Starred repositories
The official source code for "Global Context-aware Representation Learning for Spatially Resolved Transcriptomics", accepted at ICML2025
Curated list of data science interview questions and answers
Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning
MDocAgent: A Multi-Modal Multi-Agent Framework for Document Understanding
BioDiscoveryAgent is an LLM-based AI agent for closed-loop design of genetic perturbation experiments
A general framework for bridging LLMs and recommendation systems via reinforcement learning. https://arxiv.org/pdf/2503.24289
Official github repo for U-SafeBench, a comprehensive benchmark to evaluate user-specific safety of LLMs.
The official source code for "Subgraph Federated Learning for Local Generalizatioin (FedLoG)" at ICLR 2025 (Oral).
Awesome-LLM-Robustness: a curated list of Uncertainty, Reliability and Robustness in Large Language Models
The official source code of the paper "Revisiting Fake News Detection: Towards Temporality-aware Evaluation by Leveraging Engagement Earliness" (WSDM 2025)
The offical source code for [2024 NeurIPS] "Retrieval-Retro: Retrieval-based Inorganic Retrosynthesis with Expert Knowledge"
Awesome things about LLM-powered agents. Papers / Repos / Blogs / ...
[ECCV 2024] Code for the paper "Mew: Multiplexed Immunofluorescence Image Analysis through an Efficient Multiplex Network"
Pytorch Implmentation of Meta Attack via Contrastive Surrogate Objective
The official source code for SIMPLOT: Enhancing Chart Question Answering by Distilling Essentials, accepted at NAACL 2025 (Findings).
LaVIT: Empower the Large Language Model to Understand and Generate Visual Content
The official source code for "Vision Language Model is NOT All You Need: Augmentation Strategies for Molecule Language Model".
✨✨Latest Advances on Multimodal Large Language Models
Collection of AWESOME vision-language models for vision tasks
Awesome-Biomolecule-Language-Cross-Modeling: a curated list of resources for paper "Leveraging Biomolecule and Natural Language through Multi-Modal Learning: A Survey"
Code for EMNLP2023 paper "MolCA: Molecular Graph-Language Modeling with Cross-Modal Projector and Uni-Modal Adapter".
GeoSSL: Molecular Geometry Pretraining with SE(3)-Invariant Denoising Distance Matching, ICLR'23 (https://openreview.net/forum?id=CjTHVo1dvR)