Bo Zhang

Powering Neural Architecture Search with Robust Masked Autoencoders

Integer Scale: A Free Lunch for Faster Fine-grained Quantization of LLMs

LiDAR-PTQ: Post-Training Quantization for Point Cloud 3D Object Detection

Masked Autoencoders Are Robust Neural Architecture Search Learners

FPTQ: FINE-GRAINED POST-TRAINING QUANTIZATION FOR LARGE LANGUAGE MODELS

YOLOV6: A SINGLE-STAGE OBJECT DETECTION FRAMEWORK FOR INDUSTRIAL APPLICATIONS