Search papers, labs, and topics across Lattice.
5
0
9
4
Caption quality can make or break the performance of text-to-video models, revealing a critical yet often overlooked aspect of model training.
DREAM-Chunk transforms action chunking by leveraging latent world models to enhance robustness against stochastic dynamics without the need for policy retraining.
Achieve high-fidelity 4D mesh generation from video by cleverly repurposing existing positional encodings for temporal information, sidestepping the usual trade-offs between expressiveness and pretraining compatibility.
Trade strict equivariance for a performance boost: this weight-space projection method lets you dial in the right amount of symmetry for your task, even on ImageNet.
Stop single-concept defenses: this work introduces a multi-concept model immunization technique that protects open-source models from misuse across a range of harmful applications.
