Publications (15)
Lumiere: A Space-Time Diffusion Model for Video Generation
Omer Bar-Tal, Hila Chefer, Omer Tov +14
We introduce Lumiere -- a text-to-video diffusion model designed for synthesizing videos that portray realistic, diverse and coherent motion -- a pivotal challenge in video synthes…
FlowMo: Variance-Based Flow Guidance for Coherent Motion in Video Generation
Ariel Shaulov, Itay Hazan, Lior Wolf +1
Text-to-video diffusion models are notoriously limited in their ability to model temporal aspects such as motion, physics, and dynamic interactions. Existing approaches address thi…
Optimizing Relevance Maps of Vision Transformers Improves Robustness
Hila Chefer, Idan Schwartz, Lior Wolf
It has been observed that visual classification models often rely mostly on the image background, neglecting the foreground, which hurts their robustness to distribution changes. T…
Self-Supervised Flow Matching for Scalable Multi-Modal Synthesis
Hila Chefer, Patrick Esser, Dominik Lorenz +5
Strong semantic representations improve the convergence and generation quality of diffusion and flow models. Existing approaches largely rely on external models, which require sepa…
VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Models
Hila Chefer, Uriel Singer, Amit Zohar +5
Despite tremendous recent progress, generative video models still struggle to capture real-world motion, dynamics, and physics. We show that this limitation arises from the convent…
Revisiting LRP: Positional Attribution as the Missing Ingredient for Transformer Explainability
Yarden Bakish, Itamar Zimerman, Hila Chefer +1
The development of effective explainability tools for Transformers is a crucial pursuit in deep learning research. One of the most promising approaches in this domain is Layer-wise…