Search papers, labs, and topics across Lattice.
Affiliation:
4
0
7
A frozen world-model planner's performance can be drastically improved by adapting its latent rollouts to controller-induced execution shifts, rather than directly substituting predicted trajectories.
Models that appear equally accurate can possess vastly different agentic reasoning capabilities, revealing the hidden complexities of LLM performance.
Achieving a 3.56× increase in decoding throughput without sacrificing accuracy, BinaryPC revolutionizes efficiency in long-context LLMs.