Search papers, labs, and topics across Lattice.
Affiliation:
2
0
5
Spatio-temporal masking during student self-rollouts breaks the reverse-KL mode-collapse trap in autoregressive video diffusion, eliminating visual over-smoothing without relying on real video data.
Training LLMs without ground-truth solutions can yield significant performance improvements, as shown by RiVER's success in enhancing both score-based and exact-solution benchmarks.
