Shz/DeepSeek-R1-Distill-Qwen-1.5B-GRPO
Updated
lioushz
Shz
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
13 days ago
Deciphering Trajectory-Aided LLM Reasoning: An Optimization Perspective
upvoted
a
paper
3 months ago
Creation-MMBench: Assessing Context-Aware Creative Intelligence in MLLM
upvoted
a
paper
3 months ago
OmniAlign-V: Towards Enhanced Alignment of MLLMs with Human Preference
Organizations
