Abdulrahman Kerim, PhD

AAAI'26 (paper): 3 days + 2h. 3DV'26: 19 days. WACV'26 (R2,reg): 45 days. WACV'26 (R2,paper): 52 days. ICLR'26 (abs): 52 days. ICLR'26 (paper): 57 days.

The AI Adoption Dilemma in UK Businesses for 2024-2025 imperial-academic.com/ai-%26-life-bl… #AIinBusiness #UKBusiness #ArtificialIntelligence #Innovation #FutureReady

Surrey Space Centre’s new electro-thermal rocket awarded £250,000 by @spacegovuk's Enabling Technologies programme. This technology could be used in “space-tugs” to service and reposition satellites after launch ow.ly/iAKr50OUMPS @SpaceAtSurrey #ProudtobeSurrey

If you need 45 minutes of motivational videos to do 10 minutes of work, probably you are doing something wrong!

Linux users 😎💪💪 #Microsoft #Windows #crowdstrike #Infosys

🎉 Calling all researchers! 🚀 The countdown is on! ⏳ Round 1 submission deadline for #WACV2025 is just around the corner: JULY 15TH! 🗓️ 🌟 Get those papers ready and submit! 📚✨

Can generative image models be good world models? This work from @Meta FAIR shows that there is a tradeoff between realism and diversity. The more realistic a generative model becomes, the less diverse it becomes. Realism comes at the cost of coverage. In other words, the most realistic systems are mode-collapsed. My hunch, supported by a growing amount of empirical evidence, is that world models should *not* be generative. They should make predictions in representation space. In representation space, unpredictable or otherwise irrelevant information is absent. This is the main argument in favor of JEPA (Joint Embedding Predictive Architectures).

Just spotted an incredible robot 🤖 from Disney Research at @CVPR! It's amazing to see robot in animation come to life in the real world. 🌟 #Robotics #CVPR2024

BMVA Symposium: Robotics Foundation World Models One day BMVA Symposium in London, 30 October 2024 bmva.org/meetings/24-10… *** The deadline for submitting a presentation is 15th September, 2024. Submit interest through docs.google.com/forms/d/1cU4F-…

Your premise is false. Intelligent systems require the ability to reason and plan. Reasoning and planning involve a search for solutions (actions) that minimize objectives. Those objectives measure not only whether the imagined actions fulfill a goal but also whether a number of guardrails are satisfied. By construction, such a system can not produce any action that will violate the guardrails, according to the predictions of its internal world model. I call this objective-driven AI. The question becomes one of designing appropriate guardrails. We are familiar with that. It's like making laws. Except that objective-driven systems will be completely unable to violate these laws (unlike humans).

What happens when AI meets quantum computing? This is just one of the questions our panel of world-leading experts will be discussing in a free online webinar on Wednesday 5th June 2024. Register for your free ticket now bit.ly/futureofQC

@2sush Try to explain the code to someone or pretend to do that with myself!

what's your tactics ?

NeurIPS'24: 3 days. CORL'24: 18 days. ACCV'24: 44 days. WACV'25-R1: 57 days. WACV'25-R2: 113 days.

Here's my conversation with Sam Altman (@sama), his 2nd time on the podcast. We talk about the board saga, Elon lawsuit, Ilya, Sora, GPT-5, $7 trillion in compute, open source, and AGI. This was a truly fascinating conversation. It's here on X in full, and is up on YouTube, Spotify, and everywhere else. Links in comment. Timestamps: 0:00 - Introduction 1:05 - OpenAI board saga 18:31 - Ilya Sutskever 24:40 - Elon Musk lawsuit 34:32 - Sora 44:23 - GPT-4 55:32 - Memory & privacy 1:02:36 - Q* 1:06:12 - GPT-5 1:09:27 - $7 trillion of compute 1:17:35 - Google and Gemini 1:28:40 - Leap to GPT-5 1:32:24 - AGI 1:50:57 - Aliens

Per several requests, here are the PowerPoint slides for the diffusion model tutorial. 1⃣Training: bit.ly/3WudEPH 2⃣Guidance: bit.ly/3wedCky 3⃣Resolution: bit.ly/4bqxHmo 4⃣Speed: bit.ly/4bpJzoJ Explainer video: youtu.be/i2qSxMVeVLI

I have just got my own copy! #MachineLearning #DeepLearning #ComputerVision #XML #books

"The best time to plant a tree was 20 years ago. The second best time is now." -Old Chinese Proverb

Every time a league table comes out, as academics, we struggle about what to do with the results, no matter whether they're good or bad Why? Well, league tables are far from perfect. Doesn't matter the league. Doesn't matter the table. It has problems. Guaranteed 1/13

Ever asked yourself what's the best explainability method for ViT Transformer at the moment? 🚨 We present you LeGrad, a Layerwise Explainability GRADient method for large ViT transformer architectures. 🚨 So, grab your ☕️ and 🥐, release your inner 🇫🇷, and join us on our journey through the layers of different ViT models. Authors: @BousselhamWalid did all the programming, but we would have been lost without the wisdom of @angie_boggust and @hen_str ! Thanks so much for being so great collaborators! @MIT_CSAIL @MITIBMLab

@Adel_Bibi @YorkUniversity @LassondeSchool twitter.com/csprofkgd/stat…