Hiroshi Yoshihara's picture

6 5 9

Hiroshi Yoshihara

RabotniKuma

·

AI & ML interests

None yet

Recent Activity

authored a paper about 1 month ago

A Practical Two-Stage Recipe for Mathematical LLMs: Maximizing Accuracy with SFT and Efficiency with Reinforcement Learning

liked a model about 1 month ago

openai/gpt-oss-20b

upvoted a paper about 2 months ago

Wider or Deeper? Scaling LLM Inference-Time Compute with Adaptive Branching Tree Search

View all activity

Organizations

New activity in RabotniKuma/Fast-Math-R1-Token-Scheduler about 2 months ago

Improve dataset card for Token Scheduler Dataset: Add paper link and detailed description

#2 opened about 2 months ago by

New activity in RabotniKuma/Fast-Math-R1-GRPO about 2 months ago

Improve dataset card: Add paper, code, metadata, and usage

#1 opened about 2 months ago by

New activity in RabotniKuma/Fast-Math-R1-SFT about 2 months ago

Enhance dataset card: Add paper link, metadata, and usage

#2 opened about 2 months ago by

New activity in RabotniKuma/Fast-Math-Qwen3-14B about 2 months ago

Improve model card: Add pipeline tag, library name, and link to paper

#1 opened about 2 months ago by

New activity in RabotniKuma/Fast-OpenMath-Nemotron-14B about 2 months ago

Enhance model card with metadata, paper link, and project page

#1 opened about 2 months ago by

New activity in RabotniKuma/Fast-Math-R1-14B about 2 months ago

Improve model card: Add pipeline tag, library name, update paper link and enhance details

#1 opened about 2 months ago by