collaborators

12 papers

cs.CL2026

Scaling Law: Optimizing Multi-Epoch, Multi-Lingual, and Multi-Stage Training for Low-Resource Language Models

Kosuke Akimoto, Taiki Miyagawa, Masafumi Oyamada

In this paper, we study a fundamental design problem in pretraining Large Language Models (LLMs) for low-resource language regimes. Existing works adopt multi-epoch, multi-lingual,…

cs.CV2026

Learning Deliberately, Acting Intuitively: Unlocking Test-Time Reasoning in Multimodal LLMs

Yahan Yu, Yuyang Dong, Masafumi Oyamada

Reasoning is essential for large language models (LLMs), especially in complex tasks such as mathematical problem solving. However, multimodal reasoning still faces challenges in m…

cs.CL2026

Evaluating the Impact of Reviewer Guideline Design on LLM-Based Automated Peer Review

Haowen Li, Yoichi Ishibashi, Masafumi Oyamada

Peer review is an essential process in scientific research, yet the growing workload has made its automation increasingly necessary. In this study, we analyze how different types o…

stat.ML2026

Best-of- -- Asymptotic Performance of Test-Time LLM Ensembling

Junpei Komiyama, Daisuke Oba, Masafumi Oyamada

We study best-of- for large language models (LLMs) where the selection is based on majority voting. In particular, we analyze the limit , which we denote as \boinf…

cs.AI2026

SCAN: Semantic Document Layout Analysis for Textual and Visual Retrieval-Augmented Generation

Nobuhiro Ueda, Yuyang Dong, Krisztián Boros +3

With the increasing adoption of Large Language Models (LLMs) and Vision-Language Models (VLMs), rich document analysis technologies for applications like Retrieval-Augmented Genera…

cs.CL2025

Can a Crow Hatch a Falcon? Lineage Matters in Predicting Large Language Model Performance

Takuya Tamura, Taro Yano, Masafumi Enomoto +1

Accurately forecasting the performance of Large Language Models (LLMs) before extensive fine-tuning or merging can substantially reduce both computational expense and development t…