Search papers, labs, and topics across Lattice.
3
0
6
6
Disentangling high-level cross-modal reasoning from low-level modality-specific refinement in talking head generation yields superior lip-sync accuracy, video quality, and audio quality compared to entangled approaches.
Strategic data curation using a dual-consensus approach beats brute-force training on large noisy datasets for process reward modeling in biological reasoning.
MLLMs can be made significantly safer in multi-turn dialogues with a new framework that combines cold-start refusal and turn-aware policy optimization, achieving a 10% drop in attack success rate.
