Search papers, labs, and topics across Lattice.
University of Science and Technology of China
2
1
5
Achieving up to 2x faster decoding in LLMs without additional training, Progressive Tree Drafting redefines how we approach speculative decoding.
LLMs can reliably control real-world sensor networks by verifying plans against a learned spatial model *before* execution, boosting success rates by 37% while slashing token usage.
