Lior Wolf

Lior Wolf is a Professor at the School of Computer Science, Tel Aviv University. Previously, he was a postdoctoral researcher at MIT's Center for Biological and Computational Learning (CBCL) under Prof. Tomaso Poggio and earned his PhD from Hebrew University of Jerusalem with Prof. Amnon Shashua.

His educational background includes:

• PhD in Computer Science, Hebrew University of Jerusalem
• Postdoctoral Research, MIT CBCL

Prof. Wolf's research centers on artificial intelligence with seminal contributions to deep learning, computer vision, and natural language processing. His work bridges theoretical foundations (e.g., attention mechanisms, transformer analysis) with practical applications in medical imaging, speech processing, and sign language technology. He pioneered methods for neural network interpretability, efficient sequence modeling, and multimodal fusion.

Analysis of his 2023-2025 publications reveals dominant trends in large language model optimization (neuron pruning, attention analysis), efficient video generation, and cross-modal learning. His work increasingly integrates medical applications (fMRI/EEG analysis) while maintaining theoretical rigor in model architecture design.

His scientific achievements include:

• Best paper award at EMNLP 2024 for 'Backward Lens: Projecting Language Model Gradients into the Vocabulary Space'
• Best paper award at SCIA 2023 for 'Gradient Adjusting Networks for Domain Inversion'
• Best paper award at FG 2021 for 'Generating Master Faces for Dictionary Attacks'

Prof. Wolf mentors graduate students in the School of Computer Science and leads research at the ICRC building laboratory. His team collaborates with 'the friends of TAU' on projects spanning biometric security, medical imaging, and generative AI. Current work focuses on efficient transformers, neural network interpretability, and multimodal medical diagnostics.