AI

Auditing Fairness-Privacy Trade-offs: Subpopulation-Level Effects of Fairness-Enhancing Algorithms

Umid Suleymanov, Ilhama Novruzova, Khalid Mammadov, Natavan Hasanova, Murat Kantarcioglu

Machine learning (ML) models deployed in sensitive domains such as healthcare, law enforcement, and finance must satisfy not only utility requirements but also fairness and privacy guarantees. While prior work has largely examined how privacy-preserving techniques affect fairness, the inverse question-how fairness-enhancing algorithms influence privacy leakage-remains underexplored. We present the first comprehensive study of how fairness interventions affect membership inference privacy risks a…

arXiv → PDF
cs.CLcs.CY

Investigating first-language bias in LLM-based automated essay scoring: A cross-prompt evaluation of an open-weight AI-model on TOEFL essays

John Maurice Gayed

This study examines the cross-prompt generalization and first-language (L1) scoring effects of a LoRA-adapted open-weight large language model (Gemma-3-27B-it) applied to automated essay scoring. Using the identical model and inference configuration reported in "AiAWE: An Open-Source LLM Automated Writing Evaluation System Using LoRA-Adapted Instruction-Tuned Models" (Gayed, 2026), which was fine-tuned on 480 argumentative essays from two prompts, we evaluate scoring accuracy on the full TOEFL11…

arXiv → PDF
cs.LGcs.IRstat.ME

Accelerating A/B-Tests with Counterfactual Estimation: Reducing Variance through Policy Overlap

Olivier Jeunen

Online controlled experiments are the gold standard for hypothesis testing in online platforms. Notwithstanding their ubiquity, they are notoriously expensive to run, and issues of variance hamper statistical power in assessing treatment effects. While standard variance reduction techniques leverage model-based control variates to reduce outcome noise, they remain agnostic to potential structural relationships between competing policies. In this work, we identify a critical inefficiency in the s…

arXiv → PDF
cs.CV

Hough-SIFT: Robust Image Registration for Linear Structures via Hough Space

Masaki Satoh

Image registration is essential in applications such as electronic image stabilization. Scale-Invariant Feature Transform (SIFT), a widely used local keypoint detector and descriptor, typically provides accurate registration; however, it often fails in scenes with strong linear structures (e.g., shutters), where local features become ambiguous. We propose Hough-SIFT, a robust registration method that performs SIFT descriptor matching in Hough space. In this domain, linear structures form distinc…

arXiv → PDF
cs.CV

MagicPrompt: Ultra-Lightweight Prompt Tuning for Video Generation

Yinhan Zhang, Dinwei Tan, Xianghao Kong, Yue Ma, Yeying Jin, Anyi Rao

Large-scale video diffusion models (VDMs) deliver strong generation performance, but full fine-tuning for downstream tasks incurs prohibitive computational costs. Existing parameter-efficient fine-tuning (PEFT) methods have two critical flaws on billion-scale models: they still require substantial trainable parameters, and reward-based training suffers from noise-induced optimization instability in condition-guided tasks. We propose MagicPrompt, a lightweight framework that achieves extreme para…

arXiv → PDF
cs.HCcs.AIcs.CL

Memory-Driven Self-Disclosure and Relational Turning Points: A Longitudinal Multimodal Study of Human-AI Interaction

Ryuichi Sumida, Mao Saeki, Masaki Eguchi, Sadahiro Yoshikawa, Koji Inoue, Tatsuya Kawahara, Yoichi Matsuyama

As conversational AI systems are designed for repeated use, a central question is how a series of interactions becomes a relationship. We present a longitudinal multimodal study of a memory-augmented conversational agent (24 participants x 10 sessions), in which participants rated five relational constructs -- familiarity, self-disclosure, perceived memory, conversational quality, and enjoyment -- after each session. Two complementary dynamics emerge. First, conversational quality strongly shape…

arXiv → PDF
cs.CL

How Well Does AI-Generated Feedback Work? Intrinsic and Extrinsic Evaluation across more than 20,000 EFL Essay Drafts

Steven Coyne, Diana Galvan-Sosa, Ryan Spring, Machi Shimmei, Michael Zock, Keisuke Sakaguchi, Kentaro Inui

This study examines feedback in English as a Foreign Language (EFL) writing contexts, focusing on written corrective feedback (WCF). Large language models (LLMs) can provide WCF at scale, but aligning them with pedagogical best practices remains an ongoing challenge. WCF meeting criteria like factuality or relevance may still be unsuitable for learning contexts, highlighting the need for extrinsic evaluation based on the learner's perspective. We deployed WCF systems in a university-level EFL cl…

arXiv → PDF
cs.CRcs.CL

Qubes OS Security in the Public Record

Alfonso De Gregorio

Qubes OS is a revealing case for security measurement because its architecture makes component boundaries security-relevant. We present a protocol-driven longitudinal analysis of 109 public Qubes Security Bulletins (QSBs, 2011--2025), the official Qubes-maintained Xen Security Advisory (XSA) tracker, and a secondary vulnerability-event sensitivity series. The study measures the public advisory record rather than latent vulnerability incidence or realized compromise. The methodology combines audi…

arXiv → PDF
econ.GNcs.AI

Governing Artificial Intelligence: Public Preferences and Regulatory Options

Magnus Lundgren, Jonas Tallberg

Artificial intelligence (AI) is rapidly transforming economies, societies, and polities, raising fundamental questions about how it should be regulated. Policymakers face choices over whether to prioritize innovation or safety, rely on public oversight or private self-regulation, and govern nationally or internationally. Yet little is known about how citizens evaluate these competing priorities. Here we report a conjoint survey experiment conducted in seven countries with diverse political and e…

arXiv → PDF
cs.AI

MathCoPilot: An Interactive System for Human-AI Symbiotic Paradigm of Mathematical Research

Junjie Zhang, Jiayu Liu, Wenbin Liu, Zhenya Huang, Doudou Wang, Yan Jiang, Leiye Xu, Tao Xiong et al.

Existing LLM-based theorem provers have achieved impressive results on formal mathematics benchmarks, yet they remain confined to acting as autonomous agents that prove a stated proposition. In this paper, we propose MathCoPilot, a human-in-the-loop system that embodies a new human--AI symbiotic paradigm for mathematical research, in which the mathematician steers the high-level mathematical direction while AI agents carry out the detailed formalization and proof work under continuous human guid…

arXiv → PDF
cs.AIcs.CV

Multi-LLM Collaborative MRI Report Generation for Visual Instruction Tuning in Brain Oncology

Sinyoung Ra, Jonghun Kim, Hyunjin Park

Recent advances in large language models (LLMs) and their extension to vision-language models (VLMs) have made it easier to combine text and images for tasks such as report generation. Existing VLMs in medicine typically focus on 2D images (chest X-rays), and their extension to 3D imaging has been difficult because of the lack of paired 3D imaging-text data. Thus, we introduce a new method for creating a 3D image-text dataset for brain oncology using 3D MRI scans of glioma and meningioma cases.…

arXiv → PDF
cs.CVcs.LG

Advanced Image Generation: Negative Prompt Optimization and Latent Classifier Guidance

Vaddi Charan Sai Nandan Reddy, Harini B, Chandana M S

We present a novel system that integrates negative prompt optimization via a fine-tuned sequence-to-sequence LLM and latent-space classifier guidance to improve the quality of images generated by Stable Diffusion. Our approach automatically generates optimized negative prompts, and employs a CNN-RNN hybrid classifier to evaluate and guide diffusion steps, rolling back low-quality latent updates. Experimental results demonstrate that our dual-guidance framework reduces artifacts and improves sema…

arXiv → PDF
cs.HCcs.CV

Skeleton: Visual Authoring of Non-visual Data Experiences

Frank Elavsky, Chieri Nnadozie, Lucas Nadolskis, Patrick Carrington, Dominik Moritz

When sighted practitioners author accessible data visualizations, they build navigation structures (the nodes, edges, and input bindings that govern how assistive technologies traverse an interface) entirely in code, with no visual representation. Without a representation to react to, practitioners cannot develop judgment about what makes navigation good or bad, and the quality ceiling of non-visual experiences is set by the absence of a feedback loop. We address this problem through longitudina…

arXiv → PDF
cs.LGstat.ML

Sharp Stability Threshold and Certification for Designing Stable Residual Architectures

Hyemin Gu, Michael Tyrrell, Tuhin Sahai, Markos A. Katsoulakis

We propose \emph{the sublinear-growth principle} for deep residual architectures -- a sharp stability threshold on the input-magnitude exponent of every residual block's velocity field: $$\|v(x, t)\| \leq c\,\|x\|^q + b, \qquad q \in [0, 1].$$ The threshold $q = 1$ is established via two independent arguments. Classical ODE theory gives a global forward flow on $[0, T]$ at $q \le 1$ and exhibits divergent velocity fields at any $q > 1$. The optimal-control analysis, via the Hamilton-Jacobi-Bellm…

arXiv → PDF
cs.CYcs.CL

Penny: Transition Network Analysis of Learner-Chatbot Interactions in Scaffolded EFL Writing

Steve Woollaston, Brendan Flanagan, Yuko Toyokawa, Hiroaki Ogata

Generative AI chatbots promise to transform English as a Foreign Language (EFL) writing by providing immediate, personalised feedback. However, their pedagogical value depends on how learners engage with them - a process often treated as a "black box." This study uses Transition Network Analysis to model the temporal dynamics of Japanese EFL learners using "Penny," an LLM-powered writing chatbot. Analysis of over 4,500 writing sessions and 21,000 chatbot interactions reveals two dominant behavio…

arXiv → PDF
cs.AIcs.SI

Collaborative Spatial Learning with Multi-LLM Agents in Networked Social Experiments

Hao He, Chris J. Kuhlman, Xinwei Deng

Collective problem solving often requires that group members consider the tradeoff between exploitation of known solutions and exploration for new ones, where information of known solutions can be disseminated among individual members through communication networks. The Mason--Watts experiment (PNAS 2012) showed that human groups in shorter-path networks outperform those in longer-path networks on a two-dimensional search task. In this work, we focus on the investigation of such network-efficien…

arXiv → PDF
cs.AIcs.SE

Alipay-PIBench: A Realistic Payment Integration Benchmark for Coding Agents

Shiyu Ying, Xuejie Cao, Yingfan Ma, Yuanhao Dong, Wenyu Chen, Bowen Song, Lin Zhu

Payment integration is a demanding repository-level software task: agents must select a suitable product, implement coordinated client-server flows, verify payment outcomes, and preserve consistency between transaction and business states. We introduce Alipay-PIBench, a benchmark for evaluating coding agents on realistic Alipay payment integration. It contains nine product-specific projects and 18 task instances, each organized into Basic functional-completion and Advanced risk-aware hardening s…

arXiv → PDF