Official repo for separable operator networks -- extreme-scale operator learning for parametric PDEs.

PyTorch custom dataset APIs -- CUB-200-2011, Stanford Dogs, Stanford Cars, FGVC Aircraft, NABirds, Tiny ImageNet, iNaturalist2017

[ICCV 2023] I-ViT: Integer-only Quantization for Efficient Vision Transformer Inference

Code for ICLR 2023 paper (Oral) — Towards Stable Test-Time Adaptation in Dynamic Wild World

The official implementation of TinyTrain [ICML '24]

A thoroughly investigated survey for tensorial neural networks.

[TPAMI] Searching prompt modules for parameter-efficient transfer learning.

[NeurIPS 2023] MCUFormer: Deploying Vision Transformers on Microcontrollers with Limited Memory

[ICLR 2019] ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware

A curated list of papers in Test-time Adaptation, Test-time Training and Source-free Domain Adaptation

[NeurIPS'22] This is an official implementation for "Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning".

Official implementation for CVPR'23 paper "BlackVIP: Black-Box Visual Prompting for Robust Transfer Learning"

[NeurIPS 2020] MCUNet: Tiny Deep Learning on IoT Devices; [NeurIPS 2021] MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning; [NeurIPS 2022] MCUNetV3: On-Device Training Under 2…

Official implementation of Rectified Straight Through Estimator (ReSTE).

A list of papers, docs, codes about model quantization. This repo is aimed to provide the info for model quantization research, we are continuously improving the project. Welcome to PR the works (p…

[ICLR'24] "DeepZero: Scaling up Zeroth-Order Optimization for Deep Model Training" by Aochuan Chen*, Yimeng Zhang*, Jinghan Jia, James Diffenderfer, Jiancheng Liu, Konstantinos Parasyris, Yihua Zha…

A "large" language model running on a microcontroller

Companion code for the ICML 2022 paper "Generalizing Gaussian Smoothing for Random Search"

Zeroth-Order Regularized Optimization (ZORO): Approximately Sparse Gradients and Adaptive Sampling

[NeurIPS 2023] MeZO: Fine-Tuning Language Models with Just Forward Passes. https://arxiv.org/abs/2305.17333

[CVPR 2023] Towards Any Structural Pruning; LLMs / SAM / Diffusion / Transformers / YOLOv8 / CNNs

CVPR and NeurIPS poster examples and templates. May we have in-person poster session soon!

A playbook for systematically maximizing the performance of deep learning models.

A pytorch-based deep learning framework for multi-modal 2D/3D medical image segmentation

[TPAMI 2023] Low Dimensional Landscape Hypothesis is True: DNNs can be Trained in Tiny Subspaces