Search papers, labs, and topics across Lattice.
Beihang University, Telecom eSurfing Cloud
3
0
4
WDL-OPD boosts MATH500 accuracy from 0.630 to 0.685, showcasing a powerful new approach to stabilizing on-policy distillation.
RAVEN achieves a remarkable 20.2% improvement in forecasting accuracy for S&P500 by dynamically adapting its context windows to the financial regime.
Control LLM personality on a continuous spectrum, not just discrete categories, by dynamically fusing LoRA adapters with a reinforcement learning policy.
