Ingmar Posner
168 posts
Ingmar Posner
@IngmarPosner
Applied Machine Learner, Roboticist, Professor at University of Oxford.
เข้าร่วม Şubat 2017
284 กำลังติดตาม1.9K ผู้ติดตาม
Are world models the missing piece for truly dexterous tactile robots? 🤖
Great to join the @ARIA_research programme meeting on robot dexterity to discuss how predictive models perform in contact-rich settings.
#WorldModels #Robotics #ARIA @a2i_oxford @oxfordrobots
English
@ahmedkar_ Thanks! And I agree. Pixel-level prediction has been incredibly useful, but it’s often a poor proxy for relevance. What we’re really after is structure that reflects influence on behaviour, not fidelity of reconstruction.
English
@IngmarPosner Love this, especially as a contrast to video prediction objectives. Optimising for exact pixel reconstruction is unrealistic yet that’s where much of current world model research still focuses.
Brilliant work!
English
A recurring theme in our recent work (e.g. SPARTAN): predictive world models become more interpretable when they help identify which parts of the input stream actually influence behaviour.
Learning what matters, not just what happens, is central.
arxiv.org/pdf/2411.06890
Anson Lei@AnsonISL
Very excited to share our new work - SPARTAN: A Sparse Transformer Learning Local Causation. We develop a Transformer world model that learns local causal dependencies between entities, leading to improved adaptation efficiency and robustness with accurate prediction. 🧵
English
On my way to the 7th UK Manipulation W/s - a great way to start 2026! Over the years it’s become a premier UK meeting place for exchanging ideas across planning, control, and learning in robot manipulation.
If you’re attending, do come say hello.
robot-manipulation.uk
English
Our contributions at #CoRL2025 👇
Main Conference:
- D-Cubed: openreview.net/forum?id=5htQM…
- COMBO-Grasp: openreview.net/forum?id=xpEjj…
GenPrior workshop:
- Guaranteed SE(3) Equivariant Control: corl25-genpriors.github.io/Papers/15_Guar…
English
Always look forward to CoRL - for the people, papers & workshops. Sadly have to miss it this year.
Delighted that @junjungoal & Alex Mitchell are there representing A2I - and @JankowskiJulius is presenting new work from our Amazon team! 🎉
See you next year!
English
NVIDIA’s £2bn pledge to UK AI startups is recognition that we don’t just use AI: we invent it, shape it & apply it.
As @UniofOxford researcher & co-founder of a successful AI startup, I was proud to be in the room. #AI #UKTech
English
Had a great time sharing @a2i_oxford’s work on generative AI for robot & world models at the @royalsociety #SummerScience Exhibition 2025. Great energy, excellent questions!
🎥 Watch here: royalsociety.org/science-events…
@oxfordrobots @oxengsci #RobotLearning #GenerativeAI #Robotics
English
🎓 Multiple faculty positions @oxengsci ! 🎓
We welcome applications from outstanding candidates in robotics, and especially if you are working in areas such as human-robot interaction, mechanical design, novel robotic sensor design and/or field robotics. Closing soon...🚀
Maurice Fallon@MauriceFallon
Multiple faculty positions at University of Oxford in @oxengsci - Join Us! Robotics - Computer Vision - Machine Learning Faculty positions in Oxford are typically linked to a college. Please repost!
English
Amongst my favourite research directions this year: understanding model complexity and its link to generalization and intelligence. Progress here could mean leaner models, versatile representations, and less reliance on data/energy. Excited that we’re off to the races on this!
Branton DeMoss@BrantonDeMoss
I’m pleased to announce our work which studies complexity phase transitions in neural networks! We track the Kolmogorov complexity of networks as they “grok”, and find a characteristic rise and fall of complexity, corresponding to memorization followed by generalization. 🧵
English
2️⃣ RAINZ CDT (w/ @UKAEAofficial): Robot manipulation for net-zero energy systems (assembly/disassembly focus).
🗓 Deadline: 31 Jan 2025
👉 rainz-cdt.ac.uk
English
1️⃣ AIMS CDT (@Amazon-supported, w/ @j_foerst): Foundational work on learning & curating versatile world models.
🗓 Deadline: 29 Jan 2025
👉 aims.robots.ox.ac.uk/study/industry…
English
🚀 Funded PhD Studentship Alert! 🚀
Join @a2i_oxford in our mission to advance World Models for robotics and beyond. Two opportunities starting Oct 2025. Deadlines in January 2025. Details in 🧵… @oxfordrobots
🤖 #Robotics #ArtificialInteligence #MachineLearning
English
How can a transformer uncover local causal dependencies in dynamic systems, from simulations to real-world data? 🤔
The answer: Hard attention + sparsity. But with a twist.
Meet SPARTAN: More causal. More efficient. Just as accurate.
#Robotics #ML #AI #CausalAI
Anson Lei@AnsonISL
Very excited to share our new work - SPARTAN: A Sparse Transformer Learning Local Causation. We develop a Transformer world model that learns local causal dependencies between entities, leading to improved adaptation efficiency and robustness with accurate prediction. 🧵
English
🚀 Join us to push the boundaries of AI and robotics, working on cutting-edge research in real-world robot learning. You'll focus on developing multimodal world models with impactful applications in collaborative manufacturing and social care.🤖 #robotlearning #GenerativeAI
Oxford Applied AI Lab@a2i_oxford
🚀 We’re hiring a Postdoc in Multimodal World Modelling for robot skill acquisition! 🌟 Do you have a passion for deploying AI on real-world robots? Then this one may be for you... my.corehr.com/pls/uoxrecruit… #robotlearning #Robotics #GenerativeAI #MachineLearning #AI @oxfordrobots
English
On my way to #ICRA2024. Looking forward to Japan! Looking forward to seeing old friends and making new ones! And looking forward to presenting some of the work from @a2i_oxford and collaborators in Yokohama with @Jack_T_Collins, @junjungoal and @jannikzuern…
Oxford Applied AI Lab@a2i_oxford
Delighted to be at #ICRA2024. Interested in effective sim-2-real transfer for world models (WeBT7-CC.6)? Or benchmarking for robot assembly (ThAT9-CC.3)? Or predicting lane graphs for autonomous driving (ThBT6-CC.2)? Come and see us to meet, discuss, or just hang-out...
English
RIP Daniel Kahneman. And thank you for the inspiration… behavioralpolicy.princeton.edu/news/DanielKah…
English
Trajectory optimisation in high dimensional spaces is notoriously hard. What if you could leverage basic experience of what the system can do and let a diffusion model and vanilla sim guide you? Stunning work led by @junjungoal with @ShaohongZhong and @Jack_T_Collins @a2i_oxford
Jun Yamada@junjungoal
We introduce D-Cubed, a novel trajectory optimisation method using a latent diffusion model trained from a task-agnostic play dataset, including only representative hand motions, to solve dexterous deformable object manipulation tasks! (1/N)
English