activity
20242026
collaborators

7 papers

cs.LG2026

Training Tensor Attention Efficiently: From Cubic to Almost Linear Time

Yang Cao, Yingyu Liang, Zhenmei Shi +1

Tensor Attention, a multi-view attention that is able to capture high-order correlations among multiple modalities, can overcome the representational limitations of classical matri…

cs.LG2026

Exploring the Frontiers of Softmax: Provable Optimization, Applications in Diffusion Model, and Beyond

Yang Cao, Yingyu Liang, Zhenmei Shi +1

The softmax activation function plays a crucial role in the success of large language models (LLMs), particularly in the self-attention mechanism of the widely adopted Transformer…

cs.LG2026

Provable Differentially Private Computation of the Cross-Attention Mechanism

Yekun Ke, Yingyu Liang, Zhenmei Shi +2

Cross-attention has emerged as a cornerstone module in modern artificial intelligence, underpinning critical applications such as retrieval-augmented generation (RAG), system promp…

cs.DS2025

Fast John Ellipsoid Computation with Differential Privacy Optimization

Xiaoyu Li, Yingyu Liang, Zhenmei Shi +2

Determining the John ellipsoid - the largest volume ellipsoid contained within a convex polytope - is a fundamental problem with applications in machine learning, optimization, and…

cs.LG2024

Differential Privacy Mechanisms in Neural Tangent Kernel Regression

Jiuxiang Gu, Yingyu Liang, Zhizhou Sha +2

Training data privacy is a fundamental problem in modern Artificial Intelligence (AI) applications, such as face recognition, recommendation systems, language generation, and many…

cs.LG2024

Conv-Basis: A New Paradigm for Efficient Attention Inference and Gradient Computation in Transformers

Yingyu Liang, Heshan Liu, Zhenmei Shi +3

The self-attention mechanism is the key to the success of transformers in recent Large Language Models (LLMs). However, the quadratic computational cost in the input seque…