today local_bar

Yutaka Matsuo

Full Professor, The University of Tokyo

3 papers at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 3

Thursday, December 4, 2025 · 11:00 AM → 2:00 PM

Exhibit Hall C,D,E

Provably Efficient RL under Episode-Wise Safety in Constrained MDPs with Linear Function Approximation

#3316 Spotlight · Toshinori Kitamura, Arnob Ghosh, Tadashi Kozuno, Wataru Kumagai, Kazumi Kasaura, Kenta Hoshino, Yohei Hosoe, Yutaka Matsuo

We propose the first provably efficient and episode-wise safe RL algorithm for linear constrained MDPs.

Poster Session 5

Friday, December 5, 2025 · 11:00 AM → 2:00 PM

Exhibit Hall C,D,E

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

#4306 · Yuta Oshima, Masahiro Suzuki, Yutaka Matsuo, Hiroki Furuta

Poster Session 6

Friday, December 5, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

Topology of Reasoning: Understanding Large Reasoning Models through Reasoning Graph Properties

#1113 · Gouki Minegishi, Hiroki Furuta, Takeshi Kojima, Yusuke Iwasawa, Yutaka Matsuo

This study reveals that reasoning models achieve superior performance by forming distinct reasoning graphs, characterized by greater cyclicity, larger diameters, and strong small-world properties.