Search papers, labs, and topics across Lattice.
4
0
5
0
G0.5 achieves unprecedented performance in robot reasoning and action by merging decision-making and execution into a single autoregressive framework, outperforming existing models across seven challenging benchmarks.
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.
