Unverified50% confidenceEventExact time
Backtrack was evaluated on the LIBERO and MetaWorld benchmarks, covering three VLA models: SmolVLA, π0.5, and π0-FAST.
1
Sources
50%
Confidence
Long-term
Relevance
10/26/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedReLE's open-source model evaluation covers models including kimi-k2.6, deepseek-v4, Qwen3.6, llama4, GLM-5.1, gemma4, and mistral.62% similarUnverifiedMeta has open-sourced PyTorch and developed its own MTIA inference chip.60% similarUnverifiedThe project plans to integrate lightweight VLA models such as SmolVLA and OpenVLA-micro in the next step.59% similarUnverifiedMeta's LLaMA 3 series has a maximum scale of 405B, and DeepSeek-V3 is approximately 671B (mixture-of-experts architecture).59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1098088API
curl https://kongchang.com/api/v1/knowledge/claims/1098088MCP
get_claim(id=1098088)