Hadar Averbuch-Elor

Evaluating various models across diverse categories reveals that current models can only maintain short-term consistency that degrades significantly once objects leave the field of view, highlighting the gap between current model capabilities and robust visual memory ("seeing is not remembering"), providing guidance for future development of 4D foundation models.

Fine-grained identity tuning enables precise facial edits in text-to-image models without additional training, preserving identity consistency across diverse outputs.

Achieve surgical 3D edits without training: Prox-E lets you reshape objects with language by manipulating a compact set of geometric primitives.