Mind the Gap: Bridging Thought Leap for Improved Chain-of-Thought Tuning
xhl
zjuxhl
AI & ML interests
None yet
Recent Activity
upvoted a paper 17 days ago
ViSkill: Reinforcing VLM Agents with Evolving Visual-Native Skills upvoted a paper 18 days ago
ComputerSD: Online Self-Distillation from Real-Time Feedback for Computer-Use Agents upvoted a paper about 1 month ago
Spatial-Interactor: Learning Spatial Reasoning through Interaction with the Observable Physical WorldOrganizations
models 7
zjuxhl/Llama3.1-8B-NuminaMath-bridge
Updated • 15 • 3
zjuxhl/Llama3.1-8B-NuminaMath
Updated • 20 • 2
zjuxhl/CoT-Bridge
Updated • 8 • 2
zjuxhl/Qwen2.5Math1.5B-NuminaMath-bridge-GRPO
2B • Updated • 15 • 2
zjuxhl/Qwen2.5Math1.5B-NuminaMath
2B • Updated • 8 • 3
zjuxhl/Qwen2.5Math1.5B-NuminaMath-GRPO
2B • Updated • 12 • 3
zjuxhl/Qwen2.5Math1.5B-NuminaMath-bridge
2B • Updated • 11 • 3