← Leaderboard

VLA-JEPA

VLA
USTC · Feb 10, 2026

VLA pretrained with JEPA-style latent actions learned from video, from USTC with Zhongguancun Academy, SJTU and Tsinghua co-authors.

Type
VLA
Parameters
—
Backbone
Qwen3-VL-2B + V-JEPA2
Weights
Open
License
Apache-2.0
Commercial use
Allowed
Released
Feb 10, 2026
Robots
Franka Panda (sim), WidowX (Bridge), Google Robot
SO-101
–
LeRobot
–

Benchmark results

3 of 13 benchmarks
#17 of 2479.5%, self-reported by the authors, not a leaderboard entry
LIBEROSaturatedSimulation
#29 of 4697.2%, self-reported by the authors, not a leaderboard entry
SimplerEnv WidowXSaturatedSimulation
#15 of 1957.3%, self-reported by the authors, not a leaderboard entry
Not reported on 10 benchmarks
Robustness drop: 97.2% on LIBERO → 79.5% on LIBERO-Plus. The perturbed variants show how much of the LIBERO score is memorization.

Adoption

updated Nov 17, 2026
HF downloads · 30d
–
HF likes
15
GitHub stars
636
GitHub forks
59
Wrong or missing number? Report an error