hzeng/syn-plan-research-4B-sft
4B • Updated • 2
Hansi Zeng
hzeng
AI & ML interests
None yet
Recent Activity
upvoted a paper about 24 hours ago
Truncated Step-Level Sampling with Process Rewards for Retrieval-Augmented Reasoning upvoted a paper about 24 hours ago
CoSearch: Joint Training of Reasoning and Document Ranking via Reinforcement Learning for Agentic Search upvoted a paper 5 days ago
GrepSeek: Training Search Agents for Direct Corpus InteractionOrganizations
hzeng/syn-plan-research-8B-sft
8B • Updated • 1
hzeng/syn-plan-research-8B
8B • Updated • 8
hzeng/syn-plan-research-4B
4B • Updated • 4
hzeng/Lion-SP-8B-llama3-marco-mntp
Updated • 2
hzeng/Lion-DS-8B-llama3-marco-mntp
Updated • 3
hzeng/Lion-DS-1B-llama3-marco-mntp
Updated • 3
hzeng/Lion-SP-1B-llama3-marco-mntp
Updated • 290 • 2