-
Aero Realtime 4B
📺4Proactive real-time commentary on audio-video streams
-
kcz358/aero-realtime-4B
Video-Text-to-Text • 5B • Updated • 405 • 10 -
kcz358/aero-realtime-data
Preview • Updated • 945 -
Aero Realtime: Fully Aligned Input-Output Streams for Low-Latency Streaming Multimodal Generation
Paper • 2608.08469 • Published • 2
kcz PRO
kcz358
AI & ML interests
None yet
Recent Activity
authored a paper 1 day ago
Mage-VL-Cowork: A Full Training Recipe to Learn Hybrid Computer Use From Evolved Harnesses upvoted a paper 29 days ago
LifeSearch: Benchmarking Deep Research Agents for Real-World Life and ProductivityOrganizations
-
Aero Realtime 4B
📺4Proactive real-time commentary on audio-video streams
-
kcz358/aero-realtime-4B
Video-Text-to-Text • 5B • Updated • 405 • 10 -
kcz358/aero-realtime-data
Preview • Updated • 945 -
Aero Realtime: Fully Aligned Input-Output Streams for Low-Latency Streaming Multimodal Generation
Paper • 2608.08469 • Published • 2
datasets 28
kcz358/aero-realtime-data
Preview • Updated • 945
kcz358/QIVD
Preview • Updated • 11
kcz358/MMOU
Viewer • Updated • 20k • 97
kcz358/RVOS-ReasonVOS
Viewer • Updated • 458 • 20
kcz358/RVOS-Ref-YT-VOS
Viewer • Updated • 834 • 33
kcz358/RVOS-MeViS-ValidU
Viewer • Updated • 793 • 76
kcz358/RVOS-Ref-DAVIS17
Viewer • Updated • 244 • 56
kcz358/SUNRGBD-3D
Viewer • Updated • 10.3k • 1.26k
kcz358/ODinW-13
Viewer • Updated • 4.94k • 234
kcz358/OVOBench
Viewer • Updated • 1.64k • 252