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

Expanding the Lexicon of Ge'ez Based African Languages: A Comparative Study of Amharic and Tigrinya

Hailay Kidu Teklehaymanot, Debela Desalegn Yadeta, Wolfgang Nejdl

Multilingual pre-trained language models (PLMs) exhibit degraded performance on low-resource, non-Latin-script languages, driven by high out-of-vocabulary (OOV) rates and excessive subword fragmentation that result from Latin-script-centric tokenizer training. We introduce VEXMLM, a vocabulary-extended variant of XLM-R targeting the two highest-resource Ge'ez-script languages, Amharic and Tigrinya, and further evaluated on 17 additional low-resource African languages (19 total). We train a langu…

arXiv → PDF
stat.COcs.LGmath.PRstat.ML

Delocalization of bias in unadjusted Hamiltonian Monte Carlo and underdamped Langevin

Yifan Chen, Xiaoou Cheng, Jonathan Niles-Weed, Jonathan Weare

Unadjusted samplers such as unadjusted Hamiltonian Monte Carlo and underdamped Langevin are well-known to be biased. Metropolis--Hastings adjustment has been conventionally incorporated into Hamiltonian Monte Carlo to eliminate the bias. However, this adjustment can significantly increase the iteration complexity due to the small step size required for reasonable Metropolis acceptance rates. In this work, we extend the \emph{delocalization of bias} phenomenon, previously established for the over…

arXiv → PDF
cs.LGcs.RO

BadWAM: When World-Action Models Dream Right but Act Wrong

Qi Li, Xingyi Yang, Xinchao Wang

World-action models (WAMs) are emerging as a promising foundation for embodied control: rather than predicting actions alone, they learn representations that couple action generation with future world prediction. This coupling is often viewed as a source of robustness, interpretability, and safety, as a robot's action can in principle be checked against its imagined future. In this paper, we show that this assumption is fragile. We introduce BadWAM, a unified framework for modeling and evaluatin…

arXiv → PDF
cs.SEcs.AI

MM-IssueLoc: A Controlled Benchmark for Evaluating Visual Evidence in Multimodal Repository-Level Issue Localization

Shaoxiong Zhan, Shi Hu, Boyu Feng, Hai Lin, Andrew Gong, Zhengda Zhou, Jiaying Zhou, Yunyun Hou et al.

Real repository issues routinely include visual evidence such as screenshots, error dialogs, rendered UI states, and logs, yet repository-level issue localization is evaluated mostly as a text-only task. Existing multimodal SE benchmarks evaluate end-to-end repair, entangling localization with patch synthesis and obscuring whether visual input helped, hurt, or was ignored. We introduce \textbf{MM-IssueLoc}, a controlled benchmark and evaluation protocol for repository-level localization with vis…

arXiv → PDF
cs.AIcs.HCcs.MAcs.MM

Self-Evolving Human-Centered Framework for Explainable Depression Symptom Annotation

Hoang-Loc Cao, Van Pham, Truong Thanh Hung Nguyen, Phuc Truong Loc Nguyen, Phuc Ho, Veronica Whitford, Hung Cao

Annotation quality is a major bottleneck in building reliable and explainable artificial intelligence (XAI) systems for mental health research. In depression-related datasets, labels are often assigned without structured evidence, symptom-level justification, or traceable alignment with the criteria of the Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition, Text Revision (DSM-5-TR), limiting both transparency and downstream model interpretability. We propose a self-evolving, ex…

arXiv → PDF
cs.CLcs.AIcs.LG

Mask-Aware Policy Gradients for Diffusion Language Models

Haran Raajesh, Kulin Shah, Adam Klivans, Philipp Krähenbühl

Reinforcement learning has proven effective for improving reasoning in large language models, but extending it to Masked Diffusion Language Models (MDLMs) remains challenging due to the intractability of the log-likelihood estimation. Existing approaches approximate this log-likelihood by modeling only the token predictions, ignoring the order in which positions are unmasked during generation. We observe that MDLM generation involves two decisions at each step: what tokens to place at each maske…

arXiv → PDF
stat.MLcs.AIcs.LG

Subjective Risk Decomposition: A New View for Uncertainty Quantification

Raghad Alamri, Michele Caprio, Gavin Brown

We present a novel viewpoint for uncertainty quantification. Uncertainty measures are not primitives, in need of axioms and argumentation, but instead consequences, of higher-level modelling decisions. We show how epistemic and aleatoric uncertainty measures can be derived via decomposition of a subjective risk, based on a strictly proper loss. Reverse cross-entropy provides a prominent example, where decomposition recovers the classic information-theoretic uncertainty terms. The same approach r…

arXiv → PDF
cs.AI

Plover: Steering GUI Agents through Plan-Centric Interaction

Madhumitha Venkatesan, Shicheng Wen, Jiajing Guo, Jorge Piazentin Ono, Liu Ren, Dongyu Liu

Graphical user interface (GUI) automation remains challenging in real-world environments, where dynamic layouts, unexpected dialogs, and evolving interface states can cause autonomous agents to drift from user intent. Recent vision-based multimodal agents improve flexibility by operating directly over screenshots and natural language instructions, but planning and adaptation often remain internal, limiting users' ability to inspect, supervise, or correct system behavior. We present Plover, a pla…

arXiv → PDF
cs.AI

Can We Trust Item Response Theory for AI Evaluation?

Han Jiang, Sunbeom Kwon, Jinwen Luo, Ziang Xiao, Susu Zhang

AI benchmarks increasingly leverage item-level statistical models, particularly item response theory (IRT), to estimate model capabilities, rank systems, select informative examples, and diagnose benchmark quality. However, AI benchmark data often departs from the data regime of human testing, for which standard IRT estimation tools were originally developed: benchmarks typically involve fewer evaluated models, far more items, and capability distributions that may be skewed, clustered, or multim…

arXiv → PDF
cs.LGeess.SY

RTS Smoother-Guided Learning of Physics-Based Neural Differential Models

Ahmet Demirkaya, Georgios Stratis, Tales Imbiriba, Zachary D. Danziger, Deniz Erdogmus

Ordinary differential equations (ODEs) are widely used to model dynamical systems in physics, biology, neuroscience, and physiology, but in many applications some equations of the dynamics are unknown and only a subset of the state variables are measured. We propose a hybrid neural--physics framework in which the known components of the ODE are kept explicit and the missing components are represented by a neural network. The proposed method consists of two stages where we alternate between state…

arXiv → PDF
cs.CLcs.AI

T^2MLR: Transformer with Temporal Middle-Layer Recurrence

Ziyang Cai, Xingyu Zhu, Yihe Dong, Yinghui He, Sanjeev Arora

Transformer reasoning is limited by autoregressive decoding, which repeat edly compresses rich hidden computation through token space and makes it difficult for intermediate reasoning states to persist across time. We in troduce Transformers with Temporal Middle-Layer Recurrence (T2MLR), a transformers-based latent reasoning architecture that fuses a cached middle layer representation from the previous token directly into an earlier layer of the current token position, enabling abstract intermed…

arXiv → PDF
cs.AIcs.CLcs.HC

Benchmarking Multimodal Large Language Models for Scientific Visualization Literacy

Patrick Phuoc Do, Chau M. Ta, Chaoli Wang

Multimodal large language models (MLLMs) are increasingly used to interpret visualizations, yet current evaluations remain largely chart-centric and provide limited evidence of understanding of scientific visualization (SciVis). We benchmark six MLLMs on the scientific visualization literacy assessment test, a standardized SciVis literacy assessment comprising 49 items based on 18 scientific visualizations and illustrations, spanning 8 techniques and 11 task types. We evaluate three closed-sourc…

arXiv → PDF
cs.CL

Linear representations of grammaticality in neural language models

Jane Li, Najoung Kim

Whether neural language models (NLMs) possess the ability to distinguish strings on the basis of their grammaticality remains a debated topic in the computational linguistics literature. Existing evidence has largely relied on probability-based measures, testing whether models assign higher probabilities to grammatical than ungrammatical strings. However, probability comparisons have been criticized as a measure for grammatical knowledge based on the assumption that grammaticality is inherently…

arXiv → PDF
cs.AIcs.CL

MedFailBench: A Clinician-Built Open-Source Benchmark for Medical AI Safety Boundary Inspection

Goktug Ozkan

Most medical AI benchmarks measure whether a model knows the correct answer. MedFailBench asks a different question: which safety boundary failed? We present a clinician-built synthetic benchmark and failure atlas that labels medical AI errors by severity (1--5) and safety gate type (missed urgent escalation, unsafe remote dosing, unsafe discharge reassurance, evidence fabrication, unsafe protocol execution, source support gap). The current public release (v0.2.1) contains 44 clinician-reviewed…

arXiv → PDF
cs.AIcs.CY

The Industrialization of Research ; On AI-Driven Science and Its Consequences

Emmanuel Jeannot

Artificial intelligence is transforming scientific research -- not merely as a more powerful instrument, but as an autonomous participant in the research cycle itself. This transition constitutes, in the most precise sense of the term, the industrialization of research: a shift from a craft model, in which knowledge, method, and judgment are embedded in the researcher, to a pipeline model, in which these steps are decomposed, automated, and supervised. The US Department of Energy's Genesis Missi…

arXiv → PDF
cs.ROcs.AI

Scaling Behavior Foundation Model for Humanoid Robots

Weishuai Zeng, Kangning Yin, Xiaojie Niu, Shunlin Lu, Weixiang Zhong, Jiahe Chen, Feiyu Jia, Xiao Chen et al.

Humanoid control requires natural whole-body coordination, precise real-time responses to control signals, and robust generalization across diverse environmental contexts, making it a cornerstone for generalist embodied agents. Behavior Foundation Models (BFMs) have recently emerged as a promising solution to address these challenges by leveraging large-scale behavioral data to achieve superior expressiveness, versatility and generalization. However, despite growing interest in scaling BFMs to f…

arXiv → PDF
cs.LGcs.CL

On-Policy Delta Distillation

Byeongho Heo, Jaehui Hwang, Sangdoo Yun, Dongyoon Han

On-policy distillation is an alternative post-training method in reinforcement learning that alleviates the constraints imposed by reward models by providing token-level supervision from a teacher model. Although on-policy distillation has been studied and applied across various settings, its fundamental design remains underexplored. In this paper, we introduce a new distillation reward, termed the delta signal, instead of directly imitating the teacher's output distribution. The delta signal is…

arXiv → PDF
cs.CLcs.CY

Grokipedia vs Wikipedia: An LLM-Based Audit of Political Neutrality along Ideologies

Filippos Vlahos, Guillaume Bied, Tijl De Bie

Online encyclopedias shape political opinion and, through it, democratic discourse. In late 2025, Grokipedia was released, an encyclopedia written entirely by the LLM Grok. One motivation behind the project was to provide an unbiased alternative to Wikipedia, which has faced accusations of "left-wing" and "liberal" bias. But does an encyclopedia written by an LLM deliver greater neutrality, or does it simply embed a different ideology? We conduct a large-scale political bias study on Grokipedia…

arXiv → PDF
cs.AIcs.LG

Concept-Guided Spatial Regularization for World Models in Atari Pong

Yukuan Lu, Zaishuo Xia, Weyl Lu, Yubei Chen

World models are usually evaluated as components of model-based reinforcement learning (MBRL) systems, while the world models themselves are rarely studied in isolation. We examine five representative visual world-model agents in Atari Pong: DreamerV3, DIAMOND, TWISTER, Simulus, and STORM. After reproducing their training pipelines and matching the reported agent performance, we freeze the learned world models and evaluate them with a closed-loop rollout diagnostic: a policy trained separately f…

arXiv → PDF
cs.CV

Ray-based phase error correction for miniaturized DOE projector-based FPP under single-directional hyperbolic projection

Seung-Jae Son, Yatong An, Jae-Sang Hyun

Fringe Projection Profilometry (FPP) systems using miniaturized DOE pro-jectors often suffer from severe phase artifacts due to nonlinear projection characteristics and limited pattern controllability. We propose a ray-based phase error correction framework that models phase artifacts along projection rays from the projector pinhole, incorporating projector geometry without re-lying on image-domain processing or neighboring pixels. A projector pinhole estimation method based on a single-directio…

arXiv → PDF
cs.CV

DAPGNet: Dynamic Adaptive Physics-Guided Graph Diffusion Network for Hyperspectral Image Classification

Pengkun Wang, Weijia Cao, Ning Wang, Xiaofei Yang

Hyperspectral image (HSI) classification requires reliable pixel-relation modeling under spectral variability, mixed pixels, and heterogeneous boundaries. Existing graph-based HSI classifiers usually construct graph topology from spatial proximity, superpixel connectivity, or learned feature affinity. However, the spectral physical prior carried by contiguous bands has limited influence on topology estimation and message propagation. This paper presents DAPGNet, a dynamic adaptive physics-guided…

arXiv → PDF
cs.ARcs.AI

NIFA: Nonlinear IMC enhanced FPGA for efficient ML inference

Jiajun Hu, Ruthwik Reddy Sunketa, Lei Zhao, Archit Gajjar, Luca Buonanno, Aman Arora

Recent FPGAs have improved deep learning (DL) inference efficiency through dedicated tensor blocks and in-BRAM computation. ReRAM-based analog in-memory computing (IMC) pushes efficiency further, offering an order-of-magnitude improvement in compute density and energy efficiency over conventional digital logic by performing vector-matrix multiplication (VMM) directly within the ReRAM crossbar; prior work has integrated such IMC blocks into FPGAs for DL inference. However, conventional IMC design…

arXiv → PDF
cs.LGmath.CT

Learning in Infinitesimal Non-Compositional Sketches

Sridhar Mahadevan

This paper develops a categorical framework -- Learning in Infinitesimal Non-Compositional Sketches (LINCS) -- as the repair of non-compositionality: failures of diagrams to factor through quotient sketches lifted to the tangent category setting. Machine learning problems are specified as sketches: graphs with commutativity conditions $\mathcal D$, limit cones $\mathcal L$, and colimit cocones $\mathcal K$, generalizing the usual scalarization of loss functions or vector space assumptions. Non-c…

arXiv → PDF
cs.AI

Long-Context Fine-Tuning with Limited VRAM

Vladimir Fedosov, Aleksandr Sazhin, Artemiy Grinenko, Frank Woernle

Parameter-efficient fine-tuning reduces model and optimizer memory, but dense attention still makes long training sequences expensive. We combine Hierarchical Global Attention (HGA) with segment-wise backpropagation and tiered KV storage. Only the active segment remains differentiable in VRAM; older KV is detached into RAM or NVMe, and HGA loads a bounded set of exact historical tokens for each query block. On Qwen3-8B with 4-bit QLoRA and PG19, dense training on a 16 GB Quadro RTX 5000 fits 2,0…

arXiv → PDF
cs.CV

QuReC: All-in-One Image Restoration with Query-Specific Guidance and Local-Global Response Calibration

Shen Zhou, Jinghui Zhang, Wenbo Huang, Xuwei Qian, Zhen Wu, Guangwen Peng, Zhiyuan Li, Ding Ding et al.

All-in-one image restoration aims to recover clean images degraded by multiple corruption types using a single unified model. Existing methods typically rely on image-level prompts or shared guidance to handle diverse degradations. However, such a paradigm becomes inadequate when degradations are spatially heterogeneous or even coexist in mixed forms within a single image. Yet spatially adaptive guidance alone is not sufficient, since accurate restoration also requires each spatial query to reli…

arXiv → PDF
cs.CLcs.AIcs.MA

Digital Pantheon: Simulating and Auditing Coalition Formation with LLM Agents

Dylan Van Mulders, Matthias Bogaert, Dirk Van den Poel

The formation of political coalitions is a complex negotiation driven by both concrete policy objectives and deep-seated ideological convictions. While Large Language Models (LLMs) open new avenues for computational political science, the neutrality and helpfulness biases instilled by Reinforcement Learning from Human Feedback (RLHF) prevent them from sustaining steadfast partisan behaviour. We present a multi-agent framework that reconciles factual grounding with ideological alignment by combin…

arXiv → PDF
cs.CVcs.LG

AlphaWiSE: Adaptive Weight Interpolation for Continual Multimodal Representation Learning

Sarthak Jain, Qiran Hu, Zhen Zhu, Yaoyao Liu

Multimodal models such as CLIP learn a shared embedding space for cross-modal retrieval, but continual adaptation to sequentially arriving data can disrupt the cross-modal alignment acquired from earlier phases. Conventional continual-learning methods return a single checkpoint, which commits every retrieval direction to the same stability-plasticity trade-off. We propose AlphaWiSE, a post-hoc weight-space interpolation method that composes two frozen source checkpoints. For each aligned paramet…

arXiv → PDF
cs.CL

Rubrics on Trial: Evolving Rubrics from a Single Query via Synthetic Pairwise Evidence

Haocheng Yang, Licheng Pan, Xiaoxi Li, Zhichao Chen, Zhiheng Zhang, Yuan Lu, Haoxuan Li, Hao Wang et al.

Rubrics provide structured, fine-grained signals for training and evaluating large language models (LLMs). Yet reliable query-specific rubrics are difficult to construct. Existing approaches often derive supervision from human-written rubrics, preference data, or sampled responses. Direct query-to-rubric generation avoids these resources, but provides no explicit check that a plausible rubric is useful. Such a rubric may fail to distinguish answer quality, reward an optional style, or penalize a…

arXiv → PDF
cs.CV

Quantifying Training Membership Information in the Hyperspherical Embedding Geometry of Face Recognition Models

Ünsal Öztürk, Sébastien Marcel

Face recognition models represent each face as an embedding vector on the unit hypersphere by clustering embeddings of the same identity while pushing different identities apart through angular-margin losses. Because these losses act only on training identities, non-member identities may form clusters with different geometric properties. In this paper, we quantify the magnitude of this difference and what training-time factors control it. We compute four statistics based on cluster geometry acro…

arXiv → PDF
cs.CVcs.AIcs.IR

Towards Hierarchical Structure Understanding of Newspaper Images

William Mocaër, Solène Tarride, Thomas Constum, Merveilles Agbeti-Messan, Tom Simon, Clément Chatelain, Stéphane Nicolas, Pierrick Tranouez et al.

Understanding newspaper images remains a challenging task due to their complex, nested hierarchical structures and dense, heterogeneous layouts. In this paper, we explore two complementary approaches for newspaper structure understanding. First, we present a modular bottom-up pipeline that combines state-of-the-art open-source models: YOLO for layout detection, LayoutReader for reading order prediction, and a custom algorithm for article segmentation. This approach leverages existing robust comp…

arXiv → PDF