Waypoint-OPD: Transferring RL-Induced Policy Shifts via Gated On-Policy Distillation
Paper • 2610.21601 • Published • 38
Alex
ShiningMaker
AI & ML interests
None yet
Recent Activity
upvoted a paper 25 days ago
Waypoint-OPD: Transferring RL-Induced Policy Shifts via Gated On-Policy Distillation liked a model about 1 year ago
ApsaraStackMaaS/EvoQwen2.5-VL-Retriever-7B-v1 liked a model about 1 year ago
ApsaraStackMaaS/EvoQwen2.5-VL-Retriever-3B-v1Organizations
None yet
upvoted a paper 25 days ago
liked 2
models about 1 year ago
upvoted 3
papers about 1 year ago
VCRL: Variance-based Curriculum Reinforcement Learning for Large Language Models
Paper • 2509.19803 • Published • 77
PVPO: Pre-Estimated Value-Based Policy Optimization for Agentic Reasoning
Paper • 2508.21104 • Published • 33
Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR
Paper • 2508.14029 • Published • 101
After deploying with the latest sglang, I found that the responses when calling the interface were chaotic.
4
#13 opened over 1 year ago
by ShiningMaker
skips the thinking process
11
#5 opened almost 2 years ago
by 
muzizon
updated 2
collections over 2 years ago
liked a
model over 2 years ago
