johnschaefer/GRPO-olmo3_7b_creativity_grpo_purerl
Updated
John Schaefer
johnschaefer
AI & ML interests
None yet
Recent Activity
upvoted a paper about 21 hours ago
From Skills to Talent: Organising Heterogeneous Agents as a Real-World Company upvoted a paper about 21 hours ago
World-R1: Reinforcing 3D Constraints for Text-to-Video Generation upvoted a paper about 21 hours ago
TexOCR: Advancing Document OCR Models for Compilable Page-to-LaTeX ReconstructionOrganizations
None yet
models 10
johnschaefer/GRPO-olmo3_7b_physics_grpo_purerl
Updated
johnschaefer/GRPO-qwen3_8b_creativity_grpo_purerl
Updated
johnschaefer/GRPO-qwen3_8b_creativity_grpo_weighted_mul
Updated
johnschaefer/GRPO-qwen3_8b_physics_grpo_purerl
Updated
johnschaefer/DAPO-RLVR-with-full-tokens-Qwen3-8B
Updated
johnschaefer/GRPO-olmo3_7b_physics_grpo_weighted_mul
Updated
johnschaefer/GRPO-qwen3_8b_physics_grpo_weighted_mul
Updated
johnschaefer/DAPO-RLVR-with-only-high-entropy-tokens-Qwen3-8B
Updated
johnschaefer/GRPO-olmo3_7b_creativity_grpo_weighted_mul
Updated
datasets 0
None public yet