SOLAR: A Self-Optimizing Open-Ended Autonomous Agent for Lifelong Learning and Continual Adaptation
Published in ACL 2026 (Main Conference), 2026
SOLAR: A Self-Optimizing Open-Ended Autonomous Agent for Lifelong Learning and Continual Adaptation.
Publications
You can also find my articles on my Google Scholar profile.
Selected Conference Papers
Expected Return Causes Outcome-Level Mode Collapse in Reinforcement Learning and How to Fix It with Inverse Probability Scaling
Published in ICML 2026, 2026
Expected Return Causes Outcome-Level Mode Collapse in Reinforcement Learning and How to Fix It with Inverse Probability Scaling.
HypoSpace: Evaluating LLM Creativity as Set-Valued Hypothesis Generators under Underdetermination
Published in ICML 2026 (Spotlight), 2026
HypoSpace: Evaluating LLM Creativity as Set-Valued Hypothesis Generators under Underdetermination.
Initialization is Half the Battle: Generating Diverse Images from a Guidance Potential Posterior
Published in ICML 2026 (Spotlight), 2026
Initialization is Half the Battle: Generating Diverse Images from a Guidance Potential Posterior.
Bridging Mechanistic Interpretability and Prompt Engineering with Gradient Ascent for Interpretable Persona Control
Published in Transactions on Machine Learning Research (TMLR) 2026, 2026
Bridging Mechanistic Interpretability and Prompt Engineering with Gradient Ascent for Interpretable Persona Control.
Uncertainty-Based Extensible Codebook for Discrete Federated Learning in Heterogeneous Data Silos
Published in ICML 2025, 2025
Uncertainty-Based Extensible Codebook for Discrete Federated Learning in Heterogeneous Data Silos.
Unsupervised concept discovery mitigates spurious correlations
Published in ICML 2024, 2024
Unsupervised concept discovery mitigates spurious correlations.
GFlowOut: Dropout with Generative Flow Networks
Published in ICML 2023, 2023
GFlowOut: Dropout with Generative Flow Networks.
Stateful Active Facilitator: Coordination and Environmental Heterogeneity in Cooperative Multi-Agent Reinforcement Learning
Published in ICLR 2023, 2023
Stateful Active Facilitator: Coordination and Environmental Heterogeneity in Cooperative Multi-Agent Reinforcement Learning.
Discrete-Valued Neural Communication
Published in NeurIPS 2021, 2021
Discrete-Valued Neural Communication.
Selected Journal Articles
Re-timing Mortality Risk through Individualized Modeling of Lifespan Trajectories
Published in Nature Biomedical Engineering 2026, 2026
Re-timing Mortality Risk through Individualized Modeling of Lifespan Trajectories. (*Dianbo Liu is co-corresponding co-last author.)
FedWeight: mitigating covariate shift of federated learning on electronic health records data through patient re-weighting
Published in npj Digital Medicine, 2025
FedWeight: mitigating covariate shift of federated learning on electronic health records data through patient re-weighting.
Machine learning approaches to predicting no-shows in pediatric medical appointments
Published in npj Digital Medicine, 2022
Machine learning approaches to predicting no-shows in pediatric medical appointments.
ENCODE Phase III: Building an Encyclopedia of Candidate cis-Regulatory Elements for Human and Mouse
Published in Nature, 2020
ENCODE Phase III: Building an Encyclopedia of Candidate cis-Regulatory Elements for Human and Mouse.
Integrative construction of regulatory region networks in 127 human reference epigenomes by matrix factorization
Published in Nucleic Acids Research, 2019
Integrative construction of regulatory region networks in 127 human reference epigenomes by matrix factorization.