activity
20202023
most citedNot All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations

95 citations · 120 across the 7 of their papers we have counts for

collaborators

7 papers

cs.PL2023★ 11 cited

Large Language Models for Compiler Optimization

Chris Cummins, Volker Seeker, Dejan Grubisic +8

We explore the novel application of Large Language Models to code optimization. We present a 7B-parameter transformer model trained from scratch to optimize LLVM assembly for code…

q-bio.BM2023★ 8 cited

DrugChat: Towards Enabling ChatGPT-Like Capabilities on Drug Molecule Graphs

Youwei Liang, Ruiyi Zhang, Li Zhang +1

A ChatGPT-like system for drug compounds could be a game-changer in pharmaceutical research, accelerating drug discovery, enhancing our understanding of structure-activity relation…

cs.PL2023★ 2 cited

Learning Compiler Pass Orders using Coreset and Normalized Value Prediction

Youwei Liang, Kevin Stone, Ali Shameli +8

Finding the optimal pass sequence of compilation can lead to a significant reduction in program size and/or improvement in program efficiency. Prior works on compilation pass order…

cs.CV2022★ 95 cited

Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations

Youwei Liang, Chongjian Ge, Zhan Tong +3

Vision Transformers (ViTs) take all the image patches as tokens and construct multi-head self-attention (MHSA) among them. Complete leverage of these image tokens brings redundant…

cs.LG2020★ 2 cited

Large Norms of CNN Layers Do Not Hurt Adversarial Robustness

Youwei Liang, Dong Huang

Since the Lipschitz properties of convolutional neural networks (CNNs) are widely considered to be related to adversarial robustness, we theoretically characterize the nor…

cs.LG2020★ 1 cited

Multi-view Graph Learning by Joint Modeling of Consistency and Inconsistency

Youwei Liang, Dong Huang, Chang-Dong Wang +1

Graph learning has emerged as a promising technique for multi-view clustering with its ability to learn a unified and robust graph from multiple views. However, existing graph lear…

math.OC2020★ 1 cited

Gradient Projection for Solving Quadratic Programs with Standard Simplex Constraints

Youwei Liang

An important method to optimize a function on standard simplex is the active set algorithm, which requires the gradient of the function to be projected onto a hyperplane, with sign…