Reinforcement Learning for Reasoning in Small LLMs: What Works and What Doesn't
Paper
•
2503.16219
•
Published
•
48
Shubham Parashar
shubhamprshr
·
AI & ML interests
Computer Vision, Multi-Modal Learning
Recent Activity
updated
a model
3 days ago
shubhamprshr/Llama-3.2-3B-Instruct_blocksworld1246_sgrpo_cosine_0.5_0.5_True_1200
published
a model
3 days ago
shubhamprshr/Llama-3.2-3B-Instruct_blocksworld1246_sgrpo_cosine_0.5_0.5_True_1200
updated
a model
4 days ago
shubhamprshr/Qwen2.5-3B-Instruct_math_sgrpo_cosine_0.5_0.5_True_1200
Organizations
