presented "

EfficientViT: Multi-Scale Linear Attention for High-Resolution Dense Prediction

" at

Google

.

presented "

AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

" at

Apple

.

presented "

Efficient Large Language Model

" at

2023 MIT AI Hardware Fall Research Update

.

presented "

TinyML: Enable Efficient Deep Learning on Mobile Devices

" at

2023 MIT AI Hardware Fall Research Update

.

presented "

Quantization for Foundation Models

" at

the ICCV 2023 Workshop on Low-Bit Quantized Neural Networks

.

presented "

Efficient Vision Transformer

" at

the ICCV 2023 Workshop on Resource-Efficient Deep Learning for Computer Vision (RCV'23)

.

presented "

TinyChat for On-device LLM

" at

the IAP MIT Workshop on the Future of AI and Cloud Computing Applications and Infrastructure

.

presented "

SmoothQuant, AWQ, TinyChat

" at

UC Berkeley SkyLab

.

presented "

SmoothQuant, AWQ

" at

NVIDIA

.

presented "

Efficient 3D Perception for Autonomous Vehicles

" at

CVPR Workshop on Efficient Computer Vision

.

presented "

Efficient Deep Learning Computing with Sparsity

" at

CVPR Workshop on Efficient Computer Vision

.

presented "

Plenary: Putting AI on a Diet: TinyML and Efficient Deep Learning

" at

TinyML Technical Forum Asia

.

presented "

TinyML and Efficient Deep Learning for Automotive Applications

" at

Hyundai Motor Group Developers Conference

.

presented "

Today’s AI is Too Big

" at

Industry-Academia Partnership

.

presented "

Challenges and Directions of Low-Power Computer Vision

" at

International Conference on Computer Vision (ICCV) Workshop Panel

.

presented "

TinyML Techniques for Greener, Faster and Sustainable AI

" at

IBM IEEE CAS/EDS – AI Compute Symposium

.

presented "

Computationally Efficient Large-Scale AI

" at

Microsoft Research Summit

.

presented "

Efficient Methods & Hardware for TinyML

" at

Sony Professor Lecture Series

.

presented "

One-For-All Network on FPGAs

" at

Xilinx Adaptive Computing Conference

.

presented "

TinyML and Efficient Deep Learning

" at

Synopsys ARC Processor Summit

.