List your company

Audio-visual temporal grounding on VUE (TR)

46.1Vision ScoreOmniAgent
6.47616.76327.0537.337Jun 17, 2026

Evaluation results

MethodLinks
OmniAgentSize=7B2026.0646.136.5
VidiSize=7B2026.0643.933.4
VITALSize=7B2026.0635.3—
Gemini-2.0-FlashSize=-2026.0625.418.4
GPT-4oSize=-2026.062211.1
Gemini-2.5-ProSize=-2026.0621.812.1
Qwen2.5-OmniSize=7B2026.0683.5