Publications & Preprints

See also my Google Scholar profile for an up-to-date list of publications.

(*) indicates equal contribution.

BridgeDrive: Diffusion Bridge Policy for Closed-Loop Trajectory Planning in Autonomous Driving
Diffusion
Shu Liu*, Wenlin Chen*, Weihao Li*, Zheng Wang*, Lijin Yang, Jianing Huang, Yipin Zhang, Zhongzhan Huang, Ze Cheng, Hao Yang
ICLR 2026
PDF Cite OpenReview arXiv
DiffRatio: Training One-Step Diffusion Models Without Teacher Supervision
Diffusion
Wenlin Chen*, Mingtian Zhang*, Jiajun He*, Zijing Ou, José Miguel Hernández-Lobato, Bernhard Schölkopf, David Barber
arXiv preprint
PDF Cite Code arXiv
Bridging Deep Learning and Probabilistic Inference: Towards Data Efficiency, Identifiability, and Sampling Scalability
Multi-Task Diffusion AI for Science
Wenlin Chen
PhD Thesis
PDF Cite Cambridge
Progressive Tempering Sampler with Diffusion
Sampling Diffusion AI for Science
Severi Rissanen*, RuiKang OuYang*, Jiajun He, Wenlin Chen, Markus Heinonen, Arno Solin, José Miguel Hernández-Lobato
ICML 2025
PDF Cite Code PMLR arXiv
Training Neural Samplers with Reverse Diffusive KL Divergence
Sampling Diffusion AI for Science
Jiajun He*, Wenlin Chen*, Mingtian Zhang*, David Barber, José Miguel Hernández-Lobato
AISTATS 2025
PDF Cite Code PMLR arXiv
Your Image is Secretly the Last Frame of a Pseudo Video
Diffusion
Wenlong Chen*, Wenlin Chen*, Lapo Rastrelli, Yingzhen Li
DeLTa Workshop @ ICLR 2025
PDF Cite Code OpenReview arXiv
Neural Characteristic Activation Analysis and Geometric Parameterization for ReLU Networks
Optimization
Wenlin Chen, Hong Ge
NeurIPS 2024
PDF Cite Code NeurIPS Proceedings arXiv
Leveraging Task Structures for Improved Identifiability in Neural Network Representations
Multi-Task AI for Science
Wenlin Chen*, Julien Horwood*, Juyeon Heo, José Miguel Hernández-Lobato
TMLR 2024
PDF Cite Code OpenReview arXiv
Modelling Variability in Human Annotator Simulation
Uncertainty
Wen Wu*, Wenlin Chen*, Chao Zhang, Phil Woodland
ACL 2024
PDF Cite Code ACL Anthology arXiv
Diffusive Gibbs Sampling
Sampling Diffusion AI for Science
Wenlin Chen*, Mingtian Zhang*, Brooks Paige, José Miguel Hernández-Lobato, David Barber
ICML 2024
PDF Cite Code PMLR arXiv
It HAS to be Subjective: Human Annotator Simulation via Zero-shot Density Estimation
Uncertainty
Wen Wu*, Wenlin Chen*, Chao Zhang, Philip C. Woodland
Preprint
PDF Cite Code arXiv
Meta-learning Adaptive Deep Kernel Gaussian Processes for Molecular Property Prediction
Multi-Task Uncertainty AI for Science
Wenlin Chen, Austin Tripp, José Miguel Hernández-Lobato
ICLR 2023
PDF Cite Code OpenReview arXiv
Optimal Client Sampling for Federated Learning
Optimization
Wenlin Chen, Samuel Horváth, Peter Richtárik
TMLR 2022
PDF Cite Code Video OpenReview arXiv
An Evaluation Framework for the Objective Functions of De Novo Drug Design Benchmarks
AI for Science
Austin Tripp, Wenlin Chen, José Miguel Hernández-Lobato
MLDD Workshop @ ICLR 2022
PDF Cite OpenReview
Causal Representation Learning for Latent Space Optimization
Causality AI for Science
Wenlin Chen
MPhil Thesis
PDF Cite Cambridge
To Ensemble or Not Ensemble: When Does End-to-End Training Fail?
Optimization
Andrew Webb, Charles Reynolds, Wenlin Chen, Henry Reeve, Dan Iliescu, Mikel Luján, Gavin Brown
ECML 2020
PDF Cite Code Video Springer arXiv