2023

• R. Bendikas, V. Modugno, D. Kanoulas, F. Vasconcelos and D. Stoyanov, "Learning Needle Pick-and-Place Without Expert Demonstrations," in IEEE Robotics and Automation Letters, vol. 8, no. 6, pp. 3326-3333, June 2023, doi: 10.1109/LRA.2023.3266720.
   
• Bharti, Ayush & Naslidnyk, Masha & Key, Oscar & Kaski, Samuel & Briol, François-Xavier. (2023). Optimally-Weighted Estimators of the Maximum Mean Discrepancy for Likelihood-Free Inference. 10.48550/arXiv.2301.11674. 
   
• Lewis-Smith, Andrew and Jaš Šemrl. "Implication Algebras and Implication Semigroups of Binary Relations"  In proceedings of RAMiCS 2023.
   
• Jipsen, Peter and Jaš Šemrl. "Representable and diagonally representable weakening relation algebras"  In proceedings of RAMiCS 2023.
   
• DH Mguni, A Sootla, J Ziomek, O Slumbers*, Z Dai, K Shao, J wang - Timing is Everything: Learning to Act Selectively with Costly Actions and Budgetary Constraints - ICLR 2023
   
• O Slumbers*, DH Mguni, SM McAleer, SB Blumberg, J Wang, Y Yang - A Game-Theoretic Framework for Managing Risk in Multi-Agent Systems - ICML 2023
   
• L Schaefer, O Slumbers*, S McAleer, Y Du, SV Albrecht, DH Mguni - Ensemble Value Functions for Efficient Exploration in Multi-Agent Reinforcement Learning - arXiv:2302.03439
   
• Kirk, R, Zhang, A, Grefenstette, E. Rocktaeschel, T "A Survey of Zero-Short Generalisation in Deep Reinforcement Learning", Journal of Artificial Intelligence Research (JAIR), Vol 76 2023
   
• V Zantedeschi, L Franceschi, J Kaddour, M Kusner, V Niculae - DAG learning on the permutahedron -ICLR 2023
   
• A Lynch, GJS Dovonon, J Kaddour, R Silva - Spawrious: A benchmark for fine control of spurious correlation biases - arXiv preprint arXiv:2303.05470
   
• Y Yin, J Kaddour, X Zhang, Y Nie, Z Liu, L Kong, Q Liu - TTIDA: Controllable Generative Data Augmentation via Text-to-Text and Text-to-Image Models - arXiv preprint arXiv:2304.08821
   
• J Kaddour - The MiniPile Challenge for Data-Efficient Language Models - arXiv preprint arXiv:2304.08442
   
• Hossein A. Rahmani, Xi Wang, Yue Feng, Qiang Zhang, Emine Yilmaz and Aldo Lipani: A Survey on Asking Clarification Questions Datasets in Conversational Systems.  ACL 2023. To Appear.
   
• Yue Feng, Yunlong Jiao, Animesh Prasad, Nikolaos Aletras, Emine Yilmaz and Gabriella Kazai: Schema-guided User Satisfaction Modeling for Task-oriented Dialogues. ACL 2023. To Appear. 
   
• Yicheng Luo, Zhengyao Jiang, Samuel Cohen, Edward Grefenstette, Marc P. Deisenroth (2023). Optimal Transport for Offline Imitation Learning. Proceedings of the International Conference on Learning Representations (ICLR).
   
• Jake Cunningham, Daniel de Souza, So Takao, Marc van der Wilk, Marc P. Deisenroth (2023). Actually Sparse Variational Gaussian Processes. Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS).
   
• Hengyi Wang, Jingwen Wang, and Lourdes Agapito. "Co-SLAM: Joint Coordinate and Sparse Parametric Encodings for Neural Real-Time SLAM." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2023.
   
• Zwane. S, Hadjivelichkov. D, Luo. Y, Bekiroglu. Y, Kanoulas. D, Deisenroth. M P, (2023). Safe Trajectory Sampling in Model-based Reinforcement Learning. Proceedings of the International Conference on Automation Science and Engineering (CASE).
   

• Biggs. F, Schrab. A, Gretton. A, MMD-FUSE: Learning and Combining Kernels for Two-Sample Testing Without Data Splitting  June 2023 arXiv:2306.08777 

• Tan. D, Acero. F, McCarthy. R, Kanoulas. D, Li. Z, "Your Value Function is a Control Barrier Function" ICML 2023 'Outstanding Paper' in WFML 2023 workshop August 2023

• Hawkins-Hooker, A., Visonà, G., Narendra, T. et al. Getting personal with epigenetics: towards individual-specific epigenomic imputation with machine learning. Nat Commun 14, 4750 (2023). 

•  Zhang, M., Hawkins-Hooker, A., Paige, B. & Barber, D. Moment matching denoising Gibbs sampling, arXiv, 2023.  

• J Kaddour*, O Key*, P Nawrot, P Minervini, M J Kusner No Train No Gain: Revisiting Efficient Training Algorithms For Transformer-based Language Models, https://arxiv.org/abs/2307.06440

• Bharti. A, Naslidnyk. M, Key. O, Kaski. S, Briol. F-X, Optimally-Weighted Estimators of the Maximum Mean Discrepancy for Likelihood-Free Inference arXiv:2301.11674 

• Biggs, F; Guedj, B. Tighter PAC-Bayes Generalisation Bounds by Leveraging Example Difficulty. https://arxiv.org/abs/2210.11289 AISTATS 2023

• Y Zhu, L Gultchin, A Gretton, A Korba, M Kusner, A Mastouri, K Muandet, Relaxing Observability Assumption in Causal Inference with Kernel Methods (Invited talk) Causal Inference Meets Statistics Quarterly Meeting

• Y Zhu, K Budhathoki, J Kuebler, D Janzing; Meaningful Causal Aggregation and Paradoxical Confounding arXiv preprint arXiv:2304.11625

• Naslidnyk, M, Kanagawa, M, Karvonen, T, and Mahsereci, M Comparing Scale Parameter Estimators for Gaussian Process Regression: Cross Validation and Maximum Likelihood arXiv preprint 2023

2022

• Biggs, F.; Guedj, B Non-Vacuous Generalisation Bounds for Shallow Networks International Conf. Machine Learning (ICML) 2022.
   
• Biggs, F.; Guedj, B On Margins and Derandomisation in PAC-Bayes Artificial Intelligence and Statistics (AISTATS), 2022.
   
• Kaddour, J; Lynch, A Causal Machine Learning: A Survey and Open Problems  Preprint
   

• Ye, F; Feng, Y; Yilmaz, E. ASSIST: Towards Label Noise-Robust Dialogue State Tracking Findings of ACL 2022.

• Ye, F; Manotumruksa, J; Yilmaz, E Multiwoz 2.4: A multi-domain task-oriented dialogue dataset with essential annotation corrections to improve state tracking evaluation The 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL 2022).

• H Wang*, J Kaddour*, S Liu, J Tang, M Kusner, J Lasenby, Q Liu Evaluating Self-Supervised Learning for Molecular Graph Embeddings ICML2022 Pre-Training Workshop, * Equal Contribution

• J Kaddour, L Liu, R Silva, MJ Kusner A Fair Comparison of Two Popular Flat Minima Optimizers: Stochastic Weight Averaging vs. Sharpness-Aware Minimization arXiv preprint arXiv:2202.00661

• V Zantedeschi, J Kaddour, L Franceschi, M Kusner, V Niculae DAG Learning on the Permutahedron ICLR2022 Workshop on the Elements of Reasoning: Objects, Structure and Causality

• Schrab. A, Jitkrittum. W, Szabó. Z, Sejdinovic. D, Gretton. A, Discussion of ‘Multi-scale Fisher’s independence test for multivariate dependence’, Biometrika, Volume 109, Issue 3, September 2022, Pages 597–603

• Kaddour, J; Stop Wasting My Time! Saving Days of ImageNet and BERT Training with Latest Weight Averaging NeurIPS 2022 HITY

• Morreale L, Aigerman N, Guerrero P, Kim V, Mitra N Neural Conolutional Surfaces, CVPR 2022

• Konstantinos Tsinganos, Konstantinos Chatzilygeroudis, Denis Hadjivelichkov, Theodoros Komninos, Evangelos Dermatas, and Dimitrios Kanoulas. "Behavior Policy Learning: Learning Long-Horizon Tasks via Solution Sketches and Model-Based Controllers",
  In the Journal of Frontiers in Robotics and AI, Frontiers 2022.

• Denis Hadjivelichkov, Sicelukwanda Zwane, Marc Peter Deisenroth, Lourdes Agapito, Dimitrios Kanoulas."One-Shot Transfer of Affordance Regions? AffCorrs!", In the 6th Annual Conference on Robot Learning, CoRL 2022.

• Rameez, R; Rahmani, H. A.; Yilmaz, E. ViralBERT: A User Focused BERT-Based Approach to Virality Prediction, The 30th ACM Conference on User Modeling, Adaptation and Personalization (UMAP’ 22), 2022
   

• M Zhang, O Key, P Hayes, D Barber, B Paige, F-X Briol Towards Healing the Blindness of Score Matching NeurIPS 2022 Workshop on Score-Based Methods

• AN Gomez*, O Key*, K Perlin, S Gou, N Frosst, J Dean, Y Gal  Interlocking Backpropagation: Improving depthwise model-parallelism Journal of Machine Learning Research 23 (171), 1-28

• Tang, R; Liu, L; Pandey, A; Jiang, Z; Yang, G; Kumar, K; Stenetorp, P; Lin, J; Ture, F: "What the DAAM: Interpreting Stable Diffusion Using Cross Attention" Preprint 

• Ruis, L; Khan, A; Biderman, S; Hooker, S; Rocktaeschel, T; Grefenstette, E: "Large Language Models are Not Zero-Shot Communicators" Preprint

• Ruis, L. and Lake, B. M. (2022). Improving Systematic Generalization Through Modularity and Augmentation. In Proceedings of the 44th Annual Conference of the Cognitive Science Society.

• Dynamic Schema Graph Fusion Network for Multi-Domain Dialogue State Tracking. Yue Feng, Aldo Lipani, Fanghua Ye, Qiang Zhang, Emine Yilmaz. ACL 2022. 

• Tang. R*,  Liu. L*, Pandey. A, Jiang. Z, Yang. G, Kumar. K, Stenetorp. P, Lin. J, Ture. F,  "What the DAAM: Interpreting Stable Diffusion Using Cross Attention"  Oct 2022 arXiv:2210.04885 - Winner of ACL 2023 Best Paper Award

• Schrab, A.; Guedj, B.; and Gretton, A. In Oh, A. H.; Agarwal, A.; Belgrave, D.; and Cho, K., editor(s); KSD Aggregated Goodness-of-fit Test. Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, 2022

• Schrab, A.; Kim, I.; Guedj, B.; and Gretton, A. In Oh, A. H.; Agarwal, A.; Belgrave, D.; and Cho, K., editor(s); Efficient Aggregated Kernel Tests using Incomplete U-statistics. Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, 2022.

• F. Acero, K. Yuan and Z. Li, "Learning Perceptual Locomotion on Uneven Terrains Using Sparse Visual Observations," in IEEE Robotics and Automation Letters, vol. 7, no. 4, pp. 8611-8618, Oct. 2022, doi: 10.1109/LRA.2022.3188108.

• Hawkins-Hooker, A., Jones, D.T. & Paige, B. Using domain-domain interactions to probe the limitations of MSA pairing strategies, Machine Learning in Structural Biology workshop at NeurIPS, 2022.

• Mguni. DH, Jafferjee. T, Wang. J, Perez-Nieves. N, Slumbers. O, Tong. F, Li. Y, Zhu. J, Yang. Y, Wang. J; LIGS: Learnable Intrinsic-Reward Generation Selection for Multi-Agent Learning - ICLR 2022

• Y Zhu, L Gultchin, A Gretton, MJ Kusner, R Silva; Causal inference with treatment measurement error: a nonparametric instrumental variable approach UAI 2022 (Oral Presentation)

2021

• Gaujac, B., Feige, I., Barber, D. (2021). Learning Disentangled Representations with the Wasserstein Autoencoder.

• Zhao, A., Gudmundsson, E., Mogulkoc, N., Jones, M.G., van Moorsel, C., Corte, T.J., ...van Es, H.W. (2021). Mortality in combined pulmonary fibrosis and emphysema patients is determined by the sum of pulmonary fibrosis and emphysema. ERJ OPEN RESEARCH, 7 (3), doi:10.1183/23120541.00316-2021

• Yu, C., Behrens, T.E. and Burgess, N., 2020. Prediction and Generalisation over Direction Actions by Grid Cells. In Proceedings of ICLR 2021. 

• Zhengyao Jiang · Tianjun Zhang · Robert Kirk · Tim Rocktäschel · Edward Grefenstette. Graph Backup: Data Efficient Backup Exploiting Markovian Data NeurIPS 2021 

• A Mastouri*, Y Zhu*, L Gultchin, A Korba, R Silva, MJ Kusner, A Gretton, K Muandet Proximal Causal Learning with Kernels: Two-Stage Estimation and Moment Restriction ICML2021

• Liu, Linqing, Patrick Lewis, Sebastian Riedel, and Pontus Stenetorp. [2109.01156] Challenges in Generalization in Open Domain Question Answering (arxiv.org) (2021). 

• Wang. C, Yang. Y, Slumbers. O, Han. C, Guo. T, Zhang. H, and Wang. J. [2110.15105] A Game-Theoretic Approach for Improving Generalization Ability of TSP Solvers (arxiv.org) (2021).  ICLR 2022 Gamification and Multiagent Solutions Workshop - Spotlight paper

• Feng, Xidong*, Oliver Slumbers*, Ziyu Wan, Bo Liu, Stephen McAleer, Ying Wen, Jun Wang, and Yaodong Yang. "Neural Auto-Curricula in Two-Player Zero-Sum Games." Advances in Neural Information Processing Systems 34 (2021). 

• Perez-Nieves, N*, Slumbers. O*, Yang*. Y, Mguni. D.H, Wen. Y, and Wang. J. "Modelling Behavioural Diversity for Learning in Open-Ended Games." In International Conference on Machine Learning, pp. 8514-8524. PMLR, 2021. 

• Dinh, Le Cong, Yaodong Yang, Zheng Tian, Oliver Slumbers, Nicolas Perez Nieves, David Henry Mguni, Haitham Bou Ammar, and Jun Wang. [2103.07780] Online Double Oracle (arxiv.org) (2021). TMLR 2021

• Yang, Yaodong, Jun Luo, Ying Wen, Oliver Slumbers, Daniel Graves, Haitham Bou Ammar, Jun Wang, and Matthew E. Taylor. "Diverse Auto-Curriculum is Critical for Successful Real-World Multiagent Learning Systems." In Proceedings of the 20th International Conference on Autonomous Agents and MultiAgent Systems, pp. 51-56. 2021. - Blue Sky Track Best Paper Award  

• Jason McEwen, Christopher GR Wallis, Augustine N Mavor-Parker Scattering Networks on the Sphere for Scalable and Rotationally Equivariant Spherical CNNs, 2021.

• Oliver J Cobb, Christopher GR Wallis, Augustine N Mavor-Parker, Augustin Marignier, Matthew A Price, Mayeul d'Avezac, Jason D McEwen Efficient generalized spherical CNNs, , International Conference on Learning Representations, 2021. 

• T. Olugbade, Y. Cho, Z. Morgan, M. A. El Ghani and N. Bianchi-Berthouze, "Toward Intelligent Car Comfort Sensing: New Dataset and Analysis of Annotated Physiological Metrics," 2021 9th International Conference on Affective Computing and Intelligent Interaction (ACII), 2021, pp. 1-8, doi: 10.1109/ACII52823.2021.9597393. 

• Hadjivelichkov, D, Kanoulas. D. Fully Self-Supervised Class Awareness in Dense Object Descriptors, Conference on Robot Learning, 2021

• Samvelyan, M., Kirk, R., Kurin, V., Parker-Holder, J., Jiang, M., Hambro, E., Petroni, F., Kuttler, H., Grefenstette, E., Rocktäschel, T., “MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research”, Accepted to NeurIPS 2021 Datasets and Benchmarks Track. 

• Cohen, S., Amos., B. & Lipman., Y. (2021). Riemannian Convex Potential Flows. Proceedings of the International Conference in Machine Learning (ICML). 

• Cohen, S., Luise., G., Terenin., A., Amos., B., & Deisenroth, M. (2021). Aligning Time Series on Incomparable Spaces. Proceedings of the 24th International Conference on Artificial Intelligence and Statistics (AISTATS). 

• Cohen, S., Mbuvha, R., Marwala T. & Deisenroth, M. (2020). Healing Products of Gaussian Process Experts. Proceedings of the International Conference on Machine Learning (ICML). 

• Hirsch, R., & Semrl, J. (2021). Demonic Lattices and Semilattices in Relational Semigroups with Ordinary Composition. Proceedings - Symposium on Logic in Computer Science, 2021-June. doi:10.1109/LICS52264.2021.9470509 

• Liu, J., Balatti, P., Ellis, K., Hadjivelichkov, D., Stoyanov, D., Ajoudani, A., & Kanoulas, D.  Garbage Collection and Sorting with a Mobile Manipulator using Deep Learning and Whole-Body Control. (2021).

• Hirsch, R., & Semrl, J. Demonic Lattices and Semilattices in Relational Semigroups with Ordinary Composition. Proceedings - Symposium on Logic in Computer Science, 2021-June. doi:10.1109/LICS52264.2021.9470509 (2021)

• Biggs, F.; Guedj, B Differentiable PAC–Bayes Objectives with Partially Aggregated Neural Networks Entropy 2021, 23, 1280

• Fanghua Ye, Jarana Manotumruksa, Qiang Zhang, Shenghui Li, Emine Yilmaz. Slot Self-Attentive Dialogue State Tracking  Proceedings of the Web Conference 2021. 

• J Kaddour, Y Zhu, Q Liu, MJ Kusner, R Silva Causal Effect Inference for Structured Treatments NeurIPS 2021

• O Key*, T Fernandez*, A Gretton, F-X Briol Composite Goodness-of-fit Tests with Kernels Your Model is Wrong Workshop at NeurIPS 2021

• Hawkins-Hooker, A., Jones, D.T. & Paige, B. MSA-conditioned generative protein language models for fitness landscape modelling and design, Machine Learning in Structural Biology workshop at NeurIPS, 2021.

2020

• Tang, H., Meng, Z., Hao, J., Chen, C., Graves, D., Li, D., Liu, W., Yang, Y. and Yu, C., 2020. What About Taking Policy as Input of Value Function: Policy-extended Value Function Approximator.

• Augustine N Mavor-Parker, Kimberly A Young, Caswell Barry, Lewis Griffin  Escaping Stochastic Traps with Aleatoric Mapping Agents, previously presented at NeurIPS Biological and Artificial Reinforcement Learning Workshop, 2020. 

• Cohen, S., Arbel, M., & Deisenroth, M. (2020).[2007.07105] Estimating Barycenters of Measures in High Dimensions (arxiv.org)

• Kaddour, J; Saemundsson, S; Deisenroth, M  Probabilistic Active Meta-Learning  NeurIPS 2020