Accelerated General (FP32) Matrix Multiplication from scratch in CUDA

The official repo for “Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting”, ACL, 2025.

Comprehensive tools and frameworks for developing foundation models tailored to recommendation systems.

[CVPR 2025] 3D-LLaVA: Towards Generalist 3D LMMs with Omni Superpoint Transformer

MathFusion: Enhancing Mathematical Problem-solving of LLM through Instruction Fusion (ACL 2025)

3D-RCNet: A 3D Relational Convolutional Network for Hyperspectral Image Classification

[EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.

Awesome Pretrained Chinese NLP Models，高质量中文预训练模型&大模型&多模态模型&大语言模型集合

The official implementation of Autoregressive Image Generation using Residual Quantization (CVPR '22)

FABind: Fast and Accurate Protein-Ligand Binding (NeurIPS 2023)

BioT5 (EMNLP 2023) and BioT5+ (ACL 2024 Findings)

The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

Train transformer language models with reinforcement learning.

PyTorch code for KDD 2023 paper "Pre-training Antibody Language Models for Antigen-Specific Computational Antibody Design"

The official code for “Deep Unrestricted Document Image Rectification”, TMM, 2023.

Making large AI models cheaper, faster and more accessible

SSM-DTA: Breaking the Barriers of Data Scarcity in Drug-Target Affinity Prediction (Briefings in Bioinformatics 2023)

Existing Literature about Machine Unlearning

The official code for “DocTr: Document Image Transformer for Geometric Unwarping and Illumination Correction”, ACM MM, Oral Paper, 2021.

Trainable, memory-efficient, and GPU-friendly PyTorch reproduction of AlphaFold 2

A CNN based pytorch implementation on facial expression recognition (FER2013 and CK+), achieving 73.112% (state-of-the-art) in FER2013 and 94.64% in CK+ dataset

PythonLinearNonLinearControl is a library implementing the linear and nonlinear control theories in python.

The official implementation of dual-view molecule pre-training.

Codes for Causal Semantic Generative model (CSG), the model proposed in "Learning Causal Semantic Representation for Out-of-Distribution Prediction" (NeurIPS-21)