activity
20242026
collaborators

7 papers

cs.LG2026

Multi-Axis Max@K Reinforcement Learning for Representative Diversity in Text-to-Image Generation

Ku Onoda, Paavo Parmas, Hiroki Furuta +4

Text-to-image (T2I) models can synthesize realistic, prompt-aligned images, yet samples generated for the same prompt often cover only a small subset of visually distinct modes. Th…

cs.CV2026

SSM Meets Video Diffusion Models: Efficient Long-Term Video Generation with Structured State Spaces

Yuta Oshima, Shohei Taniguchi, Masahiro Suzuki +1

Given the remarkable achievements in image generation through diffusion models, the research community has shown increasing interest in extending these models to video generation.…

cs.CV2026

MultiBanana: A Challenging Benchmark for Multi-Reference Text-to-Image Generation

Yuta Oshima, Daiki Miyake, Kohsei Matsutani +4

Recent text-to-image generation models have acquired the ability of multi-reference generation and editing; that is, to inherit the appearance of subjects from multiple reference i…

cs.CV2025

WorldPack: Dynamic Frame Compression for Long-context Video World Modeling

Yuta Oshima, Yusuke Iwasawa, Masahiro Suzuki +2

Video world models have attracted significant attention for their ability to produce high-fidelity future visual observations conditioned on past observations and navigation action…

cs.CV2025

Inference-Time Text-to-Video Alignment with Diffusion Latent Beam Search

Yuta Oshima, Masahiro Suzuki, Yutaka Matsuo +1

The remarkable progress in text-to-video diffusion models enables the generation of photorealistic videos, although the content of these generated videos often includes unnatural m…

cs.LG2024

ADOPT: Modified Adam Can Converge with Any with the Optimal Rate

Shohei Taniguchi, Keno Harada, Gouki Minegishi +7

Adam is one of the most popular optimization algorithms in deep learning. However, it is known that Adam does not converge in theory unless choosing a hyperparameter, i.e., ,…