mufeili

gpt-fast

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

learning_research

本人的科研经验

s4

Structured state space sequence models

flashinfer

FlashInfer: Kernel Library for LLM Serving

punica

Serving multiple LoRA finetuned LLM as one

graph-generation

GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models

pytorch-frame

Tabular Deep Learning Library for PyTorch

Score-Entropy-Discrete-Diffusion

[ICML 2024 Best Paper] Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution (https://arxiv.org/abs/2310.16834)

ProGraML

A Graph-based Program Representation for Data Flow Analysis and Compiler Optimizations

RefChecker

RefChecker provides automatic checking pipeline and benchmark dataset for detecting fine-grained hallucinations generated by Large Language Models.

gtrick

Bag of Tricks for Graph Neural Networks.

awesome-flow-matching

A summary of related works about flow matching, stochastic interpolants

tree-ring-watermark

latent-diffusion-for-language

PASTA

PASTA: Post-hoc Attention Steering for LLMs

diffusion-visualizations

Visualizations of the theory behind diffusion models.

sfig

SVG/Javascript-based library for creating presentations/figures

HLS-Perf-Prediction-with-GNNs

High-Level Synthesis Performance Prediction using GNNs: Benchmarking, Modeling, and Advancing

graph-generation-EDGE

EDGE: Efficient and Degree-Guided Graph Generation via Discrete Diffusion Modeling

ERDiff

[NeurIPS'23 Spotlight] Official Repo for "Extraction and recovery of spatio-temporal structure in latent dynamics alignment with diffusion models"

DiffusionNAG

Official PyTorch implementation of "DiffusionNAG: Predictor-guided Neural Architecture Generation with Diffusion Models" (ICLR 2024)

ntptutorial-II

Neural theorem proving tutorial, version II

multi-table-benchmark

GGM-metrics

Official repository for the paper "On Evaluation Metrics for Graph Generative Models"

HEPT

[ICML'24 Oral] LSH-Based Efficient Point Transformer (HEPT)

PDM-Pure

PDM-based Purifier

Pair-Align

[ICML 2024] Code for Pairwise Alignment Improves Graph Domain Adaptation (Pair-Align)

DiNAS

Code for the paper- Multi-conditioned Graph Diffusion for Neural Architecture Search (https://openreview.net/forum?id=5VotySkajV)

NLB

"No Need to Look Back: An Efficient and Scalable Approach for Temporal Network Representation Learning" by Yuhong Luo and Pan Li

Multi-q-Maglap