I am a PhD candidate at UCL’s SpaceTimeLab, supervised by Dr James Haworth, Dr Aldo Lipani, and Dr Stefano Cavazzi. My research is funded by UKRI (EPSRC) and Ordnance Survey (OS).

I study how people communicate about place: what they ask, how they ask it, and what this reveals about human spatial cognition at scale. I work at the intersection of GeoAI, NLP, and HCI, using query logs and conversational AI datasets to characterise spatial information needs across interfaces. I’m particularly interested in subjective spatial questions – those that go beyond what deterministic GIS can answer, and expose the gap between place as data and place as lived experience.

I am a co-founder and CTO of Safest Way, a Geovation-backed startup developing safety-focused pedestrian navigation. Read about it on BBC News or in The Conversation.

Publications

Web search query classification COSIT 2026 (accepted)
Much of Geospatial Web Search Is Beyond Traditional GIS
Ilya Ilyankou, Stefano Cavazzi, James Haworth
[People ask the web about place far more than we thought, and most of it is practical lookups (costs, hours, contact details, weather, etc.) that GIS isn't traditionally built to answer.]
The Scenic Route to Deception paper illustration MIRAGE @ IUI 2026
The Scenic Route to Deception: Dark Patterns and Explainability Pitfalls in Conversational Navigation
Ilya Ilyankou, Stefano Cavazzi, James Haworth
[Conversational navigation risks turning routing from a verifiable geometric task into opaque persuasion; a neuro-symbolic architecture grounding LLM outputs in pathfinding algorithms offers a path to trustworthy, explainable pedestrian navigation.]
StreetVibes pipeline overview GISRUK 2026
StreetVibes: An Open, Modular Pipeline for Reproducible Street-Level Urban Perception Analysis
Ilya Ilyankou, Stefano Cavazzi, James Haworth
[A privacy-preserving, open-source tool that converts street-level imagery into semantic urban indicators by orchestrating OSM, Mapillary, and local vision-language models.]
GeoExT 2026 GeoExT @ ECIR 2026
Multilingual Synthetic Corpora for Geoparsing Using Large Language Models
Ilya Ilyankou, Franz Welscher, Paddy Smith, Tatu Leppämäki
[Using LLMs to generate synthetic geoparsing corpora across four languages and regions, exposing systematic limitations in low-resource settings tied to geographic data coverage and linguistic variation.]
Clip the Landscape landscape image examples Remote Sensing Applications: Society and Environment (2026)
CLIP the Landscape: Automated Tagging of Crowdsourced Landscape Images
Ilya Ilyankou, Natchapon Jongwiriyanurak, Tao Cheng, James Haworth
[What you see isn't always what gets tagged. A CLIP-based classifier combining image, location, and title embeddings to predict geographic context tags from landscape photos, improving spatial understanding in data-sparse regions.]
The model framework of CaLLiPer SIGSPATIAL'25
Into the Unknown: Applying Inductive Spatial-Semantic Location Embeddings for Predicting Individuals' Mobility Beyond Visited Places
Xinglei Wang, Tao Cheng, Stephen Law, Zichao Zeng, Ilya Ilyankou, Junyuan Liu, Lu Yin, Weiming Huang, Natchapon Jongwiriyanurak
[Multimodal location embeddings fusing coordinates and POI semantics via contrastive learning improve individual mobility prediction, particularly for previously unseen locations.]
V-RoAst workflow CV4DC @ ICCV'25
V-RoAst: Visual Road Assessment. Can VLM be a Road Safety Assessor Using the iRAP Standard?
Natchapon Jongwiriyanurak, Zichao Zeng, June Moh Goo, Xinglei Wang, Ilya Ilyankou, Kerkritt Sriroongvikrai, Nicola Christie, Meihui Wang, Huanfa Chen, James Haworth
[A zero-shot VQA framework using vision-language models to classify iRAP road safety attributes from street-level imagery, reducing the cost of infrastructure risk assessment in low-resource settings.]
Quantifying Geospatial paper Figure 2 SIGSPATIAL'24
Quantifying Geospatial in the Common Crawl Corpus
Ilya Ilyankou, Meihui Wang, Stefano Cavazzi, James Haworth
[Nearly one in five Common Crawl documents contains geospatial information, offering a quantitative basis for understanding why LLMs develop spatial reasoning capabilities.]
CC-GPX Figure 1 (multimodal dataset entry example) SIGSPATIAL'24
CC-GPX: Extracting High-Quality Annotated Geospatial Data from Common Crawl
Ilya Ilyankou, Meihui Wang, Stefano Cavazzi, James Haworth
[A pipeline to extract paired GPX tracks and human-written descriptions from Common Crawl, yielding a multimodal dataset of 1,416 real outdoor routes for geospatial and NLP research.]
CycleTrajectory Figure 2 SuMob @ SIGSPATIAL'24
CycleTrajectory: An End-to-End Pipeline for Enriching and Analyzing GPS Trajectories to Understand Cycling Behavior and Environment
Meihui Wang, James Haworth, Ilya Ilyankou, Nicola Christie
[An end-to-end pipeline that map-matches cyclists' GPS trajectories to OpenStreetMap, enriching raw data with road semantics and derived mobility metrics.]
GeoExT group photo GeoExT @ ECIR 2024
Do Sentence Transformers Learn Quasi-Geospatial Concepts from General Text?
Ilya Ilyankou, Aldo Lipani, Stefano Cavazzi, Xiaowei Gao, James Haworth
[Fine-tuned sentence transformers show zero-shot capacity to match hiking queries to route descriptions, hinting at untrained geospatial utility.]

Professional experience

  • Intern, The Alan Turing Institute (Autumn 2025)

  • Data engineer, Geolytix (2022–2025)

  • Full-stack developer, CTData Collaborative (2018–2022)

Teaching

As a postgraduate teaching assistant at UCL (2024–25) and lab demonstrator at Birkbeck (2025–26), I have supported modules in geospatial programming, spatial analysis, and data analytics.

Education

  • PhD in Geomatic Engineering / Geospatial AI – University College London (UCL), 2023–2027

  • MSc in Geographic Information Science (Distinction) – University of Leeds, 2019–2022

  • BSc in Computer Science and Studio Arts (summa cum laude, Phi Beta Kappa) – Trinity College (Connecticut), 2014–2018

  • Worcester College, University of Oxford – Visiting student focusing on machine learning and game theory, 2016–2017

Hands-On Data Visualization

Hands-On Data Visualization: Interactive Storytelling from Spreadsheets to Code (O’Reilly), co-authored with Jack Dougherty. Available open-access in English, and translated into Korean and Traditional Chinese.

Since 2022, all royalties (currently over $5,000) have been donated to humanitarian relief efforts in Ukraine, most recently to The HALO Trust.

Hands-On Data Visualization book cover