Publications

Li K. Wenliang, Grégoire Delétang, Matthew Aitchison, Marcus Hutter, Anian Ruoss, Arthur Gretton, Mark Rowland, Distributional Bellman Operators over Mean Embeddings, ICML [pre-print] [paper] [code]
Zhe Wang, Petar Veličković, Daniel Hennes, Nenad Tomašev, Laurel Prince, Michael Kaisers, Yoram Bachrach, Romuald Elie, Li K. Wenliang, Federico Piccinini, William Spearman, Ian Graham, Jerome Connor, Yi Yang, Adrià Recasens, Mina Khan, Nathalie Beauguerlange, Pablo Sprechmann, Pol Moreno, Nicolas Heess, Michael Bowling, Demis Hassabis, Karl Tuyls, TacticAI: an AI assistant for football tactics, Nature Communication [pre-print] [paper]
Mark Rowland, Li K. Wenliang, Rémi Munos, Clare Lyle, Yunhao Tang, Will Dabney, Near-Minimax-Optimal Distributional Reinforcement Learning with a Generative Model, arXiv [pre-print]
Anian Ruoss, Grégoire Delétang, Sourabh Medapati, Jordi Grau-Moya, Li K. Wenliang, Elliot Catt, John Reid, Tim Genewein, Grandmaster-level chess without search, arXiv [pre-print] [code]
Jordi Grau-Moya, Tim Genewein, Marcus Hutter, Laurent Orseau, Grégoire Delétang, Elliot Catt, Anian Ruoss, Li K. Wenliang, Christopher Mattern, Matthew Aitchison, Joel Veness Learning Universal Predictors, ICML [pre-print] [paper]

Tianyuan Teng*, Li K. Wenliang*, Hang Zhang, Bounded rationality in structured density estimation, NeurIPS [paper]
Elliot Catt, Jordi Grau-Moya, Marcus Hutter, Matthew Aitchison, Tim Genewein, Grégoire Delétang, Li K. Wenliang, Joel Veness, Self-Predictive Universal AI, NeurIPS [paper]
Tim Genewein, Grégoire Delétang, Anian Ruoss, Li K. Wenliang, Elliot Catt, Vincent Dutordoir, Jordi Grau-Moya, Laurent Orseau, Marcus Hutter, Joel Veness, Memory-based meta-learning on non-stationary distributions, ICML [paper]
Grégoire Delétang, Anian Ruoss, Paul-Ambroise Duquenne, Elliot Catt, Tim Genewein, Christopher Mattern, Jordi Grau-Moya, Li K. Wenliang, Matthew Aitchison, Laurent Orseau, Marcus Hutter, Joel Veness, Language modeling is compression, ICLR [paper] [code]

Li K. Wenliang, On the failure of variational score matching for VAE models arXiv [pre-print]
Grégoire Delétang, Anian Ruoss, Jordi Grau-Moya, Tim Genewein, Li K. Wenliang, Elliot Catt, Chris Cundy, Marcus Hutter, Shane Legg, Joel Veness, Pedro A Ortega, Neural networks and the chomsky hierarchy, ICLR [pre-print] [paper] [code]
Jordi Grau-Moya, Grégoire Delétang, Markus Kunesch, Tim Genewein, Elliot Catt, Li K. Wenliang, Anian Ruoss, Chris Cundy, Joel Veness, Jane Wang, Marcus Hutter, Christopher Summerfield, Shane Legg, Pedro Ortega, Beyond Bayes-optimality: meta-learning what you know you don’t know, arXiv [pre-print]
Li K. Wenliang, B Moran, Score-based generative models learn manifold-like structures with constrained mixing, NeurIPS 2022 Workshop on Score-Based Methods [pre-print] [paper]
Li K. Wenliang, A distributional Bayesian learning theory for visual perceptual learning, COSYNE Abstracts, Lisbon [abstract]

Li K. Wenliang, Heishiro Kanagawa, Blindness of score-based methods to isolated components and mixing proportions, NeurIPS Workshop Your Model is Wrong [paper]
Bin Dai, Li K. Wenliang, David Wipf, On the Value of Infinite Gradients in Variational Autoencoder Models, NeurIPS [paper]
Longyuan Li, Jian Yao, Li K. Wenliang, Tong He, Tianjun Xiao, Junchi Yan, David Wipf, Zheng Zhang, GRIN: Generative Relation and Intention Network for Multi-agent Trajectory Prediction, NeurIPS [paper]

Tianlin Xu, Li K. Wenliang, Michael Munn, Beatrice Acciaio, COT-GAN: Generating Sequential Data via Causal Optimal Transport, Advances in Neural Information Processing Systems [pre-print] [code] [contributions]
Li K. Wenliang, Theodore Moskovitz, Heishiro Kanagawa, Maneesh Sahani, Amortised learning by wake-sleep, Internatioanl Conference in Machine Learning [paper] [slides] [code]

Li K. Wenliang, Maneesh Sahani, Neural recognition and postdiction by temporal distributed distributional code, Bernstein Conference 2019, Berlin [abstract] [poster]
Li K. Wenliang, Maneesh Sahani, A neurally plausible model for online recognition and postdiction, Advances in Neural Information Processing Systems [paper] [slides (tri-center)] [poster] [pre-print]
Li K. Wenliang, Eszter Vertes, Maneesh Sahani Accurate and adaptive neural recognition in dynamical environment COSYNE Abstracts, Lisbon [poster] [abstract]
Li K. Wenliang*, Danica Sutherland*, Heiko Strathmann, Arthur Gretton, Learning deep kernels for exponential family densities, ICML, Long Beach [link] [code]

Li K. Wenliang and Aaron R. Seitz, Deep neural network for modeling visual perceptual learning, Journal of Neuroscience.
[link] [pre-print] [code]
Li Wenliang and Maneesh Sahani, Neural network trained with supervision represents uncertainty by nonlinear moments, COSYNE Abstracts, Denver, USA [poster] [abstract]

Chunfang Liu, Wenliang Li, Fuchun Sun and Jianwei Zhang, Grasp planning by human experience on a variety of objects with complex geometry Intelligent Robots and Systems (IROS), Hamburg doi: 10.1109/IROS.2015.7353420