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.LGcs.AI

Learning Sparse Decision Trees via Transformer Variational Auto-Encoders

Giacomo Fidone, Alessio Cascione, Riccardo Guidotti

Decision trees are among the most widely used models in machine learning, largely due to their transparent decision logic, making them well-suited for high-stakes decision-making contexts. However, most existing learning algorithms focus on predictive performance, overlooking the joint optimization of other desirable properties, such as structural sparsity. In this work we propose TREVIS, an approach for learning decision trees with respect to complex objectives, based on the exploration of the…

arXiv → PDF
cs.LG

TRIAGE: Three-level Routing and Intelligent Agent Guidance for Efficient Execution

Ruocan Wei

Large Language Model (LLM) agents based on the ReAct paradigm have demonstrated remarkable capabilities in tool use and task execution. However, ReAct suffers from a fundamental efficiency problem: every query triggers a complete reasoning loop from scratch, and similar queries repeat identical steps without leveraging historical experience. We propose TRIAGE,a three-level routing framework that reduces token consumption by reusing historical execution trajectories. Its core innovation is TaaS (…

arXiv → PDF
cs.CV

Pix2Rep-v2: Data-Efficient Representation Learning for Dense Medical Imaging Applications

S. Sifaoui, E. Angelini, S. Toupin, T. Pezel, L. Le Folgoc

Dense self-supervised learning (SSL) is a powerful paradigm for learning without annotations the local descriptors required to solve dense medical imaging tasks. We present Pix2Rep-v2, a framework for SSL of pixel- and voxel-level representations suitable for few-shot downstream applications. Pix2Rep-v2 addresses the main challenges of dense SSL by leveraging a redundancy reduction objective at the pixel-level with a principle of equivariance of dense representations, that scales efficiently to…

arXiv → PDF
cs.CVcs.AIcs.LGeess.IV

Semantic-Guided Multimodal Preprocessing for Vision Transformer-Based Clear Cell Renal Cell Carcinoma Grading

Fatemeh Javadian, Zhu Chen, Zahra Aminparast, Johannes Stegmaier

Clear cell renal cell carcinoma (CCRCC) grading is essential for treatment planning, yet existing approaches either analyze patch-level images directly or focus solely on nuclei-level classification, without linking to final tumor grading. We propose a semantic-guided multimodal preprocessing method that integrates nuclei classification maps from existing pre-trained models with RGB histopathology images for Vision Transformer (ViT)-based CCRCC grading. Our approach employs classification map ch…

arXiv → PDF
cs.LG

CATeye: Coupled Attribute-Topology Invariance Learning for Voucher Abuse Detection

Tian Tian, Shuaicheng Niu, Hao Kuang, Yuanhang Hu, Dong Li, Zhiqi Shen

Voucher abuse poses a major challenge in e-commerce, where malicious users exploit promotional vouchers for profit. Unfortunately, fraud patterns evolve rapidly over time and across regions, causing distribution shifts that degrade existing detection models unless retrained frequently. To tackle this, we propose the Coupled Attribute-Topology Invariance Learning framework (CATeye). The key challenge arises from coupled attribute-topology shift, where edges built from attribute proximity cause en…

arXiv → PDF
cs.CV

MegaStyle++: Scaling Image Style Space through Hierarchical Style Definition

Junyao Gao, Sibo Liu, Jiaxing Li, Yanan Sun, Weidong Zhang, Cairong Zhao, Jun Zhang

Image style is a highly abstract, human-constructed concept shaped by a range of visual factors and intrinsically entangled with content, yet a unified and explicit definition of image style remains lacking. In this work, we first discuss the fundamental question of what is style and then propose a hierarchical style definition that describes image style from an overall style identity to fine-grained visual attributes, providing a more structured, transferable, and interpretable style representa…

arXiv → PDF
cs.CL

From Rollouts to Recipes: Self-Contained Post-Training for LLMs

Yifei Li, Lingling Zhang, Muye Huang, Zihan Ma, Jiashuai Liu, Jun Liu

Post-training large language models usually applies a single training recipe to all samples, even though the model's own rollouts reveal different sample-level learning states. We propose Self-Routing, a behavior-conditioned post-training framework that uses rollout correctness and confidence to decide how each sample should be optimized. Depending on its behavior state, a sample is routed to GRPO, on-policy self-distillation, regularization, or skipping, allowing training to adapt without exter…

arXiv → PDF
cs.LGcs.AI

Provably Safe Sim-to-Real Transfer

Tingting Ni, Maryam Kamgarpour

To mitigate the sample complexity of real-world reinforcement learning (RL), a common practice is to first train a policy in a simulator, where samples are cheap, and then deploy the learned policy in the real world with the hope that it generalizes effectively. Such direct sim-to-real transfer is not guaranteed to succeed: simulator-trained policies can be suboptimal in the real world due to sim-to-real mismatch. Correcting this mismatch requires collecting data from the real system, but in man…

arXiv → PDF
cs.LG

Predicting Subsurface Abnormalities Growth using Physics-Informed Neural Networks

Mehrdad Shafiei Dizaji, Hoda Azari

The research explores the pioneering integration of Physics-Informed Neural Networks (PINNs) into the domain of Ground-Penetrating Radar (GPR) data prediction. This research presents a detailed development framework for a specialized PINN model, proficient at interpreting and forecasting GPR data, much like how medical imaging models predict tumor behavior. By harnessing the synergy between deep learning algorithms and the physical laws governing subsurface structures or in medical terms, human…

arXiv → PDF
stat.MLcs.LG

On the Reliability of Generative Augmentation: A Wasserstein-Based Theoretical and Empirical Study

Chathurika S Abeykoon, Mathias Nthiani Muia, Mallory Goldstein

Generative data augmentation is widely used to mitigate class imbalance, yet its theoretical effect on downstream generalization remains poorly understood. In this work, we develop a statistical framework for conditional generative augmentation and analyze its impact on classification risk. We formalize augmentation as a distribution-mixing process and show that the resulting risk distortion is controlled by both the augmentation strength and the class-conditional Wasserstein discrepancy between…

arXiv → PDF
cs.AIcs.CLcs.CV

EdiTikZ: Scientific Figure Editing from Revision Trajectories

Christian Greisinger, Zhixue Zhao, Steffen Eger

Vision-language models (VLMs) have shown strong performance in generating scientific figures from text or images. However, producing publication-ready figures requires iterative refinement, making scientific figure editing an important yet largely unexplored task. Existing approaches rely on costly proprietary agentic systems, focus primarily on evaluation, or construct training supervision from synthetically generated edits. Instead, we leverage naturally occurring scientific revision and devel…

arXiv → PDF
cs.AIcs.CVcs.GR

Neuro-Symbolic Geometric Abstraction (NeuSOGA): From Observations to Symbolic Mathematical Representations

Qingde Li, Qingqi Hong, Jie Tian

A fundamental challenge in artificial intelligence is the transformation of observations into explicit symbolic representations suitable for abstraction, interpretation, and reasoning. While modern AI systems achieve remarkable perceptual capabilities through large-scale statistical learning, the resulting knowledge is typically encoded within latent parameters that are difficult to inspect or manipulate analytically. Inspired by Neuro-Symbolic AI and theories of human abstraction, this paper in…

arXiv → PDF
cs.LGcs.DCcs.NI

Contribution-Aware Bandwidth Allocation for Multimodal Split Learning

Iason Ofeidis, Leandros Tassiulas

Multimodal models are increasingly the default option for perception at the network edge, yet they are trained almost entirely in the datacenter, because a client holding several sensor streams cannot host an encoder per modality. Split Learning makes such training feasible by keeping only the first layers on the device, at the cost of an uplink that must carry smashed activations for every modality at every step. Existing compression schemes give each modality the same keep-ratio, so the shared…

arXiv → PDF
cs.ROcs.AI

Evaluating Multimodal LLMs as Generalist Vision-Language-Action Agents for Drone Control: Commanding, Approaching, Tracking and Searching

Jaewoo Park, Minyoung Lee, Sukmin Seo, Moonbin Yim, Hyunwook Yoon, Dohoon Ryu, Daehee Kim, Myungseo Song et al.

Multimodal Large Language Models (MLLMs) are strong perceivers of images and video. We ask how far that reach extends into acting: dropping an MLLM directly into a drone's control loop, with its entire action space declared solely in the prompt. Recent systems approach this setting but increasingly narrow the model's decision-making. We widen it back. We introduce DroneCATS-Agent, an architecture where the MLLM is a swappable component, and DroneCATS, a benchmark treating the model as the indepe…

arXiv → PDF
stat.MLcs.AIcs.LG

Measuring consistency via ensemble margin and local prediction variability: Auditing decision systems in the presence of predictive multiplicity

Sinjini Banerjee, Tim Marrinan, Anand D. Sarwate

The Rashomon effect is a machine learning phenomenon where equally accurate models produce different predictions for the same inputs (predictive multiplicity). Existing work primarily focuses on multiplicity within individual models, but in more complex decision systems, the impact of the Rashomon effect is less well understood. In this work, we study multiplicity from the perspective of auditing incorrect ensemble predictions, where the decision to divert an instance for human review is based o…

arXiv → PDF
cs.CV

Scale-based Approach for Active Wildfire Segmentation on Satellite Imagery

Matheus F. Kovaleski, Cristiano Premebida, João Ruivo Paulo

Active wildfire mapping from satellite imagery is challenging due to the sparse and highly imbalanced nature of fire pixels, especially in early-stage or low-density fire observations. This work investigates the use of multispectral Landsat-8 imagery for active-fire segmentation under multi-scale wildfire size conditions. We propose a data-driven protocol to characterize fire-region size distributions through connected-component analysis and an interquartile range criterion, enabling the evaluat…

arXiv → PDF
cs.CV

Multimodal RGB-Infrared Combination for UAV-Based Wildfire Segmentation: A Comparative Study on FLAME3

Matheus F. Kovaleski, Luís Garrote, Cristiano Premebida, Jérôme Mendes, João Ruivo Paulo

Unmanned Aerial Vehicles (UAVs) have emerged as a promising platform for firefighting operations due to their flexibility, low operational cost, and ability to acquire high-resolution imagery in locations that may be difficult or dangerous to access using conventional methods. Recent advances in deep learning have significantly improved the capabilities of UAV-based wildfire monitoring systems. The present work investigates RGB-infrared fusion for binary wildfire segmentation on the FLAME3 datas…

arXiv → PDF
cs.CL

When Tokenization is Secretly Output Supervision

Tanja Baeumel, Josef van Genabith, Simon Ostermann

Tokenization in language models is treated by default as an input preprocessing decision. We argue that this framing is incomplete: in autoregressive models, tokenizer granularity determines what the model must resolve in a single forward pass, and therefore the supervision signal it receives. This affects both the difficulty of the learning problem and the representations that emerge inside the model. We test this in a controlled experiment on numeric reasoning with a novel decoupling of input…

arXiv → PDF
cs.CLcs.CVcs.HC

InSight: A Benchmark for Agentic Claim Verification in Interactive Visualizations

Maeve Hutchinson, Syed Mahbubul Huq, Mohammad Albinhassan, Radu Jianu, Aidan Slingsby, Pranava Madhyastha

Vision Language Models have demonstrated remarkable proficiency in interpreting static visual artifacts, but modern data analysis is inherently dynamic, requiring the active interrogation of interactive environments. Existing benchmarks are predominantly constrained to static imagery and one-shot question answering and fail to capture the epistemic demands of this domain, where evidence is frequently occluded, distributed across linked views, or conditionally revealed through user agency. In thi…

arXiv → PDF
cs.CL

Polish ModernBERT: The Long and Short of Polish Language Understanding

Michał Perełkiewicz, Sławomir Dadas, Rafał Poświata, Małgorzata Grębowiec

Encoder-only Transformers remain effective for discriminative and representation-learning tasks, yet Polish encoders still largely rely on BERT/RoBERTa-style architectures. We introduce \textbf{Polish ModernBERT}, a family of four Polish encoders available at Base and Large scales, each with 512-token and 8K context variants. We adapt the ModernBERT pretraining recipe through staged selection experiments and release a long-context benchmark covering legal topic classification, ideological decisi…

arXiv → PDF
cs.CVcs.CL

IntroConformal: Conformal Factuality Guarantees for Large Vision-Language Models via Introspective Signals

Md. Atabuzzaman, Christian Alexander, Chris Thomas

Large Vision-Language Models (LVLMs) have achieved strong multimodal performance, yet ensuring the factual correctness of generated content remains challenging. Existing methods that provide statistical guarantees on factuality typically rely on external verifiers or generation-time confidence signals, which introduce auxiliary dependencies or often fail for confident but incorrect outputs. We argue that reliable factuality control can instead be achieved through introspective signals derived fr…

arXiv → PDF
cs.CL

Behaviorally Effective LoRA Writes Are Sparse and Structured

Haruto Sato, Yuki Tanaka, Ren Nakamura, Aoi Kobayashi, Mei Ito

Low-rank adaptation fixes the rank of the update, but it does not identify which parts of a trained write actually carry behavior. We study that question directly and show that behaviorally effective LoRA writes are sparse, structured, and far more concentrated than the raw low-rank parameterization suggests. We use Learned-Basis LoRA, a learned-basis continuation recipe, to expose that structure. The recipe warms up an unconstrained adapter, converts its learned write columns into a module-wise…

arXiv → PDF
cs.CV

Diffusion Based Unpaired Data Learning for Inverse Problems

Chenglong Bao, Yiming Dang, Chenguang Duan, Yuling Jiao, Defeng Sun

Data is important in many deep learning-based inverse problem solvers. However, obtaining sufficient paired data in many scenarios remains highly challenging, while unpaired data is cheap. To maximize data utilization, this paper proposes LUD-DIF, a diffusion-based approach for solving inverse problems with unpaired data. Starting from the evidence lower bound (ELBO) of the joint distribution, we decouple it into two independent diffusion processes under the weak-coupling assumption. The method…

arXiv → PDF
cs.CL

How Correct Is Your Answer? A Semantic Correctness Framework for Open QA Evaluation

Elitsa Yotkova, Violeta Kastreva, Petar Velkov, Hristo Boyanov, Dimitar Dimitrov, Ivan Koychev, Preslav Nakov

Reliable evaluation of open-ended question answering remains a bottleneck for measuring answer correctness of modern LLMs. Unlike multiple-choice tasks, free-form answers may be correct in many surface forms and may fail in qualitatively different ways, including incompleteness, contradiction, overgeneration, and endorsement of false premises. Existing judgment-based and similarity-based metrics often collapse these distinctions. We address this gap with three reusable contributions. First, we i…

arXiv → PDF
cs.CV

Accurate Reconstruction of Gas Turbine Blade Geometry Using 3D/2D Rigid Registration and CT View Optimization

Hristo Valtchanov, Nicolas Piché, Vladimir Brailovski, Justin Byers, Catherine Désrosiers, François Guibault

Non-destructive X-ray and computed tomography (CT) testing are essential for ensuring the dimensional accuracy of manufactured components with complex internal structures, such as the cooling channels in gas turbine blades, which directly affect thermal performance and service life. This study presents a multipart 3D-2D rigid registration approach for aligning CAD models with X-ray projections as an alternative to CT reconstruction for part inspection and measurement. A greedy registration algor…

arXiv → PDF
cs.CLcs.LG

Investigating Linear Probe Robustness to Linguistic Register, Medical Specialty, and Corpus Shifts in Medical QA

Nishant Mishra, Ameen Abu-Hanna, Iacer Calixto

Linear classifiers trained on hidden states of a large language model (LLM), linear probes, can flag factual errors from a single forward pass. Geometrically, that implies that true and false statements separate along a stable direction in hidden state space, i.e., the truth direction. Prior work disagrees on whether this generalises across input shifts, but the disagreement is hard to interpret because cross-dataset probe transfer experiments confound several kinds of input change at once. We i…

arXiv → PDF
cs.AI

EDGE: Error Dependency Graph-Guided Multi-Error Attribution in Multi-Agent LLM Systems

Jun Hou, Priya Pitre, Yi Fang, Xuan Wang

Large language model (LLM) agent failures often contain multiple related errors rather than a single mistake. Existing attribution methods usually identify a responsible agent, step, or root cause, but do not explicitly model dependency between errors. We introduce EDGE, an Error Dependency Graph-guided multi-Error attribution framework. EDGE constructs an error dependency graph from observed error events and validates a reliable causal subset through counterfactual rollout. The inference graph…

arXiv → PDF
q-bio.GNcs.AI

PopPert: Population-level Joint-Distribution Modeling for Single-Cell Perturbation Prediction

Handong Wang, Jiaxin Qi, Haochen Feng, Baisheng Lai

Predicting transcriptional responses to specific perturbations is critical for understanding cellular regulatory mechanisms and accelerating drug discovery. Single-cell RNA sequencing destroys each measured cell, yielding only unpaired populations of control and perturbed cells. However, existing methods typically model perturbation prediction at the single-cell level and assume cell-to-cell correspondence, which conflicts with the unpaired nature of the observed data. To address this challenge,…

arXiv → PDF
eess.SYcs.LGmath.OC

Exact Risk-Complexity Laws for Projective Boundaries in Scenario Optimization and Distribution-Free Certification

Giuseppe C. Calafiore

Scenario optimization, conformal prediction, and related distribution-free certification methods use finite samples to construct decisions or prediction sets with violation-risk guarantees for fresh observations. In several classical settings, the conditional violation risk follows an exact beta law, whose tail has a beta-binomial representation and whose parameter is a support, calibration, or compression dimension. This paper identifies the deterministic boundary mechanism behind these formula…

arXiv → PDF
cs.CL

Separating Syntax from Language: A Mechanistic Account of Translation in Multilingual LLMs

Mikhail Sonkin, Tanja Baeumel, Daniil Gurgurov, Josef van Genabith, Simon Ostermann

Multilingual large language models (mLLMs) achieve strong performance in machine translation, yet our understanding of the mechanisms by which they transform representations from one language to another remains incomplete. Prior work suggests that translation decomposes into separable processes within an mLLM, where conceptual content is first represented independently, followed by a production into language-specific form. In this work, we show that translation is even more modular than previous…

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 →