Search papers, labs, and topics across Lattice.
3
0
7
5
Storing knowledge directly in LLM parameters offers a flexible, efficient alternative to in-context learning, bypassing context length limitations and repeated encoding costs.
Large-scale rewards can unfairly suppress learning signals from smaller rewards in multi-objective RL; CorrGRPO fixes this by normalizing reward covariances.
RLPF transforms how code generation models are trained by prioritizing runtime efficiency alongside correctness, leading to a dramatic increase in both runnable solutions and execution speed.
