Fartash Faghri

Computer Science · Physical Sciences

13h-index1.7kcitations52works5.32yr avg
OpenAlex↗ORCID↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Domain Adaptation and Few-Shot Learning(16), Advanced Neural Network Applications(15), Multimodal Machine Learning Applications(13), Advanced Image and Video Retrieval Techniques(12), Adversarial Robustness in Machine Learning(11)

Publications52 total

Beyond a Single Extractor: Re-thinking HTML-to-Text Extraction for LLM Pretraining
ArXiv.org·2026Open Access
Beyond a Single Extractor: Re-thinking HTML-to-Text Extraction for LLM Pretraining
arXiv (Cornell University)·2026Open Access
AMUSE: Audio-Visual Benchmark and Alignment Framework for Agentic Multi-Speaker Understanding
arXiv (Cornell University)·2025Open Access
Barriers for Learning in an Evolving World: Mathematical Understanding of Loss of Plasticity
arXiv (Cornell University)·2025Open Access
MobileCLIP2: Improving Multi-Modal Reinforced Training
arXiv (Cornell University)·2025Open Access
FastVLM: Efficient Vision Encoding for Vision Language Models
2025· 8 cited
Proxy-FDA: Proxy-based Feature Distribution Alignment for Fine-tuning Vision Foundation Models without Forgetting
arXiv (Cornell University)·2025Open Access
FocalLens: Instruction Tuning Enables Zero-Shot Conditional Image Representations
arXiv (Cornell University)·2025Open Access
TiC-LM: A Web-Scale Benchmark for Time-Continual LLM Pretraining
arXiv (Cornell University)·2025Open Access
TiC-LM: A Web-Scale Benchmark for Time-Continual LLM Pretraining
2025Open Access
FastVLM: Efficient Vision Encoding for Vision Language Models
arXiv (Cornell University)·2024· 1 citedOpen Access
Computational Bottlenecks of Training Small-scale Large Language Models
arXiv (Cornell University)·2024· 1 citedOpen Access
Scaling Smart: Accelerating Large Language Model Pre-training with Small Model Initialization
arXiv (Cornell University)·2024Open Access
MUSCLE: A Model Update Strategy for Compatible LLM Evolution
arXiv (Cornell University)·2024Open Access
SAM-CLIP: Merging Vision Foundation Models towards Semantic and Spatial Understanding
2024· 65 cited
DataComp-LM: In search of the next generation of training sets for language models
arXiv (Cornell University)·2024· 7 citedOpen Access
MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training
2024· 24 cited
CLIP with Quality Captions: A Strong Pretraining for Vision Tasks
arXiv (Cornell University)·2024· 2 citedOpen Access
CatLIP: CLIP-level Visual Recognition Accuracy with 2.7x Faster Pre-training on Web-scale Image-Text Data
arXiv (Cornell University)·2024Open Access
MUSCLE: A Model Update Strategy for Compatible LLM Evolution
2024· 3 citedOpen Access
page 1 of 3Next →

Frequent Co-authors

Oncel Tuzel(24), Hadi Pouransari(21), Raviteja Vemulapalli(14), Mehrdad Farajtabar(13), Sachin Mehta(11), Pavan Kumar Anasosalu Vasu(10), Mohammad Rastegari(9), Ali Ramezani-Kebrya(7), David J. Fleet(6), Daniel M. Roy(6), Chunliang Li(6), Ali Farhadi(5), Vaishaal Shankar(5), Dan Alistarh(4), Jamie Kiros(3), Sanja Fidler(3), Iman Tabrizian(3), Ilya Markov(3), Vitalii Aksenov(3), Cem Koc(3)