Pinned Repositories
lloco
The official repo for "LLoCo: Learning Long Contexts Offline"
torchsparse
[MICRO'23, MLSys'22] TorchSparse: Efficient Training and Inference Framework for Sparse Convolution on GPUs.
VILA
VILA is a family of state-of-the-art vision language models (VLMs) for diverse multimodal AI tasks across the edge, data center, and cloud.
APR
[COLM 2025] Code for Paper: Learning Adaptive Parallel Reasoning with Language Models
sglang
SGLang is a fast serving framework for large language models and vision language models.
blog
My blog built with Gatsby & React
images-preprocessing-kit
A kit for preprocessing images (crop, move, rename etc.)
q-diffusion
[ICCV 2023] Q-Diffusion: Quantizing Diffusion Models.
qlth
QLTH is a 2-step model compression scheme that applies Post-Training Quantization on the ”winning tickets” or ”matching” derived by iterative magnitude prunning.
TOAST
Official code for "Refocusing Is Key to Transfer Learning"
Xiuyu-Li's Repositories
Xiuyu-Li/q-diffusion
[ICCV 2023] Q-Diffusion: Quantizing Diffusion Models.
Xiuyu-Li/qlth
QLTH is a 2-step model compression scheme that applies Post-Training Quantization on the ”winning tickets” or ”matching” derived by iterative magnitude prunning.
Xiuyu-Li/TOAST
Official code for "Refocusing Is Key to Transfer Learning"
Xiuyu-Li/freefood
Freefood is an IOS app that can recommend surrounding Facebook events that offer free food at Cornell.
Xiuyu-Li/ArcticInference
Xiuyu-Li/ArtGAN
ArtGAN: This work presents a series of new approaches to improve Generative Adversarial Network (GAN) for conditional image synthesis and we name the proposed model as “ArtGAN”. Implementations are in Caffe/Tensorflow.
Xiuyu-Li/ddim
Denoising Diffusion Implicit Models
Xiuyu-Li/evalplus
Rigourous evaluation of LLM-synthesized code - NeurIPS 2023 & COLM 2024
Xiuyu-Li/gptq
Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".
Xiuyu-Li/LFR
Not All Low-Pass Filters are Robust in Graph Convolutional Networks
Xiuyu-Li/lmms-eval
Accelerating the development of large multimodal models (LMMs) with lmms-eval
Xiuyu-Li/MinkowskiEngine
Minkowski Engine is an auto-diff neural network library for high-dimensional sparse tensors
Xiuyu-Li/ml-learning
My implementation for some machine learning algorithms from scratch
Xiuyu-Li/NVAE
The Official PyTorch Implementation of "NVAE: A Deep Hierarchical Variational Autoencoder" (NeurIPS 2020 spotlight paper)
Xiuyu-Li/PNDM
The official implementation for Pseudo Numerical Methods for Diffusion Models on Manifolds (ICLR 2022) and a generic framework for DDIM-like models
Xiuyu-Li/Pro-GNN
Implementation of the KDD 2020 paper "Graph Structure Learning for Robust Graph Neural Networks"
Xiuyu-Li/projected_gan
[NeurIPS'21] Projected GANs Converge Faster
Xiuyu-Li/PyTorch-StudioGAN
StudioGAN is a Pytorch library providing implementations of representative Generative Adversarial Networks (GANs) for conditional/unconditional image generation.
Xiuyu-Li/radioactive-lab
Adapting the "Radioactive Data" paper to work for text models
Xiuyu-Li/robustness_of_gnns_at_scale
This repository contains the official implementation of the paper "Robustness of Graph Neural Networks at Scale" (NeurIPS, 2021).
Xiuyu-Li/routerbench
The code for the paper ROUTERBENCH: A Benchmark for Multi-LLM Routing System
Xiuyu-Li/score_sde
Official code for Score-Based Generative Modeling through Stochastic Differential Equations (ICLR 2021, Oral)
Xiuyu-Li/sglang
SGLang is a fast serving framework for large language models and vision language models.
Xiuyu-Li/spvnas-backup
[ECCV 2020] Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution
Xiuyu-Li/Styleformer
[CVPR 2022] Styleformer - Official Pytorch Implementation
Xiuyu-Li/stylegan2-ada-pytorch
StyleGAN2-ADA - Official PyTorch implementation
Xiuyu-Li/torchbox3d
3D Perception toolbox.
Xiuyu-Li/VILA
VILA - a multi-image visual language model with training, inference and evaluation recipe, deployable from cloud to edge (Jetson Orin and laptops)
Xiuyu-Li/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
Xiuyu-Li/waka-box
📊 Update a pinned gist to contain your weekly WakaTime stats