tongxiao2002/Perception-R1-7B
8B • Updated • 11 • 1
tongxiao
tongxiao2002
AI & ML interests
None yet
Recent Activity
upvoted a paper about 19 hours ago
Weak-to-Strong Generalization via Direct On-Policy Distillation upvoted a paper about 21 hours ago
Proxy Exploration and Reusable Guidance: A Modular LLM Post-Training Paradigm via Proxy-Guided Update Signals upvoted a paper 1 day ago
Gemma 4 Technical ReportOrganizations
