Great session hearing from the successful #ECRs who secured Engineering and Physical Sciences Research Council capital funds. If you didn't make the #showcase check out the winners and the equipment ⬇️ and get in touch!! ☎️ #collaboration #interdisciplinary

Wooah!! After a year, back with the CVAS group.. Some old faces, many new faces! That mafia look on everybody's face😂😂.. We seriously lack some female researchers!!

This is a video I made 9 months ago, when I was applying for some project grants on robotic automation. Never tweeted about it. Though, it ends a bit abrupt, check it out. Got some good feedback from the experts! youtu.be/yFx_GmHTiIE

Checkout my article on Robot learning, where we drastically reduce the training time for pick-place tasks. "Current robotic systems can outperform humans in specific tasks, but when it comes to generality, humans tend to be way better" CVAS group @ger_ac83 medium.com/cvas-uofg/maki…

Looking forward to virtual #ICRA2020 starting soon! Flagship #Robotic conference Checkout our work "On Simple Reactive Neural Networks for Behaviour-Based Reinforcement Learning" Video link: youtu.be/dkN3YhNy32k Paper link: arxiv.org/abs/2001.07973 @ger_ac83

We would be organising Summer school on Surgical robots (COSUR2020) in Barcelona in End September. Check it out! Do circulate the call to the ones who might be interested. #Robotics #control #medical

Event on 24th Nov to launch our new Glasgow University Software Service to local SMEs & 3rd sector orgs. Delivered by our students and run by the School. uofg-socs-guss-2020.eventbrite.com UofG SciEng University of Glasgow UofGGAs Glasgow Chamber FSB Scotland Interface DIGIT RT

In our paper, w/ Amey Pore, Bjørn Sand Jensen and @ger_ac83, we explore the concept of introspection in a deep neural network setting. We build an internal state, an abstract representation, from the neural network activations. UofG Computing Science CVAS group

We bring you more talks! Join us over on @zoom_us to hear about the use of reinforcement learning in science. Our very own Valentin Charvet will be giving us an introduction to and overview of the field, while @ger_ac83 will be sharing how he uses RL in his research in robotics 🤖

Finally managed to successfully pick and place a cube using #teleoperation on the #baxter robot using #isaacsim for inverse kinematics! Making great strides into a child safe chess playing robot ! @ger_ac83 UofG Computing Science

Aman Goel IIIT Hyderabad presented our work focuses on controllability on synthesizing close leader-follower interactions at #SCA2022 today. Code, preprint and video: github.com/Aman-Goel1/IMM CVAS group UoG IDA Section, Glasgow CS UofG Computing Science

Happy to announce our work on enhancing out-of-distribution generalisation in object-centric world models has been accepted at #NeurIPS2022! A quick summary... UofG Computing Science UoG IDA Section, Glasgow CS School of Informatics, The University of Edinburgh Snap Inc. NeurIPS Conference

New preprint on an unusual topic for me – determining quantum band-structure parameters of a 2D material (ABA graphene). This was a fun collaboration involving lots of physics that I don't understand (expertly handled by Maksym Serbyn and Areg Ghazaryan of ISTAustria)

Enjoy 3D? and diffusion models? Check out our #CVPR2023 paper RenderDiffusion, on how to train a 3D diffusion model using only 2D images! UofG Computing Science UoG IDA Section, Glasgow CS CVPR News 1/7

Having fun at the BMVA Summer School (in exotic Norwich!), talking about some of our work on structured/3D generative models. Thanks BMVA Summer School for the invitation! UoG IDA Section, Glasgow CS CVAS group

Happy to announce our work on generative 3D reconstruction "Denoising Diffusion via Image-Based Rendering" is accepted at ICLR 2026. Created by Titas Anciukevičius, partly during his Google-internship with Federico Tombari and Fabian Manhardt A quick summary... CVAS group UoG IDA Section, Glasgow CS