Checkpoints "Learn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement Learning" arxiv [2509.22601]
Yulei Qin
yolay
AI & ML interests
Medical Imaging, Computer Vision,
Language Models
Recent Activity
authored
a paper
42 minutes ago
LTD-Bench: Evaluating Large Language Models by Letting Them Draw
upvoted
a
paper
about 1 hour ago
Scalable Multi-Task Reinforcement Learning for Generalizable Spatial
Intelligence in Visuomotor Agents
upvoted
a
paper
about 1 hour ago
Agent Lightning: Train ANY AI Agents with Reinforcement Learning
Organizations
models
20
yolay/SPEAR-ReTool-Qwen2.5-32B
33B
•
Updated
•
11
yolay/SPEAR-ReTool-Qwen3-32B
33B
•
Updated
•
11
yolay/SPEAR-ALFWorld-DrBoT-GRPO-1.5B
2B
•
Updated
•
10
yolay/SPEAR-ALFWorld-DrBoT-GiGPO-1.5B
2B
•
Updated
•
9
yolay/SPEAR-ALFWorld-DrBoT-GRPO-7B
8B
•
Updated
•
13
yolay/SPEAR-ALFWorld-DrBoT-GiGPO-7B
8B
•
Updated
•
15
yolay/SPEAR-WebShop-DrBoT-GRPO-1.5B
2B
•
Updated
•
11
yolay/SPEAR-WebShop-DrBoT-GiGPO-1.5B
2B
•
Updated
•
7
yolay/SPEAR-WebShop-DrBoT-GRPO-7B
8B
•
Updated
•
11
yolay/SPEAR-WebShop-DrBoT-GiGPO-7B
8B
•
Updated
•
13