AI Research

My research publications in AI agents, LLMs, recommendation systems, and machine learning theory.

Check my Google Scholar for the most recent publications.

AI Agents

My publications on multi-agent systems, agent evaluation, agent reasoning, large action models, function calling, and more.

AgentOhana: Design Unified Data and Training Pipeline for Effective Agent Learning
Jianguo Zhang, Tian Lan, Rithesh Murthy, Zhiwei Liu, Weiran Yao, Juntao Tan, Thai Hoang, Liangwei Yang, Yihao Feng, Zuxin Liu, Tulika Awalgaonkar, Juan Carlos Niebles, Silvio Savarese, Shelby Heinecke, Huan Wang, Caiming Xiong
ArXiv, 2024

GitHub

AgentLite: A Lightweight Library for Building and Advancing Task-Oriented LLM Agent System
Zhiwei Liu, Weiran Yao, Jianguo Zhang, Liangwei Yang, Zuxin Liu, Juntao Tan Prafulla K. Choubey, Tian Lan, Jason Wu, Huan Wang, Shelby Heinecke, Caiming Xiong, Silvio Savarese
ArXiv, 2024

GitHub

Retroformer: Retrospective Large Language Agents with Policy Gradient Optimization
Weiran Yao, Shelby Heinecke, Juan Carlos Niebles, Zhiwei Liu, Yihao Feng, Le Xue, Rithesh Murthy, Zeyuan Chen, Jianguo Zhang, Devansh Arpit, Ran Xu, Phil Mui, Huan Wang, Caiming Xiong, Silvio Savarese
Proceedings of the International Conference of Learning Representations, 2024

Twitter

REX: Rapid Exploration and eXploitation for AI Agents
Rithesh Murthy, Shelby Heinecke, Juan Carlos Niebles, Zhiwei Liu, Le Xue, Weiran Yao, Yihao Feng, Zeyuan Chen, Akash Gokul, Devansh Arpit, Ran Xu, Phil Mui, Huan Wang, Caiming Xiong, Silvio Savarese
ArXiv, 2023

BOLAA: Benchmarking and Orchestrating LLM-augemented Autonomous Agents
Zhiwei Liu, Weiran Yao, Jianguo Zhang, Le Xue, Shelby Heinecke, Rithesh Murthy, Yihao Feng, Zeyuan Chen, Juan Carlos Niebles, Devansh Arpit, Ran Xu, Phil Mui, Huan Wang, Caiming Xiong, Silvio Savarese
ArXiv, 2023

GitHub, Twitter

Large Language Models (LLMs)

My publications on dialogue systems, LLM editing, and more.

DialogStudio: Towards Richest and Most Diverse Unified Dataset Collection for Conversational AI
Jianguo Zhang, Kun Qian, Zhiwei Liu, Shelby Heinecke, Rui Meng, Ye Liu, Zhou Yu, Huan Wang, Silvio Savarese, Caiming Xiong
Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics, 2024

GitHub, HuggingFace, Twitter

Enhancing Performance on Seen and Unseen Dialogue Scenarios using Retrieval-Augmented End-to-End Task-Oriented System
Jianguo Zhang, Stephen Roller, Kun Qian, Zhiwei Liu, Rui Meng, Shelby Heinecke, Huan Wang, Silvio Savarese, Caiming Xiong
SIGDIAL, 2023

Editing Arbitrary Propositions in LLMs without Subject Labels
Itai Feigenbaum, Devansh Arpit, Huan Wang, Shelby Heinecke, Juan Carlos Niebles, Weiran Yao, Caiming Xiong, and Silvio Savarese
ArXiv, 2023

Recommendation Systems

My publications on deep learning- and LLM-based recommendation systems, robust recommendation systems, and more.

DRDT: Dynamic Reflection with Divergent Thinking for LLM-based Sequential Recommendation
Yu Wang, Zhiwei Liu, Jianguo Zhang, Weiran Yao, Shelby Heinecke, Philip S. Yu
ArXiv, 2023

Deconfounded Causal Collaborative Filtering
Shuyuan Xu, Juntao Tan, Shelby Heinecke, Jia Li, and Yongfeng Zhang
ACM Transactions on Recommender Systems, 2023

Towards More Robust and Accurate Sequential Recommendation with Cascade-guided Adversarial Training
Juntao Tan, Shelby Heinecke, Zhiwei Liu, Yongjun Chen, Yongfeng Zhang, Huan Wang
SIAM International Conference on Data Mining, 2024

Zero-shot Item-based Recommendation via Multi-task Product Knowledge Graph Pre-Training
Ziwei Fan, Zhiwei Liu, Shelby Heinecke, Jianguo Zhang, Huan Wang, Caiming Xiong
Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, 2023

Lightning Talk ⚡️

RGRecSys: A Toolkit for Robustness of Recommender Systems
Zohreh Ovaisi, Shelby Heinecke, Jia Li, Yongfeng Zhang, Elena Zheleva, and Caiming Xiong
Proceedings of the Fifthteenth ACM International Conference on Web Search and Data Mining, 2022

GitHub

Machine Learning

My publications on federated learning, causal inference, entity resolution, and more.

Tackling Data Heterogeneity in Federated Learning with Class Prototypes
Yutong Dai, Zeyuan Chen, Junnan Li, Shelby Heinecke, Lichao Sun, Ran Xu
Proceedings of the AAAI Conference on Artificial Intelligence, 2023

Salesforce CausalAI Library: A Fast and Scalable Framework for Causal Analysis of Time Series and Tabular Data
Devansh Arpit, Matthew Fernandez, Chenghao Liu, Weiran Yao, Wenzhuo Yang, Paul Josel, Shelby Heinecke, Eric Hu, Huan Wang, Stephen Hoi, Caiming Xiong, Kun Zhang, Juan Carlos Niebles
ArXiv, 2023

GitHub, Twitter

Combining Data-driven Supervision with Human-in-the-loop Feedback for Entity Resolution
Wenpeng Yin, Shelby Heinecke, Jia Li, Nitish Keskar, Michael Jones, Shouzhong Shi, Stanislav Georgiev, Kurt Milich, Joseph Esposito, and Caiming Xiong
Data-Centric AI Workshop at NeurIPS, 2021

TechCrunch

Machine Learning Theory, Theoretical Computer Science

My publications in distributed PAC learning, noisy PAC learning, network science, and causal inference.

Causal Layering via Conditional Entropy
Itai Feigenbaum, Devansh Arpit, Huan Wang, Shelby Heinecke, Juan Carlos Niebles, Weiran Yao, Caiming Xiong, and Silvio Savarese
ArXiv, 2023

On the Unlikelihood of D-Seperation
Itai Feigenbaum, Huan Wang, Shelby Heinecke, Juan Carlos Niebles, Weiran Yao, Caiming Xiong, Devansh Arpit
ArXiv, 2023

AAAI_2021_slides.pdf

Communication-Aware Collaborative Learning
Avrim Blum, Shelby Heinecke, and Lev Reyzin
Proceedings of the AAAI Conference on Artificial Intelligence, 2021



Crowdsourced PAC Learning under Classification Noise
Shelby Heinecke and Lev Reyzin
Proceedings of the AAAI Conference on Human Computation and Crowdsourcing, 2019

On the Resilience of Bipartite Networks
Shelby Heinecke, Will Perkins, Lev Reyzin
In 2018 56th Annual Allerton Conference on Communication, Control, and Computing (Allerton), 2018