Efficient AI Inference
Hardware-software co-design across speculative decoding, quantization, and pruning.
News
Research Interests
Quantization
Speculative Decoding
Pruning
Agents
Building agent tooling and constructing benchmarks for evaluating agent capabilities.
Benchmark
Tool
Application
World Models
Using world-model ideas to strengthen representation learning.
Language
Multimodal
Selected Works
View allProjects
View allResNet Sparse Distillation
The increasing depth and width of neural networks improve accuracy but also raise hardware requirements and slow down inference. This project proposes a distillation loss function that enables immediate weight and activation pruning on the student model after distillation.
JEPA Architecture Probing Model
This project designed a JEPA architecture model with CNN and MLPs as encoder and predictor. The main task is to predict the trajectory of an object in an environment with wall and door.
