Scholar
Yasuhiro Fujita
Google Scholar ID: vfOynukAAAAJ
Preferred Networks, Inc.
Citations & Impact
Citations
811
H-index
8
i10-index
7
Publications
13
Co-authors
0
Publications
Resume
Academic Achievements
- 1. Entropy Controllable Direct Preference Optimization (ICML Workshop on Models of Human Feedback for AI Alignment, 2025)
- 2. Surface-Aligned Neural Radiance Fields for Controllable 3D Human Synthesis (CVPR, 2022)
- 3. ChainerRL: A Deep Reinforcement Learning Library (Journal of Machine Learning Research, 2022)
- 4. Distributed Reinforcement Learning of Targeted Grasping with Active Vision for Mobile Manipulators (IROS, 2020)
- 5. Learning Latent State Spaces for Planning through Reward Prediction (Incomplete paper)
Background
- Research interests: reinforcement learning, machine learning