[ { "authors": "Daniel Lenton, Fabio Pardo, Fabian Falck, Stephen James, Ronald Clark", "title": "Ivy: Templated Deep Learning for Inter-Framework Portability", "venue": "arXiv Preprint", "year": "2021", "image": "images/616c2c6926aac6ce40e4d666_lenton2021ivy.gif", "pdf": "http://arxiv.org/abs/2102.02886" }, { "authors": "Daniel James Lenton, Stephen James, Ronald Clark, Andrew Davison", "title": "End-to-End Egospheric Spatial Memory", "venue": "International Conference on Learning Representations (ICLR)", "year": "2021", "image": "images/616c2c448882f2716202ffb8_lenton2021endtoend.gif", "pdf": "http://arxiv.org/abs/2102.07764" }, { "authors": "Martin Piala, Ronald Clark", "title": "TermiNeRF: Ray Termination Prediction for Efficient Neural Rendering", "venue": "International conference on 3D vision (3DV)", "year": "2021", "image": "images/616c2c35f10393afd4bb9cad_piala2021terminet.gif", "pdf": "https://arxiv.org/abs/2111.03643" }, { "authors": "Michal Pándy, Daniel Lenton, Ronald Clark", "title": "Unsupervised Path Regression Networks", "venue": "IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)", "year": "2021", "image": "images/616c2c4c445d1c4d34a0547d_pandy2020learning.gif", "pdf": "http://arxiv.org/abs/2011.14787" }, { "authors": "Alexandru-Iosif Toma, Hussein Jaafar, Hao-Ya Hsueh, Stephen James, Daniel Lenton, Ronald Clark, Sajad Saeedi", "title": "Waypoint Planning Networks", "venue": "Conference on Robots and Vision (CRV)", "year": "2021", "image": "images/616c2c5a947a5d5452200810_Alexandru2021waypoint.gif", "pdf": "http://arxiv.org/abs/2105.00312" }, { "authors": "Jan Czarnowski, Tristan Laidlow, Ronald Clark, Andrew J Davison", "title": "Deepfactors: Real-time probabilistic dense monocular slam", "venue": "IEEE Robotics and Automation Letters (RAL)", "year": "2020", "image": "images/616c08035735f863649fdffe_czarnowski2020deepfactors.gif", "pdf": "http://arxiv.org/abs/2001.05049" }, { "authors": "Tristan Laidlow, Jan Czarnowski, Andrea Nicastro, Ronald Clark, Stefan Leutenegger", "title": "Towards the Probabilistic Fusion of Learned Priors into Standard Pipelines for 3D Reconstruction", "venue": "IEEE International Conference on Robotics and Automation (ICRA)", "year": "2020", "image": "images/616c08480c6cdf13054ac066_laidlow2020towards.gif", "pdf": "" }, { "authors": "Eduardo DC Carvalho, Ronald Clark, Andrea Nicastro, Paul HJ Kelly", "title": "Scalable uncertainty for computer vision with functional variational inference", "venue": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR'20)", "year": "2020", "image": "images/616c2d40809a232f87eae8ce_carvalho2020scalable.gif", "pdf": "http://arxiv.org/abs/2003.03396" }, { "authors": "Shuyu Lin, Ronald Clark, Robert Birke, Sandro Schonborn, Niki Trigoni, Stephen Roberts", "title": "Anomaly Detection for Time Series Using VAE-LSTM Hybrid Model", "venue": "IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)", "year": "2020", "image": "images/616c2d927138d4d9b2d2d404_lin2020anomaly.gif", "pdf": "" }, { "authors": "Shuyu Lin, Ronald Clark", "title": "LaDDer: Latent Data Distribution Modelling with a Generative Prior", "venue": "British Machine Vision Conference (BMVC)", "year": "2020", "image": "images/616c2db3c8aeb7762ce0c624_lin2020ladder.gif", "pdf": "http://arxiv.org/abs/2009.00088" }, { "authors": "Martin Fisch, Ronald Clark", "title": "Orientation Keypoints for 6D Human Pose Estimation", "venue": "IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)", "year": "2021", "image": "images/616c2e141ed46880bcdbcbe4_fisch2020.png", "pdf": "http://arxiv.org/abs/2009.04930" }, { "authors": "Andrea Nicastro, Ronald Clark, Stefan Leutenegger", "title": "X-section: Cross-section prediction for enhanced RGB-D fusion", "venue": "IEEE/CVF International Conference on Computer Vision (CVPR)", "year": "2019", "image": "images/616c2e6d37a2ff41fd2f0608_nicastro2019x.gif", "pdf": "http://arxiv.org/abs/1903.009870" }, { "authors": "Shuyu Lin, Bo Yang, Robert Birke, Ronald Clark", "title": "Learning Semantically Meaningful Embeddings Using Linear Constraints", "venue": "IEEE/CVF International Conference on Computer Vision Workshops (CVPR-W)", "year": "2019", "image": "images/616c2f0642a4bc5c2a04684a_lin2019learning.gif", "pdf": "https://openaccess.thecvf.com/content_CVPRW_2019/papers/Explainable%20AI/Lin_Learning_Semantically_Meaningful_Embeddings_Using_Linear_Constraints_CVPRW_2019_paper.pdf" }, { "authors": "Michael Bloesch, Tristan Laidlow, Ronald Clark, Stefan Leutenegger, Andrew J Davison", "title": "Learning meshes for dense visual SLAM", "venue": "IEEE/CVF International Conference on Computer Vision (ICCV)", "year": "2019", "image": "images/616c2f325ecc23483ed0b831_bloesch2019learning.gif", "pdf": "https://www.imperial.ac.uk/media/imperial-college/research-centres-and-groups/dyson-robotics-lab/mbloesch_etal_iccv2019.pdf" }, { "authors": "Shuyu Lin, Stephen Roberts, Niki Trigoni, Ronald Clark", "title": "Balancing reconstruction quality and regularisation in elbo for VAEs", "venue": "arXiv preprint", "year": "2019", "image": "images/616c2f5bc8aeb70a7ee0cc25_lin2019balancing.gif", "pdf": "http://arxiv.org/abs/1909.03765" }, { "authors": "Shuyu Lin, Ronald Clark, Robert Birke, Niki Trigoni, Stephen Roberts", "title": "WiSE-ALE: Wide Sample Estimator for Aggregate Latent Embedding", "venue": "International Conference on Learning Representations Workshops (ICLR-W)", "year": "2019", "image": "images/616c2e8f0666a57fbfa95e8b_lin2019wise.gif", "pdf": "http://arxiv.org/abs/1902.06160" }, { "authors": "Bo Yang, Jianan Wang, Ronald Clark, Qingyong Hu, Sen Wang, Andrew Markham, Niki Trigoni", "title": "Learning object bounding boxes for 3d instance segmentation on point clouds", "venue": "Neural Information Processing (NeurIPS)", "year": "2019", "image": "images/616c2eb7e2252ba115fc445e_yang2019learning.gif", "pdf": "http://arxiv.org/abs/1906.01140" }, { "authors": "Michael Bloesch, Jan Czarnowski, Ronald Clark, Stefan Leutenegger, Andrew J Davison", "title": "CodeSLAM-Learning a Compact, Optimisable Representation for Dense Visual SLAM", "venue": "IEEE Conference on Computer Vision and Pattern Recognition (CVPR)", "year": "2018", "image": "images/616c2f8a5f32e8f6b9e21db7_bloesch2018codeslam.gif", "pdf": "http://arxiv.org/abs/1804.00874" }, { "authors": "Wenbin Li, Sajad Saeedi, John McCormac, Ronald Clark, Dimon Tzoumanikas, Qing Ye, Yuzhong Huang, Rui Tang, Stefan Leutenegger", "title": "InteriorNet: Mega-scale multi-sensor photo-realistic indoor scenes dataset", "venue": "British Machine Vision Conference (BMVC)", "year": "2018", "image": "images/616c2fcd3773e600eb5bd8f1_li2018interiornet.gif", "pdf": "http://arxiv.org/abs/1809.00716" }, { "authors": "John McCormac, Ronald Clark, Michael Bloesch, Andrew Davison, Stefan Leutenegger", "title": "Fusion++: Volumetric object-level slam", "venue": "International conference on 3D vision (3DV)", "year": "2018", "image": "images/fusionpp.gif", "pdf": "http://arxiv.org/abs/1808.08378" }, { "authors": "Ronald Clark, Michael Bloesch, Jan Czarnowski, Stefan Leutenegger, Andrew J Davison", "title": "Learning to Solve Nonlinear Least Squares for Monocular Stereo", "venue": "European Conference on Computer Vision (ECCV)", "year": "2018", "image": "images/616c30405ecc23099fd0bc0d_clark2018learning.gif", "pdf": "http://arxiv.org/abs/1809.02966" }, { "authors": "Sen Wang, Ronald Clark, Hongkai Wen, Niki Trigoni", "title": "End-to-end, sequence-to-sequence probabilistic visual odometry through deep neural networks", "venue": "International Journal of Robotics Research (IJRR)", "year": "2018", "image": "images/616c306922a4faf837a58cb4_wang2018end.gif", "pdf": "" }, { "authors": "Hongkai Wen, Ronald Clark, Sen Wang, Xiaoxuan Lu, Bowen Du, Wen Hu, Niki Trigoni", "title": "Efficient indoor positioning with visual experiences via lifelong learning", "venue": "IEEE Transactions on Mobile Computing (TMC)", "year": "2018", "image": "images/616c309d42a4bc2271046fc3_wen2018efficient.gif", "pdf": "" }, { "authors": "Bo Yang, Hongkai Wen, Sen Wang, Ronald Clark, Andrew Markham, Niki Trigoni", "title": "3D object reconstruction from a single depth view with adversarial learning", "venue": "arXiv preprint", "year": "2017", "image": "images/616c30ad809a235abceafae7_yang20173d.gif", "pdf": "http://arxiv.org/abs/1708.07969" }, { "authors": "Ronald Clark, John McCormac, Stefan Leutenegger, Andrew Davison", "title": "Meta-learning for instance-level data association", "venue": "Proceedings of Neural Information Processing Systems Workshops (NeurIPS-W)", "year": "2017", "image": "images/616c31205ecc235f4bd0c2ee_clark2017meta.gif", "pdf": "http://metalearning.ml/2017/papers/metalearn17_clark.pdf" }, { "authors": "Sen Wang, Ronald Clark, Hongkai Wen, Niki Trigoni", "title": "DeepVO: Towards end-to-end visual odometry with deep recurrent convolutional neural networks", "venue": "IEEE International Conference on Robotics and Automation (ICRA)", "year": "2017", "image": "images/616c3163e5b1694ffd5e13f4_wang2017deepvo.gif", "pdf": "http://arxiv.org/abs/1709.08429" }, { "authors": "Ronald Clark, Sen Wang, Hongkai Wen, Andrew Markham, Niki Trigoni", "title": "VINet: Visual-Inertial Odometry as a Sequence-to-Sequence Learning Problem", "venue": "AAAI Conference on Artificial Intelligence", "year": "2017", "image": "images/616c3190afee101672a04265_clark2017vinet.gif", "pdf": "http://arxiv.org/abs/1701.08376" }, { "authors": "Ronald Clark", "title": "Visual-inertial odometry, mapping and re-localization through learning", "venue": "University of Oxford", "year": "2017", "image": "images/616c31b3afee10a03ca04286_clark2017visual.gif", "pdf": "https://ora.ox.ac.uk/objects/uuid:69b03c50-f315-42f8-ad41-d97cd4c9bf09" }, { "authors": "Ronald Clark, Sen Wang, Andrew Markham, Niki Trigoni, Hongkai Wen", "title": "Vidloc: A deep spatio-temporal model for 6-dof video-clip relocalization", "venue": "IEEE Conference on Computer Vision and Pattern Recognition (CVPR)", "year": "2017", "image": "images/616c31c3e5b1696bea5e151f_clark2017vidloc.gif", "pdf": "http://arxiv.org/abs/1702.06521" }, { "authors": "Ronald Clark, Sen Wang, Hongkai Wen, Niki Trigoni, Andrew Markham", "title": "Increasing the efficiency of 6-DoF visual localization using multi-modal sensory data", "venue": "IROS", "year": "2017", "image": "images/616c32082eb4040a7ac10de8_clark2016increasing.gif", "pdf": "http://arxiv.org/abs/1612.09257" }, { "authors": "Sen Wang, Hongkai Wen, Ronald Clark, Niki Trigoni", "title": "Keyframe based large-scale indoor localisation using geomagnetic field and motion pattern", "venue": "IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)", "year": "2016", "image": "images/616c322e2eb40428b2c10df4_wang2016keyframe.gif", "pdf": "" }, { "authors": "Hongkai Wen, Sen Wang, Ronald Clark, Savvas Papaioannou, Niki Trigoni", "title": "Efficient visual positioning with adaptive parameter learning", "venue": "ACM/IEEE International Conference on Information Processing in Sensor Networks Workshops (IPSN-W)", "year": "2016", "image": "images/616c309d42a4bc2271046fc3_wen2018efficient.gif", "pdf": "" }, { "authors": "Ronald Clark, Niki Trigoni, Andrew Markham", "title": "Robust vision-based indoor localization", "venue": "", "year": "2015", "image": "images/616c309d42a4bc2271046fc3_wen2018efficient.gif", "pdf": "" }, { "authors": "Ronald Clark, Willem Cronje, Anton van Wyk", "title": "Design Optimization of a Hybrid Energy System Through Fast Convex Programming", "venue": "IEEE International Conference on Intelligent Systems, Modelling and Simulation (ISMS)", "year": "2014", "image": "images/616c32cb2eb404b3e5c10e46_clark2014design.gif", "pdf": "" }, { "authors": "Ronald Clark, Quik Kung, Anton van Wyk", "title": "System for the recognition of online handwritten mathematical expressions", "venue": "Eurocon", "year": "2013", "image": "images/616c32ffb693b1016ce64f7e_clark2013system.gif", "pdf": "" }, { "authors": "Ronald Clark, Quik Kung, Anton van Wyk", "title": "Handwritten Symbol Recognition using an Ensemble of SVM Classifiers", "venue": "Annual Symposium of the Pattern Recognition Association of South Africa (PRASA)", "year": "2012", "image": "images/616c33297bc48daec56e336b_clark2012handwritten.gif", "pdf": "" }, { "authors": "Ronald Clark", "title": "Volumetric Bundle Adjustment for Online Photrealistic Scene Capture", "venue": "IEEE Conference on Computer Vision and Pattern Recognition (CVPR)", "year": "2022", "image": "images/6235e2cb7bd4cb630028a8a1_vba.png", "pdf": "https://openaccess.thecvf.com/content/CVPR2022/papers/Clark_Volumetric_Bundle_Adjustment_for_Online_Photorealistic_Scene_Capture_CVPR_2022_paper.pdf" }, { "authors": "Fabian Hauf, Basaran Bahadir Kocer, Hai-Nguyen Nguyen, Oscar Kwong Fai Pang, Ronald Clark, Edward Johns, Mirko Kovac", "title": "Learning Tethered Perching for Aerial Robots", "venue": "International Conference on Robotics and Automation (ICRA)", "year": "2023", "image": "images/tethered-drone.png", "pdf": "https://ieeexplore.ieee.org/document/10161135" }, { "authors": "Jacob Lin, Miguel Farinha, Edward Gryspeerdt, Ronald Clark", "title": "Volumetric Cloud Field Reconstruction", "venue": "arxiv", "year": "2023", "image": "images/6569dc7e68dd873021cecee6_clouds.png", "pdf": "https://arxiv.org/pdf/2311.17657.pdf" }, { "authors": "Niki Amini-Naieni, Tomas Jakab, Andrea Vedaldi, Ronald Clark", "title": "Instant Uncertainty Calibration of NeRFs Using a Meta-calibrator", "venue": "European Conference on Computer Vision (ECCV)", "year": "2024", "image": "images/657078ba6f50e4b444f7ba64_calibrated_uncertainty.png", "pdf": "https://arxiv.org/abs/2312.02350" }, { "authors": "Yuanze Lin, Ronald Clark, Philip Torr", "title": "DreamPolisher: Towards High-Quality Text-to-3D Generation via Geometric Diffusion", "venue": "arxiv", "year": "2024", "image": "images/6687ad9ae1923ee490b25012_dream_polisher.png", "pdf": "https://arxiv.org/pdf/2403.17237" }, { "authors": "Hunar Batra, Ronald Clark", "title": "EVCL: Elastic Variational Continual Learning with Weight Consolidation", "venue": "International Conference on Machine Learning (ICML) - SPIGM", "year": "2024", "image": "images/6687ae36a3b0947f3b7b0e5e_evcl.png", "pdf": "https://arxiv.org/pdf/2406.15972" }, { "authors": "Nillan Nimal, Wenbin Li, Ronald Clark, Sajad Saeedi", "title": "DIO: Dataset of 3D Mesh Models of Indoor Objects for Robotics and Computer Vision Applications", "venue": "Conference on Robotic Vision", "year": "2024", "image": "images/6687afa2fe17429f82473efe_dio.png", "pdf": "https://arxiv.org/pdf/2402.11836" }, { "authors": "Bradley C. A. Brown, Jordan Juravsky, Ryan Saul Ehrlich, Ronald Clark, Quoc V. Le, Christopher Ré, Azalia Mirhoseini", "title": "Large Language Monkeys: Scaling Inference Compute with Repeated Sampling", "venue": "arxiv", "year": "2024", "image": "images/6749e464902567017b0320e6_monkeys.png", "pdf": "https://doi.org/10.48550/arXiv.2407.21787" }, { "authors": "Yuanze Lin, Yunsheng Li, Dongdong Chen, Weijian Xu, Ronald Clark, Philip Torr, Lu Yuan", "title": "Rethinking Visual Prompting for Multimodal Large Language Models with External Knowledge", "venue": "arxiv", "year": "2024", "image": "images/6749e4ca4bfc1e9a97ecf0fa_prompting.png", "pdf": "https://doi.org/10.48550/arXiv.2407.04681" }, { "authors": "Georgia Channing, Juil Sock, Ronald Clark, Philip Torr, Christian Schröder de Witt", "title": "Toward Robust Real-World Audio Deepfake Detection: Closing the Explainability Gap", "venue": "arxiv", "year": "2024", "image": "images/6749e5391d5a8469c1c7e283_audio_fake.png", "pdf": "https://doi.org/10.48550/arXiv.2410.07436" }, { "authors": "Center for AI Safety, Scale AI & HLE Contributors Consortium", "title": "A benchmark of expert-level academic questions to assess AI capabilities", "venue": "Nature", "year": "2026", "image": "images/hle2.png", "pdf": "https://www.nature.com/articles/s41586-025-09962-4" }, { "authors": "Jacob Lin, Edward Gryspeerdt, Ronald Clark", "title": "Cloud4D: Estimating Cloud Properties at a High Spatial and Temporal Resolution", "venue": "NeurIPS (Spotlight)", "year": "2025", "image": "images/cloud4d.png", "pdf": "https://neurips.cc/virtual/2025/poster/116780" }, { "authors": "Yuanze Lin, Yi-Wen Chen, Yi-Hsuan Tsai, Ronald Clark, Ming-Hsuan Yang", "title": "IllumiCraft: Unified Geometry and Illumination Diffusion for Controllable Video Generation", "venue": "NeurIPS", "year": "2025", "image": "images/illumicraft.png", "pdf": "https://arxiv.org/pdf/2506.03150" }, { "authors": "Andrew M. Bean, Ryan Othniel Kearns, Angelika Romanou, Franziska Sofia Hafner et al.", "title": "Measuring what Matters: Construct Validity in Large Language Model Benchmarks", "venue": "NeurIPS", "year": "2025", "image": "images/benchmark_validity.png", "pdf": "https://neurips.cc/virtual/2025/poster/121477" }, { "authors": "Abram Schonfeldt, Benjamin Maylor, Xiaofang Chen, Ronald Clark, Aiden Doherty", "title": "Reducing Annotation Burden in Physical Activity Research Using Vision-Language Models", "venue": "Scientific Reports", "year": "2025", "image": "images/annotation-vlms.png", "pdf": "https://arxiv.org/pdf/2505.03374" }, { "authors": "Jerred Chen, Ronald Clark", "title": "Image as an IMU: Estimating Camera Motion from a Single Motion-Blurred Image", "venue": "IEEE International Conference on Computer Vision (ICCV) - Oral", "year": "2025", "image": "images/image-imu2.png", "pdf": "https://arxiv.org/pdf/2503.17358" }, { "authors": "Jacob Lin, Edward Gryspeerdt, Ronald Clark", "title": "Cloud-Stereo: a dataset and benchmark for reconstructing atmospheric clouds from stereo images", "venue": "BMVC", "year": "2025", "image": "images/cloud_stereo.png", "pdf": "https://ora.ox.ac.uk/objects/uuid:99e98d25-0632-4dba-9549-001cf5585181" }, { "authors": "Sumeet Ramesh Motwani, Chandler Smith, Rocktim Jyoti Das, Rafael Rafailov, Ivan Laptev, Philip H. S. Torr, Fabio Pizzati, Ronald Clark, Christian Schroeder de Witt", "title": "MALT: Improving Reasoning with Multi-Agent LLM Training", "venue": "Conference on Language Modelling (COLM)", "year": "2025", "image": "images/67d8157b76d2421802587a48_malt.png", "pdf": "https://arxiv.org/abs/2412.01928" }, { "authors": "Thomas Pritchard, Saifullah Ijaz, Ronald Clark, Basaran Bahadir Kocer", "title": "ForestVO: Enhancing Visual Odometry in Forest Environments through ForestGlue", "venue": "IEEE Robotics and Automation Letters (RA-L)", "year": "2025", "image": "images/forest_vo.png", "pdf": "https://arxiv.org/pdf/2504.01261" }, { "authors": "Yu Sun, Vijja Wichitwechkarn, Ronald Clark, Mirko Kovac, Basaran Bahadir Kocer", "title": "MFAN: Dynamically Adaptive and Modular Multi-layer Learning", "venue": "Transactions on Machine Learning Research (TMLR)", "year": "2025", "image": "images/mfan.png", "pdf": "https://openreview.net/pdf?id=6RCs2tLsHq" }, { "authors": "Yuanze Lin, Yunsheng Li, Dongdong Chen, Weijian Xu, Ronald Clark, Philip H. S. Torr", "title": "Olympus: A Universal Task Router for Computer Vision Tasks", "venue": "IEEE Computer Vision and Pattern Recognition (CVPR)", "year": "2025", "image": "images/67d81620d0a2f8f1f4e7f92b_olympus.png", "pdf": "https://arxiv.org/pdf/2412.09612" }, { "authors": "Ryan Ehrlich, Bradley Brown, Jordan Juravsky, Ronald Clark, Christopher Ré, Azalia Mirhoseini", "title": "CodeMonkeys: Scaling Test-Time Compute for Software Engineering", "venue": "arxiv", "year": "2025", "image": "images/67d816c235fd97e458a9f7f9_code_monkeys.png", "pdf": "https://arxiv.org/pdf/2501.14723" }, { "authors": "Chit Yuen Lam, Ronald Clark, Basaran Bahadir Kocer", "title": "XIRVIO: Critic-guided Iterative Refinement for Visual-Inertial Odometry with Explainable Adaptive Weighting", "venue": "arxiv", "year": "2025", "image": "images/67d8173764cb4000f066f5ce_xirvio.png", "pdf": "https://arxiv.org/pdf/2503.00315" }, { "authors": "Long Phan, Alice Gatti, Ziwen Han, Nathaniel Li, Josephina Hu, Hugh Zhang, Chen Bo Calvin Zhang, Mohamed Shaaban, John Ling, Sean Shi, et al.", "title": "Humanity's Last Exam", "venue": "Arxiv", "year": "2025", "image": "images/67d814c40ede6217f9f3c829_hle.png", "pdf": "https://arxiv.org/abs/2501.14249" } ]