Agentic AI for Science
LLM-based multi-agent systems that plan, run and explain scientific analyses, from plant phenotyping to observational study design in medicine.
Edinburgh, UK
Postdoctoral Researcher · University of Edinburgh
Feng Chen陈丰
Building AI systems that do science.
- Agentic AI
- Data-Efficient Learning
- Computer Vision
- AI for Life Sciences
Email: feng.chen@ed.ac.uk
About
I am a Postdoctoral Researcher in Machine Learning at the University of Edinburgh. Previously, I earned my PhD in Computer Science from the University of Nottingham.
I build AI agents, data-efficient learning algorithms and computer vision methods that help scientists turn images and data into findings, with applications mostly in agriculture and medicine.
My recent paper in Nature Communications (2026) introduces PhenoAssistant, the first conversational multi-agent AI system that automates plant phenotype analysis end to end, covering measurement, data visualisation and statistical analysis.
Research & Publications
Research directions
Data-Efficient Learning
Learning with fewer labels: weakly and semi-supervised learning, active learning, and self-supervised pre-training.
Computer Vision
Instance segmentation, counting and density estimation, and adapting vision foundation models and vision-language models to new domains.
AI for Life Sciences
Plant and crop phenotyping, agricultural foundation models, and AI for clinical research and surgery.
★ Featured paper
A Conversational Multi-Agent AI System for Automated Plant Phenotyping
Feng Chen et al.|Nature Communications, 2026
The first conversational multi-agent AI system that automates plant phenotype analysis, covering phenotype measurement, data visualisation and statistical analysis.
Publications
Full list on Google Scholar ↗- 2026A Conversational Multi-Agent AI System for Automated Plant Phenotyping
Feng Chen, Ilias Stogiannidis, Andrew Wood, Danilo Bueno, Dominic Williams, Fraser Macfarlane, Bruce D. Grieve, Darren Wells, Jonathan A. Atkinson, Malcolm J. Hawkesford, Stephen A. Rolfe, Tracy Lawson, Tony Pridmore, Sotirios A. Tsaftaris, Mario Valerio Giuffrida
- 2026The Unreasonable Benchmark
Fernando Perez-Cruz, Briland Hitaj, Giovanna Maria Dimitri, Oishi Deb, Amine M'Charrak, Shikhar Srivastava, Christopher Kanan, Anup Kumar Gupta, Zefang Liu, Tarun Kumar, Álvaro Galisteo Bermúdez, Vasilios Mavroudis, Yuyang Xue, Brian Matejek, Swati Rajwal, Avinash Kumar Pandey, Ayyüce Begüm Bektaş, Anil B Murthy, Feng Chen, Hamed Babaei Giglou, Jennifer D'Souza, Huascar Sanchez, Michael Kraus, Isamu Lautenschläger, Ziyang Wang, Xuanli He, Hyun Song Shin
Journal of Data-centric Machine Learning Research (DMLR)Paper
- 2026Count2Density: Crowd Density Estimation without Location-level Annotations
Mattia Litrico, Feng Chen, Michael Pound, Sotirios A. Tsaftaris, Sebastiano Battiato, Mario Valerio Giuffrida
Pattern RecognitionPaper
- 2026Online OCF Diagnosis for DTP-PMSM via Semi-Supervised Learning and Compression-based Deep Learning Network with OOD Detection
Hao Yu, Boyuan Zheng, Bingtao Liu, Yongsheng Huang, Junyu Yan, Yongxiang Xu, Guodong Yu, Pericle Zanchetta, Feng Chen
IEEE Transactions on Transportation ElectrificationPaper
- 2026One Thing Leads to Another: The Essentials of Time Series Causal Discovery
Kurt Butler, Damian Machlanski, Michael P. J. Camilleri, Zhihua Liu, Panagiotis Dimitrakopoulos, Feng Chen, Ricardo Silva, Sotirios A. Tsaftaris
- 2026CSEval: A Framework for Evaluating Clinical Semantics in Text-to-Image Generation
Robert Cronshaw, Konstantinos Vilouras, Junyu Yan, Yuning Du, Feng Chen, Steven McDonagh, Sotirios A. Tsaftaris
IEEE International Symposium on Biomedical Imaging (ISBI)arXiv
- 2025GMT: Guided Mask Transformer for Leaf Instance SegmentationOral
Feng Chen, Sotirios A. Tsaftaris, Mario Valerio Giuffrida
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)PaperCode
- 2025CRCE: Coreference-Retention Concept Erasure in Text-to-Image Diffusion Models
Yuyang Xue, Edward Moroshko, Feng Chen, Jingyu Sun, Steven McDonagh, Sotirios A. Tsaftaris
- 2025SWiFT: Soft-Mask Weight Fine-tuning for Bias Mitigation
Junyu Yan, Feng Chen, Yuyang Xue, Yuning Du, Konstantinos Vilouras, Sotirios A. Tsaftaris, Steven McDonagh
- 2023Adapting Vision Foundation Models for Plant Phenotyping50+ citations
Feng Chen, Mario Valerio Giuffrida, Sotirios A. Tsaftaris
IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)Paper
- 2021Learning to Localise and Count with Incomplete Dot-annotations
Feng Chen, Michael P. Pound, Andrew P. French
IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)Paper
- 2019Using Active Learning to Reduce Training Data in Deep-learning-based Flower Classification
Feng Chen, Tony Pridmore, Andrew French
CVPR Workshop on Computer Vision Problems in Plant Phenotyping (CVPPP)Paper
- 2018Citizen Crowds and Experts: Observer Variability in Image-Based Plant Phenotyping
Mario Valerio Giuffrida, Feng Chen, Hanno Scharr, Sotirios A. Tsaftaris
Plant MethodsPaper
- 2018Towards Low-Cost Image-based Plant Phenotyping using Reduced-Parameter CNN
John Atanbori, Feng Chen, Andrew P. French, Tony Pridmore
British Machine Vision Conference Workshops (BMVCW)PaperCode
Grants & Awards
Grants
- 2023 – presentResearcher on EPSRC Real-time Digital Twin Assisted Surgery (£4M) and BBSRC PhenomUK (£2.4M)
University of Edinburgh
- 2026Travel Scholarship
AIBIO-UK 3rd Annual Conference
- 2023 – 2025Co-PI, Microsoft Accelerate Foundation Models Research Grant
Agricultural Foundation Models via Domain-Specific Pre-Training (US$20,000)
Awards
- 2026Outstanding Reviewer, ECCV
- 2026Best Poster Runner-Up (of 22), AIBIO-UK Annual Conference
- 2024Outstanding Reviewer, BMVC
- 2018 – 2021International PhD Full Scholarship, University of Nottingham
- 2017Best MSc Thesis Award, School of Engineering, University of Edinburgh
- 2016National Scholarship (top 0.2% nationally), Shantou University
Teaching & Supervision
Teaching
- 2018 – 2021Teaching Assistant, University of Nottingham
- Machine Learning (UG/PG)
- Fundamentals of Artificial Intelligence (UG)
- Computer Vision (UG/PG)
Co-supervised students
- 2026Vincent Nguyen · Undergraduate summer intern (Google DeepMind Research Ready scheme), University of Nottingham
Agentic AI for image-based analysis
Winner of the Flash Talk Competition
- 2024Jingyu Sun · Undergraduate summer intern, University of Edinburgh
Pre-training agricultural foundation models with self-supervised learning
Now a PhD student at the University of Manchester
- 2023 – 2024Ziyu Huang · MSc student, University of Edinburgh
Active learning for medical image classification with fewer labels
Thesis awarded Distinction
Talks
- Jun 2026
AIBIO-UK 3rd Annual Conference, University of Aberdeen
- Dec 2024AI for Efficient and Accessible Plant Phenotyping Keynote
PhenomUK & AIBIO-UK Joint Workshop, University of Nottingham
- Sep 2024Accelerating Plant Phenotyping with AI
UK Plant Phenomics Town Hall and Conference, University of Warwick
- May 2024Retrieval-Augmented Generation: A Promising Approach to Enhance Fairness and Transparency in the Use of LLMs for Agriculture
PhenoHarmonIS Workshop, Institut Agro, France
- Apr 2018Citizen Scientists and Machine Learning to Help Feed the World
Zooniverse Team, University of Oxford
Academic Service
- 2023 – present
- 2026: Communications Chair (ECCV 2026)
- 2025: Paper Chair (ICCV 2025)
- 2024: Organising Committee Member (ECCV 2024)
- 2023: Organising Committee Member (ICCV 2023)
- 2025 – presentYoung Scientists Editorial Board Member
Plant Phenomics
- 2025Technical Consultant, Ask an Expert programme
PhenomUK
- ongoingReviewer
- CVPR
- ICCV
- ECCV
- BMVC
- Nature Scientific Data
- Nature Astronomy
- Plant Phenomics
- Plant Communications
- Plant Methods
- npj Sustainable Agriculture
- Frontiers in Plant Science
- Applied Intelligence
- Earth System Science Data