Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective
Fan Zhou
koalazf99
AI & ML interests
Deep Learning; Natural Language Processing; Foundation Models
Recent Activity
upvoted
a
paper
3 days ago
MegaFlow: Large-Scale Distributed Orchestration System for the Agentic Era
upvoted
a
paper
23 days ago
Learning to Reason in 4D: Dynamic Spatial Understanding for Vision Language Models
Organizations
Mid-training Incentivizes Reinforcement Learning Scaling
-
OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling
Paper • 2506.20512 • Published • 48 -
OctoThinker/MegaMath-Web-Pro-Max
Viewer • Updated • 69.2M • 19.9k • 36 -
OctoThinker/OctoThinker-8B-Long-Base
Text Generation • 8B • Updated -
OctoThinker/OctoThinker-8B-Hybrid-Base
Text Generation • 8B • Updated • 1.15k • 2
Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective
Mid-training Incentivizes Reinforcement Learning Scaling
-
OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling
Paper • 2506.20512 • Published • 48 -
OctoThinker/MegaMath-Web-Pro-Max
Viewer • Updated • 69.2M • 19.9k • 36 -
OctoThinker/OctoThinker-8B-Long-Base
Text Generation • 8B • Updated -
OctoThinker/OctoThinker-8B-Hybrid-Base
Text Generation • 8B • Updated • 1.15k • 2
models
0
None public yet
datasets
0
None public yet