Search papers, labs, and topics across Lattice.
with Dolby Laboratories, Inc
3
0
5
Traditional pruning methods compromise prediction accuracy, but a new rationale-informed strategy ensures both accuracy and evidence alignment in VLMs.
Current VLMs miss crucial transition-level physics, but APT-Tune teaches them to learn causal transitions without forgetting event-level context.
Video diffusion models can now generate physically plausible 4D worlds thanks to a new pipeline that combines pretraining, supervised fine-tuning, and reinforcement learning.
