Zhuang Liu

7

Papers

774

Total Citations

Papers (7)

Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs

Transformers without Normalization

A Decade's Battle on Dataset Bias: Are We There Yet?

Scaling Language-Free Visual Representation Learning

Idiosyncrasies in Large Language Models

MetaMorph: Multimodal Understanding and Generation via Instruction Tuning

ConvNet vs Transformer, Supervised vs CLIP: Beyond ImageNet Accuracy