Search papers, labs, and topics across Lattice.
University of Science and Technology of China
4
0
6
RAVEN achieves a remarkable 20.2% improvement in forecasting accuracy for S&P500 by dynamically adapting its context windows to the financial regime.
AtomMem revolutionizes memory systems for LLMs by transforming interactions into stable, high-value atomic facts, leading to superior reasoning capabilities.
Agentic search methods only achieve a maximum Recall@100 of 31.4%, revealing a critical gap in current academic paper retrieval capabilities.
StepPO reveals that aligning policy optimization with agent decision-making steps can lead to superior performance in multi-turn interactions, outperforming traditional RL methods.
