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.CV

Hierarchical Denoising For Multi-Step Visual Reasoning

Zezhong Qian, Xiaowei Chi, Chak-Wing Mak, Tianze Zhou, Ruibin Yuan, Yuhan Rui, Hengzhe Sun, Zhuoqun Wu et al.

Video models are evolving into vision foundation models, yet they still lack human-like multi-step reasoning. Streaming autoregressive diffusion models are efficient but limited in reasoning, while bidirectional diffusion enables global revision with high inference costs due to dense frame-level denoising. Both paradigms struggle to achieve logical consistency and low-latency streaming for complex reasoning tasks. We propose HDR (Hierarchical Denoising for Visual Reasoning), a unified framework…

arXiv → PDF
cs.CL

Partition, Prompt, Aggregate: Statistical Self-Consistency in Language Models

Patrik Wolf, Thomas Kleine Buening, Andreas Krause, Celestine Mendler-Dünner

In-context learning is commonly interpreted as a form of conditional inference, in which the prompt specifies a context and the model's output is treated as an estimate of the corresponding conditional distribution. If this interpretation holds, then LLM estimates should satisfy basic probabilistic identities. In particular, the law of total probability asserts that prior-weighted conditional distributions aggregate into population-level marginals over any valid partition of the population. In t…

arXiv → PDF
cs.ROcs.AIcs.LG

RoboTTT: Context Scaling for Robot Policies

Yunfan Jiang, Yevgen Chebotar, Ruijie Zheng, Fengyuan Hu, Yunhao Ge, Jimmy Wu, Tianyuan Dai, Scott Reed et al.

Recent robot foundation models operate with single-step or short-history visuomotor context. We introduce Test-Time-Training Robot Policies (RoboTTT), a robot model and training recipe that scale visuomotor context to 8K timesteps, three orders of magnitude beyond state-of-the-art policies, without growing inference latency. At this context length, we unlock new robot capabilities: one-shot in-context imitation from human video demonstrations, on-the-fly policy improvement, robustness to perturb…

arXiv → PDF
cs.CVcs.LG

MeanFlowNFT: Bringing Forward-Process RL to Average-Velocity Generators

Yushi Huang, Xiangxin Zhou, Jun Zhang, Liefeng Bo, Tianyu Pang

MeanFlow generators achieve fast few-step sampling by predicting average velocities over time intervals, making them attractive for efficient generation. Reinforcement learning (RL) has become a powerful way to align diffusion and flow models with human preferences and task-specific objectives. In particular, DiffusionNFT offers an efficient forward-process RL framework that does not require reverse-process trajectories or likelihood estimation. However, applying such RL methods to MeanFlow rema…

arXiv → PDF
cs.CLcs.AI

SciDiagramEdit: Learning to Edit Scientific Diagrams from Paper Revisions

Yasheng Sun, Zezi Zeng, Yifan Yang, Chong Luo, Wenyi Wang, Ziwei Liu, Jürgen Schmidhuber

Editing the figures in a research paper is a routine and time-consuming part of everyday research practice: authors relabel components, rearrange panels, and restyle visuals as they revise their manuscripts. Automating this editing workflow under a natural-language instruction, however, is challenging, because a scientific figure is a dense infographic in which heterogeneous visual elements such as schematics, plots, photos, captions, and arrows are composed under a tight visual grammar to advan…

arXiv → PDF
cs.CVcs.GRcs.LG

Online Neural Space Time Memory for Dynamic Novel View Synthesis

Baback Elmieh, Lynn Tsai, Zeman Li, Srinivas Kaza, Tiancheng Sun, Gabor Csapo, Ali Behrouz, Yuan Deng et al.

Online novel view synthesis from multi-view streaming videos faces a fundamental trade-off: maintaining a persistent, long-horizon memory to reconstruct temporarily occluded regions while operating under strict real-time constraints. While Test-Time Training (TTT) offers a powerful memory mechanism, standard models mandate gradient-based memory updates at every frame to adapt to the changing motion in dynamic scenes. The computational cost of heavy memory updates precludes real-time application…

arXiv → PDF
cs.CV

Motion-Conditioned Multi-View Fusion for Myocardial Infarction Localization from Echocardiography

Guang Yang, Wentian Xu, Siyu Wang, Betty Raman, Lei Li, Vicente Grau

Myocardial infarction (MI) remains a leading cause of mortality worldwide. Echocardiography (Echo) is a widely available modality for MI assessment, where regional wall motion abnormality is a key indicator. Prior learning based methods for myocardial motion analysis often use handcrafted descriptors or densely supervised estimation, but the need for extensive annotation limits applicability. Foundation models have recently improved vision-based Echo analysis; however, most methods operate on si…

arXiv → PDF
cs.AIcs.CL

Pretraining Data Can Be Poisoned through Computational Propaganda

Victoria Graf, Hannaneh Hajishirzi, Noah A. Smith, David Kohlbrenner, Kyle Lo

Poisoning pretraining data can introduce harmful behaviors to LMs that are difficult to detect and mitigate. Prior work on poisoning pretraining data has largely exploited established data sources such as Wikipedia, which do not represent the large scale and heterogeneity typical of pretraining corpora, and has ignored the interaction between poisoned data and data curation pipelines. We demonstrate that poisoning attacks on pretraining data are feasible beyond this limited setting through an ex…

arXiv → PDF
cs.CVcs.AIcs.MMcs.SD

SceneBind: Binding What and Where Across Vision, Audio and Language

Mingfei Chen, Zijun Cui, Ruoke Zhang, Hyeonggon Ryu, Eli Shlizerman

We present SceneBind, an omni-modal representation of realistic scenes with joint semantic and 3D spatial understanding across vision, audio and language. Existing omni-modal encoders excel at instance-level semantics (i.e., what is present), but often lack explicit spatial structure (i.e., where it is). SceneBind addresses this gap by representing each scene as a semantic-spatial entity, combining a global semantic embedding with object-centric semantic-spatial slots. This representation explic…

arXiv → PDF
cs.CRcs.AI

Beyond Success Rate: Cost-Aware Evaluation of Offensive and Defensive Security Agents

Paul Kassianik, Blaine Nelson, Yaron Singer

Security-agent evaluations commonly measure peak offensive capability under generous inference budgets, emphasizing vulnerability discovery, exploit development, penetration testing, and CTF completion. Such measurements are useful but incomplete: in operational security, every reasoning step, tool call, telemetry query, and enrichment request consumes budget. We evaluate language-model security agents through this cost-success lens on offensive Cybench challenges and defensive Splunk BOTS v1 in…

arXiv → PDF
cs.LGcs.CE

Decoding Market Emotion from Blockchain Activity: A Data-Driven Sentiment Classifier

Arthur G. Bubolz, Abreu Quevedo, Giancarlo Lucca, Rafael A. Berri, Eduardo Borges, Bruno L. Dalmazo

The growing use of Bitcoin as a decentralized digital asset and investment tool has sparked strong interest in understanding its market behavior. This study presents a new approach to analyze Bitcoin market sentiment by combining on-chain and financial data with social media posts. Unlike models that aim to predict prices, this work focuses on explaining market sentiment using blockchain transactions, historical price data of Bitcoin, and daily Twitter sentiment classifications. The method merge…

arXiv → PDF
cs.AIcs.IR

SearchOS-V1: Towards Robust Open-Domain Information-Seeking Agent Collaboration

Yuyao Zhang, Junjie Gao, Zhengxian Wu, Jiaming Fan, Jin Zhang, Shihan Ma, Yao Yao, Weiran Qi et al.

Recent advances in Tool-Integrated Large Language Models have made web search a core capability of information-seeking agents. However, as interaction histories grow, agents increasingly struggle to track task progress. When search attempts fail to yield useful evidence, current single- and multi-agent systems can become trapped in repetitive loops, wasting search budgets and ultimately compromising the quality and completeness of the final output. We introduce SearchOS, a system-level multi-age…

arXiv → PDF
cs.CV

HoloGeo: Mitigating Landmark Bias in Geo-localization via Evidence-Driven Reasoning

Pengcheng Zhou, Xuanyu Liu, Yanchen Yin, Bobo Li, Shengqiong Wu, Mong-Li Lee, Wynne Hsu

Recent advances in Vision-Language Models (VLMs) have significantly improved image geo-localization, yet existing models remain susceptible to landmark bias, causing them to overlook geographical cues or form spurious correlations, ultimately resulting in inaccurate localization. To systematically investigate this issue, we first design two quantitative metrics, Bias Intensity (BI) and Bias Harmfulness (BH), to characterize the impact of landmarks exerted on model reasoning, and establish a comp…

arXiv → PDF
cs.AIcs.HC

teLLMe Why (Ain't Nothing but a Jam): Exploratory Causal Analysis of Urban Driving Data

Qiwei Li, Jorge Ortiz

Traffic agencies now have access to large volumes of video-derived data for studying safety and congestion. Most of these data are observational and collected without interventions, which makes causal questions such as "How would rain change traffic density?" difficult to answer. We present teLLMe, a system for exploratory causal analysis of urban driving datasets. The system starts from a structured event table built from dashcam annotations and combines causal structure learning with the PC al…

arXiv → PDF
cs.IRcs.CL

Bridge Evidence: Static Retrieval Utility Does Not Predict Causal Utility in Multi-Step Agentic Search

Debayan Mukhopadhyay, Utshab Kumar Ghosh, Shubham Chatterjee

Retrieval systems are trained and evaluated on a static idea of usefulness: hand a document and a question to a reader model, see whether the answer improves, and score the document accordingly. The idea holds up when a document is read on its own. It breaks when a language model works as a search agent, issuing several queries and reasoning across turns, because a document can matter for what it lets the agent do next rather than for what it says about the current question. We measure that gap…

arXiv → PDF
cs.AI

AutoSynthesis: An agentic system for automated meta-analysis

Moein Taherinezhad, Sebastian Maier, Gerardo Vitagliano, Francesco Pierri, Stefan Feuerriegel

Evidence synthesis is crucial for turning primary research into reliable knowledge for science, medicine, education, and policy. Yet, quantitative evidence synthesis remains largely manual and difficult to scale. Here, we introduce AutoSynthesis, an end-to-end multi-agent system for automated meta-analysis. Given a research question in natural language, AutoSynthesis formulates a search strategy, retrieves scientific literature, screens candidate studies, assesses full-text eligibility, extracts…

arXiv → PDF
cs.CV

ARMOR++: Agentic Orchestration of a Multi-Domain Primitive Set for Transferable Attacks on Deepfake Detectors

Christos Korgialas, Gabriel Lee Jun Rong, Dion Jia Xu Ho, Pai Chet Ng, Xiaoxiao Miao, Konstantinos N. Plataniotis

The reliability of deepfake detectors frequently degrades under black-box adversarial transfer, as these models often rely on fragile, architecture-dependent forensic cues. Existing transfer attacks often lack semantic awareness and struggle to maintain effectiveness under strict no-query constraints, particularly when perturbations are transferred from convolutional surrogates to transformer-based targets. To address these limitations, this paper introduces ARMOR++, a robust multi-agent framewo…

arXiv → PDF
cs.LG

Mutable Low-Rank Sketches for Retrain-Free Recommendation

Hector J. Garcia, Nick Clayton

A common bottleneck in two-stage recommendation is embedding staleness: when a user rates a new item, their embedding remains fixed until the next retrain cycle. We propose mutable sketches, which store each user's preferences in a KP-tree (a sparse segment tree with sum aggregation), fit a low-rank projection once, and recompute embeddings on-the-fly as ratings arrive. We prove that each new observation monotonically tightens the prediction error envelope (Theorem 1), a guarantee that FunkSVD a…

arXiv → PDF
cs.CLcs.CV

Beyond the Leaderboard: Design Lessons for Trustworthy Multimodal VQA

Sushant Gautam, Vajira Thambawita, Michael A. Riegler, Pål Halvorsen, Steven A. Hicks

Healthcare multimodal AI must combine visual and textual evidence while remaining reliable and interpretable. Using MediaEval Medico 2025 as a retrospective GI endoscopy case study, we analyze design choices across nine documented systems for question answering and explanation quality. Parameter-efficient adaptation of pretrained backbones provides strong challenge performance, but answer-level gains do not consistently translate into faithful and complete clinical reasoning. Methods enforcing s…

arXiv → PDF
cs.CL

TikStance: A Multimodal and Hierarchical Dataset for Multi-target Stance Analysis in TikTok Political Conversations

Yazhi Zhang, Fuqiang Niu, Bowen Zhang

Political discourse has increasingly moved to short-video platforms, yet computational analysis of such content remains constrained by the scarcity of datasets that jointly preserve audiovisual information and hierarchical conversations. Here we present TikStance, a multimodal and context-aware dataset comprising 161 videos and 13,876 comments from TikTok, designed for stance detection in political discussions. The dataset covers three major political figures in the 2024 U.S. election cycle--Don…

arXiv → PDF
cs.CL

Language Identification via Compositional Data Analysis: A Linear-Time Classifier Based on Log-Ratio Geometry

Paul-Andrei Pogăcean, Sanda-Maria Avram

Language identification is commonly addressed using either neural architectures or statistical n-gram models. Neural approaches typically require substantial computational resources, whereas classical frequency-based methods offer efficient linear-time performance, but rely on distance metrics that are not always appropriate for compositional data. This work models character and bigram frequency distributions as compositional vectors constrained to the simplex and mapped via the centered log-rat…

arXiv → PDF
cs.CLcs.AIcs.LG

In-Place Tokenizer Expansion for Pre-trained LLMs

Jimmy T. H. Smith, Tarek Dakhran, Alberto Cabrera, Simon S. Lee, Paul Pak, Aditya Tadimeti, Tim Seyde, Maxime Labonne et al.

A tokenizer fixed at the start of pre-training allocates vocabulary in proportion to the pre-training corpus, reflecting the deployment priorities at that time. When those priorities shift, languages added later are split into many more tokens per word, which can raise latency, compute, and energy consumption for users of those languages. Cloud models can afford a broad vocabulary because the embedding and LM-head matrices are a small fraction of their parameters. On a compact model those matric…

arXiv → PDF
cs.CV

CRISP: Constrained Refinement via Iterative Squeezing Process for Robust Medical Image Segmentation under Domain Shift

Yizhou Fang, Pujin Cheng, Yixiang Liu, Xiaoying Tang, Longxi Zhou

Distribution shift in medical imaging remains a central bottleneck for the clinical translation of medical AI. Failure to address it can lead to severe performance degradation in unseen environments and exacerbate health inequities. Existing methods for domain adaptation are inherently limited by exhausting predefined possibilities through simulated shifts or pseudo-supervision. Such strategies struggle in the open-ended and unpredictable real world, where distribution shifts are effectively inf…

arXiv → PDF
cs.LGmath.OCstat.APstat.ML

Data Driven Block Replacement Scheduling

Aniruddhan Ganesaraman, VIdyadhar Kulkarni

We develop data-driven algorithms for maintaining $N$ independent identical machines under a \textit{block replacement policy}, in which each machine is replaced upon failure and all machines are jointly replaced at regular intervals of length $k$. The goal is to learn the cost-minimizing interval $k^*$ from operational data when the lifetime distribution is unknown. At each decision epoch, the operator selects $k \in \{1, 2, \ldots, K\}$, observes the resulting failure history (a mixture of com…

arXiv → PDF
cs.CVcs.HC

Divergent Gaze Patterns in Artistic Viewing: Spatial and Temporal Signatures of Attention Across Autistic Individuals, Artists, and Neurotypical Observers

Mohammed Amine Kerkouri, Daphné Senggaran, Renaud Jusiak, Océane Lehmann, Marouane Tliba, Claire Wardak, Emmanuelle Houy-Durand, Shasha Morel-Kohlmeyer et al.

How different populations visually explore artworks bears on cognitive science and on accessibility design, yet most eye-tracking work in autism has used social scenes rather than art, and has analysed where the eyes land while ignoring when and in what order. We present a comparative free-viewing study across three groups, autistic adults (ASD), trained artists, and neurotypical observers, who each viewed 30 paintings for 15s. We introduce a directed, metric-grounded framework that compares gro…

arXiv → PDF
cs.CV

Structural-Semantic Reciprocal Learning for Unsupervised Visible-Infrared Person Re-Identification

Moyao Tian, Shijia Liu, Yan Yang, Xin Yuan, Minshi Chen, Wei Wang, Xiao Wang

Unsupervised visible-infrared person re-identification (USVI-ReID) is challenging due to the large modality gap and the lack of cross-modal identity annotations. Progressive association paradigms have been proposed to gradually bridge the gap, but they suffer from two critical bottlenecks: reliance on ambiguous global representations and unchecked propagation of pseudo-label noise in an open-loop manner. To address these issues, we propose Structural-Semantic Reciprocal Learning (SSRL), a framew…

arXiv → PDF
cs.AIcs.CR

When Words Are Safe But Actions Kill: Probing Physical Danger Beyond Text Safety in Hidden-State Risk Space

Weimeng Wang, Ziqiang Wang, Zihang Zhan, Chuanpu Fu, Qi Li, Ke Xu

Large language models (LLMs) increasingly serve as high-level planners for embodied agents, where linguistically benign instructions can become unsafe once grounded in the physical world. We study whether this physically grounded danger is the same safety problem as ordinary text-level content danger. Through hidden-state direction analysis and random-split null tests, we show that content danger (CD) and physical danger (PD) form separable signals in LLM representations across Qwen2.5-3B/7B/14B…

arXiv → PDF
cs.NEcs.LG

NeuronSoup: Evolving Asynchronous, Shared-Neuron Temporal Graphs without Backpropagation

Subodh Kalia

We present NeuronSoup, a neural computation architecture that replaces synchronous layer-by-layer processing with asynchronous, delay-mediated signal propagation through a pool of shared neurons. Each path in the network routes a continuous-valued signal from one input neuron to one output neuron through a variable number of intermediate hidden neurons. Hidden neurons are physically shared across paths: when two paths pass through the same neuron, the second arrival encounters the accumulated st…

arXiv → PDF
cs.CVcs.AI

Symbal: Detecting Systematic Misalignments in Model-Generated Captions

Maya Varma, Jean-Benoit Delbrouck, Sophie Ostmeier, Akshay Chaudhari, Curtis Langlotz

Multimodal large language models (MLLMs) often introduce errors when generating image captions, resulting in misaligned image-text pairs. Our work focuses on a class of captioning errors that we refer to as systematic misalignments, where a recurring error in MLLM-generated captions is closely associated with the presence of a specific visual feature in the paired image. Given a vision-language dataset with MLLM-generated captions, our aim in this work is to detect such errors, a task we refer t…

arXiv → PDF
cs.CV

MAGiSt3R: Multi-Agent Feed-forward 3D Reconstruction from Monocular RGB Videos

Ziren Gong, Xiaohan Li, Fabio Tosi, Ninghui Xu, Stefano Mattoccia, Jianfei Cai, Matteo Poggi

This paper presents MAGiSt3R, a multi-agent 3D reconstruction framework performing reconstruction and camera tracking for monocular RGB videos at almost 10 FPS. MAGiSt3R relies on a feed-forward model from the 3R family to process RGB videos and regress local point maps, and on a merging model, MAGMA, that combines local maps at both intra-agent and inter-agent levels to obtain the final global point map. Furthermore, MAGiSt3R performs pose graph optimization to mitigate cumulative camera drift…

arXiv → PDF