Technion - Israel Institute of Technology
Tel Aviv University
Axel SauerCo-founder · Black Forest LabsResearcher↗
Researcher
Hila Chefer
Black Forest LabsResearcher
Chefer makes visual foundation models easier to understand and control. She developed widely used explanations for vision transformers[1] and contributed to Lumiere[2] and VideoJAM, systems for coherent text-to-video generation and physical motion[3]; she now conducts fundamental research at Black Forest Labs.[4]
Career & education
Current roleBlack Forest LabsJul 2025-presentResearcher
Black Forest LabsJul 2025-presentPreviously
Meta2024-2025Research Intern
Meta2024-2025Work and education history is primarily focused on AI-relevant roles and may not be comprehensive.
Citation Trend
Total citations to scholarly work, including research papers, technical reports, books and theses, as recorded by Google Scholar. Each point is a dated snapshot.
citations4,798As of Oct 21, '26
citations+705Since last snapshot, Jun 15, '26
References
- Transformer Interpretability Beyond Attention Visualizationopenaccess.thecvf.com
Chefer co-authored a method for explaining transformer predictions, including image classification.
- Lumiere: A Space-Time Diffusion Model for Video Generationarxiv.org
Chefer co-authored a text-to-video model designed for coherent motion.
- VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Modelsproceedings.mlr.press
Chefer led a paper on improving motion coherence in generated video.
- Hila Chefer — Personal websitehila-chefer.github.io
Chefer identifies her team as Fundamental Research at Black Forest Labs.
Based on public sources. If accuracy is important, verify details using the links or references.
For corrections, updates, or requests to remove information, contact us.
Reviewed August 10, 2026 · Checked for accuracy and new information.