Search papers, labs, and topics across Lattice.
2
36
5
12
By decoupling MLLM instruction tuning from DiT alignment, DuoGen achieves state-of-the-art interleaved multimodal generation without costly unimodal pretraining.
Forget synthetic data that looks like it came from a PS2 game: NVIDIA's new Cosmos-Predict2.5 generates high-fidelity videos for training embodied AI, opening the door to more realistic and reliable simulations.
