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

PCDFusion: Proposal-Context-Detail Bayesian Rendering for Infrared-Visible Image Fusion

Rui Liu, Lin Gu, Hesong Li, Ying Fu

Infrared-visible image fusion (IVIF) aims to combine visible and thermal infrared observations for human perception and downstream vision tasks. Visible and thermal infrared observations are physically complementary but unreliable in different ways. Existing deep IVIF methods mainly improve feature interaction and reconstruction, but often lack an explicit local rule for deciding when visible appearance should dominate and when thermal responses should contribute. To address this issue, we refor…

arXiv → PDF
cs.CVcs.LG

An Efficient Approach to Beetle Damage Detection of Banana Using Deep Learning

Md. Mehedi Hasan Naeem, Ishtiyak Ahmmad Araf, Md. Arefin Haque Mahir, Tushar Kanti Saha

Visible surface damage of banana fruits by Basilepta subcostata (the banana fruit scarring beetle) can reduce their market value. Here, manual inspection of Banana fruits is subjective and difficult to scale. This study presents a lightweight framework based on YOLOv8n deep learning model for locating individual bananas and classifying their visible surface condition as healthy or unhealthy. The term beetle damage in the paper title is used operationally for the locally observed scar-like surfac…

arXiv → PDF
cs.CV

FlexPart: Text-Controlled Semantics-Aware 3D Part Segmentation at Flexible Granularity

Yiqun Zhao, Jiachen Xu, Yihao Zhi, Yunfei Zhao, Zibo Zhao, Xintong Han, Chunchao Guo, Shenghua Gao et al.

A 3D asset admits multiple valid part decompositions, while semantics-aware segmentation should reflect both the desired granularity and the parts a user wants to extract. Ideally, a practical segmentation model should strive for a simple principle: what you ask for is what you get. However, realizing this goal is hindered by two core obstacles: the lack of multi-granularity training data and the absence of a holistic control mechanism. We propose FLEXPART, a unified framework for text-controlle…

arXiv → PDF
cs.CVcs.LG

A Language-Informed Loss for Visual Generation

Suchir Agarwal, Keshigeyan Chandrasegaran, Ziyu Chen, Kyle Sargent, Juan Carlos Niebles, Li Fei-Fei, Jiajun Wu

End-to-end visual generation with pixel-space loss has recently achieved competitive performance without the need for learned image tokenizers. In this work, we study whether language-informed supervision can provide a richer training signal than pixel loss for visual generation. We introduce LILIE (pronounced "lily"), a Language-Informed and Lossless Image Encoder. LILIE is an invertible image transform trained such that a vision-language model can recover captions from noised features. The enc…

arXiv → PDF
cs.CL

In Human Memories. Technology, Creativity and Self-Determination: An Ethical Proposal

Francesco Vitucci, Giuseppe Silvi, Francesco Abbrescia, Anthony Di Furia, Francesco Scagliola

This research investigates the role of artificial intelligence (AI) in modern compositional practices, with a particular focus on two case studies: Convergence (2020/21) by Alexander Schubert, for String Ensemble and AI System, and In Human Memories (2024) by Francesco Vitucci, for four cellos and one electroacoustic player, whose installation was created by the Electronic Music School of the "N. Piccinni" Conservatory of Bari. The initial historical survey traces the evolving use of technology…

arXiv → PDF
cs.LG

JAXtari: High-Throughput and Easy-to-Modify Arcade Learning Environment

Quentin Delfosse, Raban Emunds, Paul Seitz, Sebastian Wette, Jannis Blüml, Daniel Kirn, Dominik Mandok, Kristian Kersting et al.

The Arcade Learning Environment (ALE) has been a cornerstone of Deep Reinforcement Learning research, providing a standardized benchmark for evaluating general agents. However, its lack of native support for object-extraction and environment modification restricts research into evaluating whether agents learn robust causal models or rely on brittle visual heuristics. Furthermore, the ALE's dependence on CPU-based emulation creates a significant bottleneck in modern GPU-accelerated training pipel…

arXiv → PDF
cond-mat.mtrl-scics.LG

Scalable long-range machine learning interatomic potentials with electrical response for atomistic material modeling

Yicheng Chen, Xiaoyun Yu, Hyejeong Song, Xintian Wang, Zihui Li, Zixi Xia, Junmin Chen, Peichen Zhong et al.

Accurate atomistic simulations of materials under electric fields require long-range electrostatics and electrical-response modeling at length scales beyond the reach of conventional first-principles methods. Yet these capabilities remain difficult to reconcile with the scalability of machine-learning interatomic potentials (MLIPs). Strictly local models enable efficient spatial parallelization but neglect long-range interactions, whereas existing electrostatic extensions introduce global depend…

arXiv → PDF
cs.CV

Diversity Without Labels: Task-Agnostic Coreset Selection Across Perception and Action

Julia Hindel, Benjamin Ramtoula, Kyuhwan Yeon, Nick Heppert, Paul Newman, Daniele De Martini, Abhinav Valada

While data collection for model training is relatively easy, curating high-quality datasets from large collections is inherently challenging. Coreset estimation methods address this problem by identifying the best data subsets to train models on. However, existing approaches often require proxy model training, extensive annotations, or task-specific tailoring. Unsupervised alternatives typically exploit geometric properties in foundation model feature spaces, but are limited to pairwise image-to…

arXiv → PDF
cs.LGstat.ML

No-Regret Language Generation

Jiaxun Li, Vinod Raman, Ambuj Tewari

We introduce no-regret generation, which requires a generator to make a sublinear number of mistakes uniformly over all demonstration sequences and compatible target languages. We also formulate an agnostic variant that allows arbitrary demonstrations that may not be compatible with any languages. For both settings, we introduce tree-based mistake-forcing dimensions that exactly characterize finite-horizon minimax complexity and establish necessary and sufficient conditions for no-regret generat…

arXiv → PDF
cs.LGq-bio.NC

Deep LLM layers expose passage-level context in EEG during silent reading

Ingo Marquardt, Anthilia Alchanat, Priyanka Jain

In a previous report we showed that a decoder can recover open-vocabulary word-level information from 19-channel EEG recorded during silent reading, by aligning short EEG windows with hidden-state embeddings of the presented word taken from a large language model (LLM). That analysis contrasted two of the model's 33 layers: the context-free input embedding and one mid-depth layer. Here we ask how EEG-decodable structure is distributed over the full depth of the language model. We trained one dec…

arXiv → PDF
cs.HCcs.AIcs.CL

PresenceBench: An Exploratory Evaluation of Large Language Model Adaptation to User State

Peña Arroyo Gallego, Mauro Ruiz Moreno, Alejandro Acien, Sergio Romero-Tapiador, Teresa Arroyo-Gallego

Presence-aware intelligence is the capacity of an AI system's intelligence layer to adapt appropriately to the functional state of the person it serves (here readiness, flow, and stability) while preserving task quality and safety. We introduce PresenceBench, an instrument for measuring it. PresenceBench evaluates how the intelligence layer uses a supplied state, not how that state is sensed, and breaks the capability into measurable properties. Two are tested here. Receptivity: does the model t…

arXiv → PDF
cs.LG

Deconstructing Multi-Task Active Learning: The Paradox of Gradient Conflict and Orthogonal Decomposition

Juho Jung, Seongjae Kang, Jinyoung Han

Existing multi-task active learning (MTL-AL) methods predominantly rely on linear scalarization of heterogeneous objectives such as uncertainty, diversity, and gradient conflict. We argue that this entangled formulation is fundamentally limited, as linear combination fails to capture Pareto-optimal trade-offs under conflicting objectives. We propose a shift from combination to deconstruction and introduce a principled framework that rethinks MTL-AL along three orthogonal dimensions. First, we id…

arXiv → PDF
cs.CV

Stereo LWIR-RGB Automatic Labeling for Low-Light Camera-Based VRU Detection

Dimitrios Bouzoulas, Pyry Jäppinen, Pejman Habibiroudkenar, Eerik Alamikkotervo, Risto Ojala

VRU detection in low-light conditions is a key component in ensuring VRU safety during the most collision prone time of the day. Currently, advances in low-light detection are limited due to the lack of large scale datasets and automated labeling methods. Most autolabeling methods use RGB detections as their labels source, which cannot be replicated in low-light conditions. To fill this gap in this paper we present an automated pipeline for low-light VRU labeling. We use LWIR-RGB image pairs and…

arXiv → PDF
cs.LGeess.SP

GRAFT-EEG: Gauge-Aware Physical Field Transport for Cross-Dataset Motor-Imagery EEG

Ying Zhou, Mengting Liu

Cross-dataset EEG decoding often treats montage, reference, and active-sensor changes as representation shift, although they also alter the observation operator. We study target-statistics-blind transfer: fitting receives no target signal, label, or empirical statistic, and electrode coordinates only instantiate a fixed prediction operator. method removes the active-set common-reference gauge and transports each native mask through a template motor leadfield. A source-fitted spectral classifier…

arXiv → PDF
cs.LG

ThetreStageAI: Multi-View Retrieval-Augmented Generation for Structured Bengali Theatre Production Planning

Md. Mehedi Hasan Naeem, Mst. Kamrunnahar Ruma, Shakila Sultana, Nafiza Anjum, Nasreen Jannatun Nemu, Md. Sujan Ali

Staging a theatre performance requires coordinating dialogue, actor movement, stage directions, lighting focus, cue timing, and equipment constraints within the same production plan. This work presents ThetreStageAI, a retrieval augmented framework for structured Bengali theatre production planning. Rather than retrieving from one mixed corpus, the system maintains separate scene, actor-blocking, and lighting views. Bengali text is embedded with BGE-M3 and indexed in view-specific Qdrant collect…

arXiv → PDF
cs.AI

GEMS: Molecular Structure Elucidation as Learned Search over Isomer Graphs

Utku Umur Acikalin, Yingheng Wang, Goncalo J. Gouveia, Tyler J. Schwertfeger, Frank C. Schroeder, Carla P. Gomes

Identifying small-molecule structures from molecular formulas and tandem mass spectra remains a bottleneck in untargeted metabolomics and natural-product discovery. Even when database retrieval or de novo prediction misses the exact structure, the resulting candidates can provide starting points for exploring nearby structures through a few bond edits. We introduce GEMS (Guided Editing of Molecular Structures), which refines candidates through learned 2-switch bond edits that preserve the molecu…

arXiv → PDF
cs.LG

The Sign Code: The Hidden Binary Nature of Deep Networks

Niclas Göring, Shuofeng Zhang, Roi Holtzman, Yoonsoo Nam, Ard A. Louis

Every neuron in a trained network outputs a number that can be separated into its sign (positive or negative) and its magnitude (absolute size). We call the set of all neuron signs the \textit{sign code}. This raises a key question: does classification depend more on the sign code or on the magnitudes? For overparameterized vision classifiers with sign-preserving activations, the answer is overwhelmingly the sign code. A $k$-nearest neighbor classifier operating only on this binary sign code ach…

arXiv → PDF
cs.ROcs.AI

Beyond Action Prediction: Learning Search-Free Planning in Latent Space

Guanchen Du, Jinhao Du, Yanpeng Sun, Shan Zhang, Na Zhao, Zechao Li

Latent world models learn action-conditioned state transitions in a compact representation space, providing a predictive model for visual planning and control. However, planning with these models typically requires costly test-time optimization over action sequences. We propose to replace this online search with a goal-conditioned inverse model that directly predicts actions from current and goal observations. A key challenge is that action prediction alone neither ensures that goal representati…

arXiv → PDF
cs.CLcs.LG

Trajectory-Triggered Sparse Collaborative Decoding

Amit Ranjan Trivedi, Sruthikesh Surineni, Kyong Ho Lee, Mohit Mittal, Steven Li, Rex Hill

Dense assistance methods such as speculative decoding repeatedly verify draft tokens with a target model, keeping target computation coupled to generation. We study sparse collaborative decoding, where a draft model generates most tokens and a target model is invoked only for short corrective segments. The key problem is deciding when to call the target. We show that local uncertainty is a weak trigger: entropy, negative log-likelihood, logit margin, top-$k$ mass, and velocity features give near…

arXiv → PDF
cs.CLcs.AI

SIT-Eval: Situation-Based Interactive Turn-by-Turn Evaluation of Conversational Agents

Ravil Mussabayev, Saveliy Zavertyaev, Dmitriy Parpulov, Andrey Savchenko

The rapid proliferation of conversational AI agents necessitates evaluation methods that assess performance across diverse dialogue scenarios, utilizing multiple situational criteria, as appropriate behavior depends on context and encompasses various aspects. Existing dialogue benchmarks typically use static natural conversations, which underrepresent rare situations---a critical safety gap, as low-probability events become frequent failures at production scale. However, limited sample sizes for…

arXiv → PDF
cs.LG

How Many, but How Sure? Class Competition as a Confidence Proxy in Multi-Class Density-Based Counting

Villanelle O'Reilly, Georgios Leontidis, Marc Hanheide

Multi-class density estimators can count objects in crowded scenes, but their class-wise outputs offer no indication of how reliably density mass has been allocated. We introduce a training-free confidence proxy based on local competition between the strongest class channels. The resulting prominence measure requires only the predicted density maps, with no retraining or access to model internals. We test whether residual competition is diagnostic of cross-class leakage by attenuating contested…

arXiv → PDF
cs.CVcs.CL

Not Every Mention Is a Claim: Rethinking Object Hallucination Detection in Vision-Language Models

Hsin-Ling Hsu, Neeraja Kirtane, Kuan-Hao Huang

Object hallucination in vision-language models (VLMs) is usually measured by checking each object a caption names against the image. Most benchmarks and detectors alike treat every object mention as a claim that the object is present. This assumption fails when a caption names an object without asserting it, as in "a bench for people to sit on", which mentions people without claiming that any are in the image. We call such mentions non-assertive. Treating them as hallucinations inflates the erro…

arXiv → PDF
cs.CV

ADA 2025: A Multimodal Dataset for Water-Deficit Stress Detection in Sugar Beets

Piper Powell, Robert Franz, Amos Smith, Isaak Ihorst, Joachim Hertzberg, Martin Atzmueller

Research and development into artificial intelligence (AI) and machine learning (ML) applications in crop management are hindered by a lack of suitable public datasets. Whereas applications in disease and pest detection benefit from a comparatively higher amount of available data, applications like water-deficit stress detection often have very few if any public datasets available. Moreover, most datasets that are available are single-modality and frequently RGB-only, leaving the early detection…

arXiv → PDF
cs.LGphysics.app-ph

When Magnitude Suffices: Reconstructing Time-Domain-Gated Microwave Signals Without Phase on a Thoracic Phantom

Maciej Cichoń, Patrycja Gołaś, Maksymilian Bartosik, Angelika Walczak, Agata Bielecka-Dąbrowa, Maciej Ślot

Time-domain gating separates the arrivals that form a microwave S-parameter measurement. It requires the measurement of complex values, so this application almost always uses a vector network analyzer (VNA). We show that, on one calibrated measurement configuration, the gated magnitude the VNA would give can be reconstructed from a magnitude-only sweep of a spectrum analyzer with a tracking generator (SA). We select the gate center for separability of the measured states, correct each instrument…

arXiv → PDF
cs.CV

Learning to Discriminate Scene Structures Makes Self-Supervised Depth Learning Scalable

Mengtan Zhang, Yuchuan Cui, Yu Ma, Zizhan Guo, Wei Ye, Rui Fan

Self-supervised monocular depth estimation is appealing for its potential to scale with unlabeled data, yet existing methods often degrade when trained on diverse scenes. This study finds that, under self-supervision, models tend to encode dataset-specific structural biases rather than transferable scene geometry, leading to cross-domain optimization conflicts. To address this issue, this study proposes the MaSS framework, aiming to make self-supervised depth learning scalable to diverse data. M…

arXiv → PDF
cs.AI

From Trajectories to Differentiated Skills: Cognitive Differentiation for Self-Improving Agents

Yewei Zhao, Derong Xu, Wei Chen, Yin Xu, Peilun Zhou, Xiaohan Wang, Guojun Yin, Wei Lin et al.

Large language model (LLM) agents tackle complex tasks through reasoning and interaction with external environments. Agent skills provide persistent, transferable capabilities that guide task planning, inform contextual decisions, support tool use, and enable executable procedures. Yet existing skill-evolution methods largely organize knowledge around skill artifacts, overlooking the functional heterogeneity within individual skills and its implications for knowledge maintenance and use. Inspire…

arXiv → PDF
cs.AI

RL-Guided Temporal Localization for Dual-Channel Retrieval in Long-Horizon Agent Memory

Dabin Sheng, Zhe Wu, Jinming Zhao, Junliang Xing, Yuanchun Shi

Time-aware retrieval is crucial for long-horizon LLM agents to effectively leverage ever-growing long-term memory. Existing methods focus on lexical or semantic similarity, leading to target memories being crowded out by temporally mismatched yet semantically similar candidates. Even time-aware approaches inject temporal cues only during memory organization or answer generation, overlooking temporal constraints at the retrieval stage, where candidate selection occurs - the root cause of the disp…

arXiv → PDF
cs.LGcs.CGstat.ML

Boundary Detection for High-Dimensional Point Clouds

Abigail Hickok, Valerio Galanti, Osama Al Dalahmah, Andrew J. Blumberg

We introduce two new methods for boundary detection in high-dimensional point cloud data, intended to work in situations with non-uniform density, high ambient dimension, and substantial noise. Our first method fits a separating hyperplane on local neighborhoods after doing local dimension reduction---this method works best when one can reliably estimate the intrinsic dimension of the data. Our second method measures the directional uniformity of local neighborhoods, and has the best overall per…

arXiv → PDF
cs.CV

SemPurify: Semantics-Aware Data Purification for Black-box Backdoor Defense

Jiawei Yu, Syed Irfan Ali Meerza, Yi Wu, Amir Sadovnik, Jian Liu

Backdoor attacks have emerged as a critical security threat in machine learning, where adversaries embed triggers within poisoned training samples to manipulate a model's predictions on targeted inputs while leaving its general behavior unaffected. This stealthy nature makes backdoor attacks difficult to detect, as the model functions normally until activated by a specific malicious trigger. Current purification-based defenses use image transformations (e.g., blurring) to disrupt trigger pattern…

arXiv → PDF
cs.CVcs.CL

Enhancing RAG-based Medical VQA with Gated Multimodal Representations

Daniela Jimenez-Pano, Hugo Jair Escalante, Delia Irazú Hernández-Farías

Medical Vision-Language Models (Med-LVLMs) have shown strong performance in Medical Visual Question Answering (MVQA), yet they may still produce factually inconsistent responses. Retrieval-Augmented Generation (RAG) can mitigate this issue by incorporating external clinical evidence; however, retrieval is often guided by a single modality, potentially overlooking the joint semantics of medical images and clinical questions. We introduce a multimodal RAG framework that learns a joint query repres…

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 →