Scholar
Yuta Oshima
Google Scholar ID: V_tVbiIAAAAJ
University of Tokyo
Deep Learning
Generative Models
Video Generation
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
48
H-index
3
i10-index
2
Publications
4
Co-authors
4
list available
Publications
6 items
VIF-Bench: Evaluating Visual Instruction Following in Multi-Reference Image Generation
2026
Cited
0
AutoRef: Harness Optimization for Agentic Multi-Reference Image Generation
2026
Cited
0
Multi-Axis Max@K Reinforcement Learning for Representative Diversity in Text-to-Image Generation
2026
Cited
0
WorldPack: Compressed Memory Improves Spatial Consistency in Video World Modeling
2025
Cited
0
MultiBanana: A Challenging Benchmark for Multi-Reference Text-to-Image Generation
2025
Cited
0
Inference-Time Text-to-Video Alignment with Diffusion Latent Beam Search
2025
Cited
0
Co-authors
4 total
Yutaka Matsuo
Professor, University of Tokyo
Shohei Taniguchi
The University of Tokyo
Masahiro Suzuki
The University of Tokyo
Hiroki Furuta
Google DeepMind
