Search papers, labs, and topics across Lattice.
4
0
8
3
Executable Blender code transforms text-to-video generation, enabling unprecedented control over scene dynamics and visual fidelity.
SteerVTE achieves unprecedented precision in video text editing, outperforming existing methods in accuracy and style consistency.
LLMs can now be benchmarked for their ability to prepare training data, revealing that a new evaluation metric outperforms traditional methods in predicting downstream utility.
DataFlex makes data-centric LLM training dramatically easier, unifying disparate methods for data selection, mixing, and reweighting into a single, efficient, and reproducible framework.
