publications

2025

1. 

   PIPA: Preference Alignment as Prior-Informed Statistical Estimation

   Junbo Li ,  Zhangyang Wang ,  and  Qiang Liu

   ICML, 2025

   PDF

2. 

   HALoS: Hierarchical Asynchronous Local SGD over Slow Networks for Geo-Distributed Large Language Model Training

   Geon-Woo Kim ,  Junbo Li ,  Shashidhar Gandham ,  Omar Baldonado ,  Adithya Gangidi ,  Pavan Balaji ,  Zhangyang Wang ,  and  Aditya Akella

   ICML, 2025

2024

1. 

   Web2Code: A Large-scale Webpage-to-Code Dataset and Evaluation Framework for Multimodal LLMs

   Sukmin Yun ,  Haokun Lin ,  Rusiru Thushara ,  Mohammad Qazim Bhat ,  Yongxin Wang ,  Zutao Jiang ,  Mingkai Deng ,  Jinhong Wang ,  Tianhua Tao ,  Junbo Li ,  and  others

   NeurIPS Datasets and Benchmarks Track, 2024

   PDF

2. 

   Crystal: Illuminating LLM Abilities on Language and Code

   Tianhua Tao ,  Junbo Li ,  Bowen Tan ,  Hongyi Wang ,  William Marshall ,  Bhargav M Kanakiya ,  Joel Hestness ,  Natalia Vassilieva ,  Zhiqiang Shen ,  Eric P. Xing ,  and  Zhengzhong Liu

   Conference on Language Modeling, 2024

   PDF Website

3. 

   LLM360: Towards Fully Transparent Open-Source LLMs

   Zhengzhong Liu ,  Aurick Qiao ,  Willie Neiswanger ,  Hongyi Wang ,  Bowen Tan ,  Tianhua Tao ,  Junbo Li ,  Yuqi Wang ,  Suqi Sun ,  Omkar Pangarkar ,  Richard Fan ,  Yi Gu ,  Victor Miller ,  Yonghao Zhuang ,  Guowei He ,  Haonan Li ,  Fajri Koto ,  Liping Tang ,  Nikhil Ranjan ,  Zhiqiang Shen ,  Xuguang Ren ,  Roberto Iriondo ,  Cun Mu ,  Zhiting Hu ,  Mark Schulze ,  Preslav Nakov ,  Tim Baldwin ,  and  Eric P. Xing

   Conference on Language Modeling, 2024

   PDF Website

4. 

   Training Bayesian Neural Networks with Sparse Subspace Variational Inference

   Junbo Li ,  Zichen Miao ,  Qiang Qiu ,  and  Ruqi Zhang

   ICLR, 2024

   PDF

2023

1. 

   FedNAR: Federated Optimization with Normalized Annealing Regularization

   Junbo Li ,  Ang Li ,  Chong Tian ,  Qirong Ho ,  Eric P Xing ,  and  Hongyi Wang

   NeurIPS, 2023

   PDF Website

2. 

   Rethinking Certified Defense Against Patch Attacks with Vision Transformers

   Junbo Li ,  Xianhang Li ,  Hongru Zhu ,  Huan Zhang ,  and  Cihang Xie

   In submission to TPAMI, 2023

2022

1. 

   Exponential Family Model-Based Reinforcement Learning via Score Matching

   Gene Li ,  Junbo Li ,  Anmol Kabra ,  Nati Srebro ,  Zhaoran Wang ,  and  Zhuoran Yang

   NeurIPS (Oral presentation), 2022

   PDF Website

2. 

   ViP: Unified Certified Detection and Recovery for Patch Attack with Vision Transformers

   Junbo Li ,  Huan Zhang ,  and  Cihang Xie

   ECCV, 2022

   PDF Supp Website
3. Mitigating Lies in Vision-Language Models

   Junbo Li ,  Xianhang Li ,  and  Cihang Xie

   In NeurIPS ML Safety Workshop , 2022