Track manipulation, locomotion and embodied systems.
Search papers, labs, and topics across Lattice.
2
0
6
Autoregressive video pretraining unlocks the full potential of long contexts for real-time robot control, boosting success rates by 15% and enabling complex manipulation previously impossible.
LLMs can achieve 2.5x higher throughput and 10.7x KV memory reduction in long-context reasoning by compressing the KV cache using trigonometric functions derived from pre-RoPE query/key vector distributions.