Product
Help
Pricing
About
Jobs
Log in
Get started
Author
Add to collection
Kohsei Matsutani
Observed name:
Matsutani, Kohsei
Institution:
The University of Tokyo
Observed institutions:
RIKEN,
RIKEN Center for Advanced Intelligence Project,
The University of Tokyo
OpenAlex ID:
A5137954132
Few-Shot Demonstrations Elicit the Use of In-Context World Representations in LLMs
2026
·
Matsutani, Kohsei
, Minegishi, Gouki
, et al.
·
arXiv (Cornell University)
PDF
OrderGrad: Optimizing Beyond the Mean with Order-Statistic Policy Gradient Estimation
2026
·
Parmas, Paavo
, Kim, Yongmin
, et al.
·
arXiv (Cornell University)
PDF
On Advantage Estimates for Max@K Policy Gradients
2026
·
Takashiro, Shota
, Nishimori, Soichiro
, et al.
·
arXiv (Cornell University)
PDF
Zipping the Thought: When and How Compressed Reasoning Data Works in LLM Post-Training
2026
·
Kohsei Matsutani
, Gouki Minegishi
, et al.
·
Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)
PDF
RL Squeezes, SFT Expands: A Comparative Study of Reasoning LLMs
2025
·
Matsutani, Kohsei
, Takashiro, Shota
, et al.
·
arXiv (Cornell University)
PDF
Mixture of Experts Provably Detect and Learn the Latent Cluster Structure in Gradient-Based Learning
2025
·
Kawata, Ryotaro
, Matsutani, Kohsei
, et al.
·
arXiv (Cornell University)
PDF
Show more works
View as search
Works count:
6
Citation count:
H-index:
I10-index:
Year
Topic
Type
