Unverified50% confidenceFactExact time
Compared with strong VLA and WAM baselines, AMP1 reduced the failure rate in real-world tests by 20x and 15x respectively.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
11/9/2026
First Seen
Valid until: 11/23/2026
Sources
Related Entities
Related Claims
UnverifiedOn the RoboLab-120 benchmark, AMP1 achieves an 85.6% success rate zero-shot, while leading VLA and WAM policies reach only 49.2% and 42.9% respectively, and AMP1 uses no demonstration data or task-specific training.72% similarUnverifiedIn real-environment A/B testing, the post-trained checkpoint reduced the tool-call failure rate by 21.2% relatively compared to the earlier version.67% similarUnverifiedOn multiple downstream evaluation tasks in the study, none of the JEPA variants outperformed standard MLM.66% similarUnverifiedThe LoRA baseline used for comparison in the paper uses rank 19 with 6.6 million parameters, achieving a correction rate of 83.3%, but exhibited capability loss of 30% to 75%.66% similarUnverifiedThe researchers found that when χ1 is close to 1, the test error decreases monotonically in all four experimental units.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1150464API
curl https://kongchang.com/api/v1/knowledge/claims/1150464MCP
get_claim(id=1150464)