Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
2
0
6
6
Harnessing earlier recurrent states as implicit weak supervision, a training-free contrastive decoding method boosts Looped Transformer performance by up to 11.45% and enables 22.5%-48.2% FLOP reduction.
Forget slow, expensive neural verifiers: this work shows a simple corpus lookup can provide faster, better rewards for RL fine-tuning of QA models.