Search papers, labs, and topics across Lattice.
3
0
6
14
Forget generic chatbots – now, with just 10 images and interaction examples, you can fine-tune a model to embody a specific character with a consistent persona, dialogue style, and visual identity across text and images.
Despite impressive headline scores, today's best video MLLMs can't reliably ground their answers in space and time, achieving <1% accuracy when required to identify the spatio-temporal evidence supporting their predictions.
Diffusion models can generate segmentations that rival discriminative methods, but only if you reshape their vector fields with a distance-aware correction term that combats gradient vanishing.
