Trials, Errors, and Breakthroughs: Our Rocky Road to OVD SOTA with Reinforcement Learning
•
1
AI & ML interests
Multimodal AI, Agents
Recent Activity
Articles
pinned
Running
16
Open Agent Leaderboard
🥇
Open Agent Leaderboard
Running
on
Zero
70
VLM R1 Referral Expression
💬
Mark regions in images based on text descriptions
Sleeping
1
OmAgent
💬
Process and answer questions about webpage videos
Running
on
Zero
16
VLM R1 OVD
👁
VLM-R1 model for Open-Vocabulary Object Detection