2024
- Discrete Flow Matching (Spotlight). Itai Gat, Tal Remez, Neta Shaul, Felix Kreuk, Ricky T. Q. Chen, Gabriel Synnaeve, Yossi Adi, Yaron Lipman. Advances in Neural Information Processing Systems (NeurIPS), 2024
[
PDF,
BibTeX
]
@inproceedings{gat2024discrete,
title={Discrete Flow Matching},
author={Itai Gat and Tal Remez and Neta Shaul and Felix Kreuk and Ricky T. Q. Chen and Gabriel Synnaeve and Yossi Adi and Yaron Lipman},
booktitle={NeurIPS},
year ={2024},
}
- Generator Matching: Generative modeling with arbitrary Markov processes. Peter Holderrieth, Marton Havasi, Jason Yim, Neta Shaul, Itai Gat, Tommi Jaakkola, Brian Karrer, Ricky TQ Chen, Yaron Lipman.
[
PDF,
BibTeX
]
@article{holderrieth2024generator,
title={Generator Matching: Generative modeling with arbitrary Markov processes},,
author={Peter Holderrieth and Marton Havasi and Jason Yim and Neta Shaul and Itai Gat and Tommi Jaakkola and Brian Karrer and Ricky T. Q. Chen and Yaron Lipman},
journal={arXiv preprint arXiv:2410.20587},
year={2024}
}
- Exact Byte-Level Probabilities from Tokenized Language Models for FIM-Tasks and Model Ensembles. Buu Phan, Brandon Amos, Itai Gat, Marton Havasi, Matthew Muckley, Karen Ullrich.
[
PDF,
BibTeX
]
@article{phan2024exact,
title={Exact Byte-Level Probabilities from Tokenized Language Models for FIM-Tasks and Model Ensembles},
author={Phan, Buu and Amos, Brandon and Gat, Itai and Havasi, Marton and Muckley, Matthew and Ullrich, Karen},
journal={arXiv preprint arXiv:2410.09303},
year={2024}
}
- The Llama 3 Herd of Models. Llama Team, AI @ Meta.
[
PDF,
Code and Models,
Website,
BibTeX
]
@inproceedings{dubey2024llama3herdmodels,
title={The Llama 3 Herd of Models},
author={Llama Team, AI @ Meta},
booktitle={arXiv},
year ={2024},
}
- D-Flow: Differentiating through Flows for Controlled Generation. Heli Ben-Hamu, Omri Puny, Itai Gat, Brian Karrer, Uriel Singer, Yaron Lipman. International Conference on Machine Learning (ICML), 2024
[
PDF,
BibTeX
]
@inproceedings{ben2024d,
title={D-Flow: Differentiating through Flows for Controlled Generation},
author={Ben-Hamu, Heli and Puny, Omri and Gat, Itai and Karrer, Brian and Singer, Uriel and Lipman, Yaron},
booktitle={ICML},
year ={2024},
}
- SpiRit-LM: Interleaved Spoken and Written Language Model. Tu Anh Nguyen, Benjamin Muller, Bokai Yu, Marta R. Costa-jussa, Maha Elbayad, Sravya Popuri, Paul-Ambroise Duquenne, Robin Algayres, Ruslan Mavlyutov, Itai Gat, Gabriel Synnaeve, Juan Pino, Benoit Sagot, Emmanuel Dupoux. Transactions of the Association for Computational Linguistics (TACL), 2024
[
PDF,
Website,
BibTeX
]
@inproceedings{nguyen2024spirit,
title={Spirit-lm: Interleaved spoken and written language model},
author={Nguyen, Tu Anh and Muller, Benjamin and Yu, Bokai and Costa-Jussa, Marta R and Elbayad, Maha and Popuri, Sravya and Duquenne, Paul-Ambroise and Algayres, Robin and Mavlyutov, Ruslan and Gat, Itai and others},
booktitle={TACL},
year ={2024},
}
- Masked Audio Generation using a Single Non-Autoregressive Transformer. Alon Ziv, Itai Gat, Gael Le Lan, Tal Remez, Felix Kreuk, Alexandre Defossez, Jade Copet, Gabriel Synnaeve, Yossi Adi. International Conference on Learning Representations (ICLR), 2024
[
PDF,
Code and Models,
Website,
BibTeX
]
@inproceedings{ziv2024magnet,
title={Masked Audio Generation using a Single Non-Autoregressive Transformer},
author={Alon Ziv and Itai Gat and Gael Le Lan and Tal Remez and Felix Kreuk and Alexandre Defossez and Jade Copet and Gabriel Synnaeve and Yossi Adi},
year={2024},
booktitle={ICLR}
}
- Joint Audio and Symbolic Conditioning for Temporally Controlled Text-to-Music Generation. Or Tal, Alon Ziv, Itai Gat, Felix Kreuk, Yossi Adi. International Society for Music Information Retrieval (ISMIR)
[
PDF,
Code and Models,
Website,
BibTeX
]
@inproceedings{tal2024joint,
title={Joint Audio and Symbolic Conditioning for Temporally Controlled Text-to-Music Generation},
author={Tal, Or and Ziv, Alon and Gat, Itai and Kreuk, Felix and Adi, Yossi},
booktitle={ISMIR},
year ={2024},
}
- Diverse and Aligned Audio-to-Video Generation via Text-to-Video Model Adaptation. Guy Yariv, Itai Gat, Sagie Benaim, Lior Wolf, Idan Schwartz, Yossi Adi. The Thirty-Eighth AAAI Conference on Artificial Intelligence (AAAI), 2024
[
PDF,
Code and Models,
Website,
BibTeX
]
@misc{yariv2023diverse,
title={Diverse and Aligned Audio-to-Video Generation via Text-to-Video Model Adaptation},
author={Guy Yariv and Itai Gat and Sagie Benaim and Lior Wolf and Idan Schwartz and Yossi Adi},
year={2024},
booktitle={AAAI}
}
- Layer Collaboration in the Forward-Forward Algorithm. Guy Lorberbom*, Itai Gat*, Yossi Adi, Alex Schwing, Tamir Hazan. The Thirty-Eighth AAAI Conference on Artificial Intelligence (AAAI), 2024
[
PDF,
BibTeX
]
@inproceedings{lorberbom2023layer,
title={Layer Collaboration in the Forward-Forward Algorithm},
author={Guy Lorberbom and Itai Gat and Yossi Adi and Alex Schwing and Tamir Hazan},
year={2023},
booktitle={AAAI},}
2023
- Code Llama: Open Foundation Models for Code. Baptiste Rozière, Jonas Gehring, Fabian Gloeckle, Sten Sootla, Itai Gat, Xiaoqing Ellen Tan, Yossi Adi, Jingyu Liu, Tal Remez, Jérémy Rapin, Artyom Kozhevnikov, Ivan Evtimov, Joanna Bitton, Manish Bhatt, Cristian Canton Ferrer, Aaron Grattafiori, Wenhan Xiong, Alexandre Défossez, Jade Copet, Faisal Azhar, Hugo Touvron, Louis Martin, Nicolas Usunier, Thomas Scialom, Gabriel Synnaeve. arXiv, 2023
[
PDF,
Code and Models,
Blog,
BibTeX
]
@misc{roziere2023code,
title={Code Llama: Open Foundation Models for Code},
author={Baptiste Rozière and Jonas Gehring and Fabian Gloeckle and Sten Sootla and Itai Gat and Xiaoqing Ellen Tan and Yossi Adi and Jingyu Liu and Tal Remez and Jérémy Rapin and Artyom Kozhevnikov and Ivan Evtimov and Joanna Bitton and Manish Bhatt and Cristian Canton Ferrer and Aaron Grattafiori and Wenhan Xiong and Alexandre Défossez and Jade Copet and Faisal Azhar and Hugo Touvron and Louis Martin and Nicolas Usunier and Thomas Scialom and Gabriel Synnaeve},
year={2023},
eprint={2308.12950},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
- Simple and Controllable Music Generation. Jade Copet, Felix Kreuk, Itai Gat, Tal Remez, David Kant, Gabriel Synnaeve, Yossi Adi, Alexandre Défossez. Advances in Neural Information Processing Systems (NeurIPS), 2023
[
PDF,
Demo,
Code,
BibTeX
]
@inproceedings{copet2023simple,
title={Simple and Controllable Music Generation},
author={Jade Copet and Felix Kreuk and Itai Gat and Tal Remez and David Kant and Gabriel Synnaeve and Yossi Adi and Alexandre Défossez},
booktitle={NeurIPS},
year ={2023},}
}
- Textually Pretrained Speech Language Models. Michael Hassid, Tal Remez, Tu Anh Nguyen, Itai Gat, Alexis Conneau, Felix Kreuk, Jade Copet, Alexandre Defossez, Gabriel Synnaeve, Emmanuel Dupoux, Roy Schwartz, Yossi Adi. Advances in Neural Information Processing Systems (NeurIPS), 2023
[
PDF,
Samples,
BibTeX
]
@inproceedings{hassid2023textually,
title={Textually Pretrained Speech Language Models},
author={Michael Hassid and Tal Remez and Tu Anh Nguyen and Itai Gat and Alexis Conneau and Felix Kreuk and Jade Copet and Alexandre Defossez and Gabriel Synnaeve and Emmanuel Dupoux and Roy Schwartz and Yossi Adi},
booktitle={NeurIPS},
year ={2023},}
- Expresso: A Benchmark and Analysis of Discrete Expressive Speech Resynthesis. Tu Anh Nguyen, Wei-Ning Hsu, Antony d'Avirro, Bowen Shi, Itai Gat, Maryam Fazel-Zarandi, Tal Remez, Jade Copet, Gabriel Synnaeve, Michael Hassid, Felix Kreuk, Yossi Adi, Emmanuel Dupoux. International Speech Communication Association (Interspeech), 2023
[
PDF,
BibTeX
]
@inproceedings{expresso2023,
title={Expresso: A Benchmark and Analysis of Discrete Expressive Speech Resynthesis},
author={Tu Anh Nguyen, Wei-Ning Hsu, Antony d'Avirro, Bowen Shi, Itai Gat, Maryam Fazel-Zarandi, Tal Remez, Jade Copet, Gabriel Synnaeve, Michael Hassid, Felix Kreuk, Yossi Adi, Emmanuel Dupoux},
booktitle={INTERSPEECH},
year={2023}}
- AudioToken: Adaptation of Text-Conditioned Diffusion Models for Audio-to-Image Generation. Guy Yariv, Itai Gat, Lior Wolf, Yossi Adi, Idan Schwartz. International Speech Communication Association (Interspeech), 2023
[
PDF,
Page,
Code,
BibTeX
]
@inproceedings{yarivAudiotoken,
title={AudioToken: Adaptation of Text-Conditioned Diffusion Models for Audio-to-Image Generation},
author={Guy Yariv, Itai Gat, Lior Wolf, Yossi Adi, Idan Schwartz},
booktitle={INTERSPEECH},
year={2023}}
- Augmentation Invariant Discrete Representation for Generative Spoken Language Modeling (Oral). Itai Gat, Felix Kreuk, Tu Anh Nguyen, Ann Lee, Jade Copet, Gabriel Synnaeve, Emmanuel Dupoux, Yossi Adi. International Conference on Spoken Language Translation (IWSLT), 2023
[
PDF,
BibTeX
]
@inproceedings{augmentationgat23,
title={Augmentation Invariant Discrete Representation for Generative Spoken Language Modeling},
author={Itai Gat, Felix Kreuk, Tu Anh Nguyen, Ann Lee, Jade Copet, Gabriel Synnaeve, Emmanuel Dupoux, Yossi Adi},
booktitle={IWSLT},
year={2023}}
2022
- On the Importance of Gradient Norm in PAC-Bayesian Bounds. Itai Gat, Yossi Adi, Alex Schwing, Tamir Hazan. Advances in Neural Information Processing Systems (NeurIPS), 2022
[
PDF,
BibTeX
]
@inproceedings{gat2022importance,
title={On the Importance of Gradient Norm in PAC-Bayesian Bounds},
author={Gat, Itai and Adi, Yossi and Schwing, Alexander and Hazan, Tamir},
booktitle={NeurIPS},
year={2022}}
- On The Robustness of Self-Supervised Representations for Spoken Language Modeling. Itai Gat, Felix Kreuk, Ann Lee, Jade Copet, Gabriel Synnaeve, Emmanuel Dupoux, Yossi Adi. arXiv, 2022
[
PDF,
BibTeX
]
@inproceedings{gat2022robustness,
title={On the robustness of self-supervised representations for spoken language modeling},
author={Gat, Itai and Kreuk, Felix and Lee, Ann and Copet, Jade and Synnaeve, Gabriel and Dupoux, Emmanuel and Adi, Yossi},
booktitle={arXiv},
year={2022}}
- A Functional Information Perspective on Model Interpretation. Itai Gat, Nitay Calderon, Roi Reichart, Tamir Hazan. Proceedings of the International Conference on Machine Learning (ICML), 2022
[
PDF,
Code,
BibTeX
]
@inproceedings{gat22functional,
title={A Functional Information Perspective on Model Interpretation},
author={Gat, Itai and Calderon, Nitay and Reichart, Roi and Hazan, Tamir},
booktitle={ICML},
year ={2022},}
- Speech Emotion Recognition using Self-Supervised Features. Edmilson Morais, Ron Hoory, Weizhong Zhu, Itai Gat, Matheus Damasceno, Hagai Aronowitz. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022
[
PDF,
BibTeX
]
@inproceedings{Edmilson22SF,
title={Speech Emotion Recognition using Self-supervised Features},
author={Morais, Edmilson and Hoory, Ron and Zhu, Weizhong and Gat, Itai and Damasceno, Matheus and Aronowitz, Hagai},
booktitle={ICASSP},
year={2022}}
- Speaker Normalization for Self-supervised Speech Emotion Recognition. Itai Gat, Hagai Aronowitz, Weizhong Zhu, Edmilson Morais, Ron Hoory. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022
[
PDF,
BibTeX
]
@inproceedings{gat2022speaker,
title={Speaker Normalization for Self-supervised Speech Emotion Recognition},
author={Gat, Itai and Aronowitz, Hagai and Zhu, Weizhong and Morais, Edmilson and Hoory, Ron},
booktitle={ICASSP},
year={2022}}
- Towards a Common Speech Analysis Engine. Hagai Aronowitz, Itai Gat, Edmilson Morais, Weizhong Zhu, Ron Hoory. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022
[
PDF,
BibTeX
]
@inproceedings{Aronowitz2022towards,
title={Towards a Common Speech Analysis Engine},
author={Aronowitz, Hagai and Gat, Itai and Morais, Edmilson and Zhu, Weizhong and Hoory, Ron},
booktitle={ICASSP},
year={2022}}
2021
- Latent Space Explanation by Intervention. Itai Gat*, Guy Lorberbom*, Idan Schwartz, Tamir Hazan. Proceedings of the AAAI Conference on Artificial Intelligence, 2021
[
PDF,
BibTeX
]
@inproceedings{2022latentSpaceExplainations,
title={Latent Space Explanation by Intervention},
author={Gat, Itai and Lorberbom, Guy and Schwartz, Idan and Hazan, Tamir},
booktitle={AAAI},
year={2022}}
- Perceptual Score: What Data Modalities Does Your Model Perceive?. Itai Gat, Idan Schwartz, Alexander Schwing. Advances in Neural Information Processing Systems (NeurIPS), 2021
[
PDF,
Code,
BibTeX
]
@inproceedings{gat2021perceptual,
title={Perceptual Score: What Data Modalities Does Your Model Perceive?},
author={Gat, Itai and Schwartz, Idan and Schwing, Alex},
booktitle={NeurIPS},
year={2021}}
- Are VQA Systems RAD? Measuring Robustness to Augmented Data with Focused Interventions. Daniel Rosenberg, Itai Gat, Amir Feder, Roi Reichart. Association for Computational Linguistics (ACL), 2021
[
PDF,
Page,
BibTeX
]
@inproceedings{acl_rosen,
author={Daniel Rosenberg and Itai Gat and Amir Feder and Roi Reichart},
title= {Are {VQA} Systems RAD? Measuring Robustness to Augmented Data with
Focused Interventions},
booktitle = {ACL},
year = {2021}}
2020
- Removing Bias in Multi-modal Classifiers: Regularization by Maximizing Functional Entropies. Itai Gat, Idan Schwartz, Alexander Schwing, Tamir Hazan. Advances in Neural Information Processing Systems (NeurIPS), 2020
[
PDF,
Code,
BibTeX
]
@inproceedings{gat2020,
author = {Gat, Itai and Schwartz, Idan and Schwing, Alexander and Hazan, Tamir},
booktitle = {Advances in Neural Information Processing Systems},
title = {Removing Bias in Multi-modal Classifiers: Regularization by Maximizing Functional Entropies},
year = {2020}}