Skip to main content
Menu

Publications from the EPSRC CDT in Autonomous Intelligent Machines and Systems, University of Oxford

Publications

AIMS students have published their work at leading venues in their field, including CVPR, NIPS, ICCV, AAAI, ICLR and IROS: this is indicative of the high quality of research conducted at AIMS.

  • Yash Bhalgat, Vadim Tschernezki, Iro Laina, João F. Henriques, Andrea Vedaldi, Andrew Zisserman.  “3D-Aware Instance Segmentation and Tracking in Egocentric Videos”. ACCV 2024.

  • Harrison Waldon, Fayçal Drissi, Yannick Limmer, Uljad Berdica, Jakob Nicolaus Foerster, Alvaro Cartea. “DARE: The Deep Adaptive Regulator for Control of Uncertain Continuous-Time Systems”. ICML 2024. 

  • Uljad BerdicaKelvin LiMichael BeukmanAlexander David GoldiePerla MaiolinoJakob Nicolaus Foerster. “Robust Offline Learning via Adversarial World Models”.  NeurIps 2024.

  • Uljad Berdica, Matthew Jackson, Niccolò Enrico Veronese, Jakob Foerster, Perla Maiolino. “Reinforcement Learning Controllers for Soft Robots Using Learned Environments”. 2024 IEEE 7th International Conference on Soft Robotics (RoboSoft).

  • Sarah Kiden, Bernd Stahl, Beverley Townsend, Carsten Maple, Charles Vincent, Fraser Sampson, Geoff Gilbert, Helen Smith, Jayati Deshmukh, Jen Ross, Jennifer Williams, Jesus Martinez del Rincon, Justyna Lisinska, Karen O'Shea, Márjory Da Costa Abreu, Nelly Bencomo, Oishi Deb, Peter Winter, Phoebe Li, Philip Torr, Pin Lean Lau, Raquel Iniesta, Gopal Ramchurn, Sebastian Stein, and Vahid Yazdanpanah. 2024. Responsible AI governance: A response to UN interim report on governing AI for humanity. Public Policy, University of Southampton. 23pp. (doi:10.5258/SOTON/PP0057)

    (Apart from the first author, all the other authors contributed equally and were ordered alphabetically by their first name.)

    BibTeX citation - https://eprints.soton.ac.uk/cgi/export/eprint/488908/BibTeX/soton-eprint-488908.bib

  • Benedetta L Mussati, Helen McKay (Mind Foundry); Stephen Roberts. "Neural Processes for Short-Term Forecasting of Weather Attributes". ICLR2024.
  • Junyu Xie, Charig Yang, Weidi Xie, Andrew Zisserman. Moving Object Segmentation: All You Need Is SAM (and Flow). In ACCV, 2024.

  •     C. Yang, W. Xie, A. Zisserman. Made to Order: Discovering monotonic temporal changes via self-supervised video ordering. ECCV 2024.
  • Jonathan F. Carter, João Jorge, Oliver Gibson, Lionel Tarassenko. "SleepVST: Sleep Staging from Near-Infrared Video Signals using Pre-Trained Transformers" .Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
  • Tim Franzmeyer*, Aleksandar Shtedritski*, Samuel Albanie, Philip Torr, Joao F. Henriques, Jakob Foerster. HelloFresh: LLM Evaluations on Streams of Real-World Human Editorial Actions across X Community Notes and Wikipedia edits. ARL 2024.
  • Aleksandar Shtedritski, Christian Rupprecht, Andrea Vedaldi. Shape-Image Correspondences with no Keypoint Supervision. ECCV 2024.
  • Yash Bhalgat, Iro Laina, João F. Henriques, Andrew Zisserman, Andrea Vedaldi. N2F2: Hierarchical Scene Understanding with Nested Neural Feature Fields. ECCV24
  • Shu Ishida, Gianluca Corrado, George Fedoseev, Hudson Yeo, Lloyd Russell, Jamie Shotton, Joao F. Henriques, Anthony Hu. "LangProp: A code optimization framework using Large Language Models applied to driving". ICLR 2024 Workshop on Large Language Model (LLM) Agents

  • Yoshua Bengio, Geoffrey Hinton, Andrew Yao, Dawn Song, Pieter Abbeel, Trevor Darrell, Yuval Noah Harari, Ya Qin Zhang, Lan Xue, Shai Shalev-Shwartz, Gillian Hadfield, Jeff Clune, Tegan Maharaj, Frank Hutter, Atilim Gunes Baydin, Sheila McIlraith, Qiqi Gao, Ashwin Acharya, David Krueger, Anca Dragan, Philip Torr, Stuart Russell, Daniel Kahneman, Jan Brauner and Soren Mindermann.  Managing extreme AI risks amid rapid progress. Science 2024

  • Oishi Deb, Philip H.S. Torr, Sarah Kiden, Sebastian Stein, Sarvapali D. Ramchurn, et al. "Responsible AI governance: A response to UN interim report on governing AI for humanity"; Southampton, Responsible AI (RAI) UK, 2024; Full Paper Link; DOI:10.5258/SOTON/PP0057

  • Shuai Chen, Yash Bhalgat, Xinghui Li, Jia-Wang Bian, Kejie Li, Zirui Wang, Victor Adrian Prisacariu. Neural Refinement for Absolute Pose Regression with Feature Synthesis. CVPR2024. 

  • Yifu Tao, Yash Bhalgat, Nived Chebrolu, Maurice Fallon.  SiLVR: Scalable Lidar-Visual Reconstruction with Neural Radiance Fields for Robotic Inspection. ICRA 2024.
  • Aleks Petrov and Adel Bibi. "When Do Prompting and Prefix-Turning Work". ICLR2024.
  • Oishi Deb, Emmanouil Benetos, Philip H.S. Torr, "Remaining-Useful-Life Prediction and Uncertainty Quantification using LSTM Ensembles for Aircraft Engines." - PaperPoster, at WANT (Workshop on Advancing Neural-Network Training), NeurIPS 2023.
  • Oishi Deb, Prajwal Kondajji Renukananda, Andrew Zisserman, "New keypoint-based approach for recognising British Sign Language (BSL) from sequences." - BMVC 2023 CADL (Computational Aspects of Deep Learning) - Oral Presentation; and also at ICCV 2023 HANDS.

  • Jishnu Mukhoti*, Andreas Kirsch*, Joost van Amersfoort, Philip HS Torr, and Yarin Gal. "Deep Deterministic Uncertainty: A New Simple Baseline." In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2023.
  • Andreas Kirsch. "Black-Box Batch Active Learning for Regression." Transactions in Machine Learning Research (TMLR) 2023.
  • Andreas Kirsch*, Sebastian Farquhar*, Parmida Atighehchian, Andrew Jesson, Frédéric Branchaud-Charron, and Yarin Gal. "Stochastic Batch Acquisition: A Simple Baseline for Deep Active Learning." Transactions in Machine Learning Research (TMLR) 2023.
  • Andreas Kirsch. "Does Deep Learning on a Data Diet reproduce? Overall yes, but GraNd at Initialization does not." Transactions in Machine Learning Research (TMLR) 2023.
  • Matthew Thomas Jackson,Minqi Jiang,Jack Parker-Holder,Risto Vuorio,Chris Lu,Gregory Farquhar,Shimon Whiteson,Jakob Nicolaus Foerster. "Discovering General Reinforcement Learning Algorithms with Adversarial Environment Design". NeurIPS 2023.
  • Dominik Kloepfer, Dylan Campbell and Joao Henriques. "LoCUS: Learning Multiscale 3D-consistent Features from Posed Images"ICCV 2023.
  • Benjamin EllisJonathan CookSkander MoallaMikayel SamvelyanMingfei SunAnuj MahajanJakob FoersterShimon Whiteson.   “SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learning”. NeurIPS 2023
  • Aleksandar Shtedritski, Christian Rupprecht, Andrea Vedaldi. “What does CLIP know about a red circle? Visual prompt engineering for VLMs. ICCV 2023
  • Aleksandar Shtedritski, Andrea Vedaldi, Christian Rupprecht.  “Learning Universal Semantic Correspondences with No Supervision and Automatic Data Curation”. ICCV 2023
  • Siobhan Mackenzie Hall, Fernanda Gonçalves Abrantes, Hanwen Zhu, Grace Sodunke, Aleksandar Shtedritski, Hannah Rose Kirk . “VisoGender: A dataset for benchmarking gender bias in image-text pronoun resolution”. Neurips Datasets and Benchmarks 2023
  • Aleksandar Petrov, Emanuele La MalfaPhilip H.S. TorrAdel Bibi.  “Language Model Tokenizers Introduce Unfairness Between Languages”. NeurIPS 2023
  • Yash Bhalgat, Iro Laina, João F. Henriques, Andrew Zisserman, Andrea Vedaldi. “Contrastive Lift: 3D Object Instance Segmentation by Slow-Fast Contrastive Fusion”. NeurIPS 2023. 
  • Cong Lu, Philip J. Ball, Yee Whye Teh, Jack Parker-Holder. “Synthetic Experience Replay”. NeurIPS 2023.
  • Lars Holdijk, Yuanqi Du, Ferry Hooft, Priyank Jaini, Bernd Ensing and Max Welling. Stochastic Optimal Control for Collective Variable Free Sampling of Molecular Transition Paths. NeurIPS 2023.
  • Niki Amini-Naieni, Kiana Amini-Naieni, Tengda Han and Andrew Zisserman. “CounTX: Open-world Text-specified Object Counting”. BMVC 2023 (Awarded a best poster award).
  • A. Mitchell et al., "VAE-Loco: Versatile Quadruped Locomotion by Learning a Disentangled Gait Representation," in IEEE Transactions on Robotics, doi: 10.1109/TRO.2023.3297015.
  • Lewis Hammon, James Fox, Tom Everitt, Ryan Carey, Alessandro Abate & Michael Wooldridge. "Reasoning about Causality in Games". The AI Journal.
  • Alessandro Abate, Yousif, James Fox, David Hyland and Michael Wooldridge. "Learning Task Automata for Reinforcement Learning using Hidden Markov Models". ECAI 2023.
  • James Fox, Matt MacDermott, Lewis Hammond, Paul Harrenstein, Alessandro Abate & Michael Wooldridge. "On Imperfect Recall in Multi-Agent Influence Diagrams". TARK 2023 (Best Paper Award)
  • K.Doerksen, Y.Gal, F. Kalaitzis, C. Rossi, D. Petit, S. Li, S. Dadson, Precipitation-triggered landslide prediction in Nepal using Machine Learning and Deep Learning, IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, Pasadena, California, 2023.

  • Benjamin Ramtoula, Matthew Gadd, Paul Newman, Daniele De Martini. "Visual DNA: Representing and Comparing Images using Distributions of Neuron Activations". CVPR 2023.

  • Aleksandar Petrov, Emanuele La Malfa, Philip H.S. Torr, Adel Bibi. Language Model Tokenizers Introduce Unfairness Between Languages. Challenges of Deploying Generative AI workshop at ICML 2023.

  • Tom Rainforth, Adam Foster, Desi Ivanova, Freddie Bickford Smith (2023). Modern Bayesian experimental design. Statistical Science.

  • Aleksandar Petrov, Francisco Eiras, Amartya Sanyal, Philip H.S. Torr, Adel Bibi. Certifying Ensembles: A General Certification Theory with S-Lipschitzness. ICML 2023

  • Zheng Xiong, Jacob Beck, Shimon Whiteson. Universal Morphology Control via Contextual Modulation. ICML 2023.

  • Luke Rickard, Thom Badings, Licio Romao, Alessandro Abate. Formal Controller Synthesis for Markov Jump Linear Systems with Uncertain Dynamics. QEST 2023.

  • Shreshth A Malik, Salem Lahlou, Andrew Jesson, Moksh Jain, Nikolay Malkin, Tristan Deleu, Yoshua Bengio, Yarin Gal. BatchGFN: Generative Flow Networks for Batch Active Learning. ICML 2023: Structured Probabilistic Inference & Generative Modeling Workshop.

  • Bajgar, O., & Horenovsky, J. (2023). Negative Human Rights as a Basis for Long-term AI Safety and Regulation. Journal of Artificial Intelligence Research, 76, 1043-1075.
  • Jonathan Carter João Jorge, Bindia Venugopal, Oliver Gibson, Lionel Tarassenko. "Deep Learning-Enabled Sleep Staging From Vital Signs and Activity Measured Using a Near-Infrared Video Camera", was recently published at the 6th International Workshop on Computer Vision for Physiological Measurement (CVPM)  at CVPR 2023 in Vancouver. It received an Honorable Mention for the Best Paper award.
  • Benjamin Gutteridge, Xiaowen Dong, Michael Bronstein and Francesco Di Giovanni.  "DRew: Dynamically Rewired Message Passing with Dela". ICML 2023.
  • J. Beuchert, M. Camurri and M. Fallon, "Factor Graph Fusion of Raw GNSS Sensing with IMU and Lidar for Precise Robot Localization without a Base Station," 2023 IEEE International Conference on Robotics and Automation (ICRA), London, United Kingdom, 2023, pp. 8415-8421, doi: 10.1109/ICRA48891.2023.10161522.
  • Yamada Jun*, Chia-Man Hung*, Jack Collins, Ioannis Havoutis, Ingmar Posner. "Leveraging Scene Embeddings for Gradient-Based Motion Planning in Latent Space." IEEE International Conference on Robotics and Automation (ICRA), 2023. *Equal contribution

  • Yash Bhalgat, Joao Henriques and Andrew Zisserman. “A Light Approach to Teaching Transformers Multi-view Geometry”.(CVPR 2023).
  • Anna Gautier, Marc Rigter, Bruno Lacerda, Nick Hawes, and Michael Wooldridge (2023). “Risk-Constrained Planning for Multi-Agent Systems with Shared Resources”. In Proceedings of the 22nd International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2023).
  • Anna Gautier, Bruno Lacerda, Nick Hawes, and Michael Wooldridge (2023). “Multi-Unit Auctions for Allocating Chance-Constrained Resources”. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI 2023).
  • Jonas Beuchert, Amanda Matthes and Alex Rogers.  “SnapperGPS:  Open Hardware for Energy-Efficient, Low-Cost Wildlife Location Tracking with Snapshot GNSS”. Journal of Open Hardware, 7(1): 2, pp. 1–13. 2023. DOI: https://doi.org/10.5334/joh.48
  • Freddie Bickford Smith*, Andreas Kirsch*, Sebastian Farquhar, Yarin Gal, Adam Foster, Tom Rainforth. “Prediction-oriented Bayesian active learning”International Conference on Artificial Intelligence and Statistics (AISTATS 2023).
  • Gunshi Gupta, Tim G.J. Rudner, Rowan Thomas McAllister, Adrien Gaidon, Yarin Gal. "Can Active Sampling Reduce Casual Confusion in Offline Reinforcement Learning".(CleaR 2023).
  • Hugo Berg, Siobhan, Yash Bhalgat, Hannah Kirk, Aleksandar Shtedritski, Max Bain.  "A Prompt Array Keeps the Bias Away: Debiasing Vision-Language Models with Adversarial Learning".  (AACL-IJCNLP 2022).
  • Taras Rumezhak, Francisco Eiras, Philip HS Torr, Adel Bibi. "RANCER: Non-Axis Aligned Anisotropic Certification With Randomized Smoothing." IEEE Winter Conference on Applications of Computer Vision (2023).
  • Francisco Eiras, Motasem Alfarra, Philip HS Torr, M. Pawan Kumar, Puneet Dokania, Bernard Ghanem, Adel Bibi. "ANCER: Anisotropic Certification via Sample-wise Volume Maximization." Transactions of Machine Learning Research (2022).
  • K. Doerksen et al. “A Multi-Lander New Frontiers Mission Concept study for Enceladus: SILENUS”. Frontiers in Astronomy and Space Sciences
  • Reichelt, Tim, Adam Goliński, Luke Ong, and Tom Rainforth. "Expectation programming: Adapting probabilistic programming systems to estimate expectations efficiently." In Uncertainty in Artificial Intelligence, pp. 1676-1685. PMLR, 2022.
  • Tim Rudner, Freddie Bickford Smith, Qixuan Feng, Yee Whye Teh, Yarin Gal (2022). Continual learning via sequential function-space variational inference. International Conference on Machine Learning (ICML).
  • Reichelt, Tim, Luke Ong, and Thomas Rainforth. "Rethinking Variational Inference for Probabilistic Programs with Stochastic Support." Advances in Neural Information Processing Systems 35 (2022): 15160-15175
  • Siddhant Gangapurwala; Mathieu Geisert; Romeo Orsolino; Maurice Fallon; Ioannis Havoutis. “RLOC: Terrai-Aware Legged Locomotion Using Reinforcement Learning and Optimal Control”. IEEE 2022.
  • Pierre-Yves Lajoie, Benjamin Ramtoula, Fang Wu, and Giovanni Beltrame. “Towards Collaborative Simultaneous Localization and Mapping: A Survey of the Current Research Landscape”. Field Robotics, 2022.
  • Shreshth A Malik, Nora L Eisner, Chris J Lintott, Yarin Gal. Discovering Long-period Exoplanets using Deep Learning with Citizen Science Labels. NeurIPS 2022: Machine Learning and the Physical Sciences Workshop.

  • Prannay Kaul, Weidi Xie, Andrew Zisserman. “Label, Verify, Correct: A Simple Few-Shot Object Detection Method”. (CVPR2022).
  • Shu Ishida, João F. Henriques, “Towards real-world navigation with deep differentiable planners”. Computer Vision and Pattern Recognition (CVPR) 2022.
  • Cong Lu, Philip BallJack Parker-HolderMichael OsborneStephen J. Roberts. Revisiting Design Choices in Offline Model Based Reinforcement Learning”. ICLR 2022.
  • Julian Gutierrez, Thomas Steeples, Michael Wooldridge. “Mean-Payoff Games with ω-Regular Specifications”. (Games 2022)
  • Charig Yang, Weidi Xie & A Zisserman. “It's About Time: Analog Clock Reading in the Wild”. (CVPR 2022).
  • Sören Mindermann*, Jan M. Brauner*, Muhammed T. Razzak*, Mrinank Sharma*, Andreas Kirsch, Winnie Xu, Benedikt Höltgen et al. "Prioritized training on points that are learnable, worth learning, and not yet learnt." In International Conference on Machine Learning (ICML) 2022.
  • Andrew Jesson*, Panagiotis Tigas*, Joost van Amersfoort, Andreas Kirsch, Uri Shalit, and Yarin Gal. "Causal-bald: Deep bayesian active learning of outcomes to infer treatment-effects from observational data."  Advances in Neural Information Processing Systems (NeurIPS) 2021.
  • Chia-Man Hung, Shaohong Zhong, Walter Goodwin, Oiwi Parker Jones, Martin Engelcke, Ioannis Havoutis and Ingmar Posner.  “Reaching Through Latent Space: From Joint Statistics to Path Planning”. IEEE Robotics & Automations Letters.
  • Tim G. J. Rudner*, Vitchyr H. Pong*, Rowan McAllister, Yarin Gal, Sergey Levine. 
    “Outcome-Driven Reinforcement Learning via Variational Inference”
    . (NeurIPS '21).
  • Tim G. J. Rudner*, Cong Lu*, Michael A. Osborne, Yarin Gal, Yee Whye The. “On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations”. (NeurIPS '21).
  • Neil Band*, Tim G. J. Rudner*, Qixuan Feng, Angelos Filos, Zachary Nado, Michael W. Dusenberry, Ghassen Jerfel, Dustin Tran, Yarin Gal. “Benchmarking Bayesian Deep Learning on Diabetic Retinopathy Detection Tasks”. Conference on Neural Information Processing Systems 2021.
  • Tim G. J. Rudner*, Oscar Key*, Yarin Gal, Tom Rainforth. “On Signal-to-Noise Ratio Issues in Variational Inference for Deep Gaussian Processes”. International Conference on Machine Learning 2021.
  • Bryn Elesedy. “Provably Strict Generalisation Benefit for Invariance in Kernel Methods”. (NeurIPS 2021).
  • Bryn Elesedy and Sheheryar Zaidi. “Provably Strict Generalisation Benefit for Equivariant Models”. (ICML 2021).
  • Charig Yang, Hala Lamdouar, Erika Lu, Andrew Zisserman, Weidi Xie. “Self-supervised Video Object Segmentation by Motion Grouping” . ICCV, 2021 (also Best Paper Award for CVPR 2021 Workshop).
  • Yee Whye Teh, Avishkar Bhoopchand, Peter Diggle, Bryn Elesedy, Bobby He, Michael Hutchinson,Ulrich Paquet, Jonathan Read, Nenad Tomasev, Sheheryar Zaidi. “Efficient Bayesian Inference of Instantaneous Reproduction Numbers at Fine Spatial Scales, with an Application to Mapping and Nowcasting the COVID-19 Epidemic in British Local Authorities”. Royal Society Special Topic Meeting on R, Local R and Transmission of COVID-19.
  • Bobby He*, Sheheryar Zaidi*, Bryn Elesedy*, Michael Hutchinson*, Andrei Paleyes, Guy Harling, Anne Johnson, Yee Whye Teh on behalf of Royal Society DELVE group. *equal contribution.”Effectiveness and Resource Requirements of Test, Trace and Isolate Strategies2. Royal Society Open Science, 2021.
  • Bryn Elesedy, Varun Kanade, Yee Whye Teh. Lottery Tickets in Linear Models: An Analysis of Iterative Magnitude Pruning. Sparsity in Neural Networks Workshop, 2021.
  • Mikayel Samvelyan, Rob Kirk, Vitaly Kurin,Jack Parker-Holder, Minqi Jiang, Eric Hambro, Fabio Petroni, Heiner Kuttler, Edward Grefenstette, Tim Rocktäschel. “MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research”. (NeurIPS 2021).
  • Charles Blake, Vitaly Kurin, Maximilian Igl, Shimon Whiteson. “Snowflake: Scaling GNNs to high-dimensional continuous control via parameter freezing”.(NeurIPS 2021).
  • M Newton and A Papachristodoulou. “Neural Network Verification Using Polynomial Optimisation”. (CDC 2021).
  • Zheng Xiong, Luisa Zintgraf, Jacob Beck, Risto Vuorio, Shimon Whiteson. “On the Practical Consistency of Meta-Reinforcement Learning Algorithms”. (NeurIPS 2021).
  • S Ridderbusch,C Offen, S Ober-Bloebaum and P J Goulart. “Learning ODE Models with Qualitative Structure Using Gaussian Processes (I)”. (CDC202).
  • M Sharma*, S Mindermann*, C Rogers-Smith, G Leech, B Snodin, J Ahuja, JB Sandbrink, JT Monrad, G Altman, G Dhaliwal, L Finnveden, AJ Norman, SB Oehm, JF Sandkühler, L Aitchison, T Mellan, J Kulveit, L Chindelevitch, S Flaxman, Y Gal, S Mishra+, S Bhatt+, JM Brauner*+. “Understanding the effectiveness of government interventions in Europe’s second wave of COVID-19”.Nature Communications 12, 5820 (2021). (link)
  • S Mishra, S Mindermann, M Sharma, C Whittaker, TA Mellan, T Wilton, D Klapsa, R Mate, M Fritzsche, M Zambon, J Ahuja, A Howes, X Miscouridou, GP Nason, O Ratmann, E Semenova, G Leech, JF Sandkühler, C Rogers-Smith, M Vollmer, HJT Unwin, Y Gal, M Chand, A Gandy, J Martin, E Volz, NM Ferguson+, S Bhatt+, JM Brauner+,Seth Flaxman+. “Changing composition of SARS-CoV-2 lineages and rise of Delta variant in England”.  EClinicalMedicine, 39, 2021,101064.
  • G Meyerowitz-Katz, S Bhatt, O Ratmann, JM Brauner, S Flaxman, S Mishra, M Sharma, S Mindermann, V Bradley, M Vollmer, L Merone, G Yamey.Is the cure really worse than the disease? The health impacts of lockdowns during COVID-19. BMJ Global Health 2021;6:e006653.
  • Jonas Beuchert and Alex Rogers. 2021. “SnapperGPS: Algorithms for Energy-Efficient Low-Cost Location Estimation Using GNSS Signal Snapshots”. In Proceedings of the 19th ACM Conference on Embedded Networked Sensor Systems (SenSys '21). Association for Computing Machinery, New York, NY, USA, 165–177.
  • Laurynas Karazija, Iro Laina, Christian Rupprecht. “ClevrTex: A Texture-Rich Benchmark for Unsupervised Multi-Object Segmentation”. Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks, 2021. Paper | Project page
  • Alasdair Paren, Leonard Berrada, Rudra P. K. and M. Pawan Kumar. “A Stochastic Bundle Method for Interpolating Networks”. (JMLR 2022).
  • Alasdair Paren, Rudra P. K. and M. Pawan Kumar. “Faking Interpolation Until you make It”. (NeurIps 2021).
  • Lisa Schut, Miroslav Fil, Mark van der Wilk, Yarin Gal Robin Ru*, Clare Lyle*,. “Speedy Performance Estimation for Neural Architecture Search”. (NeurIPS 2021 Spotlight).
  • Lisa Schut*, Oscar Key*, Rory McGrath, Luca Costabello, Bogdan Sacaleanu, Medb Corcoran, Yarin Gal. “Generating Interpretable Counterfactual Explanations By Implicit Minimisation of Epistemic and Aleatoric Uncertainties”. (AISTATS 2021).
  • Lisa Schut, Edward Hu, Greg Yang, Yarin Gal. “Deep Ensemble Uncertainty Fails as Network Width Increases: Why, and How to Fix It”.ICML Workshop on Uncertainty in Deep Learning (UDL) 2021.
  • Benedikt Höltgen, Lisa Schut,Jan M. Brauner, Yarin Gal. “DeDUCEGenerating Counterfactual Explanations at Scale”. (NeurIPS XAI4Debugging Workshop 2021).
  • Albert Qiaochu Jiang, Clare Lyle, Lisa Schut, Yarin Gal. “Can Network Flatness Explain the Training Speed-Generalisation Connection?”. (NeurIPS BDL Workshop 2021).
  • M. N. Finean, W. Merkt, and I. Havoutis. “Where Should I Look? Optimised Gaze Control for Whole-Body Collision Avoidance in Dynamic Environments”. IEEE Robotics and Automation Letters 2021. 
  • Shaan A. Desai, Marios Mattheakis, and Stephen J. Roberts.  “Variational integrator graph networks for learning energy-conserving dynamical systems”.
  • Shaan A. Desai, Marios Mattheakis, David Sondak, Pavlos Protopapas, and Stephen J. Roberts. “Port-Hamiltonian neural networks for learning explicit time-dependent dynamical systems”.
  • Jack Parker-Holder, Vu Nguyen, Shaan Desai and Steve J. Roberts.”Tuning Mixed Input Hyperparameters on the Fly for Efficient Population Based AutoRL” (arxiv.org). NeurIps 2021.
  • Finean, Mark, W. Merkt, and I. Havoutis. “Predicted Composite Signed-Distance Fields for Real-Time Motion Planning in Dynamic Environments”. (ICAPS, 2021).
  • Finean, Mark, W. Merkt, and I. Havoutis, “Simultaneous Scene Reconstruction and Whole-Body Motion Planning for Safe Operation in Dynamic Environments”. (IEEE/RSJ IROS, 2021).
  • Moseley B., Bickel, V., Lopez-Francos, I., Rana, L., “Extreme low-light environment-driven image denoising over permanently shadowed lunar regions with a physical noise model”. Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition 2021.
  • Rhydian Windsor, Amir Jamaludin, Timor Kadir, Andrew Zisserman. “Self-Supervised Multi-Modal Alignment For Whole Body Medical Imaging”. (MICCAI 2021).
  • Bryn Elesedyand Sheheryar Zaidi. “Provably Strict Generalisation Benefit for Equivariant Models”.  (ICML 2021).
  • Yee Whye Teh, Avishkar Bhoopchand, Peter Diggle, Bryn Elesedy, Bobby He, Michael Hutchinson, Ulrich Paquet, Jonathan Read, Nenad Tomasev, Sheheryar Zaidi (YWT then alphabetical ordering).  “Efficient Bayesian Inference of Instantaneous Reproduction Numbers at Fine Spatial Scales, with an Application to Mapping and Nowcasting the COVID-19 Epidemic in British Local Authorities”. Royal Society Special Topic Meeting on R, Local R and Transmission of COVID-19. Website: info.
  • Bobby He*, Sheheryar Zaidi*, Bryn Elesedy*, Michael Hutchinson*, Andrei Paleyes, Guy Harling, Anne Johnson, Yee Whye Teh on behalf of Royal Society DELVE group (* equal contribution).  “Effectiveness and resource requirements of test, trace and isolate strategies for COVID in the UK”. Royal Society Open Science, 2021. 
  • Bryn Elesedy, Varun Kanade, Yee Whye Teh. “Lottery Tickets in Linear Models: An Analysis of Iterative Magnitude Pruning”. Sparsity in Neural Networks Workshop, 2021.
  • Alessandro Abate, Julian Gutierrez, Lewis Hammond, Paul Harrenstein, Marta Kwiatkowska, Muhammad Najib, Giuseppe Perelli, Thomas Steeples, Michael J. Wooldridge. “Rational Verification: Game-Theoretic Verification of Multi-Agent Systems”. Applied Intelligence 51, 6569–6584 (2021).
  • Thomas Steeples, Julian Gutierrez, Michael J. Wooldridge. “Mean-Payoff Games with ω-Regular Specifications”. (AAMAS 2021: 1272-1280).
  • Oliver Groth, Chia-Man Hung, Andrea Vedaldi, Ingmar Posner. “Goal-Conditioned End-to-End Visuomotor Control for Versatile Skill Primitives”. (ICRA 2021).
  • Chia-Man Hung, Li Sun, Yizhe Wu, Ioannis Havoutis, Ingmar Posner. “Introspective Visuomotor Control: Exploiting Uncertainty for Failure Recovery”. ICRA (IEEE International Conference on Robotics and Automation) 2021.
  • Freddie Bickford Smith, Brett D Roads, Xiaoliang Luo and Bradley C Love.  “Understanding top-down attention using task-oriented ablation design”. https://arxiv.org/abs/2106.11339.
  • Patane, A., Blaas, A., Laurenti, L., Cardelli, L., Roberts, S., & Kwiatkowska, M. (2021). “Adversarial Robustness Guarantees for Gaussian Processe”sarXiv preprint arXiv:2104.03180.
  • Wicker, M., Laurenti, L., Patane, A., Chen, Z., Zhang, Z., & Kwiatkowska, M. (2021, March). “Bayesian inference with certifiable adversarial robustness”. In International Conference on Artificial Intelligence and Statistics (pp. 2431-2439). PMLR.
  • Maximilian Igl et al. “Transient Non-stationarity and Generalisation in Deep Reinforcement Learning”. In: International Conference on Learning Representations (ICLR 2021).
  • Mandela Patrick, Po-Yao Hung, Yuki Asano, FLorian Metze, Alexander Hauptmann, Joao Henriques and Andrea Vedaldi. “Suppoer-set bottlenecks for video-text representation learning”.
  • James Fox, Lewis Hammond, Tom Everitt, Alessandro Abate and Mike Wooldridge.  “Equilibrium Refinements for Multi-Agent Influence Diagrams: Theory and Practice”.  (AAMAS 2021).
  • Alessandro De Palma*, Harkirat Singh Behl*, Rudy Bunel, Philip H. S. Torr, and M. Pawan Kumar. “Scaling the Convex Barrier with Active Sets”. International Conference on Learning Representations, 2021.
  • Rudy Bunel*, Alessandro De Palma*, Alban Desmaison, Krishnamurthy Dvijotham, Pushmeet Kohli, Philip H. S. Torr, and M. Pawan Kumar. “Lagrangian Decomposition for Neural Network Verification”. Conference on Uncertainty in Artificial Intelligence (UAI 2020).
  • Jan Bruaner, Mrinank Sharma et al. “Inferring the effectiveness of government interventions against COVID-19”. Science 2020
  • Sasha Salter (University of Oxford)*; Dushyant Rao (DeepMind); Markus Wulfmeier (DeepMind); Raia Hadsell (Deepmind); Ingmar Posner (Oxford University). “Attention-Privileged Reinforcement Learning”.(CoRL 2020).
  • Polymenakos, Kyriakos, et al. "Safety Guarantees for Iterative Predictions with Gaussian Processes". 2020 59th IEEE Conference on Decision and Control (CDC). IEEE, 2020.
  • Blaas, A., Patane, A., Laurenti, L., Cardelli, L., Kwiatkowska, M., & Roberts, S. (2020, June). “Adversarial robustness guarantees for classification with gaussian processes”. In International Conference on Artificial Intelligence and Statistics (pp. 3372-3382). PMLR.
  • Wicker, M., Laurenti, L., Patane, A., & Kwiatkowska, M. (2020, August). “Probabilistic safety for bayesian neural networks”. In Conference on Uncertainty in Artificial Intelligence (pp. 1198-1207). PMLR.
  • Sasha Salter (University of Oxford)*; Dushyant Rao (DeepMind); Markus Wulfmeier (DeepMind); Raia Hadsell (Deepmind); Ingmar Posner (Oxford University). “Attention-Privileged Reinforcement Learning”. RSS20-SARL.
  • Yuki M. Asano*, Mandela Patrick*, Christian Rupprecht,  Andrea Vedaldi. “Labelling unlabelled videos from scratch with multi-modal self-supervision”.  (NeurIPS2020).
  • Shuyu Lin and Ronald Clark. “LaDDer: Latent Data Distribution Modelling with a Generative Prior”.  (BMVC 2020).
  • Fabian B. Fuchs, Daniel Worrall, Volker Fischer and Max Welling.  “SE(3)-Transformers:3D Roto-Translation Equivariant Attention Networks”.
  • Vitaly Kurin, Saad Godil, Shimon Whiteson, Bryan Catanzaro. “Improving SAT Solver Heuristics with Graph Networks and Reinforcement Learning”. (NeurIPS 2020).
  • Rhydian Windsor, Amir Jamaludin, Timor Kadir and Andrew Zisserman.A Convolutional Approach to Vertebrae Detection and Labelling in Whole Spine MRI”.  Medical Image Computing and Computer Aided Intervention (MICCAI 2020).
  • Mrinank Sharma, Soren Mindermann, Jan Markus Brauner, Gavin Leech, Anna B. Stephenson, Tomas Gavenciak, Jan Kulveit, Yee Whye Teh, Leonid Chindelevitch and Yarin Gal. “On the Robustness of Effectiveness Estimation of Nonpharmaceutical Interventions against COVID-19 Transmissions”.  (NeurIPS 2020).
  • Adam Goliński*, Reza Pourreza*, Yang Yang*, Guillaume Sautiere, Taco S Cohen.  Feedback Recurrent Autoencoder for Video Compression. ACCV, 2020.
  • Tom Rainforth*, Adam Goliński*, Frank Wood, Sheheryar Zaidi. “Target–Aware Bayesian Inference: How to Beat Optimal Conventional Estimators”.JMLR 21(88):1−54, 2020.
  • Ginevra Carbone, Matthew Wicker, Luca Laurenti, Andrea Patane, Luca Bortolussi and Guido Sanguinetti. “Robustness of Bayesian Neural Networks to Gradient-Based Attacks”. In 34th Conference on Neural Information Processing Systems (NeurIPS'20), Springer. 2020.
  • Wendelin Bohmer, Vitaly Kurin, Shimon Whiteson. “Deep Coordination Graphs”. ICML2020
  • Ben Moseley, Tarjie Nissen-Meyer, Andrew Markham. “Deep Learning for Fast Simulation for Seismic Waves in Complex Media”.  Solid Earth - An interactive open-access journal of the European Geoscience Unio 2020.
  • Tim G. J. Rudner, Dino Sejdinovic, Yarin Gal. “Inter-domain Deep Gaussian Processes with RKHS Fourier Features”. (ICML 2020).
  • Gutierrez, A Murano, G. Perelli, S Rubin, T. Steeplesand M. Wooldridge. “Equilibria for Games with Combined Qualative and Quantative Objective”s. Springer 2020.
  • Maximilian Igl, Andrew Gambardella, Jinke He, Nantas Nardelli, N Siddharth, Wendelin Böhmer, Shimon Whiteson. “Multitask Soft Option Learning". UAI 2020 (The Thirty-Sixth Conference on Uncertainty in Artificial Intelligence).
  • Jamaludin, R. Windsor, S. Ather, T. Kadir, A. Zisserman, J. Braun, L. S. Gensler, P. M. Machado, M. Østergaard, D. Poddubnyy, T. Coroller, B. Porter, S. Mpofu, A. Readie. “Machine learning based Berlin scoring of magnetic resonance images of the spine in patients with ankylosing spondylitis from the MEASURE 1 study”. Annual European Congress of Rheumatology 2020.
  • Triantafyllos Afouras, Joon Son Chung, Andrew Zisserman. "ASR is all you need: Cross-modal distillation for lip reading". (ICASSP 2020).
  • Henry Kenlay, Dorina Thanou, Xiaowen Dong. “On the Stability of Polynomial Spectral Graph Filters”.  ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • B Liu, I Kiskin, S Roberts. “An Overview of Gaussian Process Regression for Volatility Forecasting”. IEEE International Conference on Artificial Intelligence in Information and Communication, 2020, 2020 (Liu et al., 2020).
  • Prannay Kaul, Danielle De Martini, Matthew Gadd and Paul Newman. “RSS-Net: Weakley-Supervised Multi-Class Semantic Segmentation with FMCW Radar”. IEEE Intelligent Vehicles Symposium (IV) 2020.
  • “HumBug Zooniverse: a crowd-sourced acoustic mosquito dataset”.I Kiskin, AD Cobb, L Wang, S Roberts, 2019 NeurIPS Machine Learning for the Developing World workshop, 2020 International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2019–2020 (Kiskin et al., 2019, 2020). 
  • Yuki M, Asano,Christian Rupprecht and Andrea Vedaldi. “Self-labelling via Simultaneous Clustering and Representation Learning”. Proc. (ICLR 2020).
  • Yuki M. Asano, Christian Rupprecht and Andrea Vedaldi. “A Critical Analysis of Self-Supervision, or What We can Learn from a Single Image”. (ICLR 2020).
  • Blaas, L Laurenti, A Patane, L Cardelli, M Kwiatkowska and S Roberts.“Adversarial Robustness Guarantees for Classification with Gaussian Processes”. (AIStats 2020).
  • Siddhant GangapurwalaAlexander Mitchelland Ioannis Havoutis. “Guided Constrained Policy Optimization for Dynamic Quadrupedal Robot Locomotion”. RA-L.
  • Shuyu Lin, Ronald Clark, Robert Birke, Sandro Schonborn, Niki Trigoni and Stephen Roberts. “Anomaly Detection for Time Series Using VAE-LSTM Hybrid Model”. (ICASSP 2020).
  • Moseley, B., Bickel, V., Burelbach, J., & Relatores, N. (2020). “Unsupervised learning for thermophysical analysis on the lunar surfac”e. The Planetary Science Journal, 1(2), 32.
  • Yijing Liu*, Shuyu Lin* and Ronals Clark* (*equal contribution). “Towards Consistent Cariational Auto-Encoding”. (AAAI 2020).
  • Rhydian Windsor and Amir Jamaludin. “The Ladder Algorithm: Finding Repetitive Structures in Medical Images by Induction”. (ISBI 2020).
  • L Cardelli, M Kwiatkowska, L Laurenti, N Paoletti, A Pataneand M Wicker. “Statistical Guarantees for the Robustness of Bayesian Neural Networks”. (IJCAI 2019).
  • “Super-resolution of Time-series Labels for Bootstrapped Event Detection”I Kiskin, U Meepegama, S Roberts, 2019 ICML Time-series workshop, 2019 (Kiskin et al., 2019).
  • Fong*, M. Patrick* and A. Vedaldi (*denotes equal contributions). “Understanding Deep Networks via Extremal Perturbations and Smooth Masks”.(ICCV 2019).
  • D Columbo, J Fernandez-Alvarez,A Patane, M Semonella, M Kwiatkowska, A Garcia-Palacios, P Cipresso, G Riva and C Botella. “Current State and Future Directions of Technology-Based Ecological Momentary Assessment and Intervention for Major Depressive Disorder: A Systematic Review”. Journal of Clinical Medicine 2019.
  • Tim G.J. Rudner, Florian Wenze and Yarin Gal.  “The Natural Neural Tangent Kernel: Neural Network: Training Dynamics under Natural Gradient Descent”. NeurIPS Workshop on Bayesian Deep Learning, 2019. (Contributed talk, top 6% of submissions).
  • Tim G.J. Rudner, Waseem Aslam, Oscar Key, Tom Rainforth and Yairn Gal. “Tighter Variational Bounds for Deep Gaussian Processes”.NeurIPS Workshop on Bayesian Deep Learning, 2019.
  • Angelos Filos, Sebastian Farquhar, Aidan N. Gomez, Tim G.J. Rudner, Zachary Kenton, Lewis Smith, Milad Alizadeh, Arnoud de Kroom and Yarin Gal. “A Systematic Comparision of Bayesian Deep Learning Robustness in Diabetic Retinopathy Tasks”. NeurIPS Workshop on Bayesian Learning, 2019.
  • Adam Golinski*, Frank Wood, Tom Rainforth*. “Amortized Monte Carlo Integration”.(ICML 2019).
  • Ben Moseley, Valentin Bickel, Jerome Burelbach, Nicole Relatores, Daniel Angerhausen, Frank Soboczenski and Dennis Wingo. “Unsupervised Learning for Thermal Detection on the Lunar Surface”. (NeurIPS 2019).
  • Andreas Kirsch,Joost van Amersfoort and Yarin Gal. “BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning”. (NeurIPS 2019).
  • Farquhar, G., Gustafson, L., Lin, Z., Whiteson, S., Usunier, N., Synnaeve, G. (2019). “Growing Action Spaces”. Under review, preprint available.
  • Gregory Farquhar,Shimon Whiteson and Jakob Foerster. “Loaded DiCE: Trading off Bias and Variance in Any-Order Score Function Gradient Estimators for Reinforcement Learning”. (NeurIPS 2019).
  • Christian Schroeder de Witt, Jakob Foerster, Gregory Farquhar, Philip Torr, Wendelin Boehmer and Shimon Whiteson. “Multi-Agent Common Knowledge Reinforcement Learning”.  (NeurIPS 2019).
  • Maximilian Igl, Kamil Ciosek, Yingzhen Li, Sebastian Tschiatschek, Cheng Zhang, Sam Devlin and Katja Hofmann. “Generalization in Reinforcement Learning with Selective Noise Injection and Information Bottleneck”. (NeurIPS 2019).
  • Matthew Fellows, Anuj Mahajan, Tim G. J. Rudner,Shimon Whiteson. “VIREL: A Variational Inference Framework for Reinforcement Learning”. (NeurIPS 2019). (Spotlight Talk, top 3% of submitted papers).
  • Atılım Güneş Baydin, Lukas Heinrich, Wahid Bhimji, Lei Shao, Saeid Naderiparizi, Andreas Munk, Jialin Liu, Bradley Gram-Hansen, Gilles Louppe, Lawrence Meadows, Philip Torr, Victor Lee, Prabhat, Kyle Cranmer, Frank Wood. “Efficient Probabilistic Inference in the Quest for Physics Beyond the Standard Model”. (NeurIps2019).
  • Supratik Paul, Vitaly Kurin, Shimon Whiteson. “Fast Efficient Hyperparameter Tuning for Policy Gradients”.  (NeurIps2019).
  • Luketina, J., Nardelli, N., Farquhar, G., Foerster, J., Andreas, J., Grefenstette, E., & Rocktäschel, T. (2019). “A Survey of Reinforcement Learning Informed by Natural Language”. (IJCAI 2019).
  • Ji, J.F. Henriques and A. Vedaldi, "Invariant Information Clustering for Unsupervised Image Classification and Segmentation"
  • I. Parisi, X. Ji, S. Wermter, "On the role of neurogenesis in overcoming catastrophic forgetting"
  • Afouras, J. Chung, A. Senior, O. Vinyals and A. Zisserman, "Deep Audio-visual Speech Recognition". IEEE Transactions on Pattern Analysis and Machine Intelligence.
  • Triantafyllos Afouras, Joon Son Chung and Andrew Zisserman. “My lips are concealed: Audio-visual speech enhancement through obstructions”. (INTERSPEECH 2019).
  • Luca Cardelli, Marta Kwiatkowska, Luca Laurenti, Nicola Paoletti, Andrea Patane, and Matthew Wicker. “Statistical Guarantees for the Robustness of Bayesian Neural Networks”. In Proc. International Joint Conference on Artificial Intelligence (IJCAI 2019).
  • Adam D. Cobb, Michael D. Himes, Frank Soboczenski, Simone Zorzan, Molly D. O’Beirne, Atilim Gunes Baydin, Yarin Gal, Shawn D. Domagal-Goldman, Giada N. Arney, Daniel Angerhausen and 2018 NASA FDL Astrobiology Team II. “An Ensemble of Abyesian Neural Networks for Exoplanetary Atmospheric Retrieval”. The Astronomical Journal.
  • Neverova, J. Thewlis, R. A. Güler, I. Kokkinos, A. Vedaldi. Slim DensePose: “Thrifty Learning from Sparse Annotations and Motion Cues”. (CVPR 2019 - Oral presentation)
  • Rob Cornish, Paul Vanetti, Alexandre Bouchard-Côté, George Deligiannidis, Arnaud Doucet. “Scalable Metropolis-Hastings for Exact Bayesian Inference with Large Datasets”. (ICML 2019).
  • Rob Cornish, George Deligiannidis, Arnaud Doucet. Robust “Out-of-Sample Uncertainty for Neural Networks via Confidence Densities”. ICML workshop on Uncertainty and Robustness in Deep Learning 2019.
  • Shuyu Lin, Bo Yang, Robert Birke and Ronald Clarke. “Learning Semantically Meaningful Embeddings Using Linear Constraints”. Accepted by Explainable AI Workshop at (CVPR 2019).
  • Shuyu Lin, Ronald Clark, Robert Birke, Niki Trigoni and Stephen Roberts. “WiSE-ALE: Wide Sample Estimator for Aggregate Latent Embedding”. Accepted by Deep Generative Models for Highly Structured Data Workshop. (ICLR 2019).
  • Edward Wagstaff, Fabian. B. Fuchs, Martin Engelcke, Ingmar Posner and Michael Osborne. “On the Limitations of Representing Functions on Sets”. (ICML 2019).
  • Mikayel Samvelyan, Tabish Rashid, Christian Schroeder de Witt, Gregory Farquhar, Nantas Nardelli, Tim G. J. RudnerChia-Man Hung, Philip H. S. Torr, Jakob Foerster, Shimon Whiteson. “The StarCraft Multi-Agent Challenge” (Extended Abstract). International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2019.
  • K. M. Judd, J. D. Gammell. “SE(3) multimotion estimation through occlusion.” in Proceedings of the long-term human motion prediction” (LHMP) workshop, IEEE international conference on robotics and automation (ICRA 2019).
  • Patané, A., Jansen, G., Conca, P., Carapezza, G., Costanza, J., & Nicosia, G. (2019). “Multi-objective optimization of genome-scale metabolic models: the case of ethanol production”. Annuals of Operations Research276(1), 211-227.
  • Laurenti, L., Patane, A., Wicker, M., Bortolussi, L., Cardelli, L., & Kwiatkowska, M. (2019). Global Adversarial Robustness Guarantees for Neural Networks.
  • K. Judd, J. D. Gammell. “The Oxford Multimotion Dataset: Multiple SE(3) motions with ground truth.” IEEE Robotics and Automation Letters (RA-L), 4(2):800–807, Apr. 2019. (ICRA 2019).
  • Luisa M Zintgraf, Kyriacos Shiarlis, Vitaly Kurin, Katja Hofmann and Shimon Whiteson. “Fast Context Adaption via Meta-Learning”. (ICML 2019).
  • Rashid, T., Samvelyan, M., Witt, C.S., Farquhar, , Foerster, J.N., & Whiteson, S. (2018). “QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning”. (ICML 2018).
  • Colombo, D., Palacios, A. G., Alvarez, J. F., Patané, A., Semonella, M., Cipresso, P., ... & Botella, C. (2018). “Current state and future directions of technology-based ecological momentary assessments and interventions for major depressive disorder: protocol for a systematic review.”Systematic reviews, 7(1), 1-7.
  • Patanè, A., Santoro, A., Romano, V., La Magna, A., & Nicosia, G. (2018). “Enhancing quantum efficiency of thin-film silicon solar cells by Pareto opti
  • mality”.Journal of Global Optimization, 72(3), 491-515.
  • Leonard Berrada, Andrew Zisserman and M Pawan Kumar. “Deep Frank-Wolfe for Neural Network Optimization”. (ICLR 2019).
  • Tim G. J. Rudner, Marc Rußwurm, Jakub Fil, Ramona Pelich, Benjamin Bischke, Veronika Kopackova, Piotr Bilinski. “Multi³Net: Segmenting Flooded Buildings via Fusion of Multiresolution, Multisensor, and Multitemporal Satellite Imagery”. (AAAI Conference on Artificial Intelligence, 2019).
  • Webb, Stefan, Rainforth, Tom, Teh, Yee Whye, and Pawan Kumar, M. “A Statistical Approach to Assesing Neural Network Robustness”. Proceedings of the Seventh International Conference on Learning Representations (ICLR2019), New Orleans.
  • “Semi-separable Hamiltonian Monte Carlo for inference in Bayesian neural networks” A D Cobb, A G Baydin, I Kiskin, A Markham, S J Roberts, 2019 NeurIPS Bayesian Deep Learning Workshop, 2019 (Cobb et al., 2019).
  • Gram-Hansen, P. Helber, I. Varatharajan, F. Azam, A. Coca-Castro, V. Kopackova and P. Bilinski, “Mapping Informal Settlements in Developing Countries using Machine Learning and Low-Resolution Multi-spectral Data” .The AAAI/ACM International Conference on AI Ethics and Society, 2019.
  • Gram-Hansen, Y, Zhou, T. Kohn, T. Rainforth, H. Yang and F. Wood. A Low-Level Probabilistic Programming Language for Non-Differentiable Models. (AISTATS 2019).
  • Gram-Hansen, Y, Zhou, T. Kohn, H. Yang and F. Wood. “Hamiltonian Monte Carlo for Probabilistic Programs with Discontinuities”. The International Conference on Probabilistic Programming 2018.
  • Foerster, J.N., Farquhar, G., Al-Shedivat, M., Rocktäschel, T., Xing, E.P., & Whiteson, S. (2018). “DiCE: The Infinitely Differentiable Monte-Carlo Estimator”. (ICML 2018).
  • “Fast Mosqutio Acoustic Detection With Field Cup Recordings: An Initial Investigation” Y Li, I Kiskin, M Sinka, D Zilli, H Chan, E HerrerosM oya, T Chareonviriyaphap, R Tisgratog, K Willis, S Roberts, Detection and Classification of Acoustic Scenes and Events 2018 (DCASE) 2018 Workshop, (Li et al., 2018).
  • Gram-Hansen, P. Helber, I. Varatharajan, F. Azam, A. Coca-Castro, V. Kopackova and P. Bilinski. “Generating Material Maps to Map Informal Settlements Machine Learning for the Developing World”. Workshop at the 32nd Conference for Neural Information Processing Systems 2018.
  • Baydin, L. Heinrich, W. Bhimji, B. Gram-Hansen, G. Louppe, L. Shao, K, Cranmer and F.Wood, “Efficient Probabilistic Inference in the Quest for Physics Beyond the Standard Model”.  arXiv preprint arXiv: 1807.07706, 2018.
  • Tim G. J. Rudner, Vincent Fortuin, Yee Whye Teh, Yarin Gal. “On the Connection between Neural Processes and Gaussian Processes with Deep Kernels”. NeurIPS Workshop on Bayesian Deep Learning, 2018.
  • Tim G. J. Rudner, Marc Rußwurm, Jakub Fil, Ramona Pelich, Benjamin Bischke, Veronika Kopackova, Piotr Bilinski. “Rapid Computer Vision-Aided Disaster Response via Fusion of Multiresolution, Multisensor, and Multitemporal Satellite Imagery”. NeurIPS Workshop on AI for Social Good, 2018.
  • Maximilian Igl, Wendelin Boehmer, Andrew Gambardella, Nantas Nardelli, Siddharth Narayanaswamy and Shimon Whiteson. “Bayesian hierarchical multitask learning”. NeurIPS workshop 2018.
  • Oliver E Bent, Sekou L Remy, Nelson K Bore. “A machine learning environment to determine novel malaria policies”. NeurIPS Demonstration, 2018.
  • Kevin M. Judd, Jonathan D. Gammell and Paul Newman. “Multimotion Visual Odometry (MVO): Simultaneous Estimation of Camera and Third-Party Motions”. (IROS 2018).
  • Kyriacos Shiarlis, Markus Wulfmeier, Sasha Salter, Shimon Whiteson, Ingmar Posner. “TACO: Learning Task Decomposition via Temporal Alignment for Control”.
  • Fabian B. Fuchs, Oliver Groth, Adam R. Kosiorek, Alex Bewley, Markus Wulfmeier, Andrea Vedaldi, Ingmar Posner. “Neural Stethoscopes: Unifying Analytic, Auxiliary and Adversarial Network Probing”.
  • Jack Hunt, Victor A. Prisacariu, Stuart Golodetz, Tommaso Cavallari, Nicholas A. Lord and Philip H. S. Torr. “Probabilistic Object Reconstruction with Online Global Model Correction”. Proceedings of the 5th International Conference on 3D Vision. 3DV 2017.
  • A Patane, S Ghiasi, E P Scilingo, M Kwiatkowska. Automated Recognition of Sleep Arousal using Multimodal and Personalized Deep Ensembles of Neural Networks. Computing in Cardiology 2018.
  • A Patane, M Kwiatkowska. Calibrating the Classifier: Siamese Neural Network Architecture for End-to-End Arousal Recognition from ECG. The Fourth International Conference on Machine Learning, Optimization, and Data Science. 2018.
  • L Cardelli, M Kwiatkowska, L Laurenti, A Patane. “Robustness Guarantees for Bayesian Inference with Gaussian Processes”. (2019, July). Robustness guarantees for bayesian inference with gaussian processes. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 33, No. 01, pp. 7759-7768).
  • Ankush Gupta, Andrea Vedaldi, Andrew Zisserman. Learning to Read by Spelling: Towards Unsupervised Text Recognition.
  • Aravindh Mahendran, James Thewlis, Andrea Vedaldi. “Self-Supervised Segmentation by Grouping Optical-Flow”. POCV Workshop on Action, Perception and Organization, ECCV 2018 Workshops.
  • Patane, A., Ghiasi, S., Scilingo, E. P., & Kwiatkowska, M. (2018, September). !Automated recognition of sleep arousal using multimodal and personalized deep ensembles of neural networks”. In 2018 Computing in Cardiology Conference (CinC) (Vol. 45, pp. 1-4). IEEE.
  • Xu Ji, Joao F. Henriques and Andrea Vedaldi. “Invariant Information Distillation for Unsupervised Image Segmentation and Clustering”.
  • Aravindh Mahendran, James Thewlis, Andrea Vedaldi. “Cross Pixel Optical Flow Similarity for Self-Supervised Learning”. (ACCV 2018).
  • Stefan Webb, Adam Golinski, Robert Zinkov, N. Siddharth, Tom Rainforth, Yee Whye Teh and Frank Wood. “Faithful Inversion of Generative Models for Effective Amortized Inference”. (NIPS2018).
  • James Thewlis, Hakan Bilen and Andea Vedaldi. “Modelling and unsupervised of symmetric deformable object categories”. (NIPS2018).
  • Tomas Jakab*, Ankush Gupta*, Hakan Bilen, Andrea Vedaldi. Conditional Image Generation for Learning the Structure of Visual. NIPS2018 (* indicates equal contribution).
  • Tom Rainforth, Adam R. Kosiorek, Tuan Anh Le, Chris J Maddision, Maximilian Igl, Frank Wood and Yee Whye Teh. “Tighter variational bounds are not necessarily better”. International Conference on Machine Learning. (ICML 2018).
  • M. Igl, L. Zintgraf, TA. Le, F. Wood and S. Whiteson. “Deep variational reinforcement learning for POMDP”. (ICML 2018).
  • Benjamin Moseley, Andrew Markham, Tarje Nissen-Meyer. “Fast approximate simulation of seismic waves with deep learning”.
  • Oliver Groth, Fabian B. Fuchs, Ingmar Posner, Andrea Vedaldi. “ShapeStacks: Learning Vision-Based Physical Intuition for Generalised Object Stacking”. (ECCV 2018).
  • Ivan Kiskin, Davide Zilli, Yunpeng Li, Marianne Sinka, Kathy Willis, Stephen Roberts. “Bioacoustic detection with wavelet-conditioned convolutional neural networks”. Springer Neural Computing & Applications Special Issue in Deep learning for Music and Audio, 2018 (Kiskin et al., 2018). 
  • Golinski, Adam, Teh, Yee Whye, Wood Frank and Rainforth, Tom. “Amortized Monte Carlo Integration”. UAI 2018 Workshop on Uncertainty in Deep Learning.
  • Gupta, Ankush, Vedaldi, Andrea and Zisserman, Andrew. “Inductive Visual Localisation: Factorised Training for Superior Generalisation”. Proceedings of the British Machine Vision Conference (BMVC 2018).
  • Smith, Lewis and Gal, Yarin. “Understanding Measures of Uncertainty for Adversarial Example Detection”. (UAI 2018).
  • Ghoshal, S. and Roberts, S. “Thresholded ConvNet Ensembles: Neural Networks for Technical Forecasting”. Data Science in Fintech, KDD 2018.
  • Tim G. J. Rudner and Dino Sejdinovic. “Inter-domain Deep Gaussian Processes. Bayesian Deep Learning”. NIPS Workshop, 2017.
  • Rainforth, T., Cornish, R., Yang, H., Warrington, A., & Wood, F. “On Nesting Monte Carlo Estimators”. International Conference on Machine Learning. (ICML 2018).
  • Novotny*, S. Albanie*, D. Larlus, A. Vedaldi. Semi-convolutional operators for instance segmentation, ECCV 2018.
  • Nagrani*, S. Albanie*, and A. Zisserman. “Learnable PINs: Cross-Modal Embeddings for Person Identity”.  (ECCV 2018).
  • Berrada, L, A. Zisserman, M. P. Kumar. “Smooth Loss Functions for Deep Top-k Classification”. International Conference on Learning Representations, 2018.
  • T. Afouras, J. S. Chung, A. Zisserman. “The Conversation: Deep Audio-Visual Speech Enhancement”. (INTERSPEECH 2018)
  • T. Afouras, J. S. Chung, A. Zisserman. “Deep Lip Reading: a comparison of models and an online application”. (INTERSPEECH 2018).
  • Adam D. Cobb, Stephen J. Roberts, Yarin Gal. “Loss-Calibrated Approximate Inference in Bayesian Neural Networks”.
  • Stefano Rosa, Andrea Patanè, Xiaoxuan Lu, and Niki Trigoni. “CommonSense: Collaborative learning of scene semantics by robots and humans”. In Proceedings of the 1st International Workshop on Internet of People, Assistive Robots and ThingS (pp. 1-6). ACM. 2018, June.
  • S Rosa, A Patane, C X Lu and N Trigoni. “Semantic Place Understanding for Human-Robot Coexistence-Toward Intelligent Workplaces”. IEEE Transactions on Human-Machine Systems 2018.
  • Simon Eberz, Giulio Lovisotto, Andrea Patané, Marta Kwiatkowska, Vincent Lenders, and Ivan Martinovic. “When Your Fitness Tracker Betrays You: Quantifying the Predictability of Biometric Features Across Contexts”. IEEE Symposium on Security and Privacy (S&P), San Francisco, CA, USA, May 2018.
  • Adam D. Cobb, Richard Everett, Andrew Markham, Stephen J. Roberts. (2018). “Identifying Sources and Sinks in the Presence of Multiple Gaents with Gaussian Process Vector Calculus”.
  • Baydin, A. G.,Cornish, R., Martínez Rubio, D., Schmidt, M., & Wood, F. (2017). “Online Learning Rate Adaptation with Hypergradient Descent”. In Sixth International Conference on Learning Representations (ICLR), Vancouver, Canada, April 30 – May 3, 2018.
  • Cornish, R., Wood, F., & Yang, H. (2017). “Towards a testable notion of generalisation for generative adversarial networks”. In NIPS Workshop on Deep Learning: Bridging Theory and Practice.
  • Albanie, H. Shakespeareand T. Gunter. “Unknowable Manipulators: Social Network Curator Algorithms”. (NIPS 2016 Symposium: Machine Learning and the Law).
  • Nagrani,  Albanie, A. Zisserman. “Seeing Voices and Hearing Faces: Cross-modal biometric matching”. CVPR, 2018. (* denotes equal contribution)
  • Novotny*,  Albanie*, D. Larlus, A  Vedaldi. “Self-supervised Learning of Geometrically Stable Features Through Probabilistic Introspection”. CVPR, 2018. (* denotes equal contribution).
  • Le, Tuan Anh, Igl, Maximilian, Jin, Tom, Rainforth, Tom, Wood, Frank. “Auto-encoding sequential Monte Carlo”. (ICLR 2018).
  •  Border, R. D. Gammell, and P. Newman. “Surface Edge Explorer (SEE): Planning Next Best Views Directly from 3D Observations”. (ICRA 2018).
  • Farquhar, G., Rocktäschel, T., Igl, M., & Whiteson, S. “TreeQN and ATreeC: Differentiable Tree Planning for Deep Reinforcement Learning”. (ICLR 2018).
  • Foerster, J., Farquhar, G., Afouras, T., Nardelli, N., & Whiteson, S. “Counterfactual multi-agent policy gradients”. 32nd AAAI Conference on Artificial Intelligence (AAAI’18).
  • Stefan Webb, Adam Golinski, Robert Zinkov, N. Siddharth, Tom Rainforth, Yee Whye Teh and Frank Wood. “Faithful Model Inversion Substantially Improves Auto-encoding Variational Inference”. NIPS2017 Workshop in Bayesian Deep Learning.
  • Stefan Webb and Yee Whye Teh. “A Tighter Monte Carlo Objective with Renyi divergence Measures”. NIPS 2016 Workshop in Bayesian Deep Learning.
  • N Paoletti,  Patane, M Kwiatkowska. “Closed-loop quantitative verification of rate-adaptive pacemakers”. ACM Transactions on Cyber-Physical Systems, to appear, 2018.
  • Zand, Jaleh& Roberts, S. “MiDGaP: Mixture Density Gaussian Processes”. NIPS time series workshop 2017.
  • Thewlis and H. Bilen and A. Vedaldi. “Unsupervised learning of object landmarks by factorized spatial embeddings”. Proceedings of the International Conference on Computer Vision. ICCV 2017.
  • “Mosquito Detection with Neural Networks: The Buzz of Deep Learning”. I Kiskin, B.P. Orozco, T. Windebank, D. Zilli, M. Sinka, K. Willis, S Roberts, arXiv pre-print, submitted to ECML 2017, 2017 (Kiskin et al., 2017).
  • “Mosquito detection with low-cost smartphones: Data acquisition for malaria research”. Y Li, D Zilli, H Chan, I Kiskin, M Sinka, S Roberts, K Willis,NeurIPS 2017 Workshop on Machine Learning for the Developing World, 2017 (Li et al., 2017b).
  • “Cost-sensitive detection with variational autoencoders for environmental acoustic sensing”. Y Li, I Kiskin, D Zilli, M Sinka, H Chan, K Willis, S Roberts, NeurIPS 2017 Workshop on Machine Learning for Audio Signal Processing, 2017 (Li et al., 2017a).
  • Thewlis and H. Bilen and A. Vedaldi. “Unsupervised object learning from dense invariant image labelling”. Proceedings of Advances in Neural Information Processing Systems. NIPS 2017 (oral presentation).
  • Jakob Foerster, Nantas Nardelli, Gregory Farquhar, Triantafyllos Afouras, Philip H.S. Torr. Pushmeet Kohli, Shimon Whiteson. “Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learning”. (ICML 2017).
  • Cobb, A, Markham, A and Roberts, S. “Learning from lions: inferring the utility of agents from their trajectories”.
  • Ghoshal, S and Roberts, S. “Reading the Tea Leaves: A Neural Network Perspective on Technical Trading. Knowledge Discovery and Data Mining”. (KDD 2017).
  • Gram-Hansen and S.J Roberts. “Multi-layer Stacked Gaussian Processes”. preprint: http://www.robots.ox.ac.uk/~bradley/papers/mp1.pdf , 2017
  • Berrada, Leo. “Trusting SVM for Piecewise Linear CNNs”. ICLR 2017 (International Conference on Learning Representations).
  • Bartlett, O, C. Gurau, L. Marchegiani, and I. Posner. “Enabling Intelligent Energy Management for Robots using Publicly Available Maps”. Iin IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Daejeon, South Korea, 2016.
  • James Thewlis, Shuai Zheng, Philip H. S. Torr, Andrea Vedaldi. “Fully-Trainable Deep Matching”. British Machine Vision Conference (BMVC 2016).
  • Sam Albanieand Andrea Vedaldi. “Learning Grimaces by Watching TV”. (BMVC 2016).
  • Leonard Hasenclever, Stefan Webb, Thibaut Lienart, Sebastian Vollmer, Balaji Lakshminarayanan, Charles Blundell, Yee Whye Teh. “Distributed Bayesian Learning with Stochastic Natural-gradient Expectation Propagation and the Posterior Server”. Journal of Machine Learning Research 18 (2017) 1-37.
  • Ghoshal, Sid and S. Roberts. “Extracting Predictive Information from Heterogeneous Data Streams using Gaussian Processes”. Algorithmic Finance, vol. 5, no. 1-2, pp. 21-30, 2016.
  • Gupta, Ankush and Vedaldi, Andrea and Zisserman, Andrew. “Synthetic Data for Text Localisation in Natural Images”. The IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016).