Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
Affiliation:
3
0
6
7
Jointly diffusing token and cluster embeddings unlocks significant gains in continuous diffusion language models, achieving state-of-the-art perplexity and reasoning performance with minimal overhead.
End-to-end learning of temporally predictable latent spaces for world models unlocks superior future scene understanding without the need for separate representation and prediction training stages.
Image diffusion models get a boost by letting their semantic feature space evolve during training, leading to faster convergence and better image quality.