Gal Chechik | Research

Gal Chechik

Gal Chechik is a Sr. Director of AI research, leading NVIDIA research in Israel.

Gal is also a Professor of computer science at Bar-Ilan University. Before joining NVIDIA, he was a Staff Research Scientist at Google, a postdoctoral research associate at Stanford University, and received his PhD from the Hebrew University of Jerusalem. Gal published ~140 papers, including publications in Nature Biotechnology, Cell and PNAS, and holds 50 issued patents. His work won awards for outstanding papers at NeurIPS and ICML.

Gal's group of NVIDIA research in Israel spans algorithms, theory and applications of deep learning, with a focus on computer vision and reinforcement learning. A particular interest is in perception, action, and reasoning (PAR) and their intersection for the purpose of smarter generalization.

Research Area(s)

Artificial Intelligence and Machine Learning

Main Field of Interest

Artificial Intelligence and Machine Learning

Google Scholar

https://scholar.google.com/citations?user=Wk2gAZUAAAAJ&hl=en

Publications

2024

MaskedMimic: Unified Physics-Based Character Control Through Masked Motion Inpainting

Chen Tessler, Kelly Guo, Ofir Nabati, Gal Chechik, Jason Peng

SIGGRAPH Asia 2024

Breathing Life Into Sketches Using Text-to-Video Priors

Rinon Gal, Yael Vinker, Yuval Alaluf, Amit Bermano, Daniel Cohen-Or, Ariel Shamir, Gal Chechik

LCM-Lookahead for Encoder-based Text-to-Image Personalization

Rinon Gal, Or Lichter, Elad Richardson, Or Patashnik, Amit H Bermano, Gal Chechik, Daniel Cohen-Or

ConsiStory: Training-Free Consistent Text-to-Image Generation

Yoad Tewel, Omri Kaduri, Rinon Gal, Yoni Kasten, Lior Wolf, Gal Chechik, Yuval Atzmon

Generating images of rare concepts using pre-trained diffusion models

Dvir Samuel, Rami Ben-Ari, Simon Raviv, Nir Darshan, Gal Chechik

2023

Point-Cloud Completion with Pretrained Text-to-image Diffusion Models

Yoni Kasten, Ohad Rahamim, Gal Chechik

Domain-Agnostic Tuning-Encoder for Fast Personalization of Text-To-Image Models

Moab Arar, Rinon Gal, Yuval Atzmon, Gal Chechik, Daniel Cohen-Or, Ariel Shamir, Amit Bermano

SIGGRAPH Asia 2023

Syntactic Binding in Diffusion Models: Enhancing Attribute Correspondence through Attention Map Alignment

Royi Rassin, Eran Hirsch, Daniel Glickman, Shauli Ravfogel, Yoav Goldberg, Gal Chechik

Oral presentation

Norm-guided latent space exploration for text-to-image generation

Dvir Samuel, Rami Ben-Ari, Nir Darshan, Haggai Maron, Gal Chechik

Encoder-based Domain Tuning for Fast Personalization of Text-to-Image Models

Rinon Gal, Moab Arar, Yuval Atzmon, Amit Bermano, Gal Chechik, Daniel Cohen-Or

Key-Locked Rank One Editing for Text-to-Image Personalization

Yoad Tewel, Rinon Gal, Gal Chechik, Yuval Atzmon

Guided Deep Kernel Learning

Idan Achituve, Gal Chechik, Ethan Fetaya

Encoder-based Domain Tuning for Fast Personalization of Text-to-Image Models

Rinon Gal, Moab Arar, Yuval Atzmon, Amit H. Bermano, Gal Chechik, Daniel Cohen-Or

Learning to Initiate and Reason in Event-Driven Cascading Processes

Yuval Atzmon, Eli Meirom, Shie Mannor, Gal Chechik

Train Hard, Fight Easy: Robust Meta Reinforcement Learning

Ido Greenberg, Shie Mannor, Gal Chechik, Eli Meirom

CALM: Conditional Adversarial Latent Models for Directable Virtual Characters

Chen Tessler, Yoni Kasten, Yunrong Guo, Shie Mannor, Gal Chechik, Xue Bin Peng

Equivariant Architectures for Learning in Deep Weight Spaces

Aviv Navon, Aviv Shamsian, Idan Achituve, Ethan Fetaya, Gal Chechik, Haggai Maron

Implementing Reinforcement Learning Datacenter Congestion Control in NVIDIA NICs

Benjamin Fuhrer, Yuval Shpigelman, Chen Tessler, Shie Mannor, Gal Chechik, Eitan Zahavy, Gal Dalal

2022

"This is my unicorn, Fluffy": Personalizing frozen vision-language representations

Niv Cohen, Rinon Gal, Eli Meirom, Gal Chechik, Yuval Atzmon

On Covariate Shift of Latent Confounders in Imitation and Reinforcement Learning

Guy Tenneholtz, Assaf Hallak, Gal Dalal, Shie Mannor, Gal Chechik

An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion

Rinon Gal, Yuval Alaluf, Yuval Atzmon, Or Patashnik, Amit H. Bermano, Gal Chechik, Daniel Cohen-Or

Top 25%

Optimizing tensor network contraction using reinforcement learning

Eli Meirom, Haggai Maron, Shie Mannor, Gal Chechik

International Conference on Machine Learning, PMLR 162:15278-15292, 2022

StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators

Rinon Gal, Or Patashnik, Haggai Maron, Amir Bermano, Gal Chechik, Daniel Cohen-Or

"This is my unicorn, Fluffy": Personalizing frozen vision-language representations

Niv Cohen, Rinon Gal, Gal Chechik, Yuval Atzmon

Oral

Reinforcement Learning for Datacenter Congestion Control

Chen Tessler, Yuval Shpigelman, Gal Dalal, Amit Mendelbaum, Doron Kazakov, Benjamin Fuhrer, Gal Chechik, Shie Mannor

IAAI 2022

2021

Improve Agents without Retraining: Parallel Tree Search with Off-Policy Correction

Gal Dalal, Assaf Hallak, Steven Dalton, Iuri Frosio, Shie Mannor, Gal Chechik

Advances in Neural Information Processing Systems 34 (NeurIPS 2021)

Known unknowns: Learning novel concepts using exploratory reasoning-by-elimination

Harsh Agrawal, Eli Meirom, Yuval Atzmon, Shie Mannor, Gal Chechik

Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Inte…

Oral

Controlling graph dynamics with reinforcement learning and graph neural networks

Eli Meirom, Haggai Maron, Shie Mannor, Gal Chechik

From local structures to size generalization in graph neural networks

Gilad Yehudai, Ethan Fetaya, Eli Meirom, Gal Chechik, Haggai Maron

Auxiliary Learning by Implicit Differentiation

Aviv Navon, Idan Achituve, Haggai Maron, Gal Chechik, Ethan Fetaya

Learning the Pareto Front with Hypernetworks

Aviv Navon, Aviv Shamsian, Ethan Fetaya, Gal Chechik

Planning and Learning with Adaptive Lookahead

Aviv Rosenberg, Assaf Hallak, Shie Mannor, Gal Chechik, Gal Dalal

Federated Learning with Heterogeneous Architectures using Graph HyperNetworks

Or Litany, Haggai Maron, David Acuna, Jan Kautz, Gal Chechik, Sanja Fidler

Self-Supervised Learning for Domain Adaptation on Point-Clouds

Idan Achituve, Haggai Maron, Gal Chechik

Winter Conference on Applications of Computer Vision (WACV), 2021

From Generalized Zero-Shot Learning to Long-Tail with Class Descriptors

Dvir Samuel, Yuval Atzmon, Gal Chechik

Winter Conference on Applications of Computer Vision (WACV) 2021

2020

A Causal View of Compositional Zero-Shot Recognition

Yuval Atzmon, Felix Kreuk, Uri Shalit, Gal Chechik

Neural Information Processing Systems (NeurIPS) 2020 (Spotlight)

ZEST: Zero-shot Learning from Text Descriptions using Textual Similarity and Visual Summarization

Tzuf Paz-Argaman, Yuval Atzmon, Gal Chechik, Reut Tsarfaty

Findings of EMNLP

Learning Object Permanence from Video

Aviv Shamsian, Ofri Kleinfeld, Amir Globerson, Gal Chechik

On Learning Sets of Symmetric Elements

Haggai Maron, Or Litany, Gal Chechik, Ethan Fetaya

International Conference on Machine Learning (ICML) 2020

Outstanding Paper, ICML 2020

Contrastive Learning for Weakly Supervised Phrase Grounding

Tanmay Gupta, Arash Vahdat, Gal Chechik, Xiaodong Yang, Jan Kautz, Derek Hoiem

European Conference on Computer Vision (ECCV) 2020 (Spotlight)

Learning Canonical Representations for Scene Graph to Image Generation

Roei Herzig, Amir Bar, Huijuan Xu, Gal Chechik, Trevor Darrell, Amir Globerson

2019

Joint Optimization for Cooperative Image Captioning

Gilad Vered, Gal Oren, Yuval Atzmon, Gal Chechik

International conference on computer vision (ICCV)

Adaptive Confidence Smoothing for Generalized Zero-Shot Learning

Yuval Atzmon, Gal Chechik

Computer Vision and Pattern Recognition (CVPR) 2019

Informative Object Annotations: Tell Me Something I Don't Know

Lior Bracha, Gal Chechik

Computer Vision and Pattern Recognition

2018

Mapping Images to Scene Graphs with Permutation-Invariant Structured Prediction

Roei Herzig, Moshiko Raboh, Gal Chechik, Jonathan Berant, Amir Globerson

Neural Information processing systems (NeurIPS)

Probabilistic AND-OR Attribute Grouping for Zero-Shot Learning

Yuval Atzmon, Gal Chechik

The conference on uncertainty in artificial intelligence (UAI 2018)

2017

Group online adaptive learning

Alon Zweig, Gal Chechik

Journal Machine Learning

Context-aware Captions from Context-agnostic Supervision

Ramakrishna Vedantam, Samy Bengio, Kevin Murphy, Devi Parikh, Gal Chechik

Computer Vision and Pattern Recognition

Learning From Noisy Large-Scale Datasets With Minimal Supervision

Andreas Veit, Neil Alldrin, Gal Chechik, Ivan Krasin, Abhinav Gupta, Serge Belongie

Computer Vision and Pattern Recognition

2016

Learning to generalize to new compositions in image understanding

Yuval Atzmon, Jonathan Berant, Vahid Kezami, Amir Globerson, Gal Chechik

2015

Learning Sparse Metrics, One Feature at a Time

Yuval Atzmon, Uri Shalit, Gal Chechik

Journal of Machine Learning Research

Graph Positional Encoding via Random Feature Propagation

Moshe Eliasof, Fabrizio Frasca, Beatrice Bevilacqua, Eran Treister, Gal Chechik, Haggai Maron