activity
20212026
most citedEVA-02: A Visual Representation for Neon Genesis

212 citations · 306 across the 9 of their papers we have counts for

collaborators

9 papers

cs.LG2026

Lightweight Gaussian Process Inference in C++ on Metal and CUDA

Yu-Hsueh Fang

Gaussian process (GP) inference in Python is dominated by libraries such as GPyTorch and GPflow, which are built on deep-learning frameworks and inherit their dispatch overhead and…

cs.LG2026

Negligible in Size, Significant in Effect: On Scale Vectors in Large Language Models

Mingze Wang, Shuchen Zhu, Yuxin Fang +3

Normalization layers in modern large language models (LLMs) consist of a deterministic normalization operation and a learnable scale vector. While the normalization operation has b…

cs.CL2026

Mixture-of-Depths Attention

Lianghui Zhu, Yuxin Fang, Bencheng Liao +10

Scaling depth is a key driver for large language models (LLMs). Yet, as LLMs become deeper, they often suffer from signal degradation: informative features formed in shallow layers…

cs.CV2023★ 81 cited

EVA-CLIP: Improved Training Techniques for CLIP at Scale

Quan Sun, Yuxin Fang, Ledell Wu +2

Contrastive language-image pre-training, CLIP for short, has gained increasing attention for its potential in various scenarios. In this paper, we propose EVA-CLIP, a series of mod…

cs.CV2023★ 212 cited

EVA-02: A Visual Representation for Neon Genesis

Yuxin Fang, Quan Sun, Xinggang Wang +3

We launch EVA-02, a next-generation Transformer-based visual representation pre-trained to reconstruct strong and robust language-aligned vision features via masked image modeling.…

cs.CV2022★ 4 cited

Unleashing Vanilla Vision Transformer with Masked Image Modeling for Object Detection

Yuxin Fang, Shusheng Yang, Shijie Wang +3

We present an approach to efficiently and effectively adapt a masked image modeling (MIM) pre-trained vanilla Vision Transformer (ViT) for object detection, which is based on our t…