2025
DecisionFlow: Advancing Large Language Model as Principled Decision Maker.
CoRR, May, 2025

Graph Foundation Models: A Comprehensive Survey.
CoRR, May, 2025

ModelingAgent: Bridging LLMs and Mathematical Modeling for Real-World Challenges.
CoRR, May, 2025

RM-R1: Reward Modeling as Reasoning.
CoRR, May, 2025

A Desideratum for Conversational Agents: Capabilities, Challenges, and Future Directions.
CoRR, April, 2025

OTC: Optimal Tool Calls via Reinforcement Learning.
CoRR, April, 2025

ToolRL: Reward is All Tool Learning Needs.
CoRR, April, 2025

SMART: Self-Aware Agent for Tool Overuse Mitigation.
CoRR, February, 2025

Beyond Sample-Level Feedback: Using Reference-Level Feedback to Guide Data Synthesis.
CoRR, February, 2025

Internal Activation as the Polar Star for Steering Unsafe LLM Behavior.
CoRR, February, 2025

Towards LifeSpan Cognitive Systems.
Trans. Mach. Learn. Res., 2025

Chain-of-Factors Paper-Reviewer Matching.
Proceedings of the ACM on Web Conference 2025, 2025

Beyond Answers: Transferring Reasoning Capabilities to Smaller LLMs Using Multi-Teacher Knowledge Distillation.
Proceedings of the Eighteenth ACM International Conference on Web Search and Data Mining, 2025

Semi-supervised Fine-tuning for Large Language Models.
Proceedings of the Findings of the Association for Computational Linguistics: NAACL 2025, Albuquerque, New Mexico, USA, April 29, 2025

Strategist: Self-improvement of LLM Decision Making via Bi-Level Tree Search.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024
One Step towards Autonomous AI Agent: Reasoning, Alignment and Planning
PhD thesis, 2024

Disentangling Structured Components: Towards Adaptive, Interpretable and Scalable Time Series Forecasting.
IEEE Trans. Knowl. Data Eng., 2024

EscapeBench: Pushing Language Models to Think Outside the Box.
CoRR, 2024

PIANIST: Learning Partially Observable World Models with LLMs for Multi-Agent Decision Making.
CoRR, 2024

SemiEvol: Semi-supervised Fine-tuning for LLM Adaptation.
CoRR, 2024

Self-Updatable Large Language Models with Parameter Integration.
CoRR, 2024

Strategist: Learning Strategic Skills by LLMs via Bi-Level Tree Search.
CoRR, 2024

Large Scale Knowledge Washing.
CoRR, 2024

Bridging Language and Items for Retrieval and Recommendation.
CoRR, 2024

MEMORYLLM: Towards Self-Updatable Large Language Models.
CoRR, 2024

TinyLLM: Learning a Small Student from Multiple Large Language Models.
CoRR, 2024

TPD: Enhancing Student Language Model Reasoning via Principle Discovery and Guidance.
CoRR, 2024

IterAlign: Iterative Constitutional Alignment of Large Language Models.
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), 2024

MEMORYLLM: Towards Self-Updatable Large Language Models.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

Language Models as Semantic Indexers.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

Data Science Tasks Implemented with Scripts versus GUI-Based Workflows: The Good, the Bad, and the Ugly.
Proceedings of the 40th International Conference on Data Engineering, ICDE 2024, 2024

A Comprehensive Survey of Scientific Large Language Models and Their Applications in Scientific Discovery.
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024

PlayBest: Professional Basketball Player Behavior Synthesis via Planning with Diffusion.
Proceedings of the 33rd ACM International Conference on Information and Knowledge Management, 2024

MinPrompt: Graph-based Minimal Prompt Data Augmentation for Few-shot Question Answering.
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2024

2023
A Multi-View Multi-Task Learning Framework for Multi-Variate Time Series Forecasting.
IEEE Trans. Knowl. Data Eng., August, 2023

"Why Should I Review This Paper?" Unifying Semantic, Topic, and Citation Factors for Paper-Reviewer Matching.
CoRR, 2023

MinPrompt: Graph-based Minimal Prompt Data Augmentation for Few-shot Question Answering.
CoRR, 2023

Professional Basketball Player Behavior Synthesis via Planning with Diffusion.
CoRR, 2023

Learning Structured Components: Towards Modular and Interpretable Multivariate Time Series Forecasting.
CoRR, 2023

Gotta: Generative Few-shot Question Answering by Prompt-based Cloze Data Augmentation.
Proceedings of the 2023 SIAM International Conference on Data Mining, 2023

Weakly Supervised Multi-Label Classification of Full-Text Scientific Papers.
Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2023

2022
MotifClass: Weakly Supervised Text Classification with Higher-order Metadata Information.
Proceedings of the WSDM '22: The Fifteenth ACM International Conference on Web Search and Data Mining, Virtual Event / Tempe, AZ, USA, February 21, 2022

Scalable Graph Representation Learning via Locality-Sensitive Hashing.
Proceedings of the 31st ACM International Conference on Information & Knowledge Management, 2022

ReLiable: Offline Reinforcement Learning for Tactical Strategies in Professional Basketball Games.
Proceedings of the 31st ACM International Conference on Information & Knowledge Management, 2022

2021
The Pulse of Urban Transport: Exploring the Co-evolving Pattern for Spatio-temporal Forecasting.
ACM Trans. Knowl. Discov. Data, 2021

Hierarchical Metadata-Aware Document Categorization under Weak Supervision.
Proceedings of the WSDM '21, 2021

ST-Norm: Spatial and Temporal Normalization for Multi-variate Time Series Forecasting.
Proceedings of the KDD '21: The 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2021

Evaluating Audience Loyalty and Authenticity in Influencer Marketing via Multi-task Multi-relational Learning.
Proceedings of the Fifteenth International AAAI Conference on Web and Social Media, 2021

#StayHome or #Marathon?: Social Media Enhanced Pandemic Surveillance on Spatial-temporal Dynamic Graphs.
Proceedings of the CIKM '21: The 30th ACM International Conference on Information and Knowledge Management, Virtual Event, Queensland, Australia, November 1, 2021

2020
Few-Shot Learning for New User Recommendation in Location-based Social Networks.
Proceedings of the WWW '20: The Web Conference 2020, Taipei, Taiwan, April 20-24, 2020, 2020

2018
TaxoGen: Unsupervised Topic Taxonomy Construction by Adaptive Term Embedding and Clustering.
Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2018

Doc2Cube: Allocating Documents to Text Cube Without Labeled Data.
Proceedings of the IEEE International Conference on Data Mining, 2018

ATRank: An Attention-Based User Behavior Modeling Framework for Recommendation.
Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, 2018