M
MODELYST
AI research terminal
●
live · verified Jul 13
Search
⌘K
Frontier
Models
Compare
Leaderboards
Changes
Media
Benchmarks
Papers
Pick
Discover
Ask
Frontier
Models
Compare
Leaderboards
Changes
Media
Benchmarks
Papers
Pick
Discover
Ask
People
/
Zhijiang Guo
PPL
Zhijiang Guo
☆ Watch
Papers (2)
DGPO: Beyond Pairwise Preferences with Directional Consistent Groupwise Optimization
Prune-OPD: Efficient and Reliable On-Policy Distillation for Long-Horizon Reasoning