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

CAPTURE: Disentangling Preference Drift from Memory Poisoning in Personalized LLM Agents

S M Asif Hossain, Ruksat Khan Shayoni, Md Kishor Morol

Personalized language agents use persistent memory to adapt to users over time, but the same mechanism creates an attack surface. When new information conflicts with stored preferences, an agent must distinguish genuine preference drift from temporary context shifts, ambiguity, or adversarial memory poisoning. We formulate this problem as a continuous-time partially observable decision process over a latent user state and show why rules based only on recency and provenance are insufficient. CAPT…

arXiv → PDF
cs.AIcs.LGcs.MA

Codebook Agent: Amortized Topology Design for LLM Multi-Agent Systems

Jinxi Yu, Yubei Li, Eric Hanchen Jiang, Zhi Zhang, Dong Liu, Wenxiao Zhao, Levina Li, Kai-Wei Chang et al.

Adapting the communication topology of an LLM multi-agent system to each query improves both accuracy and efficiency, yet current designers treat this as conditional graph generation: a variational, autoregressive, or diffusion decoder searches the $N \times N$ adjacency space, and a graph-network proxy trained on utility and a structural cost such as edge count ranks the sampled candidates. We argue that this formulation is misaligned with the problem. Empirically, topologies that survive a rew…

arXiv → PDF
cs.SIcs.CL

From Detection to Characterization: A Large-Scale Study of Ragebait on Japanese X

Zhiyang Qi, Kazuhiro Ito, Jinghui Chen, Hibiki Nakamura, Zhangxuan Chen, Erina Murata, Masaki Chujyo, Fujio Toriumi et al.

Ragebait refers to online content intentionally designed to provoke anger or outrage and thereby increase attention and engagement. However, reliable large-scale detection and systematic analysis of ragebait remain limited, hindering efforts to understand its prevalence, impact, and mitigation. This study aims to develop an effective ragebait detection framework and to clarify the characteristics of ragebait at scale, providing a basis for understanding and mitigating emotionally provocative con…

arXiv → PDF
cs.CV

T2LSC-Bench: Benchmarking Localized Semantic Control in Text-to-Image Generation

Yan Wang, Xinyi Hou, Weiguo Lin, Junjun Si, Siwei Ma

Recent text-to-image models have become increasingly capable of rendering explicit text, but reliable localized text control requires more than generating the correct string. In applications such as product labeling, signage, and interface design, target text should be rendered within a designated text-bearing region without altering the predefined subject identity or surrounding scene semantics. We refer to violations of this requirement as target-text-associated semantic leakage, in which targ…

arXiv → PDF
cs.AIcs.CL

APEx: Distillation of Agent Procedural Experience for Adaptive Deep Research Question Answering

Jie Ding, Rui Sun, Xinyuan Zhang, Zeyu Zhang, Xin Liu

Deep research agents augment large language models with external tools to answer complex, long-horizon questions through multi-turn reasoning. Learning from prior experience is crucial for continual improvement, yet existing methods either retrieve verbose task-specific traces that burden decision-making, or distill procedural skills that remain decoupled from downstream policy adaptation. We propose APEx, a hierarchical experience utilization framework that organizes interaction history into in…

arXiv → PDF
cs.ROcs.AI

DiffuSearch: How Hybrid Trajectory Planning Benefits from Aligned Objectives in Diffusion and Action Space

Steffen Hagedorn, Aron Distelzweig, Alexandru P. Condurache

In trajectory planning for autonomous driving, hybrid planning architectures are often realized as a collection of disparate modules, each with its own objectives. This lack of a unifying principle can lead to inconsistencies between the initial and refined trajectory, resulting in suboptimal behavior. We address this by introducing DiffuSearch, a novel hybrid planner that uses a unified set of objectives across generation and refinement. Our model encourages all components to follow the same sh…

arXiv → PDF
cs.CV

Handwriting Trajectory Recovery via Autoregressive Ordered Stroke Instance Prediction

En-Guang Wang, Yan-Ming Zhang, Fei Yin, Cheng-Lin Liu

Handwriting trajectory recovery aims to infer the dynamic writing process hidden behind a static handwritten image. Since offline handwriting preserves only the final spatial ink pattern, temporal information such as stroke order, writing direction, and pen-tip motion is lost, making recovery inherently ambiguous. Existing learning-based methods often directly predict the complete character trajectory without explicitly exploiting the stroke-level organization of handwriting. We argue that recov…

arXiv → PDF
cs.MAcs.CLcs.ETcs.LG

RideSkill: A Hierarchical Algorithm for Generalized Ride Sharing with LLM-Driven Automatic Evolution

Zijian Zhao, Sen Li, Xialiang Tong, Mingxuan Yuan

Ride-sharing, which allows multiple passengers with different origin-destination (OD) pairs to share a single vehicle, is a challenging operational problem, as it requires orders with different OD pairs to be efficiently bundled and assigned to vehicles under uncertain and varying scenarios. Although multi-agent reinforcement learning (MARL) solutions have achieved promising performance, they suffer from limited generalization (adapting to different environmental scenarios), low transferability…

arXiv → PDF
cs.CVcs.AI

SAUF-Net: Structure--Appearance Representation Learning with Uncertainty Feedback for Semi-Supervised Medical Image Segmentation

Qin Lu, Zheyang Jing, Yujie Yang, Jianwang Li, Chen Yi, Shaofeng Jiang

Semi-supervised learning has shown great potential for reducing annotation costs in medical image segmentation. However, most existing methods mainly exploit unlabeled data through prediction-level consistency, while the reliability of internal feature representations is often overlooked. In medical images, target-related structural cues are easily entangled with unstable appearance variations, which may lead to unreliable pseudo labels and error accumulation during training. To address these is…

arXiv → PDF
cs.AIcs.LG

LLM-as-a-Judge Is Not an Oracle: Why Self-Improving Agents Need Deterministic Guardrails

Vansh Wahi

Self-improving agent pipelines have a problem at their center. An optimizer rewrites prompts to score higher, and the score comes from a judge that is itself an LLM. That judge has the last word on whether the system is getting better, and our position is that it has not earned it. The judge should be demoted from oracle to advisor: its verdict becomes one input among several, and every change is gated instead by a deterministic verification layer the judge cannot override. We reached this posit…

arXiv → PDF
cs.AI

Task-Level Natural Language Priors as Learning Signals for Low-Resource LLM Training

Jian Gao, Xiao Zhang, Xun Zhu, Miao Li, Ji Wu

Large language models (LLMs) often struggle when low-resource training data are ambiguous or incomplete. Task-level natural-language priors can provide useful guidance in such settings, but existing approaches usually treat these priors as input context rather than as learning signals during training. We propose Prior-Guided Tuning (PGT), a training perspective that incorporates natural-language priors as auxiliary learning signals for low-resource LLM training. Under this perspective, we introd…

arXiv → PDF
cs.AIcs.HCcs.MA

Propose to Learn, Learn to Propose: Evaluability-Aware Assistance under Bounded Rationality

Yifan Zhu, Sammie Katt, Samuel Kaski

AI assistants often collaborate by proposing candidate edits, plans, or designs that users evaluate before adoption. Existing assistance methods focus on proposal quality or user-goal inference, often assuming that the user can reliably evaluate any proposal, which can fail in practice because of bounded rationality. We study evaluability-aware proposal planning, where proposals serve both as task interventions and as probes for learning latent preferences and evaluation constraints, where the r…

arXiv → PDF
cs.LG

Similarity-Aware Personalized Federated Learning in Heterogeneous Environments

Arun Kumar A, Sunil Gupta, Dang Ngyuen, Bao Duong, Dat Phan Trong

Federated Learning (FL) allows decentralized clients to train models collaboratively while preserving data privacy. However, distribution mismatch across clients often leads to poor global generalization and degraded local client-level performance. In such scenarios, some of the clients with their local models trained solely on local data may perform better than the globally learnt model, thus nullifying the benefits of collaborative federated learning. To address this, we propose SAPE-FL (Simil…

arXiv → PDF
cs.LGcs.RO

Recursive Value Learning for Long-Horizon Offline Goal-Conditioned RL

Hyeonseong Jeon, Youngwoon Lee

Scaling offline goal-conditioned reinforcement learning (GCRL) to long-horizon tasks is difficult because (1) long-range value learning depends on shorter-range estimates that may still be inaccurate, and (2) max-based value backups can amplify overestimation through repeated propagation. We propose DCRL (Divide-and-Conquer RL), which recursively decomposes each trajectory segment into a balanced binary tree and trains the values from leaves to root. Each parent is therefore updated only after i…

arXiv → PDF
cs.AI

PGPO: Potential-Guided Policy Optimization for Multi-Turn Agentic Tasks

Yuyao Zheng, Haipeng Sun, Junwei Bao, Lemao Liu, Hongfei Jiang, Yang Song, Dejing Dou

Group-based reinforcement learning (RL) has become an effective paradigm for LLM post-training, but in multi-turn agentic tasks with sparse terminal rewards, it often provides coarse credit for intermediate actions. To obtain more fine-grained credit assignment, recent work such as GiGPO introduces step-level advantages for intermediate actions. However, these step-level signals still rely on the final outcome of each individual trajectory. As a result, actions within failed trajectories can rem…

arXiv → PDF
cs.CVcs.AI

InfraPatch: Cross-Task Targeted Grayscale Patch Attacks on Infrared-Adapted Vision-Language Models

Chengyin Hu, Dingyi Lu, Jiaju Han, Xiang Chen, Weiwen Shi, Jiahuan Long, Yiwei Wei, Jiujiang Guo et al.

Infrared vision-language models (IR-VLMs) have emerged as a promising paradigm for multimodal perception under low-visibility conditions, yet their robustness to targeted adversarial attacks remains poorly understood. Existing adversarial patch methods mainly study RGB-based models or a single downstream task and do not characterize whether localized perturbations can induce an intended semantic target in IR-VLMs. We propose InfraPatch, a white-box, per-instance framework for targeted digital gr…

arXiv → PDF
cs.AI

PhoenixNest-Video: Evidence-Grounded Multimodal Agent Framework for Automated Video Interview Assessment

Fan Yuxuan, Huang Miaojun, Zhang Haimei, Wu Jingshen, Liu Hao

Interview assessment requires per-criterion judgments grounded in behavioral evidence, yet surging applicant volumes have made human-only evaluation costly and inconsistent, while existing AI approaches yield opaque scores without traceable rationale. We introduce PhoenixNest-Video, an evidence-grounded multimodal agent framework for automated video interview assessment. It builds a semantic video graph as structured working memory, performs rubric-conditioned retrieval with cross-modal verifica…

arXiv → PDF
cs.CVcs.AI

Signal or Noise? Auditing Rotation-Induced Saliency Drift in Medical and Aerial Imaging

Khawaja Murad ul Hassan, Mehran Ebrahimi

Post-hoc saliency maps such as Grad-CAM are increasingly used to audit why a deployed vision model made a decision, yet the heatmap drifts when the input is rotated, even when the prediction is unchanged. In domains with no canonical orientation, such as histopathology and aerial imagery, this undermines using saliency as evidence. We ask whether that drift is faithful signal or noise introduced by the CAM operator, and answer it by measuring equivariance at every stage of the operator rather th…

arXiv → PDF
cs.ROcs.ARcs.CVcs.LG

Hardware-Accelerated Instance Segmentation for Resource-Constrained Space Robotics with Criticality Analysis

Siddhant Shete, Hilmi Dogu Kücüker, Udo Frese, Frank Kirchner

Autonomous lunar missions require real-time per- ception under three coupled constraints: extreme low-light conditions, limited onboard compute, and radiation-induced hardware faults that can silently corrupt inference. We present a deployment-oriented instance segmentation framework for resource-constrained lunar robotics that jointly addresses quan- tization calibration and system-level fault exposure under strict compute constraints. First, we introduce Activation Variance Informative Samplin…

arXiv → PDF
cs.AI

SkillGLoW: Procedural-Family Skill Consolidation for Self-Improving Agents on Long-Horizon Task Streams

Ao Yan, Xin Zhang, Jiawei Du, Joey Tianyi Zhou

LLM agents increasingly self-improve by writing and reusing textual skills, kept either as one global document or as a flat pool of per-task entries, though most of the evidence comes from domains with structurally similar tasks. On long-horizon workloads where each task demands a different solution, the two forms fail in opposite ways: the document collapses into generic discipline, while the pool inflates and its entries stay bound to the instance that wrote them. We argue the missing unit of…

arXiv → PDF
cs.AI

PEARL: Path-Entity Aligned Relational Learning with Contextual Subgraphs for Inductive Knowledge Graph Completion

Yunchi Yang, Longlong Li, Cunquan Qu

Inductive knowledge graph completion (IKGC) aims to predict missing links involving entities unseen during training, requiring models to learn transferable relational and structural patterns. Existing subgraph- and path-based approaches often encode relational paths independently of their surrounding query subgraphs, although the predictive relevance of a path may vary across structural contexts. We propose PEARL, a Path-Entity Aligned Relational Learning framework that models paths as context-c…

arXiv → PDF
cs.AI

ASCII Attack: Recontextualising Harmful Requests as Artistic Critique in Large Language Models

Da Cheng Gu, Yifei Dong, Xinghao Yang, Yongshun Gong, Wei Liu

Safety alignment trains large language models to refuse harmful requests stated plainly, but that training is applied mostly to surface form. Requests that only recontextualise the same operational content, changing how the model reads it, are therefore only weakly covered. The ASCII Attack is one such recontextualisation. It is single-turn and black-box: one message, with no access to model internals. It embeds a fully legible harmful request in ASCIl-art characters, presents it as artwork, and…

arXiv → PDF
cs.CV

FuDU: A Fuzzy Dual-dimensional Uncertainty Framework for Streaming Active Learning in Industrial Defect Detection

Zhaoyang Wang, Haiyong Chen, Binyi Su, Xinwei Lyu

Ensuring the reliability of deep learning models in real-time industrial defect detection is critical for high-stakes quality inspection. To mine uncertain samples within continuous industrial media streams, thereby enhancing the reliability of the detection system, this paper proposes a streaming active learning method based on the Fuzzy Dual-dimensional Uncertainty (FuDU) framework. Specifically, we first design a Prototype-based Global Uncertainty Quantification (PGUQ) module on the backbone…

arXiv → PDF
cs.CV

Asymmetric Paired-Annotation Learning for Multi-Structure ULF Pediatric Brain MRI Segmentation

Ha-Hieu Pham, Dang P. M. Cao, Minh Hoang Pham, Khanh Nguyen Vo Ngoc, Thanh-Huy Nguyen, Ulas Bagci, Huy-Hieu Pham

Portable ultra-low-field (ULF) MRI can expand access to pediatric neuroimaging, but segmentation at 0.064 T remains challenging because anatomical boundaries are weakly delineated, small structures may be only partially visible, and high-field references can be locally misregistered. The LISA 2026 Challenge provides two non-equivalent annotations reflecting different sources of anatomical evidence: a highfield-derived (HF) mask defining the scored target and a low-field-edited (LF) mask aligned…

arXiv → PDF
physics.chem-phcs.LG

Prototype-guided transfer of sparse literature knowledge for electrolyte additive discovery

Weixiang Hong, Hongting Du, Jiayue Tang, Ruifeng Tan, Yangjian Quan, Jia Li, Jiaqiang Huang

Electrolyte additive discovery remains challenging because experimentally validated molecules are sparse, whereas accessible chemical spaces are vast and largely unlabeled. This challenge is amplified in lithium-ion batteries, where additive performance arises from coupled interfacial reactions rather than a single molecular property. Here, we develop a prototype-guided molecular intelligence, ProtoMI, a literature-driven framework that learns transferable structural priors from reported electro…

arXiv → PDF
cs.CVcs.CL

LeakageBench: Document-Level Leakage Risk for Redacting Personally Identifiable Information in Document Images

Vishnu Prasad Vijaya Kumar, Santhosh Venkatesh, Ivan P. Yamshchikov

Real-world personally identifiable information (PII) redaction often operates on document images---scans, screenshots, and PDF renderings---where OCR errors, layout structure, and visual noise determine whether sensitive information is actually removed. Existing PII benchmarks are mostly text-centric and do not measure document-level redaction risk: a page remains unsafe if even one identifier is missed. We introduce LeakageBench, a challenge set of 500 document images with 11,954 GDPR-aligned P…

arXiv → PDF
cs.CV

TAME: Temporal-Aware Mixture-of-Experts for Text-Video Retrieval

Uicheol Jung, Juyoung Hong, Hojung Kwon, Yukyung Choi

Text-Video Retrieval (TVR) retrieves videos that match a natural-language query, but extending image-text models such as CLIP to videos is fundamentally limited by the lack of temporal modeling. Videos exhibit frame-wise heterogeneity in appearance and motion, and compressing all frames into a single representation often obscures temporal structure and semantic transitions. To address this, we propose Temporal-Aware Mixture-of-Experts for Text-Video Retrieval (TAME), a CLIP-based framework that…

arXiv → PDF
cs.LGcs.AI

SMart: A Multi-source Multi-phase Time Series Representation Transfer Framework

Fang He, Wang-chien Lee

Time series representation learning (TSRL) has attracted growing research interests in recent years. Two recent explorations in TSRL are: i) exploiting a transformer-based framework to learn time series; ii) instead of using only the targeted dataset, borrowing time series from other datasets to to facilitate representation transfer. While these two explorations are shown effective, the self-supervised time series recovery task in (i) and the single-source dataset used in (ii) are technically si…

arXiv → PDF
stat.MLcs.AIcs.LG

Schrödinger Bridges on Lie Group Manifolds for Probabilistic Intrinsic Generation

Shizhe Zhang, Mingyang Zhao, Lei Ma

Generative modeling directly on geometric manifolds can avoid errors introduced by flattening non-Euclidean data, repeated ambient projection, and coordinate inconsistency in Euclidean representations. Schrodinger bridges provide a probabilistic generative framework for entropy-regularized transport between prescribed endpoint distributions. We study Schrodinger bridges for kinetic dynamics on Lie group manifolds with state X_t = (g_t, xi_t) in G x g, allowing endpoint observations to constrain…

arXiv → PDF
cs.LGcs.CE

Learning the Constitutive Behavior of Materials via Neural Operators and Causal Attention: Case Studies in Plasticity and Damage

Rishabh Arora, Lisa Scheunemann, Tim Brepols, Shahed Rezaei

Classical constitutive modeling of path-dependent inelastic materials relies on internal state variables whose evolution equations must be postulated based on domain knowledge and calibrated against experimental data. However, in many practical settings, the relevant internal variables are typically not measurable in experiments, and the constitutive response must be inferred entirely from measured strain-stress data without any prior knowledge of the material's internal state. We propose a data…

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 →