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

Anisotropic Representation Dynamics in Transformers

Nguyen Do, My T. Thai

Small differences between internal representations can shrink or grow as they pass through a Transformer layer, affecting how information is preserved and how sensitive the model is to perturbations. Yet it remains unclear when changes in attention weights can turn a representation difference that would otherwise shrink into one that grows. We develop a \textbf{Mixture-Gated Theory of Anisotropic Representation Dynamics} that separates self-attention into value transport, query gating, and key g…

arXiv → PDF
cs.LG

Response-Informed Value Estimation for Cost-Aware Multi-Turn LLM Routing

Haotian Yan, Jiaqi Liu, Bingyi Jing, Tianjun Yao

Multi-turn LLM routing selects a model at every turn before its response is available, yet task success is revealed only when the interaction ends, leaving each intermediate choice without a label of its own. Logged trajectories, however, retain the response each call produced, which exposes what each turn required and how well the chosen model served it, evidence that outcomes alone hide. We introduce RIVET (Response-Informed Value Estimation for Turn-Level Routing), which exploits this post-ca…

arXiv → PDF
cs.CV

Kingfisher: Fast Personalized Visual Autoregressive Generation via Scale-Aware Prompt-Conditioned Scale Decomposition

Dinh-Khoi Vo, Akihiro Sugimoto, Minh-Triet Tran, Trung-Nghia Le

Personalized image generation has been extensively studied in diffusion models, often relying on subject-specific optimization of model weights, textual embeddings, LoRA modules, or adapters. In this work, we explore a different direction for fast personalization in visual autoregressive models. Our key observation is that a short prefix of early autoregressive scale codes is sufficient to strongly determine both object structure and global appearance, while later scales primarily refine the est…

arXiv → PDF
cs.CVcs.GR

X-Splat: Unified Gaussian Splatting for Joint RGB and X-ray 3D Reconstruction

Wangze Xu, Chu Zhou, Mae Yamaguchi, Linrui Dai, I-Chao Shen, Takashi Ijiri, Imari Sato

Jointly reconstructing RGB and X-ray provides new insights by connecting external appearance with internal structure, enabling a more complete understanding of real-world objects than single modality. Yet existing methods train separate models per modality and suffer from redundant geometry, alignment artifacts, and loose coupling that limits cross-modal insight discovery. We propose a unified representation in which all Gaussian primitives share a single set of geometric parameters, with only s…

arXiv → PDF
cs.CL

MultiAgent-OPD: End-to-End Training of Hierarchical Multi-Agent Systems with On-Policy Distillation

Yuhan Sun, Jiaxin Zhao, Yongdong Luo, Yibo Hu, Meiguang Jin, Junfeng Ma, Weixun Wang, Weihang Pan et al.

In a hierarchical multi-agent system, a Leader assigns tasks and subagents carry them out. Jointly training the Leader and the subagents is difficult because a final answer gives only indirect feedback to the subagents. An LLM judge can score the performance of the subagents, but these scores depend on the judge's own assessment of the quality of subagents' responses. We present MultiAgent-OPD, which combines on-policy distillation with reinforcement learning to jointly train a shared-parameter…

arXiv → PDF
cs.CV

RAP: A Dataset for Paper-to-Poster Generation via Declarative Markup from Human-Crafted Exemplars

Haonan Han, Yukang Lin, Minliang Lin, Haoxian Tan, Jun-Yan He, Rui Yang, Zhi-Qi Cheng, Jie Hu et al.

Making a conference poster is visual coding in miniature: an entire paper must be compressed onto a single page, which exercises summarization, visual design, and code implementation at once, using nothing beyond the paper itself. Yet benchmarks for this task in the context of visual coding remain scarce: existing resources are small and annotated only with layout boxes, so evaluation must fall back on VLM-as-judge or human checklists rather than objective render-and-compare, and the generation…

arXiv → PDF
cs.AIcs.LG

Characterising and Analysing Retrieval-Augmented Generation Techniques

Emmanuel Igbekele, Olawande Daramola

The advent of Large Language Models (LLMs) across many application domains has increased the need for Retrieval-Augmented Generation (RAG) to reduce hallucinations and improve LLM performance. Thus far, several RAG techniques with impressive features and capabilities have been proposed in the literature, making it a herculean task to select the most appropriate RAG techniques for specific problem scenarios. Thus, we propose a conceptual framework comprising main dimensions and sub-dimensions for…

arXiv → PDF
cs.CL

ReLaDrift: Recurrent Language Generation via Drifting for Test-Time Scaling

Yuki Otsuka, Daisuke Oba, Naoaki Okazaki

Drifting Models generate a sample with a single function evaluation, making them attractive for fast parallel language generation, but their one-step formulation does not support iterative refinement. We propose Recurrent Language Generation via Drifting (ReLaDrift), which uses a shared Drifting Model to generate an initial draft from noise and iteratively refine it in a continuous latent space. We train this recurrence by sampling the number of rounds and applying the drifting loss only at the…

arXiv → PDF
cs.LG

Process Reward Modeling with Reliability- and Conservatism-Aware Bayesian Belief

Zhongjian Qiao, Zhixiang Zhou, Jiafei Lyu, Peisong Wang, Qiaosheng Zhang, Siyang Gao, Shuang Qiu

Process Reward Models (PRMs) play a central role in test-time scaling for large language model (LLM) reasoning. However, PRMs may provide inaccurate process rewards for test-time scaling, which we identify as arising from two sources of uncertainty: (1) \textit{PRM uncertainty} that arises from insufficient supervision data and imperfect PRM training; and (2) \textit{policy uncertainty} that results from the mismatch between the policy to collect supervision data and the policy for test-time sca…

arXiv → PDF
cs.ARcs.AI

qGAMMA: A Framework for Optimal DNN Mapping on Multi-Precision Accelerators

Leandro Fiorin, Luigi Altamura, Cristina Silvano

This work describes qGAMMA, a flexible framework for exploring and optimizing the mapping of mixed-precision Deep Neural Network (DNN) models onto general-purpose spatial accelerators that support a range of fixed- and floating-point precisions. qGAMMA navigates the design space using a domain-specific genetic algorithm and an analytical performance model based on hardware synthesis results. The framework identifies the optimal mapping and accelerator configuration that minimizes target metrics.…

arXiv → PDF
cs.CV

MLLM Frame Subset Ensembling for Audio-Visual Video QA and MLLM-based Reranking for Ad-hoc Video Search in TRECVID 2025

Andreas Goulas, Damianos Galanopoulos, Ioannis Patras, Vasileios Mezaris

This paper presents the overview of the runs related to the Ad-hoc Video Search (AVS) and Video Question Answering (VQA) tracks of TRECVID 2025 on behalf of the CERTH-ITI team. For the AVS track, we introduce a two-stage framework built on foundation models. In the first stage, multiple vision-language models (VLMs) encode both the input query, augmented through LLM-generated rephrasings, and the candidate video shots, producing weighted similarity scores for initial retrieval. In the second sta…

arXiv → PDF
cs.AI

Not All Test-Time Compute Is Evidence: Model-Specific Bias in LLM Reasoning

Ming Shen, Tianjun Yao

Test-time scaling methods implicitly assume that additional computation from the same model provides independent evidence. We show that this assumption fails within a single reasoning model: errors are correlated across repeated samples, across reasoning depth, and in the model's own self-evaluation, so more compute from the same model is not more evidence. We introduce DIA (Disagreement-triggered Independent Arbitration), which treats disagreement between an intermediate-stage and the final-sta…

arXiv → PDF
cs.CL

MAS-Bai: Linguistically Informed Adaptive Multi-Agent Translation for Bowen-Script Bai

Jingting Zheng, Hong Ren, Yuehan Cui, Shaolin Zhu, Deyi Xiong

Large Language Models (LLMs) remain unreliable for extremely low-resource languages whose writing systems conflict with high-resource pretraining priors. We study Bai-Chinese translation in the Bowen script, where Chinese characters are frequently borrowed phonetically rather than semantically, causing severe literal-translation hallucinations. We propose MAS-Bai, a linguistically informed adaptive multi-agent framework for Bowen-script Bai-Chinese translation. MAS-Bai routes each input through…

arXiv → PDF
cs.LG

Non-Parametric Optimization for Scalable Learning in Stochastic Decision Problems

Mohsen Amidzadeh, Lauri Viitasaari, Mario Di Francesco

Stochastic optimization (SO) plays a central role in decision-making under uncertainty. Among SO problems, time-varying stochastic optimization (TV-SO) is particularly important due to its applications in adaptive control and machine learning. Non-parametric approaches have been proposed for time-varying deterministic optimization; however, they have not been developed for their stochastic counterparts. This work addresses that gap by developing a stochastic variational framework based on Mallia…

arXiv → PDF
cs.SIcs.AIphysics.soc-ph

Validating LLM-generated political networks with survey-reported partisan exposure

Marco Tonin, Michele Tizzoni, Bruno Lepri, Luca Maria Aiello

Large language models (LLMs) are increasingly used to simulate human behavior in social science research, including decisions, interactions, and social relationships. However, in network formation tasks, existing evaluations often focus on aggregate network properties, while networks with plausible structural properties may still fail to reproduce individuals' social and political environments. Here, we generate LLM-based political networks using personas sampled from the nationally representati…

arXiv → PDF
cs.SDcs.AI

Framing Spatial Hearing within the Free Energy Principle: A Hierarchical Model of Perceptual Learning

Roberto Barumerli, Nils Meyer-Kahlen, Lorenzo Picinali

Spatial hearing relies on dynamic internal representations to decode spatial information from ever-changing acoustic conditions. A fundamental example is sound localisation, where listeners infer the direction of an invisible sound. Bayesian inference provides a computational account of such a localisation process; however, modelling efforts are largely limited to static listening scenarios. Instead, the free energy principle (FEP) describes perception, learning, and action as joint minimisation…

arXiv → PDF
cs.AI

FuzzInsight: Navigating the Efficiency-Effectiveness Trade-off in Coverage-Guided DNN Fuzzing

Vivek Vekariya, Fathiyeh Faghih, Alexander Pretschner

Collecting and labeling diverse test datasets for evaluating Deep Neural Networks (DNNs) is costly and time-consuming. This has motivated coverage-guided fuzzing techniques that generate defect-revealing corner cases from limited test data. However, their effectiveness depends heavily on configuration choices, particularly coverage criteria and seed-selection strategies. We present a configuration-oriented analysis and decision guidelines for scalable DNN fuzzing targeting two bottlenecks: ineff…

arXiv → PDF
cs.AI

OfficeTown: Generative Organizations for Evolving Agent Intelligence

Hongchen Wei, Daohong Ying, Zhi Hong, Aidan Wu, Bei Liu, Ruichun Ma, Yifan Yang, Qi Dai et al.

AI agents increasingly use files and software tools to produce professional deliverables. Such work draws on materials, decisions, and feedback accumulated across assignments. We introduce OfficeTown, a generative simulation framework for professional organizations in which tasks and their context arise from continuing organizational work. From a natural-language description of an organization's purpose and activities, OfficeTown initializes an organization whose members coordinate work, delegat…

arXiv → PDF
cs.GTcs.LGecon.TH

Proportionality in Ranking Compression

Daniel Halpern, Xinyu Liu, Evi Micha, Yu Peng Ng, Warut Suksompong

Motivated by applications in reinforcement learning from human feedback, we consider a setting where a given collection of rankings needs to be compressed into a smaller collection of rankings. This can also be seen as a combination of two fundamental social choice frameworks: ranking aggregation and multiwinner voting. We propose three proportionality notions that capture different types of representation in this setting: positional proportionality, pairwise proportionality, and proportionality…

arXiv → PDF
cs.LGcs.AI

LangNCO: Compiling Natural-Language Constraints into Inference-Time Interventions for Neural Combinatorial Optimization

Hironori Ohigashi

Neural combinatorial optimization (NCO) rapidly produces high-quality solutions for problem structures encountered during training, but operational requirements may change after deployment and be communicated in natural language. We propose LangNCO, a framework that compiles instance-specific requirements into structured inference-time interventions for a frozen NCO solver, without changing the pretrained policy's architecture, learned input representation, or parameters. A pretrained LLM serves…

arXiv → PDF
cs.LGcs.AI

A Stronger Teacher Within: Strengthening MoE Models via On-Policy Bidirectional Distillation

Haoyu Chen, Jun Bai, Yang Liu, Jianfei Zhang, Wenge Rong

Reinforcement Learning with Verifiable Rewards (RLVR) has substantially improved Mixture-of-Experts (MoE) LLMs, but its outcome-level rewards provide only sparse supervision. On-Policy Distillation offers dense token-level feedback, yet requires a stronger compatible teacher, while on-policy self-distillation relies on hand-designed privileged information. We observe that the MoE architecture itself offers a way to resolve this dilemma, as increasing the activation budget per token exposes laten…

arXiv → PDF
cs.CL

AMEND: Constraint-Guided Multi-Agent Text Detoxification with Isolated Critics

Tianyu Wang

Text detoxification requires balancing toxicity removal, semantic preservation, and fluency. Existing methods typically optimize an unconstrained scalar objective---enabling safety scores to mask semantic loss---or rely on open-ended iterative debate prone to semantic drift and high computational cost. We propose AMEND, an inference-time framework that decouples detoxification into role-conditioned proposal generation, isolated multidimensional criticism, and constraint-first selection. AMEND ev…

arXiv → PDF
cs.CL

What LLMs Do in the Shadows: Reading Context Reliance from the Unembedding Dark Space

Alexandra Kuleshova, Andrey Volodichev, Daria Kotova, Alexey Zaytsev

Detecting faithfulness hallucinations in large language models (LLMs) is crucial for their safe deployment in high-stakes domains. Recent approaches address this by contrasting contextual against parametric knowledge utilization, yet measuring context reliance typically demands noticeable overhead, such as materializing attention maps, running additional forward passes, or training auxiliary probes. In this work, we show that context reliance can be estimated by projecting hidden states onto the…

arXiv → PDF
cs.LGcs.AIcs.CL

Tree-Aware Posterior Distillation for Long-Horizon Agentic Reinforcement Learning

Heming Zou, Qi Wang, Yixiu Mao, Yun Qu, Yuyi Guo, Zeyuan Liu, Chenglin Li, Weijie Liu et al.

Reinforcement learning with verifiable rewards has become a scalable post-training paradigm for large language models. However, training agents over long-horizon interactions presents two challenges: using only terminal rewards makes turn-level credit assignment sparse and high-variance, while sequential mini-batch updates on a fixed rollout batch introduce policy staleness as the current policy drifts from the behavior policy. Existing approaches obtain denser credit via learned critics, proces…

arXiv → PDF
cs.CL

Do Speech BCIs Need Larger Models? Rethinking Neural Decoding beyond Scaling

Zehui Feng, Weichuan Wang, Xiaohan Chen, Cuntai Guan, Ting Han

Recent speech brain-computer interfaces (BCIs) increasingly rely on large models and complex multi-stage pipelines for neural decoding. However, in speech BCI, where training data are scarce, noisy, and expensive to collect, the benefits of model scaling remain unclear. This work revisits a fundamental question: are large models truly necessary for accurate neural decoding? We propose BEST (Brain-Encoding-Speech-Text), a two-stage framework for efficient neural-to-text decoding. Instead of relyi…

arXiv → PDF
cs.LGcs.GRcs.RO

Structural Affinity: An Algorithm for Coherent Cage-Based Shape Design

Aviraj Newatia, Shengan Yang, Hantao Zhong, Rika Antonova

Cage-based deformation (CBD) parametrises 3D geometry through a small set of control handles, effectively enabling a variety of tasks from animation and interactive modelling to tool-based co-design, neural deformation transfer, and aerodynamic shape optimization. Many optimization approaches relying on CBD employ regularisation strategies to reduce the distortion of the deformed mesh by encouraging smooth, regular cage deformations. These techniques offer soft guidance to an optimization algori…

arXiv → PDF
cs.CV

Knowledge-Guided Distributional Prompt Learning with Visual Hierarchy for Zero-Shot Anomaly Detection

Jiyul Ham, Seongho Yoon, Yonggon Jung, Sangjae Lee, Jun-Geol Baek

Zero-shot anomaly detection (ZSAD) aims to detect anomalies in previously unseen classes using auxiliary images, with applications such as industrial visual inspection and medical imaging. Recent vision-language-model-based approaches improve ZSAD by aligning textual and visual representations, while distributional prompting further models prompt variability for unseen categories. However, existing methods do not explicitly combine normality-referenced distributional modeling with hierarchy-spec…

arXiv → PDF
cs.CL

Chinese Decision: A Family of Language Models for Single-Pass Probabilistic Decision-Making

Qiang Yan

Many language-based applications require probabilities over a finite set of decisions rather than open-ended responses. We present Chinese Decision, a family of Chinese-language models for single-pass probabilistic decision-making. Given context, an instruction, and candidate descriptions, the model extracts final-position candidate-letter logits in one forward pass and normalizes them over valid options, without autoregressive answer generation. A shared interface supports Boolean judgments, ca…

arXiv → PDF
cs.AI

LongForge: Measuring and Improving Long-Context Instruction Data via Evidence-Assertion Reasoning Graphs

Ziyang Chen, Junlong Jia, Xing Wu, Tinghao Yu, Songlin Hu

Existing quality control for long-context instruction-tuning data is a one-shot judgment inside the generation pipeline that leaves only a scalar, revealing neither which document parts an answer uses nor how many reasoning steps it writes down; the data can thus be neither audited nor controlled. We formalize data quality as a property of the alignment structure among document, question, and answer, and build LongForge, which pairs an analyzer that measures long-context data with a synthesizer…

arXiv → PDF
cs.CLcs.AIcs.LG

Explaining Chess and Go in Natural Language

Ori Press, Alexander Golubev

Modern chess engines play far beyond human ability, often choosing moves whose underlying ideas are difficult for humans to understand. We propose an automatic metric for evaluating chess explanations, grounded in chess-engine evaluations. Evaluating state-of-the-art language models using this metric, we find that they perform surprisingly poorly, often relying on surface-level board observations rather than robust, transferable chess concepts. We then introduce BinProp, a training-free method t…

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 →