Search papers, labs, and topics across Lattice.
Fudan University, Shanghai Innovation Institute
3
0
4
Gradual bridging with embodied trajectory-coupled data transforms VLMs into robust robot control policies, overcoming significant transfer challenges.
One-step action generation in VLA models can outperform ten-step methods by simply biasing training towards high-noise states, challenging the need for complex iterative processes.
Forget robotics pre-training: ActionCodec, a new action tokenizer designed with information-theoretic principles, achieves state-of-the-art VLA performance on LIBERO.
