ML PhD @ucl | @adobe | ex @nvidia | @ELLISforEurope | Interested in visual generation
London, UK
Joined July 2012
- Tweets165
- Following478
- Followers347
- Likes1.1K
Pinned Tweet
🎉 LoST: Level of Semantics Tokenization (CVPR 2026)
What if 3D generation didn’t start from coarse geometry, but from semantics?
We introduce LoST, a semantic-first 3D tokenizer that orders tokens by semantic salience, so even very short prefixes can already decode into complete, plausible, recognizable 3D shapes 🧩
Early tokens capture the principal semantics.
Later tokens refine the details.
Result: Generate 3D shapes starting from as few as 1 token!
The goal is to have high fidelity shapes even with very few tokens, with more tokens semantic alignment increases.
Project: lost3d.github.io/
Paper: arxiv.org/abs/2603.17995
@CVPR @AdobeResearch @Adobe
Really cool work and shows how one can enable various levels of detail during generation.
Checkout our #CVPR 2026 work on 3D generation-- Level of Semantics Tokenization for 3D Shapes
lost3d.github.io/
Code is now released.
Diffusion models spend the same compute on a blank wall as on a face. But you often know in advance where the detail will be.
Introducing Level-of-Token (LoT) Diffusion: we turn that knowledge into a multiresolution token layout, with fine tokens where detail is needed and coarse tokens elsewhere.
1/9🧵
4
226
Excited to announce the @TheBMVA Symposium on World Models! 🌍
📍 London | 🗓 Nov 18, 2026
We have an amazing lineup of speakers joining us! Check out the full program, registration, and poster submission details:bmva.org/meetings/26-11-18-W…
#AI #worldmodels #computervision
Join us at the Visual Concepts Workshop at CVPR!
The Visual Concepts Workshop is coming soon to @CVPR 2026!
Join us on June 4 for an exciting discussion on all aspects of visual concepts: from discovery and reasoning, to controllable generation, robotics, and more!
Hope to see you in Denver! #CVPR
3
247
Excited to share the 3rd Workshop on Visual Concepts at @CVPR 2026! Call for papers is now open till April 1. We welcome submissions on the following topics. See our website for more info: sites.google.com/stanford.ed…
Join us in Denver!
#CVPR2026
Animation brings characters to life 🎬✨
Introducing our #SIGGRAPHAsia '25 (TOG) paper:
Self-Supervised Motion Fields (SMF) that can transfer motion from any source (even 2D video) to any stylized character!
🚫 No Rigging 🚫 No Templates (SMPL) ✅ Any source
🧵Thread👇
Can an LLM learn professional photo retouching by solving puzzles?
Our new work, MonetGPT, presented at #SIGGRAPH2025, shows it can.
By solving visual puzzles, our MLLM becomes operation-aware and develops image aesthetics.
Check out our blog from @AdobeResearch & code below👇
#AI #MLLM
2
7
322
✍️ Blog Post: research.adobe.com/news/adob…
💻 GitHub: github.com/niladridutt/monet…
🌐 Project Website: monetgpt.github.io/
1
1
134
Hi Londoners
Join us on April 15 for an evening on Gen AI for 3D at UCL! We have an amazing list of keynote speakers and lightning talks. Register at londongenai.github.io
Very excited to co-organize this with Michael and Preddy!
1
96
Come check out our #ECCV2024 poster today- Temporal Residual Jacobians for Rig-free Motion Transfer
📅 10/1 (Today) 4:30 PM - 6:30 PM
📍Poster #216
🔗 temporaljacobians.github.io/
13
328
Thanks @_akhaliq for featuring our paper on @huggingface
Excited to share that our work-Temporal Residual Jacobians has been accepted at #ECCV'24!
@eccvconf
Temporal Residual Jacobians For Rig-free Motion Transfer
We introduce Temporal Residual Jacobians as a novel representation to enable data-driven motion transfer. Our approach does not assume access to any rigging or intermediate shape keyframes, produces geometrically and
1
8
652
Paper- arxiv.org/abs/2407.14958
Project website- temporaljacobians.github.io/
142
🧵I'm excited to share that our paper "Diffusion 3D Features (Diff3F): Decorating Untextured Shapes with Distilled Semantic Features" has been accepted at @CVPR 2024! A big thank you to my co-authors.
Project page- diff3f.github.io/
arXiv- arxiv.org/abs/2311.17024
#CVPR2024
Thank you for sharing our work!
You can find more details and visual results on our project website- proteusnerf.github.io/
ProteusNeRF: Fast Lightweight NeRF Editing using 3D-Aware Image Context
Binglun Wang, Niladri Shekhar Dutt, Niloy J. Mitra
tl;dr: simple, fast, and lightweight NeRF editing setup
arxiv.org/pdf/2310.09965.pdf
We were a team of 6 when we started building @nftport_xyz . Can't believe how far we've come in just 1 year! 🚀🌚
Andrew Ng's latest newsletter just arrived!
Here's some wisdom on the difference between thinking tactically and thinking strategically.
@deeplearningai_
1
7
So much for Open Source
GitHub confirms it has blocked developers in Iran, Syria, and Crimea techcrunch.com/2019/07/29/gi…
6