Search papers, labs, and topics across Lattice.
The University of Sydney
4
0
8
FracEvent achieves superior event timing and downstream performance by accurately modeling pixel dynamics, outperforming traditional simulators.
Deep transformers can encode complex grammatical structures in low-dimensional spaces, supporting the linear representation hypothesis.
Finally, a way to judge the *vibes* of your 3D Gaussian Splatting scenes, without needing to render a bunch of images.
MLLMs can be significantly boosted by curriculum learning that focuses on reward design rather than data selection, dynamically weighting generalized rubrics based on the model's evolving competence.
