Search papers, labs, and topics across Lattice.
6
0
8
26
Automated data curation and imbalance-aware training strategies significantly enhance LALMs' performance on culturally diverse folk music, yet deep musical understanding remains elusive.
HOMIE redefines video personalization by seamlessly integrating inter- and intra-subject inputs, achieving unprecedented fidelity and interaction accuracy.
Embedding reference tokens at semantic positions allows for unprecedented precision in multi-reference video editing, setting a new benchmark for instruction quality.
Harnesses can evolve in real-time during evaluation, leading to significant performance gains without retraining the underlying model.
MiniMax-M2 proves that massive parameter counts don't always translate to better agentic performance; strategic activation of a smaller subset can unlock frontier-level intelligence.
Control both multi-subject identity and multi-granularity motion in video generation with DreamVideo-Omni, a framework that uses latent identity reinforcement learning to avoid identity degradation.
