Search papers, labs, and topics across Lattice.
3
0
3
Achieving high-quality model performance with just 10% of the required labels could revolutionize the scalability of RLVR in large language models.
A fixed span can recover most of the benefits of movable low-rank factors in LLM adaptation, achieving superior performance with drastically fewer trainable parameters.
Over 57% of training samples suffer from suppressed criteria, but a new self-distillation method can reverse this trend and enhance performance in RL tasks.
