Search papers, labs, and topics across Lattice.
6
0
9
RHO achieves a 45.0% success rate in robotic tasks, 2.5x higher than the best multi-turn agent, showcasing a breakthrough in real-time control efficiency.
Current LLMs often overfit and fail to leverage past knowledge, with naive in-context learning outperforming dedicated memory systems in continual learning tasks.
Stop hand-tuning your retrieval pipelines: BRANE slashes costs by up to 89% while matching accuracy by dynamically configuring pipelines per query.
Modular training with BAR allows independent updates of domain experts, achieving superior performance without the pitfalls of catastrophic forgetting.
Even the most advanced LLMs stumble when asked to reason over a large, heterogeneous document corpus, achieving only 34% accuracy on the new OfficeQA Pro benchmark despite direct access to the relevant documents.
LLM-driven program evolution gets a smart upgrade: AdaEvolve dynamically allocates resources to promising solution candidates, leaving static schedules in the dust.
