Search papers, labs, and topics across Lattice.
2
0
4
2
One model to control them all: Qwen-VLA achieves impressive zero-shot generalization across diverse robotic tasks and embodiments by unifying vision-language-action modeling.
By decoupling visual and motor information during pretraining, FutureVLA unlocks more effective visuomotor prediction for vision-language-action models, boosting performance without modifying downstream architectures.
