HarryHsing/OmniAgent
OmniAgent (ICML 2026): the first native omni-modal agent for active video perception — a 7B agent that beats Qwen2.5-VL-72B with 73% fewer frames on LVBench.
⭐ 67
⑂ 6
Python
Apache-2.0
· 13 天前推送
67
Watchers
0
贡献者
0
Commits
0
Releases
2
Open Issues
13 天前
最近推送
原文
中文
暂无 README