Search papers, labs, and topics across Lattice.
Huawei Central Research Institute
4
0
8
Transforming the data manifold into a nearly cost-free reward model could revolutionize text-to-video generation by drastically improving realism and detail without the need for extensive human annotations.
SpecLoR cuts through noise and drift in text-to-video generation, achieving remarkable motion coherence with minimal computational cost.
Homogeneous neural networks can be trained with provable generalization guarantees using significantly larger stepsizes than previously thought possible.
LLM benchmark accuracy jumps 10% when evaluated on a cleaned-up version of Humanity's Last Exam, highlighting the significant impact of dataset noise on performance metrics.
