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.CVcs.RO

VQ-Touch: A Data-Efficient Tactile Generation Framework Across Sensors and Scenarios

Kailin Lyu, Long Xiao, Jianing Zeng, Di Wu, Lin Shu, Jie Hao

Tactile image generation significantly reduces the dependency on expensive and wear-prone sensors by synthesizing high-fidelity tactile data, offering an efficient solution for tactile information acquisition in robotic perception and human-machine interaction systems. However, existing methods depend on large-scale, diverse datasets from specific sensors and lack efficient data utilization and robust generalization capabilities, struggling in vision-limited environments. To address this, we int…

arXiv → PDF
cs.CV

WorkDrive: Roadwork Chain of Causation for Autonomous Driving

Tianyi Jiang, Wen Zhang, Sihan Yang, Ming Lu, Wentao Zhang

Autonomous driving vision-language models (VLMs) struggle in roadwork zones, where familiar visual cues such as lane markings and permanent signs are altered or absent, and temporary devices such as cones and barriers redefine the drivable corridor. VLMs can detect these objects, but without explicit guidance they anchor their reasoning on familiar elements from pre-training and fail to connect work-zone observations to correct planning decisions. We propose WorkDrive, a framework that construct…

arXiv → PDF
cs.CV

AE-UAV: An Air-to-Air Event-Based UAV Tracking Benchmark and a Real-Time Frequency-Domain Tracker

Zixin Jiang, Bing He, Chaoran Xiong, Zhenzhen Wang, Xin Zhao, Ling Pei

Air-to-air (A2A) unmanned aerial vehicle (UAV) tracking is fundamental to airborne remote sensing of low-altitude aerial targets. However, the deployment of continuous, real-time tracking systems on UAVs presents significant challenges. In A2A scenarios, traditional frame-based cameras suffer from severe performance degradation under low illumination, overexposure, and high-speed motion owing to their limited dynamic range and fixed temporal sampling. Although event cameras offer a promising alt…

arXiv → PDF
cs.CVcs.LG

Multimodality as Supervision: Self-Supervised Specialization to the Test Environment via Multimodality

Kunal Pratap Singh, Ali Garjani, Rishubh Singh, Muhammad Uzair Khattak, Efe Tarhan, Jason Toskov, Andrei Atanov, Oğuzhan Fatih Kar et al.

Cross-modal learning, i.e., learning to predict one modality from another, is a fundamental mechanism for self-supervision via leveraging multimodality. Many practical applications, e.g., deploying a household robot, involve devices that are equipped with a rich set of sensors that enable multimodal sensing in their test environment. This presents an opportunity to apply cross-modal learning to the multimodal data sensed by these devices to learn representations. Findings in developmental psycho…

arXiv → PDF
cs.CV

Causal-Adversarial Probing of Clinical Covariates for Prostate MRI Grading

Yipei Wang, Shiqi Huang, Wen Yan, Weixi Yi, Dean C. Barratt, Mark Emberton, Daniel C. Alexander, Veeru Kasivisvanathan et al.

Deep learning models for prostate MRI-based cancer grading may encode clinical covariates that either reflect useful disease-related signal or non-generalising shortcut information, but their role is usually assumed. We propose a causal-reasoning framework for probing covariate dependence in MRI-based International Society of Urological Pathology (ISUP) Grade Group prediction. Rather than treating mpMRI as a direct cause of grade, we model MRI appearance and ISUP grade as observations of latent…

arXiv → PDF
cs.LG

Counterfactuals for Feature-Weighted Clustering

Richard J. Fawley, Renato Cordeiro de Amorim

Counterfactual explanations provide local, interpretable insight by identifying changes to an input that would alter its assigned outcome. Although well established in supervised learning, their extension to clustering is less direct, since cluster assignments are unlabeled and governed by the geometry of the partition. This paper introduces VoICE, a Voronoi-Induced Counterfactual Explainability framework for feature-weighted $k$-means clustering. Rather than treating cluster change as a crossin…

arXiv → PDF
econ.GNcs.CLcs.MA

Does Multi-Agent Debate Improve AI Feedback on Research Papers?

Tomas Havranek, Zuzana Irsova

Probably not, at least for meta-analyses in economics. In a pre-registered, identity-masked, within-paper experiment, the authors of 44 meta-analyses ranked three AI reports on their own paper by usefulness for improving it: a single pass by a frontier model against two multi-agent debate tools we built and expected to win. All reports were held to a common length and template. The authors preferred the single pass, by 0.66 rank points over mad-research (95% CI 0.32 to 1.00) and 0.57 over paper-…

arXiv → PDF
cs.CVcs.AI

VideoSEMA: a scalable and efficient Mamba-like attention for video understanding

Nhat Thanh Tran, Fanghui Xue andShuai Zhang, Jiancheng Lyu, Yunling Zheng, Yingyong Qi, Jack Xin

We present for video understanding (classification) a split space-time attention model, VideoSEMA, consisting of a scalable and efficient Mamba-like attention (SEMA) block in space and a softmax temporal attention in time. In each frame, SEMA attention applies a local window attention in parallel with a global averaging in a Mamba macro-architecture, which is called Mamba-like. Under certain rank conditions, we prove that the computationally cheaper split space-time attention is equivalent to fu…

arXiv → PDF
cs.CVeess.SY

Variational Inference for Bird's Eye View Segmentation in Autonomous Driving

Jingyue Shi, Huaicheng Li, Junhui Zhao, Yanxiang Jiang

The bird's eye view (BEV) has emerged as a pivotal approach for environmental perception in autonomous driving, providing a unified spatial representation for vehicles. Nevertheless, despite BEV's significance in addressing the challenges inherent to autonomous driving, effectively fusing data from multiple camera sensors and operating in complex external driving environments remains a considerable challenge. To mitigate this issue, we recast the BEV segmentation problem within a variational inf…

arXiv → PDF
cs.CL

Gold-Guided Programmatic Distillation for Financial Reasoning over Hybrid Tables and Text

Yun Dong, Erica Zhao, Elana Chen

Financial question answering over hybrid tabular and textual data may require multi-source reasoning and precise numerical computation. While large language models (LLMs) can generate intermediate reasoning steps, natural-language rationales remain prone to arithmetic errors, making them an unreliable supervision source for distillation. Building on programmatic distillation, we develop an approach that transfers reliable numerical reasoning from a large teacher model to a compact student using…

arXiv → PDF
cs.CLcs.AI

Harnessing LLMs for Reliable Academic Supervision: A Comparative Study

Akash Raj

Large language models routinely produce fluent answers to single-shot prompts, yet deploying them as reliable components of a domain decision system is substantially harder. Closing this gap is the work of harness engineering: the deliberate composition of deterministic scaffolding (symbolic filters, retrieval, schema-typed I/O, LLM-as-judge loops, HITL gates, persistent state, audit trails) around an LLM core. We present a case study in academic supervision, a domain combining high-stakes recom…

arXiv → PDF
cs.LG

MESHA: Mechanism-Enforced Sequential Halving for Strategic Linear Bandits

Xin Li, Zixin Zhong

We design and analyze \underline{M}echanism-\underline{E}nforced \underline{S}equential \underline{HA}lving (MESHA), an algorithm for Best Arm Identification (BAI) in strategic linear bandits. In this setting, each arm may strategically misreport its feature vector to maximize the probability of being identified as the best arm, when rewards are generated from the arms' true but unobservable features. The design of MESHA applies the naïve uniform sampling rule and an epoch-wise Grim Trigger Cond…

arXiv → PDF
cs.LG

Grad2Fair: A Gradient-driven Approach for Graph Fairness without Demographics

Yuchang Zhu, Zezhong Xie, Huizhe Zhang, Huazhen Zhong, Jintang Li, Liang Chen, Zibin Zheng

Graph neural networks (GNNs) frequently encounter group fairness issues, often yielding biased predictions against specific demographic groups defined by sensitive attributes such as gender or race. While this challenge has motivated extensive research, most existing solutions rely on the strong assumption that demographics are fully available. To bypass this strict requirement, a few recent studies have attempted to use predicted demographics as proxies to enforce fairness constraints. However,…

arXiv → PDF
cs.CVcs.AI

Pretraining Multiple Instance Learning Networks with Multi-Teacher Distillation from Pathology Slide Foundation Models

Mingxi Fu, Jiawen Li, Renao Yan, Jiali Hu, Qiehe Sun, Tian Guan, Yonghong He

Multiple instance learning (MIL) has become the main paradigm for whole-slide image (WSI) analysis in computational pathology. However, existing MIL aggregators are still typically trained from scratch for each downstream task, relying on limited slide-level labels to learn both aggregation mechanisms and downstream discriminative representations simultaneously. As a result, they often suffer from unstable optimization, overfitting, and limited transferability. Similar to pretrained ResNet and V…

arXiv → PDF
cs.CVcs.AI

Team RAS in 11th ABAW Competition: Multimodal Ambivalence Recognition Approach

Elena Ryumina, Maxim Markitantov, Alexandr Axyonov, Fedor Shchetinin, Timur Abdulkadirov, Dmitry Ryumin, Alexey Karpov

Automatic recognition of ambivalence and hesitancy is challenging because these states may be expressed through inconsistent linguistic, acoustic, facial, and contextual patterns, while top-performing systems often rely on computationally expensive ensembles. We present a single text-centered multimodal approach for video-level ambivalence and hesitancy recognition for the 11th Affective & Behavior Analysis in-the-Wild (ABAW) Challenge. The proposed approach combines linguistic, acoustic, facial…

arXiv → PDF
cs.CV

GlobalForge: Towards Robust AI-Generated Image Detection

Manni Cui, Ruiqi Liu, Dianyuan Zou, Ziheng Qin, Jingrui Xu, ZiAn Wang, Jianglan Wei, Han Zhou et al.

AI-generated image (AIGI) detectors achieve strong accuracy on clean benchmarks, but their performance drops sharply after images are propagated through real-world channels. We trace this fragility to what these detectors actually learn: they overfit to local artifacts left by generators in small spatial neighborhoods, which are easily destroyed by common propagation degradations such as JPEG compression and blur. Instead, we shift the discriminative cue from fragile local artifacts to more robu…

arXiv → PDF
cs.AI

InCarEmo: A Multimodal Dataset for In-Cabin Emotion Recognition and Driver State Monitoring

Hao Yang, Yanyan Zhao, Kewei Zhao, Hongbo Zhang, Tian Zheng, Yusheng Liu, Xing Fu, Bichen Wang et al.

Understanding driver emotion and state is critical for the next generation of intelligent in-cabin systems that ensure safety and enhance human-vehicle interaction. However, existing public datasets for in-cabin affective computing are largely limited to visual modalities and rarely include conversational information, making it difficult to capture the linguistic and interactive cues underlying driver emotion. To address these gaps, we introduce InCarEmo, a multimodal dataset for in-cabin emotio…

arXiv → PDF
cs.AIcs.CLcs.LG

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment

Harikrishnan P M, Goutham Vignesh, Ganesh Parab, Saisubramaniam Gopalakrishnan, Vishal Vaddina, Varun V, Rohit Agrawal

Efficient multimodal document question answering with explicit visual grounding, locating the precise document region that supports each answer remains an open challenge. Current approaches bifurcate into Supervised Fine-Tuning (SFT), which requires large annotated datasets and reaches optimization plateaus, and reasoning-centric Reinforcement Learning (RL), which depends on verbose intermediate traces that inflate inference token cost without clear benefit. We introduce Perception-RFT, a traini…

arXiv → PDF
cs.CV

ReBind: Multi-Reference Video Editing via Structured Instructions with Explicit Reference Relationships

Xinyu Liu, Shihao Li, Weihong Lin, Xinlong Chen, Yang Shi, Yujin Han, Yiyang Cai, Yanghao Wang et al.

Recent diffusion-based video generation models have made significant progress in multi-reference image-conditioned video editing. However, existing methods still struggle to coordinate information from multiple visual sources accurately. We identify a critical deficiency in existing approaches. Existing editing instructions lack explicit reference relationships, and most multimodal large language models (MLLMs) cannot generate them reliably. To address this problem, we propose ReBind, a systemat…

arXiv → PDF
cs.ROcs.AI

An Intelligent-Cloud Edge Multimodal Interaction System for Robots

Zihan Guo, Xiaoqi Li

Robust human-robot interaction in complex environments requires accurate gesture perception, semantic scene understanding, and reliable task planning under limited onboard computing resources. This paper presents a cloud-edge multimodal interaction framework that integrates an enhanced YOLO-based gesture detector with coordinated large language model (LLM) and vision-language model (VLM) agents. The proposed detector, incorporates the Convolutional Block Attention Module (CBAM) into the neck and…

arXiv → PDF
cs.AIcs.HC

Project Kaleidoscope: Contextual, Human-Aligned Evaluation for Real-World AI Applications

Leanne Tan, Rohan Jaggi, Shaun Khoo, Roy Ka-Wei Lee

Evaluations (Evals) are a deployment bottleneck for real-world AI applications: public benchmarks rarely match a team's users, context, or policies, and human review is often tedious to scale. Motivated by our work with AI applications in the public sector, this project addresses recurring evaluation challenges encountered when applications must satisfy local policy and governance requirements. We present Kaleidoscope, an integrated workflow for contextual functional evaluation that links person…

arXiv → PDF
cs.LG

Scalable Training of Continuous-Time Spiking Neural Networks with Differentiable Spike-Time Discretization

Yusuke Sakemi, Tomoya Takeuchi, Takeo Hosomi, Kazuyuki Aihara

Continuous-time spiking neural networks (SNNs) provide an event-driven framework for temporal computation, computational neuroscience, and neuromorphic hardware. However, training deep continuous-time SNNs is severely constrained by the memory required for exact spike-time computation, which evaluates and retains candidate firing times over intervals determined by presynaptic spike ordering. Here we introduce a memory-efficient training framework based on differentiable spike-time discretization…

arXiv → PDF
cs.AI

SmartRAG: Native Graph-Based RAG for Mobile Device

Zhihan Jiang, Meng Li, Shenghao Liu, Keran Li, Ruiben Zhou, Xianjun Deng, Shuai Wang, Haipeng Dai et al.

Deploying large language models (LLMs) as personal assistants on mobile devices demands privacy, low latency, and offline availability, yet the computational cost of giant models clashes with strict edge-hardware budgets. We argue that this tension cannot be resolved by model compression alone; it requires decomposing on-device intelligence into complementary functional roles. We present SmartRAG, a fully on-device framework that organizes an intelligent assistant around four coordinated modules…

arXiv → PDF
cs.CV

VIABench: A Comprehensive Video Benchmark Collected from Blind Individuals for Visual Impairment Assistance

Yunfeng Liu, Yuandong Yang, Jiarui Han, Zhenpeng Huang, Yuqing Tang, Xiangyu Zeng, Gangshan Wu, Limin Wang et al.

Visually impaired individuals (VIIs) encounter significant daily challenges due to limited access to visual information. Although Multimodal Large Language Models (MLLMs) have achieved impressive results on general vision and language tasks, their practical utility in real-world blind assistance still remains largely underexplored. To fill this gap, we introduce VIABench, a comprehensive video benchmark specifically designed to evaluate MLLMs in Visually Impaired Assistance scenarios using first…

arXiv → PDF
cs.SEcs.AI

LLM-Driven Approach to Modeling Tool Interoperability in Automotive Domain

Nenad Petrovic, Jiajie Zhang, Vahid Zolfaghari, Alois Knoll

Interoperability between heterogeneous modeling tools remains a significant challenge in Model-Driven Engineering (MDE), particularly in the automotive domain where multiple modeling languages, as well as defacto standard proprietary and open-source tools coexist. This paper presents an LLM-driven approach for automated model interoperability by considering two relevant aspects: 1) mapping model instances to a target metamodel 2) merging of metamodels. The proposed methodology is demonstrated th…

arXiv → PDF
cs.AI

TopoAgent: A Self-Evolving Topological Agent for Multimodal Scientific Reasoning

Mingze Xu, Yinghui Li, Jiayi Kuang, Zhanhui Kang, Di Yin, Ying Shen, Xing Sun, Yuxing Han et al.

While Multimodal Large Language Models (MLLMs) excel in general tasks, rigorous scientific reasoning remains challenging due to the limitations of monolithic, linear planning. Such sequential designs often suffer from visual-semantic misalignment, long-context hallucinations, and brittle execution under fixed task granularity. We propose TopoAgent, a self-evolving topological framework that replaces linear trajectories with dynamic, state-isolated graph evolution. TopoAgent first employs a front…

arXiv → PDF
cs.LGmath.NA

Trajectory-Aware Flow Matching for Topology Optimisation

Shusheng Xiao, Jinshuai Bai, Hyogu Jeong, Yunfei Xi, Yilin Gui, YuanTong Gu

Topology optimisation (TO) often requires repeated finite element analysis and sensitivity-based material updates, which can be costly when multiple candidate designs are needed under varying physical and design conditions. Generative TO offers a route to rapid design exploration, but existing models may rely on adversarial training, long reverse-diffusion sampling, or external guidance to maintain structural feasibility and physical consistency. This study develops a flow matching-based topolog…

arXiv → PDF
cs.CRcs.AI

MemPoison: Uncovering Persistent Memory Threats and Structural Blind Spots in LLM Agents

Jifeng Gao, Kang Xia, Yi Zhang, Xiaobin Hong, Mingkai Lin, Xingshen Wei, Wenzhong Li, Sanglu Lu et al.

Persistent external memory enhances agent continuity but introduces persistent security vulnerabilities: adversarial content can be injected via standard interaction channels, retained across turns, and later distort downstream behavior. To address this challenge, we propose MemPoison, a comprehensive benchmark and analysis framework featuring 1227 hand-validated cases across four attack types, three injection channels, and three representative memory substrates, evaluated on seven open-weight a…

arXiv → PDF
cs.CL

D-cut: Adaptive Verification Depth Pruning for Batched Speculative Decoding

Tianyu Liu, Yuhao Shen, Rui Cen, Junhan Shi, Jiebin Zhang, Guangshuo Qin, Hong Liu, Song Liu et al.

Speculative decoding accelerates large language model (LLM) inference without compromising output quality. Recent parallel drafting methods further improve single-request performance by decoupling draft length from drafting latency, enabling longer drafts and higher mean accepted tokens (MAT). However, under high request concurrency, long drafts waste substantial computation on rejected tokens, increasing verification cost and potentially making speculative decoding slower than autoregressive de…

arXiv → PDF
cs.CV

Autoregressive Modeling of Film with Applications in Video Montage

Marcelo Sandoval-Castañeda, Fabian Caba Heilbron, Shiry Ginosar, Bryan Rusell, Josef Sivic, Alexei A. Efros, Greg Shakhnarovich

This work introduces FilmGPT, an autoregressive transformer designed to address the challenge of video montage--turning a collection of raw, "unwatchable" footage into coherent cinematic sequences. Inspired by language learning in modern LLMs, we train a long-context autoregressive transformer on a large corpus of movies. The aim is to implicitly capture the "grammar" of film directly from data rather than from hand-coded rules. Unlike other generative models, FilmGPT does not generate any new v…

arXiv → PDF