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.CL

MuninAI: A Self-Hosted Agentic Framework for Independent Research Groups

Markus Fischer, Jens Meiler, Matthias Elgeti

Research groups that want a language model grounded in their own literature face a choice between hosted services that receive their unpublished work and self-hosted deployments that keep the data local but give the model no access to the corpus. Munin is an open-source framework for a self-hosted scientific assistant that indexes a group's corpus and its citation graph, and wraps whichever open-weight model the group can serve in an agent harness with specialised reading, search, and computatio…

arXiv → PDF
stat.MLcond-mat.dis-nncs.LG

Towards optimal selection schedules for online active learning

Hugo Cui, Francesca Mignacco, Francesco Mori

We consider the problem of online linear classification, where a stream of unlabeled samples is available, and annotation is costly. We investigate the optimal query policy, that prescribes whether and when a sample should be labeled and used for a training step, or instead discarded, so as to minimize a given objective. We focus on the realizable case, under Gaussian design, in the high-dimensional regime where data dimension and number of unlabeled samples grow proportionally. We consider two…

arXiv → PDF
cs.CV

TAN: A Size- and Form-Adaptive Masked-Convolution Encoder for Tissue Graphs

Jan Herschel, Anselm von Gladiss

Tissue graphs represent histology images as graphs over tissue-conforming superpixels, which keeps homogeneous tissue regions intact instead of cutting them into rectangular patches. To embed superpixels, current encoders crop them to bounding boxes and then pad, resize, or mask them, so background or fill values can leak into the node features. This matters in practice, and especially in medical imaging, where a prediction should depend on the tissue and not on an arbitrary preprocessing choice…

arXiv → PDF
cs.IRcs.AIcs.LGcs.NE

QD-Rec: Open-Ended Evolution of Recommendations via Quality-Diversity

Takashi Ishida, Taro Makino, Issa Sugiura

Open-ended search combined with foundation models has produced advances such as faster algorithms, new results on open mathematical problems, and self-improving agents. We extend this paradigm to recommendation for decision-making, focusing on decisions where the set of possible choices is fixed but the reasons for choosing them are not. In high-stakes decisions, e.g., which company to acquire or which customer to target, comparing diverse, well-reasoned options can be more useful than a single…

arXiv → PDF
cs.CV

When Evidence Vanishes: Distilling Visual-Evidence Dependency in Medical Vision-Language Models

Qizhen Lan, Yiling Ma, Ruiqi Chen, Mengchen Fan, Xi Xiao, Lin Zhao, Liang He, Baocheng Geng et al.

Compact medical vision-language models (VLMs) can answer clinical questions correctly without reliably using the image, relying instead on question wording or learned priors. Standard knowledge distillation copies a teacher's answer preference on the original image, but it leaves unchecked whether that preference is conditional on the visual evidence required by the question. We study this missing target as medical visual evidence dependency: support for the correct answer should decrease when t…

arXiv → PDF
cs.SIcs.CEcs.CYcs.ETcs.LG

Graphlet-based Decentralized Finance Transaction Method Classification

Célestin Coquidé, Alessio Brini, Natkamon Tovanich

Decentralized Finance (DeFi) transactions involve complex interactions among accounts, smart contracts, and tokens. We investigate whether network topology can identify transaction methods that describe DeFi operations. We extract directed graphlet features to classify the 30 most frequent methods. Our results show that graphlet features complement event log counts in improving classification performance. Using SHapley Additive exPlanations (SHAP), we further derive model explanations that revea…

arXiv → PDF
cs.AI

S-GAP: Stealthy Graph Attack Primitives for Graph Large Language Models

Wenda Li, Tongya Zheng, Shunyu Liu, Hanyang Yuan, Kaixuan Chen, Yu Wang, Yuchen Ying, Haoze Jiang et al.

Graph Large Language Models (GraphLLMs) enable powerful semantic understanding and reasoning over Text-Attributed Graphs (TAGs), while their semantic reasoning may exhibit vulnerabilities to perturbations in node text and graph structure under adversarial attack evaluation. Existing attacks typically construct textual and structural perturbations in separate stages guided by distinct realization intents. However, this separation results in attack-intent fragmentation, causing semantic incoherenc…

arXiv → PDF
cs.CL

A low-dimensional dynamical basis for tongue shape control

Sam Kirkham, Patrycja Strycharczuk

Speech production involves the control of a high-dimensional articulatory system with many degrees-of-freedom, but a widespread hypothesis is that speakers navigate this complexity using a set of lower-dimensional control variables. Common candidates for these control variables include individual articulators (e.g. tongue body) and abstract tract variables (e.g. tongue body constriction location), but identifying the most appropriate coordinate system for articulatory control remains an open que…

arXiv → PDF
cs.CLcs.LG

HydraLLM: Adaptive Width Slicing for Elastic Text and Vision-Language Models

Oscar Kemme, Janek Haberer, Ali Hojjat, Olaf Landsiedel

LLMs and LVLMs are increasingly deployed across heterogeneous hardware, ranging from data-center GPUs to resource-constrained edge devices. Their fixed-size architectures limit the ability to reuse a single model across deployment settings with different compute, latency, and model-size targets. We introduce HydraLLM, an elastic MQA-based architecture. Its number of active attention heads determines the effective widths of the embeddings, attention projections, feed-forward layers, and the outpu…

arXiv → PDF
cs.CV

TriINR: Unsupervised Atmospheric Turbulence Mitigation with Triple Implicit Neural Representations

Yuka Ogino, Rikuto Otsuka, Yuho Shoji, Takuya Ogawa, Takahiro Toizumi, Atsushi Ito

Atmospheric turbulence degrades image quality in long-range imaging. The degradation is generally modeled with two spatio-temporally varying components, tilt and blur. Recent unsupervised turbulence mitigation methods have demonstrated the effectiveness of representing a sharp image as an implicit neural representation (INR). However, their tilt and blur representations remain frame-dependent, and the number of optimization parameters grows with the number of input frames. To address this limita…

arXiv → PDF
cs.LG

Predictable Scaling: Efficient Model Exploration via Scaling-Law Prediction

Aishwarya Wesanekar, Sheng-Tao Yang, Jiawei Zhang, Flavio Sales Truzzi, Chen Chen, Nader Beigiparast, Shengyuan Huang, Roshanak Zilouchian Moghaddam et al.

Evaluating candidate changes (hypotheses) to recommendation models requires full-scale training runs consuming thousands of GPU-hours, severely limiting the hypothesis space engineers can feasibly explore. We introduce Predictable Scaling (PS), a systematic framework that exploits empirically verified regularity conditions to predict full-scale model performance from small-scale proxies. PS constructs scaled-down variants via composable scaling functions along distinct resource axes, and project…

arXiv → PDF
cs.AI

GatewayBench: Unified Capability and Security Evaluation Platform for MCP Gateways

Yitian Zheng, Zhaorun Chen, Haoyu Li, Bo Li

AI agents have increasingly interacted with external environments by invoking tools, with Model Context Protocol (MCP) emerging as a standard interface for connecting agents to heterogeneous tools and services. As organizations deploy agents at scale, MCP gateways have become a critical middleware layer for aggregating, governing, and shaping the tool surface exposed to agents. Despite the growing importance of MCP gateways in agentic systems, no prior work has systematically studied how gateway…

arXiv → PDF
cs.LG

Regularized free deconvolution for spectral repair of resampling distortion in high-dimensional particle filters

Deming Song, Chi-Kin Lam, Kefeng Li, Hui Yu, Xilin Li, Huagang Lin

Resampling is the standard remedy for weight degeneracy in particle filters, but in high dimensions it distorts the spectrum of the ensemble covariance in a way that is computable from the importance weights. This paper studies the inverse problem: recovering the pre-resampling spectrum from the observed weights and the empirical spectrum alone, and using it without biasing the filter. We first show that the forward spectral law extends to random importance weights once one conditions on the wei…

arXiv → PDF
cs.SIcs.CL

"You" Is Not Toxic: How LLM Labelers Rewrite the Web's Conversation Laws

Liang Yue, Eric A. Vance

What the Web community believes about toxic conversations, such as that toxicity rises in longer and deeper threads, was measured mostly with Google's Perspective API, which is shutting down; large language models (LLMs) will make the next measurements. We find that LLM labelers mistake second-person address for toxicity, and that this one bias manufactures laws that human labels do not show. On 1.25 million news comments with crowd labels, Claude Haiku flags 12% of the non-toxic comments that c…

arXiv → PDF
cs.LGcs.AI

RECREG: Recovery-based Shielding for Regular Safety Properties in Reinforcement Learning

Alexander W. Goodall, Francesco Belardinelli

In many real-world scenarios we need to consider formal requirements, such as safety and constraint compliance, to deploy Reinforcement Learning (RL) agents. In this paper we introduce RecReg, a safe RL framework capable of enforcing non-Markovian regular safety properties via recovery-based shielding. RecReg is a unified approach that supports different levels of a priori knowledge and safety guarantees. The paper primarily focuses on building the theoretical foundations for RecReg in the tabul…

arXiv → PDF
cs.AIcs.CL

ScoutRoute: Efficient Mixture-of-Experts Routing Using Internal Language Model Signals

Rajdeep Pandhare, Delzaan Bharucha

Efficient expert routing is a fundamental challenge in Mixture-of-Experts (MoE) systems, particularly for heterogeneous collections of independently trained Large Language Mod els (LLMs). Existing routing approaches typically rely on jointly trained gating networks, prompt-based predictors, or computationally expensive multi-model inference, limiting their flexibility and efficiency. This paper presents ScoutRoute, a lightweight post-hoc routing framework that predicts expert competence using in…

arXiv → PDF
cs.CV

ShadowCast: On-the-Fly Context-Aware Shadow Augmentation for Remote Sensing Image Segmentation

Yechan Kim, Dongho Yoon, Jongmin Joo, JongHyun Park, Moongu Jeon

Shadows cast by elevated objects alter the spectral appearance and obscure the boundaries of objects in remote sensing images, thereby degrading semantic segmentation performance. Most existing approaches handle shadows as degradations to be detected and removed, requiring additional costs from dedicated networks and shadow-specific annotations. We propose ShadowCast, which takes the opposite approach: it synthesizes shadows and injects them during training for remote sensing segmentation. It ex…

arXiv → PDF
cs.AIcs.LG

Generative Policy Improvement from Observational Data

Jonas Schweisthal, Dennis Frauen, Stefan Feuerriegel, Emma Brunskill

We study how to improve decision policies from observational data to generate better actions when actions are complex, structured objects, such as text messages or images. This task is subject to two major challenges: (i) action-level overlap is often too weak for reliable off-policy evaluation and improvement, and (ii) generating new structured actions often requires expensive training or fine-tuning (e.g., of an LLM) and can be ill-defined due to information loss in action representations. To…

arXiv → PDF
cs.LG

Bridging Compressed Communication and Local Steps via Spectral Method in Federated Learning

Dmitriy Bystrov, George Chirkov, Daniil Medyakov, Dmitry Bylinkin, Aleksandr Beznosikov

Federated Learning (FL) enables collaborative training of complex models across large-scale networks of edge devices while keeping data localized. However, data heterogeneity and high communication overhead remain fundamental bottlenecks. Recently, the spectral optimizer Muon has demonstrated remarkable advantages over Adam-like methods in centralized training. While recent efforts have attempted to transition Muon to FL, naive integrations into traditional architectures fail short. Crucially, e…

arXiv → PDF
cs.CV

Momentum: Persistent Dynamics for Video World Models

Nedko Savov, Stefan Maria Ailuro, Danda Pani Paudel, Yilun Du, Xi Wang, Luc Van Gool

Video world models must capture how a scene evolves beyond the current camera view to generate consistent observations when its content reappears. Existing approaches rely on observation history, static point clouds, or image caches constructed from past frames. These representations are often expensive and, more importantly, cannot update dynamic scene content outside the field of view: generated vehicles and pedestrians may be forgotten after leaving the field of view or reappear in physically…

arXiv → PDF
cs.LG

Residual Stochastic Concept Bottleneck Models

Stephen Marcou, Mateo Espinosa Zarlenga, Sonia Laguna, Moritz Vandenhirtz, Julia E. Vogt, Mateja Jamnik

Concept-based models (CMs) learn human-interpretable intermediate representations that enable users to understand the model's reasoning and steer its predictions through test-time concept interventions. However, in realistic settings, their performance can be limited by concept incompleteness, where the training concepts fail to capture all task-relevant information. Adding an unconstrained residual pathway to the model's predictive process can overcome the consequences of incompleteness. Howeve…

arXiv → PDF
cs.HCcs.CV

mmPencil: Toward Writing-Style-Independent In-Air Handwriting Recognition via mmWave Radar and Large Vision-Language Model

Yifan Guo, Zhu Wang, Qian Qin, Yangqian Lei, Qiwen Gan, Zhuo Sun, Chao Chen, Bin Guo et al.

In-air handwriting recognition based on radio frequency (RF) signals offers a promising solution for human-computer interaction, yet existing methods are often limited by predefined writing planes, constrained writing styles, and small recognition vocabularies. To address these limitations, we propose m^2VLMs, a modality mapping architecture that bridges millimeter-wave (mmWave) radar sensing and large vision-language models (VLMs), and develop mmPencil, a 3D in-air handwriting word recognition…

arXiv → PDF
cs.CV

GeoReason: Bridging Logical Reasoning and Spatial Fidelity in Remote Sensing Segmentation

Cheng Fan, Han Wu, Tingzhang Luo, Minjing Dong, Yehui Tang, Jianyuan Guo

Multimodal Large Language Models (MLLMs) have significantly advanced instruction-driven perception through the "Embedding-as-Mask" paradigm. However, extending this capability to Remote Sensing (RS) reasoning segmentation remains exceptionally challenging under cluttered geographical contexts and extreme scale variations, often leading to Spatial Fidelity Degradation and Target Misidentification. We identify a critical yet underexplored bottleneck: the sequential alienation of the segmentation t…

arXiv → PDF
cs.CV

Can We Use Saliency Maps for the Evaluation of Generative Image Models?

Eleonora Ristori, Luca Bindini, Marco Lippi, Paolo Frasconi

Evaluating generative image models remains challenging, as commonly used metrics depend on fixed pretrained feature extractors optimized for different tasks that do not always align with human realism perception across datasets and model families. To address this limitation, we investigate a human-inspired evaluation framework that avoids representations learned for unrelated tasks. Specifically, we train a generator-specific classifier to distinguish real images from samples produced by a given…

arXiv → PDF
cs.LGcs.DCcs.SD

Flash RNN-T: Memory-Efficient Joint Network and Transducer Loss Computation

Mahmoud Ashraf

The recurrent neural network transducer (RNN-T) remains a practical choice for streaming speech recognition, but training requires large intermediate tensors. We present Flash RNN-T, a joint and loss implementation combining specialized kernels with optional tiled recomputation over the full alignment space and vocabulary. Tiled and untiled Flash form the entire measured throughput-memory frontier on medium and long workloads. On H100, untiled Flash achieves 24-39% higher throughput with 26-56%…

arXiv → PDF
cs.CV

LithoWorld: An Endpoint World Model for Lithography Process-Window Recovery

Botong Zhao, Fang Yu, Xinyuan Chen, Yue Lu

Lithography process drift can move a fabricated pattern outside its process window, producing unqualified scanning electron microscopy (SEM) morphology. We present LithoWorld, an endpoint world model for SEM-guided parameter recovery. Interior representative targets jointly determine qualified reference appearance and correction supervision. A causal predictive branch aligns currentimage features with endpoint representations, while a conditional flow policy generates a two-dimensional correctio…

arXiv → PDF
cs.LGcs.IT

Information Estimation with Discrete Diffusion

Alberto Foresti, Giulio Franzese, Pietro Michiardi

Information-theoretic measures, such as Mutual Information (MI), play a crucial role in understanding non-linear relationships between random variables and are widely used across scientific disciplines. Yet, their use on real-world discrete data remains challenging. Existing methods typically rely on embedding discrete data into a continuous space and apply neural estimators originally designed for continuous distributions. This process requires careful engineering for both the embedding model a…

arXiv → PDF
cs.LGcs.GT

Contracting with an Agent under Model Mismatch

Elif Yılmaz, Jakub Tłuczek, Victor Villin, Christos Dimitrakakis

In the classical principal-agent setting, the principal delegates some task to the agent, who receives a payment conditioned on the outcome of the task, which in turn benefits the principal. To align their objectives, the principal designs a contract that incentivizes the agent to take actions beneficial to the principal. In practice, however, the agent may act under misspecified beliefs about the underlying environment, leading to systematically suboptimal decisions. In this work, we study this…

arXiv → PDF
cs.CL

On the Tip of the Tongue: First-Token Cueing as a Behavioral Probe of Recall Failures in LLMs

Jaewon Sok, Jewon Yeom, Seonghyeon Park, Jeongjae Park, Hwiyeong Lee, Taesup Kim

Large language models often answer factual questions incorrectly in closed-book settings, and such errors are usually attributed to missing knowledge. Yet models often encode answers they fail to produce. We show that many closed-book errors are first-token recall failures: the model commits to a wrong first token, but once given the right one it completes the answer and often recognizes it as correct. We study this with First-Token Cueing, a behavioral probe that prefills the response with the…

arXiv → PDF
cs.ROcs.AI

AWAM: Active Trajectory-Conditioned View Imagination for Robust Robot Manipulation

Jiawei Geng, Zhenyang Liu, Yuzheng Wu, Yanwei Fu

Rapid progress in embodied intelligence has enabled increasingly capable robots to follow language instructions and manipulate diverse objects. However, strong results in structured environments do not automatically transfer to open-world conditions, where clutter, occlusion, and changing viewpoints can obscure the spatial relationships required for action. To address this perceptual gap, a virtual active-perception paradigm is introduced. AWAM, an Active World-Action Model actively plans where…

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 →