Shenghsin

NM-sparsity

ATS

Adaptive Token Sampling for Efficient Vision Transformers (ECCV 2022 Oral Presentation)

SMSR

[CVPR 2021] Exploring Sparsity in Image Super-Resolution for Efficient Inference

DCNv4

[CVPR 2024] Deformable Convolution v4

EdgeNets

This repository contains the source code of our work on designing efficient CNNs for computer vision

EdgeBERT

HW/SW co-design of sentence-level energy optimizations for latency-aware multi-task NLP inference

SWE-agent

SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It solves 12.47% of bugs in the SWE-bench evaluation set and takes just 1 minute to run.

DeltaCNN

DeltaCNN End-to-End CNN Inference of Sparse Frame Differences in Videos

dynconv

Code for Dynamic Convolutions: Exploiting Spatial Sparsity for Faster Inference (CVPR2020)

AnytimeClassification

Code for "Towards Anytime Classification" paper (NeurIPS 2023)

Soft-Module

Code for "Multi-task Reinforcement Learning with Soft Modularization"

optuna-examples

Examples for https://github.com/optuna/optuna

cmaes

Python library for CMA Evolution Strategy.

MAPIE

A scikit-learn-compatible module to estimate prediction intervals and control risks based on conformal predictions.

XGBoostLSS

An extension of XGBoost to probabilistic modelling

tabular-dl-tabr

The implementation of "TabR: Unlocking the Power of Retrieval-Augmented Tabular Deep Learning"

PDPbox

python partial dependence plot toolbox

yandex-shifts-weather

The best solution of the Weather Prediction track in the Yandex Shifts challenge

summit

Optimising chemical reactions using machine learning

stat_rethinking_2022

Statistical Rethinking course winter 2022

pymc-resources

PyMC educational resources

DeepQuantumNeuralNetworks

LITv2

[NeurIPS 2022 Spotlight] This is the official PyTorch implementation of "Fast Vision Transformers with HiLo Attention"

awesome-english-ebooks

经济学人(含音频)、纽约客、卫报、连线、大西洋月刊等英语杂志免费下载,支持epub、mobi、pdf格式, 每周更新

coder2gwy

互联网首份程序员考公指南，由3位已经进入体制内的前大厂程序员联合献上。

DeepRC

DeepRC: Immune repertoire classification with attention-based deep massive multiple instance learning

Carbon_Capture_ML

Survey of all published Carbon Capture ML papers, data, code and supplemental materials for the benefit of all humanity

GPBoost

Combining tree-boosting with Gaussian process and mixed effects models

tabularGP

Gaussian process applied to tabular models (implemented with fastai)

STUNT

Official PyTorch implementation of STUNT: Few-shot Tabular Learning with Self-generated Tasks from Unlabeled Tables (ICLR 2023 Spotlight).