Search papers, labs, and topics across Lattice.
5
0
11
None of the 30 LLM agents evaluated in CausalGame demonstrated reliable causal thinking, revealing a critical gap in AI's ability to perform scientific reasoning.
HALOMI bridges the human-to-humanoid gap, achieving 85% success in complex loco-manipulation tasks by leveraging active perception from human demonstrations.
LLMs are far more alike than you think: shared biases and failure modes mean that ensembling them is less effective than you'd hope.
LLMs can be guided to discover better solutions in open-ended scientific tasks by identifying and reasoning about causal factors that influence the evolutionary process.
Forget brute-force KV cache: CHESS achieves comparable quality to full KV cache using only 1% of the memory, unlocking 4.56x higher throughput for long-context LLMs.
