Research

Our research addresses the emerging needs of next-generation artificial intelligence, focusing on brain-inspired large-scale models, brain-inspired world models, and interdisciplinary research at the intersection of brain-inspired intelligence and life sciences. We aim to develop brain-inspired foundation models, world models, and intelligent algorithms for robotics, while leveraging large models to advance life sciences research, including the analysis of genetic causes of disease, the investigation of fundamental biological mechanisms, and medical research on brain disorders.

(1) X. Li; Z. Zhou; K. Shen; W. Zhou; S. Guo*. Beyond Logits: Metastable Latent Dynamics for Sample-Efficient Best-of-N Selection in LLMs. Proceedings of the 43rd International Conference on Machine Learning (ICML), 2026.

(2) C. Gao; L. Li; Y. Zhou; S. Guo*. Complete-Tree Space Favors Data-Efficient Link Prediction. Proceedings of the 42nd International Conference on Machine Learning (ICML), Vancouver, Canada, 2025.

(3) Z. Yang; S. Guo*; Y. Fang; Z. Yu; J. K. Liu. Spiking Variational Policy Gradient for Brain Inspired Reinforcement Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025, 47(3): 1975–1990.

(4) Y. Tang; S. Guo*; J. Liu; B. Wan; L. An; J. K. Liu. Hierarchical Reinforcement Learning from Imperfect Demonstrations through Reachable Coverage-Based Subgoal Filtering. Knowledge-Based Systems, 2024, 294(1).

(5) T. Zhang†; S. Guo†; T. Tan; X. Hu; F. Chen. Adjacency Constraint for Efficient Hierarchical Reinforcement Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45(4): 4152–4166.

(6) S. Guo; Q. Yan; X. Su; X. Hu; F. Chen. State-Temporal Compression in Reinforcement Learning with the Reward-Restricted Geodesic Metric. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 44(9): 5572–5589.

† Equal contribution (co-first authors); * Corresponding author.