Chefer, Hila

10 publications

NeurIPS 2025 FlowMo: Variance-Based Flow Guidance for Coherent Motion in Video Generation Ariel Shaulov, Itay Hazan, Lior Wolf, Hila Chefer

NeurIPS 2025 Revisiting LRP: Positional Attribution as the Missing Ingredient for Transformer Explainability Yarden Bakish, Itamar Zimerman, Hila Chefer, Lior Wolf

ICML 2025 VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Models Hila Chefer, Uriel Singer, Amit Zohar, Yuval Kirstain, Adam Polyak, Yaniv Taigman, Lior Wolf, Shelly Sheynin

ICLR 2024 The Hidden Language of Diffusion Models Hila Chefer, Oran Lang, Mor Geva, Volodymyr Polosukhin, Assaf Shocher, Michal Irani, Inbar Mosseri, Lior Wolf

ICCV 2023 Discriminative Class Tokens for Text-to-Image Diffusion Models Idan Schwartz, Vésteinn Snæbjarnarson, Hila Chefer, Serge Belongie, Lior Wolf, Sagie Benaim

ECCV 2022 Image-Based CLIP-Guided Essence Transfer Hila Chefer, Sagie Benaim, Roni Paiss, Lior Wolf

ECCV 2022 No Token Left Behind: Explainability-Aided Image Classification and Generation Roni Paiss, Hila Chefer, Lior Wolf

NeurIPS 2022 Optimizing Relevance Maps of Vision Transformers Improves Robustness Hila Chefer, Idan Schwartz, Lior Wolf

ICCV 2021 Generic Attention-Model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers Hila Chefer, Shir Gur, Lior Wolf

CVPR 2021 Transformer Interpretability Beyond Attention Visualization Hila Chefer, Shir Gur, Lior Wolf