Obserwuj
Hila Chefer
Hila Chefer
PhD student at Tel Aviv University, Google
Zweryfikowany adres z mail.tau.ac.il - Strona główna
Tytuł
Cytowane przez
Cytowane przez
Rok
Transformer interpretability beyond attention visualization
H Chefer, S Gur, L Wolf
Proceedings of the IEEE/CVF conference on computer vision and pattern …, 2021
8712021
Attend-and-excite: Attention-based semantic guidance for text-to-image diffusion models
H Chefer, Y Alaluf, Y Vinker, L Wolf, D Cohen-Or
ACM Transactions on Graphics (TOG) 42 (4), 1-10, 2023
4392023
Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers
H Chefer, S Gur, L Wolf
Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2021
3542021
Lumiere: A space-time diffusion model for video generation
O Bar-Tal*, H Chefer*, O Tov*, C Herrmann, R Paiss, S Zada, A Ephrat, ...
arXiv preprint arXiv:2401.12945, 2024
1802024
Optimizing relevance maps of vision transformers improves robustness
H Chefer, I Schwartz, L Wolf
Advances in Neural Information Processing Systems 35, 33618-33632, 2022
452022
Image-based clip-guided essence transfer
H Chefer, S Benaim, R Paiss, L Wolf
European Conference on Computer Vision 13673, 695-711, 2022
412022
No token left behind: Explainability-aided image classification and generation
R Paiss, H Chefer, L Wolf
European Conference on Computer Vision, 334-350, 2022
302022
The hidden language of diffusion models
H Chefer, O Lang, M Geva, V Polosukhin, A Shocher, M Irani, I Mosseri, ...
The International Conference on Learning Representations (ICLR) 2024 (2024), 2024
182024
Discriminative class tokens for text-to-image diffusion models
I Schwartz, V Snæbjarnarson, H Chefer, S Belongie, L Wolf, S Benaim
Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2023
92023
Still-moving: Customized video generation without customized video data
H Chefer, S Zada, R Paiss, A Ephrat, O Tov, M Rubinstein, L Wolf, T Dekel, ...
ACM Transactions on Graphics (TOG) 43 (6), 1-11, 2024
82024
VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Models
H Chefer, U Singer, A Zohar, Y Kirstain, A Polyak, Y Taigman, L Wolf, ...
arXiv preprint arXiv:2502.02492, 2025
2025
Nie można teraz wykonać tej operacji. Spróbuj ponownie później.
Prace 1–11