Haoran You

9

Papers

2

Total Citations

Papers (9)

Early-Bird Diffusion: Investigating and Leveraging Timestep-Aware Early-Bird Tickets in Diffusion Models for Efficient Training

When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models

Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention at Vision Transformer Inference

HALO: Hardware-Aware Learning to Optimize

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers

SuperTickets: Drawing Task-Agnostic Lottery Tickets from Supernets via Jointly Architecture Searching and Parameter Pruning

ShiftAddNet: A Hardware-Inspired Deep Network

FracTrain: Fractionally Squeezing Bit Savings Both Temporally and Spatially for Efficient DNN Training

ShiftAddViT: Mixture of Multiplication Primitives Towards Efficient Vision Transformer