- 2023: AAAI, ICLR, IJCAI, ICML, KDD, NeurIPS, ICRA, CVPR, ACL, ICCV, IROS, CoRL
- 2024: AAAI, ICLR, IJCAI, ICML, KDD, NeurIPS, ICRA, CVPR, ACL
- TAPE: Leveraging Agent Topology for Cooperative Multi-Agent Policy Gradient Link
- ConcaveQ: Non-Monotonic Value Function Factorization via Concave Representations in Deep Multi-Agent Reinforcement Learning Link
- Settling Decentralized Multi-Agent Coordinated Exploration by Novelty Sharing Link
- Intrinsic Action Tendency Consistency for Cooperative Multi-Agent Reinforcement Learning Link
- RGMComm: Return Gap Minimization via Discrete Communications in Multi-Agent Reinforcement Learning Link
- PMAC: Personalized Multi-Agent Communication
- Accelerate Multi-Agent Reinforcement Learning in Zero-Sum Games with Subgame Curriculum Learning Link
- Bidirectional Temporal Plan Graph: Enabling Switchable Passing Orders for More Efficient Multi-Agent Path Finding Plan Execution Link
- Adaptive Anytime Multi-Agent Path Finding Using Bandit-Based Large Neighborhood Search Link
- Traffic Flow Optimisation for Lifelong Multi-Agent Path FindingLink
- Decentralized Monte Carlo Tree Search for Partially Observable Multi-agent Pathfinding Link
- Improved Anonymous Multi-Agent Path Finding Algorithm Link
- Transition-Informed Reinforcement Learning for Large-Scale Stackelberg Mean-Field Games Link
- U-Trustworthy Models. Reliability, Competence, and Confidence in Decision-Making Link
- Learning Discrete-Time Major-Minor Mean Field Games Link
- PerFedRLNAS: One-for-All Personalized Federated Neural Architecture Search Link
- EG-NAS: Neural Architecture Search with Fast Evolutionary Exploration Link
- Towards Automated RISC-V Microarchitecture Design with Reinforcement Learning Link
- Accelerating Cutting-Plane Algorithms via Reinforcement Learning Surrogates Link
- DMMR: Cross-Subject Domain Generalization for EEG-Based Emotion Recognition via Denoising Mixed Mutual Reconstruction Link
- Controlling Behavioral Diversity in Multi-Agent Reinforcement Learning Link
- Policy-Based Bayesian Active Causal Discovery with Deep Reinforcement Learning Link
- Automatic Multi-Task Learning Framework with Neural Architecture Search in Recommendations Link
- Semi-Supervised Learning for Time Series Collected at a Low Sampling Rate Link
- Calibration of Time-Series Forecasting Detecting and Adapting Context-Driven Distribution Shif Link
- Heterogeneity-Informed Meta-Parameter Learning for Spatiotemporal Time Series Forecasting Link
- SensitiveHUE: Multivariate Time Series Anomaly Detection by Enhancing the Sensitivity to Normal Patterns Link
- AutoXPCR: Automated Multi-Objective Model Selection for Time Series Forecasting Link
- PATE: Proximity-Aware Time Series Anomaly Evaluation Link
- CAFO: Feature-Centric Explanation on Time Series Classification Link
- ReCTSi: Resource-efficient Correlated Time Series Imputation via Decoupled Pattern Learning and Completeness-aware Attentions Link