Staff profile

Chris G. Willcocks is a Turing Fellow with a background in both theoretical deep learning and large-scale generative modelling. His key contributions include benchmark evals widely used by frontier AI labs, several widely cited advances to generative diffusion models, and self-regulated sampling strategies in frontier LLMs. He is particularly interested in multimodal AI; current systems offer bespoke solutions for text or images, but real-world data is far more diverse. Future AI must generalise across modalities at scale. He is also interested in neural scaling laws for decentralised AI, and how to evaluate and improve agentic systems working together.

He has authored 40+ peer-reviewed publications in world-leading conferences/journals within computer science, applied mathematics, and security, including ICLR, TPAMI, CVPR, ECCV, ICCV and TIFS. More information is available on his website and a full list of his publications is on Google scholar.

Research highlights

The group's recent theoretical work, ∞-diff (ICLR 2024), demonstrated diffusion models in an infinite-dimensional Hilbert space for arbitrary resolution synthesis. They also released a highly cited comparative review on deep generative models (TPAMI 2022) and proposed strategies that improve frontier AI sampling, such as the GPT models. He also developed gradient origin networks (ICLR 2021), showing encoders are often unnecessary in autoencoders (see Yannic Kilcher's video on GONs). He is internationally recognised for unsupervised anomaly detection, including AnoDDPM (CVPR 2022), and has applied diffusion models in unpaired translation. The group's research has also been applied in unsupervised medical anomaly detection (IEEE ISBI 2021), cross-domain imagery (ICPR 2021), multi-view transformers for object detection, generating 3D CT-like images from 2D X-rays MedNeRF (IEEE EMBC), and in threat detection (IEEE TIFS).

Undergraduate teaching

He created and teaches the deep learning and reinforcement learning modules and the year two cyber security submodule. Slides and other material are available in the teaching section of his website. He also has a YouTube channel with deep learning and reinforcement learning material.

• Deep Learning (2019-present)
• Reinforcement Learning (2020-present)
• Cyber Security (2017-2024)
• Machine Learning (2018)

Industry engagement

His research has been applied commercially, collaborating with multinationals and SMEs, including P&G, Unilever, Dyson, Heidelberg Engineering, AstraZeneca, Gliff.ai, Scott Logic, and Waterstons, as well as the public sector: the NCA, NERCCU, DASA, DSTL, and the NHS. He is a fellow of the HEA, and has delivered over 15 invited talks and participated in public discussions on ethics and cyber security with Microsoft and engaged with the UK Cabinet Office. In 2016, he co-founded a Durham University research spinout following successful InnovateUK seed funding for a high-growth AI SME, and led the research team in the early stages.

Professional activities

He serves as area chair for BMVC, is the admissions tutor for computer science, and is a member of the scientific computing group. In the past, he has been the open day coordinator and has been an invited speaker at several conferences and universities, including the 2023 and 2024 national DICE conferences, and the Chinese University of Hong Kong (CUHK). He was a speaker on BBC sunday politics about cyber security spending in public bodies, and is a reviewer for NeurIPS, CVPR, ICLR, the EU commission, and IEEE including TPAMI, TIFS, TNNLS, TIP and TMI.

Research interests

His research interests are centred in theoretical generative modelling, machine reasoning and frameworks for AI alignment. If you are interested in joining his research group and have a background in mathematics, computer science, engineering or physics, please see the information here and email to discuss.

• Machine reasoning
• Large-scale generative modelling
• Frontier AI evaluation
• Decentralised and agentic AI
• Multimodal modelling
• Diffusion and autoregressive models
• Neural scaling laws

Esteem indicators

• Turing Fellow (2026)
• Admissions tutor (2021-2026).
• Fellowship of the HEA (FHEA).
• Invited speaker at National DICE Conference (2024).
• Area Chair of BMVC 2023.
• Invited speaker at Chinese University of Hong Kong (CUHK), 2023.
• Invited speaker at National DICE Conference (2023).
• Invited speaker at BMVA 2022 Summer School.
• Open Day coordinator (2021-2022).
• Area Chair of BMVC 2021.
• Invited speaker at 2020 Cyber Operational Conference on ‘Meta learning: Smart Interfacing’.
• Area Chair of BMVA 2020 Conference.
• Participating scientist on Scientist Next Door (SND).
• Invited speaker at Chinese University of Hong Kong (CUHK), 13th Aug 2019.
• Chair of BMVA symposium of ‘Deep Learning in 3-Dimensions’, 20th Feb 2019.
• Speaker on BBC Sunday Politics discussing Cyber Security spending in public bodies.
• Invited to present at Durham Celebrating Excellence research exhibition.
• Member of W3C Web Assembly.
• Reviewer for EU Commission.
• Reviewer for IEEE TIFS, TMI, TIP, TPAMI, JRTIP, NNLS.
• Reviewer for NeurIPS, CVPR, ICLR.

Conference Paper

• Controllable Image Generation with Composed Parallel Token Prediction
  
  Stirling, J., Al Moubayed, N., Willcocks, C. G., & Shum, H. P. H. (in press). Controllable Image Generation with Composed Parallel Token Prediction. In Proceedings of the 2026 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshop. IEEE.
• Repeat and Concatenate: 2D to 3D Image Translation with 3D to 3D Generative Modeling
  
  Corona-Figueroa, A., Shum, H. P. H., & Willcocks, C. G. (2024, September 27). Repeat and Concatenate: 2D to 3D Image Translation with 3D to 3D Generative Modeling. Presented at 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, Washington. https://doi.org/10.1109/CVPRW63382.2024.00237
• Self-Regulated Sample Diversity in Large Language Models
  
  Liu, M., Frawley, J., Wyer, S., Shum, H. P. H., Uckelman, S. L., Black, S., & Willcocks, C. G. (2024). Self-Regulated Sample Diversity in Large Language Models. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics (pp. 1891–1899). Association for Computational Linguistics.
• ∞-Diff: Infinite Resolution Diffusion with Subsampled Mollified States
  
  Bond-Taylor, S., & Willcocks, C. G. (2024). ∞-Diff: Infinite Resolution Diffusion with Subsampled Mollified States. In The Twelfth International Conference on Learning Representations.
• Exact-NeRF: An Exploration of a Precise Volumetric Parameterization for Neural Radiance Fields
  
  Isaac-Medina, B., Willcocks, C., & Breckon, T. (2023, June). Exact-NeRF: An Exploration of a Precise Volumetric Parameterization for Neural Radiance Fields. Presented at IEEE/CVF Conference on Computer Vision and Pattern Recognition 2023, Vancouver, BC.
• Unaligned 2D to 3D Translation with Conditional Vector-Quantized Code Diffusion using Transformers
  
  Corona-Figueroa, A., Bond-Taylor, S., Bhowmik, N., Gaus, Y. F. A., Breckon, T. P., Shum, H. P., & Willcocks, C. G. (2023). Unaligned 2D to 3D Translation with Conditional Vector-Quantized Code Diffusion using Transformers. In ICCV ’23: Proceedings of the 2023 IEEE/CVF International Conference on Computer Vision. IEEE. https://doi.org/10.1109/ICCV51070.2023.01341
• Unleashing Transformers: Parallel Token Prediction with Discrete Absorbing Diffusion for Fast High-Resolution Image Generation from Vector-Quantized Codes
  
  Bond-Taylor, S., Hessey, P., Sasaki, H., Breckon, T., & Willcocks, C. (2022). Unleashing Transformers: Parallel Token Prediction with Discrete Absorbing Diffusion for Fast High-Resolution Image Generation from Vector-Quantized Codes. In Computer Vision – ECCV 2022 (pp. 170-188). Springer Verlag. https://doi.org/10.1007/978-3-031-20050-2_11
• Multi-view Vision Transformers for Object Detection
  
  Isaac-Medina, B., Willcocks, C., & Breckon, T. (2022, August). Multi-view Vision Transformers for Object Detection. Presented at International Conference on Pattern Recognition, Montreal, Canada.
• AnoDDPM: Anomaly Detection With Denoising Diffusion Probabilistic Models Using Simplex Noise
  
  Wyatt, J., Leach, A., Schmon, S. M., & Willcocks, C. G. (2022, June). AnoDDPM: Anomaly Detection With Denoising Diffusion Probabilistic Models Using Simplex Noise. Presented at 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, New Orleans, LA. https://doi.org/10.1109/cvprw56347.2022.00080
• Cross-modal Image Synthesis in Dual-Energy X-Ray Security Imagery
  
  Isaac-Medina, B., Bhowmik, N., Willcocks, C., & Breckon, T. (2022, June). Cross-modal Image Synthesis in Dual-Energy X-Ray Security Imagery. Presented at 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), New Orleans, Louisiana. https://doi.org/10.1109/cvprw56347.2022.00048
• Denoising Diffusion Probabilistic Models on SO(3) for Rotational Alignment
  
  Leach, A., Schmon, S. M., Degiacomi, M. T., & Willcocks, C. G. (2022). Denoising Diffusion Probabilistic Models on SO(3) for Rotational Alignment. Presented at ICLR 2022 Workshop on Geometrical and Topological Representation Learning.
• MedNeRF: Medical Neural Radiance Fields for Reconstructing 3D-aware CT-Projections from a Single X-ray
  
  Corona-Figueroa, A., Frawley, J., Bond-Taylor, S., Bethapudi, S., Shum, H. P., & Willcocks, C. G. (2022). MedNeRF: Medical Neural Radiance Fields for Reconstructing 3D-aware CT-Projections from a Single X-ray. Presented at 2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), Glasgow, Scotland. https://doi.org/10.1109/embc48229.2022.9871757
• Real Time Fencing Move Classification and Detection at Touch Time during a Fencing Match
  
  Sunal, C. E., Willcocks, C. G., & Obara, B. (2021, October). Real Time Fencing Move Classification and Detection at Touch Time during a Fencing Match. Presented at International Conference on Pattern Recognition (ICPR), Milan. https://doi.org/10.1109/icpr48806.2021.9412024
• Robust 3D U-Net Segmentation of Macular Holes
  
  Frawley, J., Willcocks, C. G., Habib, M., Geenen, C., Steel, D. H., & Obara, B. (2021). Robust 3D U-Net Segmentation of Macular Holes. In A. Pakrashi, E. Rushe, M. H. Z. Bazargani, & B. Mac Namee (Eds.), CEUR Workshop Proceedings (pp. 36-47). CEUR-WS.org.
• Data Augmentation via Mixed Class Interpolation using Cycle-Consistent Generative Adversarial Networks Applied to Cross-Domain Imagery
  
  Sasaki, H., Willcocks, C., & Breckon, T. (2021). Data Augmentation via Mixed Class Interpolation using Cycle-Consistent Generative Adversarial Networks Applied to Cross-Domain Imagery. Presented at 25th International Conference on Pattern Recognition (ICPR 2020), Milan, Italy. https://doi.org/10.1109/icpr48806.2021.9413023
• Multi-view Object Detection Using Epipolar Constraints within Cluttered X-ray Security Imagery
  
  Isaac-Medina, B., Willcocks, C., & Breckon, T. (2021). Multi-view Object Detection Using Epipolar Constraints within Cluttered X-ray Security Imagery. Presented at 25th International Conference on Pattern Recognition (ICPR 2020), Milan, Italy. https://doi.org/10.1109/icpr48806.2021.9413007
• Unsupervised Region-based Anomaly Detection in Brain MRI with Adversarial Image Inpainting
  
  Nguyen, B., Feldman, A., Bethapudi, S., Jennings, A., & Willcocks, C. G. (2021). Unsupervised Region-based Anomaly Detection in Brain MRI with Adversarial Image Inpainting. Presented at 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI), Nice, France. https://doi.org/10.1109/isbi48211.2021.9434115
• Gradient Origin Networks
  
  Bond-Taylor, S., & Willcocks, C. G. (2021). Gradient Origin Networks. Presented at International Conference on Learning Representations, Vienna / Virtual.
• Unmanned Aerial Vehicle Visual Detection and Tracking using Deep Neural Networks: A Performance Benchmark
  
  Isaac-Medina, B. K., Poyser, M., Organisciak, D., Willcocks, C. G., Breckon, T. P., & Shum, H. P. (2021). Unmanned Aerial Vehicle Visual Detection and Tracking using Deep Neural Networks: A Performance Benchmark. Presented at 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), Montreal, BC, Canada. https://doi.org/10.1109/iccvw54120.2021.00142
• Segmentation of macular edema datasets with small residual 3D U-Net architectures
  
  Frawley, J., Willcocks, C. G., Habib, M., Geenen, C., Steel, D. H., & Obara, B. (2020). Segmentation of macular edema datasets with small residual 3D U-Net architectures. Presented at 20th IEEE International Conference on BioInformatics and BioEngineering, Cincinnati, OH. https://doi.org/10.1109/bibe50027.2020.00100
• Shape tracing: An extension of sphere tracing for 3D non-convex collision in protein docking
  
  Leach, A., Rudden, L. S., Bond-Taylor, S., Brigham, J. C., Degiacomi, M. T., & Willcocks, C. G. (2020). Shape tracing: An extension of sphere tracing for 3D non-convex collision in protein docking. In 2020 IEEE 20th International Conference on Bioinformatics and Bioengineering (BIBE) (pp. 49-52). Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/bibe50027.2020.00016
• TMIXT: A process flow for Transcribing MIXed handwritten and machine-printed Text
  
  Medhat, F., Mohammadi, M., Jaf, S., Willcocks, C., Breckon, T., Matthews, P., McGough, A. S., Theodoropoulos, G., & Obara, B. (2018, December 1). TMIXT: A process flow for Transcribing MIXed handwritten and machine-printed Text. Presented at IEEE International Conference on Big Data., Seattle, WA, USA.

Doctoral Thesis

• Sparse Volumetric Deformation - Animating and rendering huge amounts of volumetric data using GPGPU computing
  
  Willcocks, C. G. (2013). Sparse Volumetric Deformation - Animating and rendering huge amounts of volumetric data using GPGPU computing [Thesis]. Durham University.

Journal Article

• Dynamic Unary Convolution in Transformers
  
  Duan, H., Long, Y., Wang, S., Zhang, H., Willcocks, C. G., & Shao, L. (2023). Dynamic Unary Convolution in Transformers. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(11), 12747-12759. https://doi.org/10.1109/tpami.2022.3233482
• Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models
  
  Bond-Taylor, S., Leach, A., Long, Y., & Willcocks, C. G. (2021). Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(11), 7327-7347. https://doi.org/10.1109/tpami.2021.3116668
• The relationship between curvilinear structure enhancement and ridge detection approaches
  
  Alhasson, H., Willcocks, C. G., Alharbi, S. S., Kasim, A., & Obara, B. (2021). The relationship between curvilinear structure enhancement and ridge detection approaches. Visual Computer, 37(8), 2263-2283. https://doi.org/10.1007/s00371-020-01985-4
• Deep Learning Protein Conformational Space with Convolutions and Latent Interpolations
  
  Ramaswamy, V. K., Musson, S. C., Willcocks, C. G., & Degiacomi, M. T. (2021). Deep Learning Protein Conformational Space with Convolutions and Latent Interpolations. Physical Review X, 11(1), Article 011052. https://doi.org/10.1103/physrevx.11.011052
• Interactive GPU Active Contours for Segmenting Inhomogeneous Objects
  
  Willcocks, C. G., Jackson, P. T., Nelson, C. J., Nasrulloh, A., & Obara, B. (2019). Interactive GPU Active Contours for Segmenting Inhomogeneous Objects. Journal of Real-Time Image Processing, 16(6), 2305-2318. https://doi.org/10.1007/s11554-017-0740-1
• Sequential graph-based extraction of curvilinear structures
  
  Alharbi, S. S., Willcocks, C., Jackson, P. T., Alhasson, H. F., & Obara, B. (2019). Sequential graph-based extraction of curvilinear structures. Signal, Image and Video Processing, 13(5), 941-949. https://doi.org/10.1007/s11760-019-01431-6
• Using Deep Convolutional Neural Network Architectures for Object Classification and Detection within X-ray Baggage Security Imagery
  
  Akcay, S., Kundegorski, M., Willcocks, C., & Breckon, T. (2018). Using Deep Convolutional Neural Network Architectures for Object Classification and Detection within X-ray Baggage Security Imagery. IEEE Transactions on Information Forensics and Security, 13(9), 2203-2215. https://doi.org/10.1109/tifs.2018.2812196
• Multi-scale Segmentation and Surface Fitting for Measuring 3D Macular Holes
  
  Nasrulloh, A., Willcocks, C., Jackson, P., Geenen, C., Habib, M., Steel, D., & Obara, B. (2018). Multi-scale Segmentation and Surface Fitting for Measuring 3D Macular Holes. IEEE Transactions on Medical Imaging, 37(2), 580-589. https://doi.org/10.1109/tmi.2017.2767908
• Extracting 3D parametric curves from 2D images of helical objects
  
  Willcocks, C., Jackson, P. T., Nelson, C. J., & Obara, B. (2016). Extracting 3D parametric curves from 2D images of helical objects. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(9), 1757-1769. https://doi.org/10.1109/tpami.2016.2613866
• Feature-Varying Skeletonization
  
  Willcocks, C. G., & Li, F. W. (2012). Feature-Varying Skeletonization. Visual Computer, 28(6-8), 775-785. https://doi.org/10.1007/s00371-012-0688-x