Haotong Qin

[NeurIPS 2023] This project is the official implementation of our accepted NeurIPS 2023 paper BiMatting: Efficient Video Matting via Binarization.

[CVPR 2020] This project is the PyTorch implementation of our accepted CVPR 2020 paper : forward and backward information retention for accurate binary neural networks.

[NeurIPS 2023 Spotlight] This project is the official implementation of our accepted NeurIPS 2023 (spotlight) paper QuantSR: Accurate Low-bit Quantization for Efficient Image Super-Resolution.

Pytorch implementation of BiFSMN, IJCAI 2022

Pytorch implementation of BiFSMNv2, TNNLS 2023

This project is the official implementation of our accepted IEEE TPAMI paper Diverse Sample Generation: Pushing the Limit of Data-free Quantization

[ICML 2023] This project is the official implementation of our accepted ICML 2023 paper BiBench: Benchmarking and Analyzing Network Binarization.

This project is the official implementation of our accepted ICLR 2022 paper BiBERT: Accurate Fully Binarized BERT.

[ICML 2024 Oral] This project is the official implementation of our Accurate LoRA-Finetuning Quantization of LLMs via Information Retention

How Good is Google Bard's Visual Understanding? An Empirical Study on Open Challenges

This project is the official implementation of our accepted ICLR 2021 paper BiPointNet: Binary Neural Network for Point Clouds.

A curated list for Efficient Large Language Models

Paper Writing Tips

dabnn is an accelerated binary neural networks inference framework for mobile platform

Awesome LLM compression research papers and tools.

We introduce a novel approach for parameter generation, named neural network diffusion (\textbf{p-diff}, p stands for parameter), which employs a standard latent diffusion model to synthesize a new set of parameters

A beautiful, simple, clean, and responsive Jekyll theme for academics

AI and Memory Wall blog post

decentralising the Ai Industry, just some language model api's...

Making big AI models cheaper, easier, and scalable

Quantization of Convolutional Neural networks.

OpenMMLab 3D Human Parametric Model Toolbox and Benchmark

An efficient modular implementation of Associating Objects with Transformers for Video Object Segmentation in PyTorch

training script for space time memory network

Associating Objects with Transformers for Video Object Segmentation

Aerie ADS-B Data Analysis Platform

micronet, a model compression and deploy lib. compression: 1、quantization: quantization-aware-training(QAT), High-Bit(>2b)(DoReFa/Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference)、Low-Bit(≤2b)/Ternary and Binary(TWN/BNN/XNOR-Net); post-training-quantization(PTQ), 8-bit(tensorrt); 2、 pruning: normal、regular and group convolutional channel pruning; 3、 group convolution structure; 4、batch-normalization fuse for quantization. deploy: tensorrt, fp32/fp16/int8(ptq-calibration)、op-adapt(upsample)、dynamic_shape

No description provided.

Geoff Boeing's academic CV in LaTex

PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation