Live Streaming Risk Assessment on May Dataset 1.0 (test) benchmark leaderboard · SOTA2 Research

Live Streaming Risk Assessment on May Dataset 1.0 (test)

71.21F1-scoreLPCD

Evaluation Results

Method	Links
LPCD2026.06		71.21	—	88.32	11.58	78.41
CS-VAR2026.01		70.99	77.21	87.61	11.9	—
AC-MIL + IB-IRM2026.06		70.8	—	87.66	12.19	77.19
AC-MIL + GroupDRO2026.06		70.49	—	87.71	12.05	77.16
AC-MIL + ASGDRO2026.06		70.38	—	87.66	12.22	77.15
AC-MIL + IRM2026.06		70.33	—	87.81	12.13	76.99
AC-MIL + CORAL2026.06		70.29	—	86.92	13.15	76.76
AC-MIL + MIXUP2026.06		70.18	—	87.76	12.11	77.26
AC-MIL + FOIL2026.06		70.12	—	87.9	11.91	77.47
AC-MIL2026.06		70.02	—	87.22	12.6	76.76
AC-MIL + VREx2026.06		69.69	—	87.07	13.03	76.26
AC-MIL + EIIL2026.06		68.24	—	87.56	12.07	76.86
TimeMIL2026.01		67.9	73.53	85.99	14.36	—
TimeMIL2026.06		67.9	—	85.99	14.36	73.53
TAIL-MIL2026.01		67.85	73.16	85.7	13.41	—
TAIL-MIL2026.06		67.85	—	85.7	13.41	73.16
AdMIL2026.01		67.81	71.96	83.89	15.68	—
mi-NET2026.01		67.69	72.76	85.6	13.2	—
AtMIL2026.01		67.63	72.52	85.5	14.41	—
Reformer2026.01		67.52	72.03	85.75	14.36	—
Reformer2026.06		67.52	—	85.75	14.36	72.93
MIL-LET2026.01		67.49	72.41	85.46	14.18	—
MIL-LET2026.06		67.49	—	85.46	14.18	72.41
Informer2026.01		67.08	72.46	84.38	15.55	—
Informer2026.06		67.08	—	84.38	15.55	72.46
Transformer2026.01		66.68	71.89	83.94	15.8	—
Transformer2026.06		66.68	—	83.94	15.8	71.89