activity
20232026
most citedOn the Limitation of Diffusion Models for Synthesizing Training Datasets

4 citations · 5 across the 6 of their papers we have counts for

collaborators

6 papers

cs.CV2026

Parallel In-context Learning for Large Vision Language Models

Shin'ya Yamaguchi, Daiki Chijiwa, Tamao Sakao +1

Large vision-language models (LVLMs) employ multi-modal in-context learning (MM-ICL) to adapt to new tasks by leveraging demonstration examples. While increasing the number of demo…

cs.CV2026

MultiModal Fine-tuning with Synthetic Captions

Shohei Enomoto, Shin'ya Yamaguchi

In this paper, we address a fundamental gap between pre-training and fine-tuning of deep neural networks: while pre-training has shifted from unimodal to multimodal learning with e…

cs.CV2025

Difference Vector Equalization for Robust Fine-tuning of Vision-Language Models

Satoshi Suzuki, Shin'ya Yamaguchi, Shoichiro Takeda +7

Contrastive pre-trained vision-language models, such as CLIP, demonstrate strong generalization abilities in zero-shot classification by leveraging embeddings extracted from image…

cs.CL2025

Lossless Vocabulary Reduction for Auto-Regressive Language Models

Daiki Chijiwa, Taku Hasegawa, Kyosuke Nishida +4

Tokenization -- the process of decomposing a given text into a sequence of subwords called tokens -- is one of the key components in the development of language models. Particularl…

cs.AI2023★ 4 cited

On the Limitation of Diffusion Models for Synthesizing Training Datasets

Shin'ya Yamaguchi, Takuma Fukuda

Synthetic samples from diffusion models are promising for leveraging in training discriminative models as replications of real training datasets. However, we found that the synthet…

cs.LG2023★ 1 cited

Generative Semi-supervised Learning with Meta-Optimized Synthetic Samples

Shin'ya Yamaguchi

Semi-supervised learning (SSL) is a promising approach for training deep classification models using labeled and unlabeled datasets. However, existing SSL methods rely on a large u…