Track manipulation, locomotion and embodied systems.
Search papers, labs, and topics across Lattice.
3
0
8
Most social LLMs fail to achieve verifiable success in coordination tasks, even when rated highly by conversational judges.
A lightweight latent world model directly conditions VLA action generation on predicted future consequences, boosting real-world robotic success rates from 38.3% to 73.3% without pixel-level video prediction.
Existing autoregressive post-training weights, often discarded after diffusion model conversion, can be directly applied to significantly boost dLLM performance, even outperforming dedicated diffusion post-training when combined.