Mind the Gap: Bridging Thought Leap for Improved Chain-of-Thought Tuning
xhl
zjuxhl
AI & ML interests
None yet
Recent Activity
upvoted a paper 9 days ago
ViSkill: Reinforcing VLM Agents with Evolving Visual-Native Skills upvoted a paper 10 days ago
ComputerSD: Online Self-Distillation from Real-Time Feedback for Computer-Use AgentsOrganizations
models 7
zjuxhl/Llama3.1-8B-NuminaMath-bridge
Updated • 16 • 3
zjuxhl/Llama3.1-8B-NuminaMath
Updated • 31 • 2
zjuxhl/CoT-Bridge
Updated • 7 • 2
zjuxhl/Qwen2.5Math1.5B-NuminaMath-bridge-GRPO
2B • Updated • 22 • 2
zjuxhl/Qwen2.5Math1.5B-NuminaMath
2B • Updated • 8 • 3
zjuxhl/Qwen2.5Math1.5B-NuminaMath-GRPO
2B • Updated • 17 • 3
zjuxhl/Qwen2.5Math1.5B-NuminaMath-bridge
2B • Updated • 11 • 3