divelab/Qwen3-8B-a2d-init
8B • Updated • 4
AI & ML interests
None defined yet.
Recent Activity
Papers
Learnability-Informed Fine-Tuning of Diffusion Language Models
Curriculum Reinforcement Learning from Easy to Hard Tasks Improves LLM Reasoning
divelab/Qwen3-4B-a2d-init
4B • Updated • 2 • 1
divelab/Qwen3-1.7B-a2d-init
2B • Updated
divelab/Qwen3-0.6B-a2d-init
0.6B • Updated
divelab/E2H-Reasoning
Updated
divelab/orbevo_model
Updated
divelab/DAPO_E2H-countdown-gaussian_0p5_0p5
Text Generation • 2B • Updated • 8 •
divelab/DAPO_E2H-math-gaussian_0p5_0p5
Text Generation • 2B • Updated • 9 •
divelab/DAPO_E2H-math-cosine
Text Generation • 2B • Updated • 8 •
divelab/DAPO_E2H-gsm8k-gaussian_0p25_0p75
Text Generation • 2B • Updated • 9 •