[ICLR 2026] Code for the paper "Graph-of-Agents: A Graph-based Framework for Multi-Agent LLM Collaboration"

Fast and accurate coarse-grained neural network molecular dynamics

Modular Multi-Agent System for Scientific Research Assistance

[KDD 2025] Code for the paper "Oldie but Goodie: Re-illuminating Label Propagation on Graphs with Partially Observed Features"

The official source code for "Global Context-aware Representation Learning for Spatially Resolved Transcriptomics", accepted at ICML2025

[ICML 2025] I2MoE: Interpretable Multimodal Interaction-aware Mixture-of-Experts.

Implementation of Enformer, Deepmind's attention network for predicting gene expression, in Pytorch

ALL Molecular ML papers from ICLR'25.

The code implementation of Skill-MoE

The official source code for "Subgraph Federated Learning for Local Generalization (FedLoG)" at ICLR 2025 (Oral).

Multimodal Automated Reasoning and Interpretation for Early Lupus detection

Course Page for Comp683, Spring 2025

The official source code for "3D Interaction Geometric Pre-training for Molecular Relational Learning"

Course Page for Comp683, Spring 2024

The code and data for "MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark" [NeurIPS 2024]

The official source code for [2024 NeurIPS] "Retrieval-Retro: Retrieval-based Inorganic Retrosynthesis with Expert Knowledge"

Code for "VideoRepair: Improving Text-to-Video Generation via Misalignment Evaluation and Localized Refinement [ACL 2026 Findings]"

[ICLR 2025] Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates (Oral)

AlphaFold 3 inference pipeline.

Toward High-Accuracy Open-Source Biomolecular Structure Prediction.

Code for paper "Semantic Diversity-aware Prototype-based Learning for Unbiased Scene Graph Generation (ECCV 2024)"

Official code for the paper "Glider: Global and Local Instruction-Driven Expert Router"

Efficient LLM inference on the TACC Vista clusters using vLLM