Kohsei Matsutani

According to our database, Kohsei Matsutani authored at least 4 papers between 2025 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2026

Zipping the Thought: When and How Compressed Reasoning Data Works in LLM Post-Training.

Kohsei Matsutani, Gouki Minegishi, Takeshi Kojima, Yusuke Iwasawa, Yutaka Matsuo

CoRR, May, 2026

2025

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

Yuta Oshima, Daiki Miyake, Kohsei Matsutani, Yusuke Iwasawa, Masahiro Suzuki, Yutaka Matsuo, Hiroki Furuta

CoRR, November, 2025

RL Squeezes, SFT Expands: A Comparative Study of Reasoning LLMs.

Kohsei Matsutani, Shota Takashiro, Gouki Minegishi, Takeshi Kojima, Yusuke Iwasawa, Yutaka Matsuo

CoRR, September, 2025

Mixture of Experts Provably Detect and Learn the Latent Cluster Structure in Gradient-Based Learning.

Ryotaro Kawata, Kohsei Matsutani, Yuri Kinoshita, Naoki Nishikawa, Taiji Suzuki

Proceedings of the Forty-second International Conference on Machine Learning, 2025