July 27 - London AI, ML, and Computer Vision Meetup
Join our in-person meetup to hear talks from experts on cutting-edge topics across AI, ML, and computer vision. Register to reserve your seat! Date, Time and Location Jul 27, 2026 5:30 PM - 8:30 PM BST Imperial College London, Skempton Building (LT201), South Kensington, London SW7 2AZ UniLight: Unified Multi-Modal Lighting Representation Lighting has a strong influence on visual appearance, yet understanding and representing lighting in images remains notoriously difficult. UniLight introduces a joint latent space to unify previously incompatible lighting representation - environment maps, images, irradiance and text descriptions. Modality-specific encoders are trained contrastively to align their representations, with an auxiliary spherical-harmonics prediction task reinforcing directional understanding. Our joint lighting embedding enables applications such as retrieval, example-based light control during image generation, and environment map generation from various modalities. About the Speaker Zitian Zhang - is a PhD candidate in Computer Science at Université Laval, and a research scientist intern in Adobe Research London. He focuses on image understanding, generation, and lighting representations through foundation models. LoST: Level of Semantics Tokenization for 3D Shapes Tokenization is fundamental to generative modeling and especially important for autoregressive 3D generation. However, current 3D shape tokenizers rely on geometric level-of-detail hierarchies that are token-inefficient and poorly aligned with semantic structure. We propose Level-of-Semantics Tokenization (LoST), which orders tokens by semantic salience so early tokens produce complete, plausible shapes and later tokens refine detailed geometry and semantics. LoST is trained with Relational Inter-Distance Alignment (RIDA), a semantic alignment loss that matches relationships in 3D shape latent space to those in DINO feature space. Experiments show that LoST achieves state-of-the-art reconstruction and efficient high-quality AR 3D generation while using only 0.1%–10% of the tokens required by prior methods. About the Speaker Niladri Dutt - is an ELLIS PhD student at University College London (UCL), sponsored by Adobe Research. He is advised by Prof Niloy Mitra (UCL) and Duygu Ceylan (Adobe). Material selection in 2D and beyond - methods, tricks and applications In this talk, we'll explore reasoning about images from a material-centric perspective, namely through the lens of material understanding. Materials distinguish themselves by their response to light, which is governed and modelled through physical properties like roughness or gloss - however, understanding such properties is a non-trivial task for current algorithms and models. We'll see how we can select materials similar to a given query material, significantly improve selection fidelity and eventually even venture beyond 2D, to enable selection in the 3D domain. About the Speaker Michael Fischer - is a research scientist at Adobe research London. He obtained his PhD from University College London (UCL), advised by Niloy Mitra and Tobias Ritschel. Michael has authored several top-tier publications (CVPR, ICCV, SIGGRAPH, ...) and is a recipient of both the Meta PhD scholarship and the Rabin Ezra scholarship as well as the Eurographics PhD Thesis award 2026. Lessons from the Trenches of Agentic Engineering A candid lessons-learned from running an agentic engineering consultancy with clients ranging from federal governments to early-stage AI startups. I'll cover what's held up under real production pressure, what I tried and abandoned, and the approaches that are quietly dead but still being sold. Expect specifics, opinions, and a few uncomfortable conclusions. About the Speaker John Adeojo - runs Brainqub3 an agentic engineering consultancy serving clients from federal governments to early-stage AI startups, and recently served briefly as CTO of a pre-seed AI startup.
