Share your thoughts, 1 month free Claude Pro on usSee more

Task Progression Failure Detection on Cover Object Policy Success Rate (In-Distribution)

100TPR

Temporal Non-Distr. Min.

Updated 1mo ago

Evaluation Results

Method	Links
Temporal Non-Distr. Min. 2026.03		100	93	2.4
STAC For. KL 2026.03		100	95	2.4
STAC Rev. KL 2026.03		100	93	2.4
STAC MMD* 2026.03		100	93	2.4
GPT-4o Image QA 2026.03		100	7	12
GPT-4o Video QA 2026.03		100	5	5.6
Gemini 1.5 Pro Image QA 2026.03		100	5	12
Gemini 1.5 Pro Video QA 2026.03		100	0	5.6
Claude 3.5 Sonnet Image QA 2026.03		100	81	12
Claude 3.5 Sonnet Video QA 2026.03		100	84	12
Claude 3.5 Sonnet Video QA + Success Video 2026.03		100	77	12
Claude 3.5 Sonnet Video QA + Goal Images 2026.03		100	93	5.6
Claude 3.5 Sonnet Prompt Ensemble* 2026.03		100	93	12
Sentinel (STAC MMD* + Claude 3.5 Sonnet Video QA) 2026.03		100	79	2.4
Sentinel (STAC MMD* + Claude 3.5 Sonnet Prompt Ensemble*) 2026.03		100	88	2.4
Diffusion Output Variance 2026.03		0	77	-