Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients
Paper • 2606.18216 • Published • 60
Min-Hung Chen
cmhungsteve
AI & ML interests
Multimodal AI, Transfer Learning, Unsupervised Learning, Video Understanding, Vision Transformer, Computer Vision, Deep Learning
Recent Activity
upvoted a paper 8 days ago
Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients upvoted a collection 12 days ago
Cosmos3 authored a paper 12 days ago
SpatialClaw: Rethinking Action Interface for Agentic Spatial ReasoningOrganizations
upvoted a paper 8 days ago
upvoted a collection 12 days ago
authored a
paper 12 days ago
upvoted a paper 13 days ago
submitted a
paper to Daily Papers 13 days ago
authored 3
papers 19 days ago
FineBench: Benchmarking and Enhancing Vision-Language Models for Fine-grained Human Activity Understanding
Paper • 2605.19846 • Published • 3
DVSM: Decoder-only View Synthesis Model Done Right
Paper • 2605.29891 • Published • 2
Physics in 2-Steps: Locking Motion Priors Before Visual Refinement Erases Them
Paper • 2606.06361 • Published • 16
upvoted 3
papers 20 days ago
FineBench: Benchmarking and Enhancing Vision-Language Models for Fine-grained Human Activity Understanding
Paper • 2605.19846 • Published • 3
DVSM: Decoder-only View Synthesis Model Done Right
Paper • 2605.29891 • Published • 2
Physics in 2-Steps: Locking Motion Priors Before Visual Refinement Erases Them
Paper • 2606.06361 • Published • 16
fix links
#1 opened 23 days ago
by 
cmhungsteve
liked a
model 23 days ago
upvoted a paper 26 days ago
upvoted a paper 28 days ago
upvoted an article about 1 month ago
Article
Fine-Tuning NVIDIA Cosmos Predict 2.5 with LoRA/DoRA for Robot Video Generation
nvidia
• • 21 liked a
dataset about 1 month ago
liked a
model about 2 months ago
License for RoboFAC?
#6 opened about 2 months ago
by cmhungsteve
selected as CVPR'26 Highlight
#6 opened 2 months ago
by cmhungsteve