Search papers, labs, and topics across Lattice.
5
0
7
4
MRRG reveals that leveraging multiple evaluative perspectives can significantly enhance the quality of reward signals for LLM optimization, outperforming traditional single-role approaches.
Achieving one-step audio waveform generation with a 17脳 speedup while preserving quality could revolutionize TTS systems.
Leveraging hidden states from reward models can boost RLHF performance by over 6% on challenging benchmarks, transforming how we utilize reward signals.
Merging concrete visual rollouts with abstract reasoning leads to a 10.6% and 10.9% performance boost on challenging reasoning benchmarks, showcasing the power of hybrid models.
LLMs can compile GUI code, but can't actually *play* it, highlighting a critical gap in their ability to generate logically correct, interactive applications.
