Hiroshi Yoshihara

RabotniKuma's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 6 months ago

Nemotron-Cascade 2: Post-Training LLMs with Cascade RL and Multi-Domain On-Policy Distillation

Paper • 2603.19220 • Published Mar 19 • 70

upvoted 2 papers about 1 year ago

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

Paper • 2503.04412 • Published Mar 6, 2025 • 6

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

Paper • 2507.08267 • Published Jul 11, 2025 • 11

upvoted 3 collections over 1 year ago

OpenMathReasoning

Collection

Models and datasets from "AIMO-2 Winning Solution: Building State-of-the-Art Mathematical Reasoning Models with OpenMathReasoning dataset" • 7 items • Updated 25 days ago • 48

Cosmos-Preidct1

Collection

⚠️ This collection is archived. 👉 https://huggingface.co/collections/nvidia/cosmos3 • 14 items • Updated 25 days ago • 303

Reasoning Vector

Collection

Reasoningモデルとベースモデルの重み差分 • 4 items • Updated Feb 18, 2025 • 3