This repository contains implementations and illustrative code to accompany DeepGlint publications. Along with publishing papers to accompany research conducted at DeepGlint, we release open-source data sets, and code to enable the broader research community to engage with our work and build upon it, with the ultimate goal of accelerating scientific progress to benefit society.
- V-SWIFT
- Croc: Pretraining Large Multimodal Models with Cross-Modal Comprehension
- Multi-label Cluster Discrimination for Visual Representation Learning, ECCV2024
- VAR-CLIP: Text-to-Image Generator with Visual Auto-Regressive Modeling
- RWKV-CLIP: A Robust Vision-Language Representation Learner, EMNLP2024
- ALIP: Adaptive Language-Image Pre-training with Synthetic Caption, ICCV2023
- Unicom: Universal and Compact Representation Learning for Image Retrieval, ICLR2023
- Killing Two Birds With One Stone: Efficient and Robust Training of Face Recognition CNNs by Partial FC , CVPR 2022
- Partial FC: Training 10 Million Identities on a Single Machine, ICCVW 2021
- EasyQuant: Post-training Quantization via Scale Optimization