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

Evaluating covariate balance for long time horizon Markov decision processes

Joshua Spear, Rebecca Pope, Neil J Sebire

This article explores the application of covariate balance diagnostics for detecting the presence of hidden confounding/model miss-specification in studies applying offline reinforcement learning (RL) to deriving optimal treatment recommendations. The results demonstrate that, either there is a high risk of bias within existing offline RL studies for treatment recommendations or, existing covariate balance metrics are not sufficient to assess such studies. Regardless, existing offline RL studies…

arXiv → PDF
cs.AI

BrainPilot: Automating Brain Discovery with Agentic Research

Haoxuan Li, Tianci Gao, Jianhe Li, Yang Fan, Runze Shi, Weiran Wang, Tianxiang Zhao, Zezhao Wu et al.

Understanding the brain increasingly depends on integrating evidence across scales, modalities, and disciplines. Addressing a single research question therefore requires a coordinated sequence of operations, from surveying prior work to executing analyses and interpreting results in light of domain knowledge. AI agents promise to accelerate this process, but current agents lack domain expertise in brain science, may fabricate claims, drift during multi-step reasoning, and offer few defined point…

arXiv → PDF
cs.LG

An Introduction to Sparse Identification of Nonlinear Dynamics for Engineering Applications

Yao Cheng Li, Ana Larrañaga, Steven L. Brunton, Urban Fasel

Many engineering problems involve phenomena whose governing equations are poorly characterized or only partially known. Surrogate modeling techniques such as neural networks can capture the behavior of these systems, but they typically demand large training datasets that are difficult to obtain in engineering contexts and yield models with limited physical interpretability. The Sparse Identification of Nonlinear Dynamics (SINDy) method addresses both limitations by performing sparse regression o…

arXiv → PDF
eess.IVcs.CVeess.SP

ESAR: Event-Based Synthetic Aperture Reconstruction

Harbir Antil, Daniel Blauvelt, David Sayre

Event cameras report asynchronous polarity events when changes in log--radiance exceed a fixed contrast threshold, producing signed temporal contrast measurements rather than conventional image frames. We formulate monocular event-based imaging as a synthetic-aperture inverse problem for a static ground-domain log--radiance field $θ\in \mathbb{R}^{N_g}$. Instead of reconstructing a latent pixel-time volume $v \in \mathbb{R}^{N_pN_t}$, we impose the geometric relation $v=Pθ$, where $P$ maps the f…

arXiv → PDF
cs.LG

Kernel weighted importance sampling for off-policy evaluation in contextual bandits

Joshua Spear, Matthieu Komorowski, Rebecca Pope, Neil J Sebire, Erica E. M. Moodie

This article presents a novel estimator for performing off-policy evaluation using only offline data for contextual bandits. The proposed estimator, Kernel-WIS is demonstrated to be asymptotically consistent and to empirically outperform strong baselines (including vanilla weighted importance sampling), particularly under complex conditions including behaviour policy miss-specification. The benefit of Kernel-WIS is derived from combining the bounded property of vanilla weighted importance sampli…

arXiv → PDF
cs.ROcs.CVcs.LG

DriftWorld: Fast World Modeling through Drifting

Susie Lu, Haonan Chen, Weirui Ye, Yilun Du

Predictive world models enable robots to plan by imagining the outcomes of their actions, but their value for control hinges on generating many rollouts quickly. This creates a bottleneck for diffusion-based world models: multistep sampling makes each rollout expensive, limiting large-scale action search at inference time. We introduce DriftWorld, an action-conditioned world model based on drifting generative models. Rather than denoising iteratively at inference, DriftWorld learns an action-con…

arXiv → PDF
cs.CVcs.RO

SUFLECA: Scaling Up Feature Learning for CAD-to-image Alignment

Saad Ejaz, Miguel Fernandez-Cortizas, Javier Civera, Holger Voos, Jose Luis Sanchez-Lopez

CAD-to-image alignment aims to estimate an object's 9D pose (rotation, translation, and anisotropic scale) from a single RGB image, enabling applications in robotics and augmented reality. Recent zero-shot methods use visual foundation models to match image regions to CAD models, yet typically their correspondences are appearance-driven and degrade under occlusion or sim-to-real domain shift. To address these limitations, we introduce SUFLECA (Scaling Up Feature LEarning for CAD Alignment), a we…

arXiv → PDF
cs.CV

Beyond Single Expert: Harmonizing Diverse Visual Priors in MLLMs for Spatial Understanding

Xiao Lin, Xiaohu Huang, Kai Han

Multimodal Large Language Models (MLLMs) have demonstrated substantial promise in spatial understanding. Existing works typically incorporate prior knowledge extracted from a pre-trained foundation model to further enhance the spatial awareness of MLLMs. In this paper, we first reveal that when integrating diverse foundation models into MLLMs, different models provide complementary spatial priors that benefit different tasks. Motivated by this, we propose $\textbf{ViPS}$, a novel multi-model pri…

arXiv → PDF
cs.NIcs.AI

ANet Patu-1: The Value of Connection in the Agent Network

Mu Yuan, Jinke Song, Zhaomeng Zhou, Lan Zhang

The Internet taught us that the value of a network depends on \emph{how} its nodes connect: broadcast stars scale as $V\!\propto\!N$ (Sarnoff), fully-connected meshes as $N^2$ (Metcalfe), and group-forming networks as $2^{N}$ (Reed). We ask the analogous question for networks of AI agents. We model the net value of connection as a function of coordination-group size, derive from it the properties an optimal collaboration protocol must have, and introduce ANet Patu-1 -- a self-organizing consensu…

arXiv → PDF
cs.CV

RoGS: Adaptive Meshgrid Gaussian for Large-Scale Road Surface Mapping

Tianchen Deng, Zhiheng Feng, Wenhua Wu, Ziming Li, Siting Zhu, Hesheng Wang

Road surface mapping plays a crucial role in autonomous driving, supporting high-definition map generation, lane-level perception, and automatic road annotation. Recent mesh-based road surface reconstruction methods have shown promising results, but they still suffer from limited reconstruction quality and high optimization cost, especially in large-scale driving scenarios. To address these limitations, we propose ROADGS-T, a robust and efficient large-scale road surface mapping framework based…

arXiv → PDF
cs.CVcs.AIcs.LG

Parameter-efficient Prompt Tuning of Vision Foundation Model With Adaptive Focal Loss for Interpretable MCI Screening

Javad Khoramdel, Farhad Hoseyni, Amirhossein Nikoofard

Mild Cognitive Impairment is a critical early stage of cognitive decline that frequently precedes Alzheimer's disease, yet its automated detection from neuropsychological drawing tests remains fundamentally constrained by data scarcity, class imbalance, and diagnostic ambiguity near clinical boundaries. Existing methodologies attempt to bypass these constraints using computationally expensive, fully fine-tuned hybrid architectures that relegate spatial explainability to a post-hoc approximation…

arXiv → PDF
cs.CV

Weakly-Supervised RGB-D Salient Object Detection via SAM-driven Pseudo Annotation and State Space Interaction-based Diffusion

Wenqi Si, Gongyang Li, Shixiang Shi, Weisi Lin

Weakly-supervised RGB-D Salient Object Detection (SOD) is explored to reduce the heavy burden of pixel-level annotations. But scribble annotations lack the structure and details of objects, resulting in inaccurate saliency maps. In this paper, we propose a novel scribble-supervised RGB-D SOD method, consisting of a Segment Anything Model (SAM)-driven pseudo annotation generation method (\emph{SAM-PAG}) and a state space interaction-based conditional diffusion model (\emph{$S^2$Diff}). Specifical…

arXiv → PDF
cs.CV

Video = World + Event Stream

Lianghua Huang, Zhi-Fan Wu, Yupeng Shi, Wei Wang, Mengyang Feng, Cheng Yu, Chen Liang, Junjie He et al.

We present Wan-Streamer v0.3, which reframes our native-streaming interaction model under a single organizing view: a video is a world plus an event stream. The world is the persistent context in which a video unfolds, including the environment, scene, subjects, ambient acoustic conditions, voice characteristics, and other relatively stable conditions. The event stream is everything that changes over time within that world, including scene or environmental changes, subject behavior, speech, and…

arXiv → PDF
cs.AI

Man, Machine, and Masterpiece: Artistic Ownership in the AI Era

Sofi Gjing Jovanovska, Kuntal Ghosh, Daniel Muhu Njenga, Ahmed Mufassir, Shadan Sadeghian

The integration of AI-driven systems in creative work has sparked debates among artists and legal communities about notions of ownership. Yet there remains little consensus on how ownership should be defined and attributed when human and AI contributions are intertwined. To provoke critical reflection on these tensions, we designed ArtSplit, a provotype that explicitly quantifies human and AI contributions across different stages of creative work. Rather than aiming to resolve ownership, the pro…

arXiv → PDF
stat.MLcs.LGstat.COstat.ME

cGAP: Generalized Association Plots with HOMALS-Guided Heatmaps for Visualization of High-Dimensional Categorical Data

Chun-houh Chen, Shun-Chuan Chang, Chiun-How Kao, Yi-Ju Lee, Shang-Ying Shiu, Yin-Jing Tien, ShengLi Tzeng, Han-Ming Wu et al.

High-dimensional categorical data arise in genetics, biomedicine, and the social sciences, yet visualization tools for such data remain far less developed than those for continuous variables. Existing methods either scale poorly, rely heavily on low-dimensional displays detached from the original data matrix, or prioritize predictive accuracy over interpretability. To address this gap, we introduce categorical Generalized Association Plots (cGAP), a visualization framework for nominal, ordinal,…

arXiv → PDF
cs.HCcs.AI

When AI Blurs the Boundaries of Contribution: An Empirical Study of Authorship Calibration

Célina Treuillier, Denis Lalanne

The broad adoption of Artificial Intelligence (AI), especially Generative AI, raises pressing questions about how users interact with these systems to produce new content. In this paper, we introduce the concept of authorship calibration, defined as users awareness of their actual authorship when interacting with AI. Using the CoAuthor dataset, we empirically examine how authorship calibration varies across users and how it relates to their frequency of AI use. Our results reveal high variabilit…

arXiv → PDF
cs.AIcs.LGcs.NE

SMC-ES: Automated synthesis of formally verified control policies

Riccardo Curcio, Toni Mancini, Enrico Tronci

The deployment of autonomous cyber-physical systems in safety-critical environments requires closed-loop control strategies (i.e., policies) that are not only performant but also provably safe and robust. While learning-based methodologies such as Reinforcement Learning offer flexible and scalable approaches to automatically synthesize such controllers, they typically lack the formal guarantees necessary for safe deployment. To bridge this gap, we propose a novel simulation-based methodology to…

arXiv → PDF
hep-latcs.AIhep-ph

LQCDMaster: Agentic Scientific Computing for Lattice Quantum Chromodynamics Research

Haofei Gao, Tingjia Miao, Wenkai Jin, Muhua Zhang, Hanzhang Wang, Jie Ran, Jinxin Tan, Zhentao Zhang et al.

Lattice quantum chromodynamics (LQCD) provides a first-principles framework for computing hadronic observables, but its practical use remains limited by the substantial expertise required to turn research motivation into reliable computing workflows. Here we present \textsc{LQCDMaster}, a tool-augmented, skill-guided and domain-specialized scientific computing agent that converts natural-language LQCD research tasks into executable PyQUDA computing workflows, including measurement scripts, job-s…

arXiv → PDF
cs.AIcs.CY

Moral Attitudes of Sentient ASI towards Humanity and Implications for AGI Development

Jean-Paul Van Belle

This paper suggests the adoption of a novel inversion in AI ethics: instead of asking how humans should treat artificial superintelligence (ASI), it examines how future sentient ASI may morally consider and evaluate humanity. We are not only designing intelligent systems but also shaping the initial conditions under which those systems form judgments about us. The paper proposes a preliminary set of post-human moral principles that may govern sentient ASI actions. The implication is that technic…

arXiv → PDF
cs.LGq-bio.QM

Multimodal Semantic-Aware Contrastive Learning For False Negative Mitigation in 3D Medical Imaging

Sara Ketabi, Matthias W. Wagner, Cynthia Hawkins, Uri Tabori, Birgit Betina Ertl-Wagner, Farzad Khalvati

Multimodal Contrastive Learning (CL) has shown significant performance in aligning representations across various data modalities and improving downstream tasks, especially in healthcare. It works by minimizing the distance between matched (positive) data modalities, while maximizing the distance between mismatched (negative) samples. Traditional CL frameworks typically assume instance-based correspondence within data batches, treating all non-paired samples as negatives. However, this assumptio…

arXiv → PDF
cs.CV

JADE-GS: Joint Alternating Deblurring Guided by Events in 3D Gaussian Splatting

Haoyu Fu, Jiafeng Huang, Yuchen Wang, Shengjie Zhao

When a camera moves fast during exposure, blur destroys the intra-exposure motion a 3D model needs to recover the sharp scene, while event cameras capture exactly this signal at microsecond resolution. Turning them into reliable 3D supervision faces two obstacles. First, the two restoration priors fail in opposite ways: physics-based event-integration priors preserve edges but accumulate drift; learned networks recover texture but distort boundaries. Second, existing pipelines run in one directi…

arXiv → PDF
cs.CLcs.AI

OmniaBench: Benchmarking General AI Agents Across Diverse Scenarios

Chengyu Shen, Yujie Fu, Gangtao Xin, Yanheng Hou, Wenlong Fei, Guojie Zhu, Jiawei Li, Hongcheng Gao et al.

Large language models are increasingly evolving from text generators into general agents capable of understanding user requests, invoking external tools, and completing complex tasks through interaction. However, existing agent benchmarks often focus on limited scenarios, tool ecosystems, or interaction formats, making it difficult to systematically characterize model capabilities across heterogeneous application settings. We introduce OmniaBench, a benchmark for evaluating general agents across…

arXiv → PDF
cs.AI

Demographically-Conditioned Synthetic Medical Images for Bias Mitigation and Bias Detection in Disease Classifiers

Mahmoud Ibrahim, Bart Elen, Chang Sun, Gokhan Ertaylan, Michel Dumontier

Per-subgroup fairness audits of medical image classifiers face a sample-size problem: minority subgroups in held-out test sets have so few samples that the resulting confidence intervals on per-subgroup performance are wider than the bias the audit is meant to detect. We argue that a demographically-conditioned synthetic generator can do both: mitigate bias on the training side and detect bias on the evaluation side. Working on COVID-19 chest CT classification with an end-to-end fine-tuned Stabl…

arXiv → PDF
cs.CV

From Draft to Draft-Free: One-Step Video Object Removal via Privileged Distillation and Fast Planting

Zizhao Chen, Ping Wei, Guang Dai, Jingdong Wang, Mengmeng Wang

Video object removal is a fundamental yet challenging task in video editing. Despite recent progress, existing methods typically fall into two categories. Traditional approaches based on optical flow or attention mechanisms often introduce noticeable artifacts and yield unnatural results. In contrast, diffusion-based methods improve visual realism but demand multiple denoising steps, limiting their practicality. To address these issues, we propose From-Draft-to-Draft-Free (D2DF), a framework tha…

arXiv → PDF
cs.AI

CFM-Bench: A Unified Multi-Domain, Multi-Task Benchmark for Channel Foundation Models

Yuan Gao, Wenjun Yu, Jun Jiang, Yunfan Li, Xinyu Guo, Shugong Xu

Channel foundation models (CFMs) are developing rapidly, with recent studies reporting benefits from pretraining across downstream wireless tasks. Yet CFMs are commonly evaluated in model-specific pipelines with different data, radio configurations, partitions, adaptation procedures, task definitions, and metrics. Reported comparisons therefore tend to show that pretraining improves over supervised training from scratch within one pipeline, but neither rank CFMs nor compare them fairly with task…

arXiv → PDF
cs.CVcs.CR

On Success and Simplicity: A Second Look at Transferable Vision-Language Attack Pipeline

Yuchen Ren, Zhengyu Zhao, Chenhao Lin, Bo Yang, Chao Shen

Vision-Language Pre-training Models (VLPMs) are known to be vulnerable to adversarial attacks. Recent transferable attacks on VLPMs have followed a common pipeline with complicated loss functions or multi-stage text/image attacks. However, in this paper, we demonstrate that such a sophisticated attack pipeline can be simpler yet more successful. Specifically, we identify three previously overlooked issues caused by inappropriate cross-modal interactions and excessive operations. To address them,…

arXiv → PDF
cs.AI

Explaining Process Control Optimisation Recommendations via GradientSHAP and Implicit Differentiation

Paul Darm, Cem Alpturk, Kenneth Ulrich, William Duncan, Ali Anwar, Annalisa Riccardi

Automated optimisation is increasingly adopted in industrial processes, yet a trust gap persists between engineers who design these algorithms and operators who must act on their recommendations. Explainable AI methods like SHAP (SHapley Additive exPlanations) have transformed interpretability for machine learning predictions; optimisation outputs could benefit from similar techniques. We present an approach that integrates Implicit Function Theorem (IFT) based sensitivity analysis with SHAP att…

arXiv → PDF
cs.CV

Stitch-Inferencer: Enhance Endoscopic Video Segmentation and Tracking via Panoramic Reconstruction

Shunsuke Kikuchi, Atsushi Kouno, Hiroki Matsuzaki

Surgical video understanding is fundamental to navigation systems. Endoscopic perception is often hindered by a limited field-of-view and frequent instrument occlusions, making spatio-temporal context essential for robust inference. These challenges have motivated video models that aggregate information across frames. However, existing video models typically store past observations implicitly in learned feature representations, often requiring task-specific video training, substantial annotated…

arXiv → PDF
cs.CLcs.AI

Latent Trajectory Discrimination for AI-Generated Text Detection

Gianluca Bonifazi, Christopher Buratti, Michele Marchetti, Federica Parlapiano, Giulia Quaglieri, Davide Traini, Domenico Ursino, Luca Virgili et al.

Most existing approaches to AI-Generated Text Detection (AIGTD) treat documents as static objects and base their decisions on aggregate statistics or globally compressed embeddings. However, this perspective overlooks the inherently dynamic nature of autoregressive generation, where content evolves progressively through the latent space. In this paper, we reformulate AIGTD as the problem of distinguishing between latent generation trajectories. Instead of relying on static representations, we mo…

arXiv → PDF
cs.CV

U-shaped Multi-granularity Learning for Vision-Language Models

Biao Chen, Yunqian Yu, Xiangxu Zhao, Zhongshu Chen, Mengmeng Jing, Lin Zuo

The prompt learning paradigm for vision-language models is effective yet faces a granularity dilemma: global prompts lack fine-grained semantic awareness, while local prompts ignore contextual associations, limiting cross-task generalization. This dilemma exists in dense prediction tasks. Inspired by U-Net, which unifies multi-level representations across granularities, we propose UPrompt, a U-shaped multi-granularity prompt learning framework for vision-language models. Similar to how U-Net int…

arXiv → PDF