Oncel Tuzel

Pretraining with hierarchical memories: separating long-tail and common knowledge

arXiv 2025

FastVLM: Efficient Vision Encoding for Vision Language Models

CVPR 2025 1

GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models

arXiv 2024

Graph-Based Captioning: Enhancing Visual Descriptions by Interconnecting Region Captions

arXiv 2024

Dataset Decomposition: Faster LLM Training with Variable Sequence Length Curriculum

arXiv 2024

HUGS: Human Gaussian Splats

CVPR 2024 1

TiC-CLIP: Continual Training of CLIP Models

arXiv 2023

Reinforce Data, Multiply Impact: Improved Model Accuracy and Robustness with Dataset Reinforcement

ICCV 2023 1

Hadi Pouransari

Chun-Liang Li

Fartash Faghri

Mehrdad Farajtabar

Pavan Kumar Anasosalu Vasu

Cem Koc

James Gabriel

Jen-Hao Rick Chang

Sachin Mehta

Vaishaal Shankar