List your company
ResearchFormerly WizWand

Audio-Visual Dialogue on Daily-Omni

71.9ScoreSEATS
57.8661.50565.1568.795May 19, 2026
Updated 5mo ago

Evaluation results

MethodLinks
SEATSR (Rv-Ra)=35 (32-70), TFLOPs=13.32026.0571.955.499.8
Full tokensR (Rv-Ra)=100 (100-100), TFLOPs=47.22026.0571.855.5100
VisionZipR (Rv-Ra)=35 (29-100), TFLOPs=13.42026.0571.454.498
SEATSR (Rv-Ra)=25 (22-60), TFLOPs=9.02026.0571.254.798.6
VisionZip-omR (Rv-Ra)=35 (32-70), TFLOPs=13.42026.0571.154.598.2
OmniZipR (Rv-Ra)=35 (32-70), TFLOPs=13.42026.0570.954.698.4
DivPrune-omR (Rv-Ra)=35 (32-70), TFLOPs=13.42026.0570.454.297.7
SEATSR (Rv-Ra)=15 (12-50), TFLOPs=5.52026.0570.153.896.9
DivPruneR (Rv-Ra)=35 (29-100), TFLOPs=13.42026.0569.85497.3
VisionZip-omR (Rv-Ra)=25 (22-60), TFLOPs=9.42026.0569.853.896.9
RandomR (Rv-Ra)=35 (32-70), TFLOPs=13.42026.0569.553.696.6
DivPruneR (Rv-Ra)=25 (18-100), TFLOPs=9.42026.0569.553.696.6
DivPrune-omR (Rv-Ra)=25 (22-60), TFLOPs=9.42026.056953.796.7
FastVR (Rv-Ra)=35 (29-100), TFLOPs=13.72026.0568.653.396
DyCokeR (Rv-Ra)=35 (29-100), TFLOPs=13.42026.0568.653.796.7
FastVIDR (Rv-Ra)=25 (18-100), TFLOPs=9.12026.0568.352.995.3
RandomR (Rv-Ra)=25 (22-60), TFLOPs=9.42026.0568.152.995.3
SEATSR (Rv-Ra)=10 (7-45), TFLOPs=3.92026.0568.15395.5
VisionZipR (Rv-Ra)=25 (18-100), TFLOPs=9.42026.056852.995.3
DivPruneR (Rv-Ra)=15 (8-100), TFLOPs=5.82026.0567.851.893.3
FastVR (Rv-Ra)=25 (18-100), TFLOPs=9.82026.056751.693
FastV-omR (Rv-Ra)=35 (32-70), TFLOPs=13.72026.0566.451.492.6
DivPrune-omR (Rv-Ra)=15 (12-50), TFLOPs=5.82026.0566.351.893.3
OmniZipR (Rv-Ra)=25 (25-25), TFLOPs=8.52026.056652.594.5
VisionZip-omR (Rv-Ra)=15 (12-50), TFLOPs=5.82026.056651.592.8
VisionZipR (Rv-Ra)=15 (8-100), TFLOPs=5.82026.0565.451.292.3
RandomR (Rv-Ra)=15 (12-50), TFLOPs=5.82026.0564.650.691.2
DivPrune-omR (Rv-Ra)=10 (7-45), TFLOPs=4.02026.056450.991.7
FastV-omR (Rv-Ra)=25 (22-60), TFLOPs=9.82026.0562.949.589.2
VisionZip-omR (Rv-Ra)=10 (7-45), TFLOPs=4.02026.0561.849.889.7
RandomR (Rv-Ra)=10 (7-45), TFLOPs=4.02026.0561.249.188.5
FastV-omR (Rv-Ra)=15 (12-50), TFLOPs=6.32026.0558.446.784.2