Fartash Faghri

58 papers A* 10A 1Journal 39Unranked 7
YearRankTypeTitle / Venue / Authors
2026 — conf
Beyond a Single Extractor: Re-thinking HTML-to-Text Extraction for LLM Pre-training.
EACL (Findings)
Jeffrey Li, Joshua P. Gardner, Doug Kang, Fangping Shi, Karanjeet Singh, Chun-Liang Li, Herumb Shandilya, David Leo Wright Hall, Oncel Tuzel, Percy Liang, Ludwig Schmidt, Hadi Pouransari, Fartash Faghri
2026 J jnl
Beyond a Single Extractor: Re-thinking HTML-to-Text Extraction for LLM Pretraining.
CoRR
Jeffrey Li, Josh Gardner, Doug Kang, Fangping Shi, Karanjeet Singh, Chun-Liang Li, Herumb Shandilya, David Hall, Oncel Tuzel, Percy Liang, Ludwig Schmidt, Hadipour Ansari, Fartash Faghri
2025 J jnl
AMUSE: Audio-Visual Benchmark and Alignment Framework for Agentic Multi-Speaker Understanding.
CoRR
Sanjoy Chowdhury, Karren D. Yang, Xudong Liu, Fartash Faghri, Pavan Kumar Anasosalu Vasu, Oncel Tuzel, Dinesh Manocha, Chun-Liang Li, Raviteja Vemulapalli
2025 J jnl
Barriers for Learning in an Evolving World: Mathematical Understanding of Loss of Plasticity.
CoRR
Amir Joudaki, Giulia Lanzillotta, Mohammad Samragh Razlighi, Iman Mirzadeh, Keivan Alizadeh, Thomas Hofmann, Mehrdad Farajtabar, Fartash Faghri
2025 J jnl
Data-Centric Lessons To Improve Speech-Language Pretraining.
CoRR
Vishaal Udandarao, Zhiyun Lu, Xuankai Chang, Yongqiang Wang, Violet Z. Yao, Albin Madapally Jose, Fartash Faghri, Josh Gardner, Chung-Cheng Chiu
2025 A* conf
FastVLM: Efficient Vision Encoding for Vision Language Models.
CVPR
Pavan Kumar Anasosalu Vasu, Fartash Faghri, Chun-Liang Li, Cem Koc, Nate True, Albert Antony, Gokula Santhanam, James Gabriel, Peter Grasch, Oncel Tuzel, Hadi Pouransari
2025 J jnl
FocalLens: Instruction Tuning Enables Zero-Shot Conditional Image Representations.
CoRR
Cheng-Yu Hsieh, Pavan Kumar Anasosalu Vasu, Fartash Faghri, Raviteja Vemulapalli, Chun-Liang Li, Ranjay Krishna, Oncel Tuzel, Hadi Pouransari
2025 J jnl
MobileCLIP2: Improving Multi-Modal Reinforced Training.
CoRR
Fartash Faghri, Pavan Kumar Anasosalu Vasu, Cem Koc, Vaishaal Shankar, Alexander Toshev, Oncel Tuzel, Hadi Pouransari
2025 J jnl
MobileCLIP2: Improving Multi-Modal Reinforced Training.
Trans. Mach. Learn. Res.
Fartash Faghri, Pavan Kumar Anasosalu Vasu, Cem Koc, Vaishaal Shankar, Alexander T. Toshev, Oncel Tuzel, Hadi Pouransari
2025 A* conf
Proxy-FDA: Proxy-based Feature Distribution Alignment for Fine-tuning Vision Foundation Models without Forgetting.
ICML
Chen Huang, Skyler Seto, Hadi Pouransari, Mehrdad Farajtabar, Raviteja Vemulapalli, Fartash Faghri, Oncel Tuzel, Barry-John Theobald, Joshua M. Susskind
2025 J jnl
Proxy-FDA: Proxy-based Feature Distribution Alignment for Fine-tuning Vision Foundation Models without Forgetting.
CoRR
Chen Huang, Skyler Seto, Hadi Pouransari, Mehrdad Farajtabar, Raviteja Vemulapalli, Fartash Faghri, Oncel Tuzel, Barry-John Theobald, Joshua M. Susskind
2025 — conf
TiC-LM: A Web-Scale Benchmark for Time-Continual LLM Pretraining.
ACL (1)
Jeffrey Li, Mohammadreza Armandpour, Iman Mirzadeh, Sachin Mehta, Vaishaal Shankar, Raviteja Vemulapalli, Samy Bengio, Oncel Tuzel, Mehrdad Farajtabar, Hadi Pouransari, Fartash Faghri
2025 J jnl
TiC-LM: A Web-Scale Benchmark for Time-Continual LLM Pretraining.
CoRR
Jeffrey Li, Mohammadreza Armandpour, Iman Mirzadeh, Sachin Mehta, Vaishaal Shankar, Raviteja Vemulapalli, Samy Bengio, Oncel Tuzel, Mehrdad Farajtabar, Hadi Pouransari, Fartash Faghri
2024 J jnl
CLIP meets Model Zoo Experts: Pseudo-Supervision for Visual Enhancement.
Trans. Mach. Learn. Res.
Mohammadreza Salehi, Mehrdad Farajtabar, Maxwell Horton, Fartash Faghri, Hadi Pouransari, Raviteja Vemulapalli, Oncel Tuzel, Ali Farhadi, Mohammad Rastegari, Sachin Mehta
2024 J jnl
CLIP with Quality Captions: A Strong Pretraining for Vision Tasks.
CoRR
Pavan Kumar Anasosalu Vasu, Hadi Pouransari, Fartash Faghri, Oncel Tuzel
2024 J jnl
CatLIP: CLIP-level Visual Recognition Accuracy with 2.7x Faster Pre-training on Web-scale Image-Text Data.
CoRR
Sachin Mehta, Maxwell Horton, Fartash Faghri, Mohammad Hossein Sekhavat, Mahyar Najibi, Mehrdad Farajtabar, Oncel Tuzel, Mohammad Rastegari
2024 — conf
Computational Bottlenecks of Training Small-scale Large Language Models.
ENLSP
Saleh Ashkboos, Seyed-Iman Mirzadeh, Keivan Alizadeh-Vahid, Mohammad Hossein Sekhavat, Moin Nabi, Mehrdad Farajtabar, Fartash Faghri
2024 J jnl
Computational Bottlenecks of Training Small-scale Large Language Models.
CoRR
Saleh Ashkboos, Iman Mirzadeh, Keivan Alizadeh, Mohammad Hossein Sekhavat, Moin Nabi, Mehrdad Farajtabar, Fartash Faghri
2024 A* conf
DataComp-LM: In search of the next generation of training sets for language models.
NeurIPS
Jeffrey Li, Alex Fang, Georgios Smyrnis, Maor Ivgi, Matt Jordan, Samir Yitzhak Gadre, Hritik Bansal, Etash Kumar Guha, Sedrick Scott Keh, Kushal Arora, Saurabh Garg, Rui Xin, Niklas Muennighoff, Reinhard Heckel, Jean Mercat, Mayee F. Chen, Suchin Gururangan, Mitchell Wortsman, Alon Albalak, Yonatan Bitton, Marianna Nezhurina, Amro Abbas, Cheng-Yu Hsieh, Dhruba Ghosh, Josh Gardner, Maciej Kilian, Hanlin Zhang, Rulin Shao, Sarah M. Pratt, Sunny Sanyal, Gabriel Ilharco, Giannis Daras, Kalyani Marathe, Aaron Gokaslan, Jieyu Zhang, Khyathi Raghavi Chandu, Thao Nguyen, Igor Vasiljevic, Sham M. Kakade, Shuran Song, Sujay Sanghavi, Fartash Faghri, Sewoong Oh, Luke Zettlemoyer, Kyle Lo, Alaaeldin El-Nouby, Hadi Pouransari, Alexander Toshev, Stephanie Wang, Dirk Groeneveld, Luca Soldaini, Pang Wei Koh, Jenia Jitsev, Thomas Kollar, Alex Dimakis, Yair Carmon, Achal Dave, Ludwig Schmidt, Vaishaal Shankar
2024 J jnl
DataComp-LM: In search of the next generation of training sets for language models.
CoRR
Jeffrey Li, Alex Fang, Georgios Smyrnis, Maor Ivgi, Matt Jordan, Samir Yitzhak Gadre, Hritik Bansal, Etash Kumar Guha, Sedrick Keh, Kushal Arora, Saurabh Garg, Rui Xin, Niklas Muennighoff, Reinhard Heckel, Jean Mercat, Mayee F. Chen, Suchin Gururangan, Mitchell Wortsman, Alon Albalak, Yonatan Bitton, Marianna Nezhurina, Amro Abbas, Cheng-Yu Hsieh, Dhruba Ghosh, Josh Gardner, Maciej Kilian, Hanlin Zhang, Rulin Shao, Sarah M. Pratt, Sunny Sanyal, Gabriel Ilharco, Giannis Daras, Kalyani Marathe, Aaron Gokaslan, Jieyu Zhang, Khyathi Raghavi Chandu, Thao Nguyen, Igor Vasiljevic, Sham M. Kakade, Shuran Song, Sujay Sanghavi, Fartash Faghri, Sewoong Oh, Luke Zettlemoyer, Kyle Lo, Alaaeldin El-Nouby, Hadi Pouransari, Alexander Toshev, Stephanie Wang, Dirk Groeneveld, Luca Soldaini, Pang Wei Koh, Jenia Jitsev, Thomas Kollar, Alexandros G. Dimakis, Yair Carmon, Achal Dave, Ludwig Schmidt, Vaishaal Shankar
2024 J jnl
FastVLM: Efficient Vision Encoding for Vision Language Models.
CoRR
Pavan Kumar Anasosalu Vasu, Fartash Faghri, Chun-Liang Li, Cem Koc, Nate True, Albert Antony, Gokula Santhanam, James Gabriel, Peter Grasch, Oncel Tuzel, Hadi Pouransari
2024 A* conf
Knowledge Transfer from Vision Foundation Models for Efficient Training of Small Task-specific Models.
ICML
Raviteja Vemulapalli, Hadi Pouransari, Fartash Faghri, Sachin Mehta, Mehrdad Farajtabar, Mohammad Rastegari, Oncel Tuzel
2024 — conf
MUSCLE: A Model Update Strategy for Compatible LLM Evolution.
EMNLP (Findings)
Jessica Maria Echterhoff, Fartash Faghri, Raviteja Vemulapalli, Ting-Yao Hu, Chun-Liang Li, Oncel Tuzel, Hadi Pouransari
2024 J jnl
MUSCLE: A Model Update Strategy for Compatible LLM Evolution.
CoRR
Jessica Maria Echterhoff, Fartash Faghri, Raviteja Vemulapalli, Ting-Yao Hu, Chun-Liang Li, Oncel Tuzel, Hadi Pouransari
2024 A* conf
MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training.
CVPR
Pavan Kumar Anasosalu Vasu, Hadi Pouransari, Fartash Faghri, Raviteja Vemulapalli, Oncel Tuzel
2024 — conf
SAM-CLIP: Merging Vision Foundation Models towards Semantic and Spatial Understanding.
CVPR Workshops
Haoxiang Wang, Pavan Kumar Anasosalu Vasu, Fartash Faghri, Raviteja Vemulapalli, Mehrdad Farajtabar, Sachin Mehta, Mohammad Rastegari, Oncel Tuzel, Hadi Pouransari
2024 — conf
Scaling Smart: Accelerating Large Language Model Pre-Training with Small Model Initialization.
ENLSP
Mohammad Samragh, Seyed-Iman Mirzadeh, Keivan Alizadeh-Vahid, Fartash Faghri, Minsik Cho, Moin Nabi, Devang Naik, Mehrdad Farajtabar
2024 J jnl
Scaling Smart: Accelerating Large Language Model Pre-training with Small Model Initialization.
CoRR
Mohammad Samragh, Iman Mirzadeh, Keivan Alizadeh-Vahid, Fartash Faghri, Minsik Cho, Moin Nabi, Devang Naik, Mehrdad Farajtabar
2024 A* conf
TiC-CLIP: Continual Training of CLIP Models.
ICLR
Saurabh Garg, Mehrdad Farajtabar, Hadi Pouransari, Raviteja Vemulapalli, Sachin Mehta, Oncel Tuzel, Vaishaal Shankar, Fartash Faghri
2023 J jnl
CLIP meets Model Zoo Experts: Pseudo-Supervision for Visual Enhancement.
CoRR
Mohammadreza Salehi, Mehrdad Farajtabar, Maxwell Horton, Fartash Faghri, Hadi Pouransari, Raviteja Vemulapalli, Oncel Tuzel, Ali Farhadi, Mohammad Rastegari, Sachin Mehta
2023 A* conf
FastFill: Efficient Compatible Model Update.
ICLR
Florian Jaeckle, Fartash Faghri, Ali Farhadi, Oncel Tuzel, Hadi Pouransari
2023 J jnl
FastFill: Efficient Compatible Model Update.
CoRR
Florian Jaeckle, Fartash Faghri, Ali Farhadi, Oncel Tuzel, Hadi Pouransari
2023 J jnl
Label-efficient Training of Small Task-specific Models by Leveraging Vision Foundation Models.
CoRR
Raviteja Vemulapalli, Hadi Pouransari, Fartash Faghri, Sachin Mehta, Mehrdad Farajtabar, Mohammad Rastegari, Oncel Tuzel
2023 J jnl
MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training.
CoRR
Pavan Kumar Anasosalu Vasu, Hadi Pouransari, Fartash Faghri, Raviteja Vemulapalli, Oncel Tuzel
2023 A* conf
Reinforce Data, Multiply Impact: Improved Model Accuracy and Robustness with Dataset Reinforcement.
ICCV
Fartash Faghri, Hadi Pouransari, Sachin Mehta, Mehrdad Farajtabar, Ali Farhadi, Mohammad Rastegari, Oncel Tuzel
2023 J jnl
Reinforce Data, Multiply Impact: Improved Model Accuracy and Robustness with Dataset Reinforcement.
CoRR
Fartash Faghri, Hadi Pouransari, Sachin Mehta, Mehrdad Farajtabar, Ali Farhadi, Mohammad Rastegari, Oncel Tuzel
2023 J jnl
SAM-CLIP: Merging Vision Foundation Models towards Semantic and Spatial Understanding.
CoRR
Haoxiang Wang, Pavan Kumar Anasosalu Vasu, Fartash Faghri, Raviteja Vemulapalli, Mehrdad Farajtabar, Sachin Mehta, Mohammad Rastegari, Oncel Tuzel, Hadi Pouransari
2023 J jnl
TiC-CLIP: Continual Training of CLIP Models.
CoRR
Saurabh Garg, Mehrdad Farajtabar, Hadi Pouransari, Raviteja Vemulapalli, Sachin Mehta, Oncel Tuzel, Vaishaal Shankar, Fartash Faghri
2023 J jnl
Weight subcloning: direct initialization of transformers using larger pretrained ones.
CoRR
Mohammad Samragh, Mehrdad Farajtabar, Sachin Mehta, Raviteja Vemulapalli, Fartash Faghri, Devang Naik, Oncel Tuzel, Mohammad Rastegari
2022 J jnl
APE: Aligning Pretrained Encoders to Quickly Learn Aligned Multimodal Representations.
CoRR
Elan Rosenfeld, Preetum Nakkiran, Hadi Pouransari, Oncel Tuzel, Fartash Faghri
2022 J jnl
MixTailor: Mixed Gradient Aggregation for Robust Learning Against Tailored Attacks.
CoRR
Ali Ramezani-Kebrya, Iman Tabrizian, Fartash Faghri, Petar Popovski
2022 J jnl
MixTailor: Mixed Gradient Aggregation for Robust Learning Against Tailored Attacks.
Trans. Mach. Learn. Res.
Ali Ramezani-Kebrya, Iman Tabrizian, Fartash Faghri, Petar Popovski
2022 J jnl
RangeAugment: Efficient Online Augmentation with Range Learning.
CoRR
Sachin Mehta, Saeid Naderiparizi, Fartash Faghri, Maxwell Horton, Lailin Chen, Ali Farhadi, Oncel Tuzel, Mohammad Rastegari
2022 — —
Training Efficiency and Robustness in Deep Learning
Fartash Faghri
2021 J jnl
Bridging the Gap Between Adversarial Robustness and Optimization Bias.
CoRR
Fartash Faghri, Cristina Nader Vasconcelos, David J. Fleet, Fabian Pedregosa, Nicolas Le Roux
2021 J jnl
NUQSGD: Provably Communication-efficient Data-parallel SGD via Nonuniform Quantization.
J. Mach. Learn. Res.
Ali Ramezani-Kebrya, Fartash Faghri, Ilya Markov, Vitalii Aksenov, Dan Alistarh, Daniel M. Roy
2021 J jnl
Training Efficiency and Robustness in Deep Learning.
CoRR
Fartash Faghri
2020 J jnl
A Study of Gradient Variance in Deep Learning.
CoRR
Fartash Faghri, David Duvenaud, David J. Fleet, Jimmy Ba
2020 A* conf
Adaptive Gradient Quantization for Data-Parallel SGD.
NeurIPS
Fartash Faghri, Iman Tabrizian, Ilia Markov, Dan Alistarh, Daniel M. Roy, Ali Ramezani-Kebrya
2020 J jnl
Adaptive Gradient Quantization for Data-Parallel SGD.
CoRR
Fartash Faghri, Iman Tabrizian, Ilia Markov, Dan Alistarh, Daniel M. Roy, Ali Ramezani-Kebrya
2020 J jnl
Adversarial Robustness through Regularization: A Second-Order Approach.
CoRR
Avery Ma, Fartash Faghri, Amir-massoud Farahmand
2019 J jnl
NUQSGD: Improved Communication Efficiency for Data-parallel SGD via Nonuniform Quantization.
CoRR
Ali Ramezani-Kebrya, Fartash Faghri, Daniel M. Roy
2018 — conf
Adversarial Spheres.
ICLR (Workshop)
Justin Gilmer, Luke Metz, Fartash Faghri, Samuel S. Schoenholz, Maithra Raghu, Martin Wattenberg, Ian J. Goodfellow
2018 J jnl
Adversarial Spheres.
CoRR
Justin Gilmer, Luke Metz, Fartash Faghri, Samuel S. Schoenholz, Maithra Raghu, Martin Wattenberg, Ian J. Goodfellow
2018 A conf
VSE++: Improving Visual-Semantic Embeddings with Hard Negatives.
BMVC
Fartash Faghri, David J. Fleet, Jamie Ryan Kiros, Sanja Fidler
2017 J jnl
VSE++: Improved Visual-Semantic Embeddings.
CoRR
Fartash Faghri, David J. Fleet, Jamie Ryan Kiros, Sanja Fidler
2016 A* conf
Adversarial Manipulation of Deep Representations.
ICLR (Poster)
Sara Sabour, Yanshuai Cao, Fartash Faghri, David J. Fleet
2012 J jnl
Graph based semi-supervised human pose estimation: When the output space comes to help.
Pattern Recognit. Lett.
Nima Pourdamghani, Hamid R. Rabiee, Fartash Faghri, Mohammad Hossein Rohban