Search papers, labs, and topics across Lattice.
Affiliation:
5
0
8
A unified benchmark that combines synthetic data with real-world testing could revolutionize how we train robots for complex manipulation tasks.
Vid2WAM achieves superior task generalization and data efficiency by leveraging video diffusion priors, even with minimal expert demonstrations.
Ternary LLMs can now achieve efficient attention computation without the overhead of high-precision K/V processing, revolutionizing their performance.
WeaveLA transforms the way robots handle repetitive tasks, boosting success rates dramatically by enabling seamless memory transfer across sub-tasks.
Forget training from scratch: Nexusformer lets you scale Transformers by nonlinearly expanding attention, inheriting knowledge and slashing compute by up to 41.5%.
