I have an opening for a two years post-doc position on instance-level (personalized) visual generation. Eligibility: (i) <=7 years from Ph.D. (ii) studies or 1 year outside of Czechia (ii) >=3 journal with IF or CORE A*/A conference papers. Deadline: 15 Feb. Details: www.euraxess.cz/jobs/399390

🚀New task: Instance-level Image+Text→Image Retrieval 🔎Given a query image + an edit (“during night”), retrieve the same specific instance after the change — not just any similar object. 🛢New dataset on HF: i-CIR huggingface.co/datasets/bil... 🔥Download, run, and share results!

1/n REGLUE Your Latents! 🚀 We introduce REGLUE: a unified framework that entangles VAE latents ➕ Global ➕ Local semantics for faster, higher-fidelity image generation. Links (paper + code) at the end👇

✨This NASA/ESA/CSA #Webb Space Telescope image shows the Westerlund 1 cluster, a group of massive stars located in our galaxy which are nearly as bright as a million Suns each. 🌌🎄🧪🔭 🔗 esa.int/ESA_Multimedia/Images/2024/10/The_exotic_stellar_population_of_Westerlund_1

Evaluate your policy on REALM - our new real-to-sim validated benchmark for generalization in robot manipulation! REALM is a good real-world proxy, evidenced by the high correlation with real-world evals. ALSO: Follow the rising star @msedlacek.bsky.social and ask him any questions about REALM!

📣 i-CIR dataset (NeurIPS 25) is now on @hf.co. 🚀Easier download + better discoverability + WebDataset shards for large-scale use (~750K images). 🤗 Grab it here: huggingface.co/datasets/bil... #computervision #retrieval #datasets #huggingface #NeurIPS

Yejin Choi on whether small companies or Labs can compete with big ones on AI and LLMS. Neurips 2025 invited talk.

Heading to #NeurIPS2025? Come by Poster Session 6, Fri 16:30, #4514 🧵 We present instance-level composed image retrieval, the new i-CIR dataset, and our training-free method BASIC. Drop in and say hi!

🤞🏾A few days left for #CVPR submissions. 🪩 If submitting a paper on composed image retrieval, test your method on i-CIR, the real-world, truly compositional dataset. #cvpr2026 #composed_image_retrieval #image_retrieval

🎉 Instance-level Composed Image Retrieval @ #NeurIPS2025 🎨 Task: given (image of an object instance) + (text modification), retrieve photos of that exact instance under the change. E.g.: Temple of Poseidon 🏛️ ➕ during sunset 🌅 📦 Project page: vrg.fel.cvut.cz/icir/

Instance-Level Composed Image Retrieval @billpsomas.bsky.social George Retsinas @nikos-efth.bsky.social Panagiotis Filntisis,Yannis Avrithis, Petros Maragos, Ondrej Chum, @gtolias.bsky.social tl;dr: condition-based retrieval (+dataset) - old photo/sunset/night/aerial/model arxiv.org/abs/2510.25387

🚀 new state-of-the-art on ILIAS dataset! Curious how well the latest models can recognize particular objects? We evaluated the base and large variants of DINOv3 and Perception Encoder (PE) on instance-level image retrieval. See the results 👉 vrg.fel.cvut.cz/ilias/

The Colloquium in Pattern Recognition and Computer Vision of the Visual Recognition Group at CTU in Prague has a long tradition dating back to 1998. The list of all speakers is available docs.google.com/spreadsheets.... Enjoy! The 50th edition is coming soon cmp.felk.cvut.cz/colloquium/

🚨 Deadline Extension Instance-Level Recognition and Generation (ILR+G) Workshop at ICCV2025 @iccv.bsky.social 📅 new deadline: June 26, 2025 (23:59 AoE) 📄 paper submission: cmt3.research.microsoft.com/ILRnG2025 🌐 ILR+G website: ilr-workshop.github.io/ICCVW2025/ #ICCV2025 #ComputerVision #AI

Our remote sensing foundation model Galileo has been accepted to ICML 2025! Galileo outperforms state-of-the-art across different input data modalities and shapes, and using it requires only minimal data and compute. More at: arxiv.org/abs/2502.09356

Can you train a performant language model using only openly licensed text? We are thrilled to announce the Common Pile v0.1, an 8TB dataset of openly licensed and public domain text. We train 7B models for 1T and 2T tokens and match the performance similar models like LLaMA 1 & 2

We will be presenting the 🍄 FungiTastic 🍄, a multimodal, highly challenging dataset and benchmark covering many ML problems at @fgvcworkshop.bsky.social CVPR-W on Wednesday! ⏱️ 16:15 📍104 E, Level 1 📸 www.kaggle.com/datasets/pic... 📃 arxiv.org/abs/2408.13632 @cvprconference.bsky.social

#KostasThoughts: As an AC, it’s frustrating when reviewers only see the rebuttal through the lens of their own review. Step back—consider all reviews and discussions. DON’T rush to finalize; see the FULL picture!

#KostasThoughts: There is no shame getting the initial review wrong, e.g., by missing an important detail. It is wrong when you let your ego get in the way of arriving at the correct decision.

VRG from CTU in Prague has 9 of its members listed as outstanding reviewers. Congratulations to @gkordo.bsky.social, @billpsomas.bsky.social , @stojnicv.xyz , Pavel Suma, @ducha-aiki.bsky.social , Miroslav Purkrábek, Tomas Vojir, and Yaqing Ding.

NeurIPS'25 (abs): 4 days + 2h. NeurIPS'25 (paper): 8 days + 2h.

🚨 Call for Papers! 7th Instance-Level Recognition and Generation (ILR+G) Workshop at @iccv.bsky.social 📍 Honolulu, Hawaii 🌺 📅 October 19–20, 2025 🌐 ilr-workshop.github.io/ICCVW2025/ in-proceedings deadline: June 7 out-of-proceedings deadline: June 30 #ICCV2025

🚀 Calling all Greeks in AI 🇬🇷🤖 Are you researching Computer Vision, NLP, or anything AI-related — and have Greek roots or connections? Join the Greeks in AI Starter Pack to connect and collaborate. 🧵 Follow here: go.bsky.app/Rakqp7M 💬 Reply or DM if you’d like to be added or suggest others!

Greeks in AI is taking off! 🇬🇷🤖 Over 200 signups, 30+ OpenReview submissions, and 🔥 sponsors. 🧠 If you’re in Greece’s AI scene (or want to be), this is the event to attend. 📍 Limited seats at Serafeio — register now: www.greeksin.ai More updates coming soon! #GreeksInAI #AI #ML #Research #Greece

We are back at #ICCV2025 for the second workshop on Hyperbolic and Hyperspherical Learning for Computer Vision. We will have 2 tracks: one for new research (to be published in proceedings) and one for recently published works. Deadline: June 1st Link: sites.google.com/view/beyonde...

Have you ever wondered what makes two models different? We all know the ViT-Large performs better than the Resnet-50, but what visual concepts drive this difference? Our new ICLR 2025 paper addresses this question! nkondapa.github.io/rsvc-page/

Check check check 👌🏽

The Greeks 🇬🇷 in #AI Symposium aims to bring together researchers from #AI, #ML, #ComputerVision, #Robotics, #Neuroscience, & related fields to share their latest research. There are no proceedings, allowing authors to present their already published work to a broader audience. www.greeksin.ai

Exciting News! Shoutout to @hf.co 🤗 for hosting ILIAS in its full scale! You can now easily download it via: huggingface.co/datasets/vrg... This marks a milestone in i2i and t2i retrieval, paving the way for significant advancements in the field. Huge thanks to @hf.co team for their support!

The Visual Recognition Group at CTU in Prague organizes the 49th Pattern Recognition and Computer Vision Colloquium with D. Karatzas, M. Masana, T. Tommasi, P. Mettes @pascalmettes.bsky.social , E. Brachmann @ericbrachmann.bsky.social and V. Stojnic @stojnicv.xyz cmp.felk.cvut.cz/colloquium/#...

ILIAS is a large-scale test dataset for evaluation on Instance-Level Image retrieval At Scale. It is designed to support future research in image-to-image and text-to-image retrieval for particular objects and serves as a benchmark for evaluating foundation models and retrieval techniques.

1/n🚀If you’re working on generative image modeling, check out our latest work! We introduce EQ-VAE, a simple yet powerful regularization approach that makes latent representations equivariant to spatial transformations, leading to smoother latents and better generative models.👇

🚀Exciting news🚀 I’ve been awarded the Marie Skłodowska-Curie Postdoctoral Fellowship (#MCSA-PF) 2024 with 98/100!🎉 🥟My project, RAVIOLI, hosted at CTU in Prague, under @gtolias.bsky.social, integrates retrieval-augmented predictions into vision-language models for open-vocabulary segmentation.

For PhD and MSc students interested in a research visit to Prague/VRG in 2025: we're open to hosting short-term collaborations or internships on a range of computer vision topics. If this sounds exciting, reach out by e-mail! We'd love to discuss potential projects. Some examples 🧵 #Internship #CV

1/n 🚀 Excited to share our latest work: DINO-Foresight, a new framework for predicting the future states of scenes using Vision Foundation Model features! Links to the arXiv and Github 👇

🧵 1/ Big news! Our WACV 2025 paper, "Composed Image Retrieval for Training-Free Domain Conversion", has been selected for an Oral Presentation! 🎤✨

Team members on bluesky: @gkordo.bsky.social @billpsomas.bsky.social @nikos-efth.bsky.social @psuma.bsky.social @stojnicv.xyz @annetka.bsky.social

A late introduction: I am an Associate Professor at CTU in Prague and a computer vision researcher at the Visual Recognition Group (VRG - vrg.fel.cvut.cz). VRG consists of about 40 members and I am leading a small team within VRG. I am made in Greece and exported to France + Czech Republic 🧵⬇️

Image Matching Workshop is accepted to #CVPR2025. You know the drill - we will have IMC challenge, papers and invited talks, all as usual. P.S. Website will be updated later image-matching-workshop.github.io @atabb.bsky.social @cvprconference.bsky.social

Entropy is one of those formulas that many of us learn, swallow whole, and even use regularly without really understanding. (E.g., where does that “log” come from? Are there other possible formulas?) Yet there's an intuitive & almost inevitable way to arrive at this expression.

From @fchollet.bsky.social over on the other site. "they demand serious scientific attention" -- indeed! But how to do science on these results without more openness?

New to Bsky and interested in #computervision? Check out my 2 Starter Packs of #computervision researchers. go.bsky.app/M7HGC3Y go.bsky.app/Gjcs339

Excited to present UDON at NeurIPS '24 tomorrow (Thursday 12/12)! If you are interested in a scalable training method for multi-domain image embeddings, come to poster #1410 in the East Exhibit Hall A-C of the Vancouver Convention Center from 11 am to 2 pm (PST) to discuss!

1/ 🎉 Excited to share our work, "Composed Image Retrieval for Training-Free Domain Conversion", accepted at WACV 2025! 🚀

🚀 New paper alert: FREEDOM is here! Check out “Composed Image Retrieval for Training-FREE DOMain Conversion,” our training-free method for domain conversion with VLMs. 🎯 📜 WACV 2025 💡 Retrieve images using image+text queries! 📖 arxiv.org/abs/2412.03297 🔗 github.com/NikosEfth/fr... #WACV2025 #AI

#Bluesky passes 23M users 🦋

It blows my mind that NASA is able to receive data from 4.67 billion miles away, but I lose Wi-Fi signal in my kitchen.

Our starter pack 🎉

Here are my thoughts about Bluesky based on a couple weeks of experience using it. tl;dr: very, very impressive

🆕 Submit a “highly irresponsible” #CVPR2025 review, your paper submissions will be desk rejected. More info: cvpr.thecvf.com/Conferences/...