GTR: Guided Thought Reinforcement Prevents Thought Collapse in RL-based VLM Agent Training
Paper
•
2503.08525
•
Published
•
8
•
1
Steven
yijunyang
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 8 hours ago
GTR: Guided Thought Reinforcement Prevents Thought Collapse in RL-based
VLM Agent Training
commented on
a paper
about 8 hours ago
GTR: Guided Thought Reinforcement Prevents Thought Collapse in RL-based
VLM Agent Training
upvoted
a
paper
13 days ago
R2-T2: Re-Routing in Test-Time for Multimodal Mixture-of-Experts
Organizations
yijunyang's activity
commented
a
paper
about 8 hours ago