iiinova — where your digital self keeps evolving

Bill Psomas @billpsomas.bsky.social · 16/09/2026

🔥 Composed image retrieval, as it should be. 📸 i-CIR (NeurIPS 2025): a photo says which particular object, a text says how it should look. 🔍︎ Explore every composed query in our new dataset browser: vrg.fel.cvut.cz/icir/ More to come... #ComputerVision #ImageRetrieval #AI #MultimodalSearch

vrg.fel.cvut.cz

i-CIR: Instance-Level Composed Image Retrieval (NeurIPS 2025)

A photo says which object, a text says how it should look. 202 instances, 1,883 composed queries, 752K curated hard negatives as hard as 40M random distractors, and an interactive dataset browser.

161

Reposted by Bill Psomas

TMLR Published Papers @tmlr-pub.bsky.social · 12/09/2026

Instance-Level Generation for Representation Learning Yankun Wu, Zakaria Laskar, Giorgos Kordopatis-Zilos, Noa Garcia, Giorgos Tolias Action editor: Brian Kulis openreview.net/forum?id=T3JgJXH3ZK #datasets #recognition #instance

072

Reposted by Bill Psomas

VisionBernie - Bernhard Egger @visionbernie.bsky.social · 11/09/2026

"I'm looking for a postdoc" "3D Computer Vision" 🎤🫳 #ECCV2026 And yes, I really am looking for a postdoc @csprofkgd.bsky.social please spread the world

4176

Reposted by Bill Psomas

Kosta Derpanis @csprofkgd.bsky.social · 11/09/2026

Greeks at #ECCV2026 💪

2183

Reposted by Bill Psomas

Pier @pierl.bsky.social · 06/09/2026

Most of what @thegoodailab.bsky.social does can be described as building a connection. A bridge between frontier AI research and humanitarian action, education, and sustainability. 🌱🧵 cv4good.thegoodailab.org w/@msf.org

cv4good.thegoodailab.org

CV4GOOD — Computer Vision for Humanitarian Action

ECCV 2026 workshop in Malmö, Sweden on Tuesday, September 8, 2026, pairing CV researchers with humanitarian practitioners from MSF.

1106

Bill Psomas @billpsomas.bsky.social · 21/08/2026

🎉 Our #ICLR26 paper on efficient probing (EP) now has a home that outlives the paper. ⏱️ Probing Frozen Encoders — a standing ImageNet-1k benchmark for k-NN, linear (LP) and efficient probing (EP). Built to stay. Issues and PRs welcome 👇 github.com/billpsomas/e...

github.com

GitHub - billpsomas/efficient-probing: [ICLR 2026] - Official implementation of "Attention, Please! Revisiting Attentive Probing Through the Lens of Efficiency"

[ICLR 2026] - Official implementation of "Attention, Please! Revisiting Attentive Probing Through the Lens of Efficiency" - billpsomas/efficient-probing

172

Reposted by Bill Psomas

Klara Janouskova @klara-cz.bsky.social · 07/08/2026

We needed region annotations. We looked at what already existed… and we decided to build our own dataset. Meet STRAP 🎉 🤗 huggingface.co/datasets/vrg-prague/STRAP 🔗 klarajanouskova.github.io/STRAP Region–text annotations for 2M web images, from a single pass of a frozen open MLLM. 🧵

165

Bill Psomas @billpsomas.bsky.social · 17/07/2026

🎥 @tim-arav.bsky.social presenting our #CVPR26 highlight paper ⭐ RNS in a spotlight talk at @greeksinai.bsky.social. An overview of how a few retrieved, annotated examples can help bridge the gap between open-vocabulary and fully supervised segmentation. Watch below 👇 📄 arxiv.org/abs/2602.23339

021

Bill Psomas @billpsomas.bsky.social · 21/06/2026

🎉 REGLUE accepted at #ECCV2026 🎉 🎨 A unified framework jointly modeling VAE latents ➕ global ➕ local VFM semantics for faster, higher-fidelity diffusion image generation. 💨 Matches 1M-step SOTA in just 700k iterations (~30% fewer steps). 🌐 reglueyourlatents.github.io More info below👇

190

Reposted by Bill Psomas

fravery.bsky.social @fravery.bsky.social · 08/06/2026

Kevin Kia The Two Doors

281912184

Bill Psomas @billpsomas.bsky.social · 06/06/2026

🚨 Presenting today at #CVPR2026! Our highlight ⭐ paper Retrieve and Segment (RNS) asks a simple question: Can a few examples bridge the supervision gap in open-vocabulary segmentation? ✅ Turns out they can. 📍 Poster #578 ⏰ 16:45–18:45 📄 arxiv.org/abs/2602.23339

0103

Reposted by Bill Psomas

Giorgos Tolias @gtolias.bsky.social · 25/05/2026

The instance level recognition and generation workshop will be back at @eccv.bsky.social 2026. With excellent keynote speakers, a call for papers, and travel grants for students.

0124

Reposted by Bill Psomas

Giorgos Tolias @gtolias.bsky.social · 31/05/2026

Vision Transformers are brittle to variable input resolutions. In dense prediction tasks, the standard fix is sliding-window inference with heavy overlap, which is effective but painfully slow. SPAR (Single-Pass Any-Resolution ViT), takes a different approach.

1143

Reposted by Bill Psomas

Giorgos Tolias @gtolias.bsky.social · 04/06/2026

Our work Global-Aware Edge Prioritization for Pose Graph Initialization is a CVPR 2026 oral paper and award candidate. Oral: Sun, Jun 7, 10:15 — 11:30 at Bluebird Ballroom (Oral Session 5A: Dynamic Perception) 📎 Poster: Sun, Jun 7, 11:45 AM — 1:45 PM at ExHall F (Poster Session 5), Poster #2

172

Reposted by Bill Psomas

Dmytro Mishkin @ducha-aiki.bsky.social · 04/06/2026

Get ready to Image Matching Workshop 2026 today at @cvprconference.bsky.social Room: 504 13:00 local time 3 star speakers: ⭐ @pesarlin.bsky.social ⭐ Nikhil Keetha ⭐ @jianyuanwang.bsky.social ✅10 papers ✅IMC2026 story #CVPR2026

0115

Reposted by Bill Psomas

Giorgos Tolias @gtolias.bsky.social · 04/06/2026

Indexing Multimodal Language Models for Large-scale Image Retrieval - CVPR 2026 Findings paper A multimodal LLM (like Qwen) can estimate image-to-image similarity remarkably well without any task-specific training. 📍 Main conference — Poster #12, ExHall A 📅 Sun 7/6, 7:30–9:00

1103

Reposted by Bill Psomas

Klara Janouskova @klara-cz.bsky.social · 03/06/2026

📍 @c1rcuslegend.bsky.social is presenting our work at #CVPR2026 Findings, find the poster with the most 🐈🐾 🗓 Friday, 07:00–08:30 📌 ExHall A; Poster #166 Stop by if you're curious whether MLLMs make good classifiers or to discuss our "Doomed to Reannotate" ImageNet project (preprint coming soon) 📝

042

Reposted by Bill Psomas

Giorgos Tolias @gtolias.bsky.social · 03/06/2026

𝑹𝒆𝒕𝒓𝒊𝒆𝒗𝒆 𝒂𝒏𝒅 𝑺𝒆𝒈𝒎𝒆𝒏𝒕 (𝑹𝑵𝑺) at CVPR 2026 — selected as a 🌟 𝑯𝒊𝒈𝒉𝒍𝒊𝒈𝒉𝒕 🌟 (top ~4% of submissions)! 𝗪𝗵𝗲𝗿𝗲 𝘁𝗼 𝗳𝗶𝗻𝗱 𝘂𝘀 𝗮𝘁 𝗖𝗩𝗣𝗥 𝟮𝟬𝟮𝟲 (𝗗𝗲𝗻𝘃𝗲𝗿): 🔹 𝑴𝒂𝒊𝒏 𝑪𝒐𝒏𝒇𝒆𝒓𝒆𝒏𝒄𝒆 Poster Session 4 (#578) — June 6, 16:45–18:45 🔹 𝑾𝒉𝒂𝒕 𝒊𝒔 𝑵𝒆𝒙𝒕 𝒊𝒏 𝑴𝒖𝒍𝒕𝒊𝒎𝒐𝒅𝒂𝒍 𝑭𝒐𝒖𝒏𝒅𝒂𝒕𝒊𝒐𝒏 𝑴𝒐𝒅𝒆𝒍𝒔? Workshop — June 3, 14:30–16:00

185

Bill Psomas @billpsomas.bsky.social · 03/06/2026

🚀 Reminder: Our #CVPR2026 highlight ⭐ paper "Retrieve and Segment" will be presented today at the What is Next in Multimodal Foundation Models? Workshop. 🕝 Today, 14:30–16:00 📄 Paper: arxiv.org/abs/2602.23339 💻 Code: github.com/TilemahosAra... Looking forward to the discussions and feedback!

1102

Bill Psomas @billpsomas.bsky.social · 01/06/2026

🎉This week at #CVPR2026, we’ll be presenting Retrieve and Segment (RNS), our ⭐ highlight paper. 📍 Poster Session 4 (#578) 🗓️ June 6, 16:45–18:45 📄 Paper: arxiv.org/abs/2602.23339 💻 Code: github.com/TilemahosAra... 🌐 Page: vrg.fel.cvut.cz/rns/ See you in Denver!

160

Bill Psomas @billpsomas.bsky.social · 01/06/2026

🚀 Instance-Level Composed Image Retrieval 💥Given a query image + a text modification, the goal is to retrieve the same particular object after the change — not just any semantically similar object. 📦 Dataset: huggingface.co/datasets/bil... 💻 Code: github.com/billpsomas/i... #VLM #AI #MultimodalAI

020

Reposted by Bill Psomas

Noa Garcia @noagarciad.bsky.social · 27/05/2026

The Instance-Level Recognition and Generation workshop is back at ECCV 2026! For the first time, this edition will have best paper award prizes and student support grants. Submit your paper by June 26.

061

Reposted by Bill Psomas

International Conference on 3D Vision @3dvconf.bsky.social · 26/05/2026

Looking for a nice home for your paper? #3DV2027 is waiting! 🎉 ⏰ Conference dates: April 6-9, 2027 ✈️ Place: #Thessaloniki (#SKG), #Greece 🇬🇷 📝 Paper ddl: Aug 28 🎥 Supp ddl: Sep 02 🆕 Rebuttal only upon invite for borderline papers #CallForPapers: 3dvconf.github.io/2027/call-fo...

0114

Bill Psomas @billpsomas.bsky.social · 13/05/2026

📢 Deadline Extended! 🇬🇷🤖 The submission deadline for the #GreeksInAI 2026 Symposium has been extended to May 25🎉 More time to submit your latest work in AI, ML, CV, NLP, Robotics & more🚀 📍Athens, July 15–17 📄Link: openreview.net/group?id=gre... #AI #MachineLearning #ComputerVision #NLP #Robotics

openreview.net

Greeks in AI 2026 Symposium

Welcome to the OpenReview homepage for Greeks in AI 2026 Symposium

020

Bill Psomas @billpsomas.bsky.social · 29/04/2026

🇬🇷 Reminder: the Call for Papers for #GreeksInAI 2026 is open! 📍Eugenides Foundation, Athens 📅15–17 July 2026 📝Submission deadline: 15 May 2026 We invite submissions on recent/ongoing/emerging work in AI/ML worldwide. Submit via: openreview.net/group?id=gre...

openreview.net

Greeks in AI 2026 Symposium

Welcome to the OpenReview homepage for Greeks in AI 2026 Symposium

021

Bill Psomas @billpsomas.bsky.social · 24/04/2026

🇧🇷 Presenting our ICLR 2026 paper “Efficient Probing” (EP) today! ❓What if linear probing is asking the wrong question? 🥳 EP is a lightweight attention probing method that better evaluates local, patch-level representations from models like MIM. 📍Friday 24 April, P4-#3713, 15:15–17:45

0157

Reposted by Bill Psomas

Pavel Suma @psuma.bsky.social · 23/04/2026

🚨 Efficient Local Visual Similarity (ELViS) @ #ICLR 2026 🇧🇷 ELViS is a fast, lightweight, and interpretable module for estimating image-to-image similarity that generalizes well to many image domains. Paper: arxiv.org/abs/2603.28603 Code: github.com/pavelsuma/ELViS Come see poster today @ P4-#3715

1147

Bill Psomas @billpsomas.bsky.social · 18/04/2026

🚨 Efficient Probing (EP) @ #ICLR 2026 🇧🇷 Models trained to learn local representations (e.g., MIM) are often undervalued by standard global evaluation. 👉 EP unlocks their potential via attention-based aggregation. Paper: arxiv.org/abs/2506.10178 Poster 👇 See you in Rio! 🌴

020

Bill Psomas @billpsomas.bsky.social · 09/04/2026

🎉 RNS is a Highlight paper at #CVPR 2026 🎉 💡1.5 years ago, just after finishing my PhD, I wrote my #MSCA PF proposal around a simple idea: can memory extend VLMs for open-vocabulary segmentation? 🎉 Today, the first paper is a CVPR Highlight. 🎯 From idea → funded project → highlight paper.

150

Bill Psomas @billpsomas.bsky.social · 24/03/2026

🚀 This week at #ELLIS Winter School: our #CVPR2026 paper Retrieve and Segment (RNS) is being presented by @tim-arav.bsky.social. 🎯 RNS shows how a few pixel-level annotated images can boost zero-shot Open Vocabulary Segmentation. 📝 arxiv.org/pdf/2602.23339 #ComputerVision #FoundationModels #OVS

040

Bill Psomas @billpsomas.bsky.social · 23/03/2026

🚀 New task: Instance-level Composed Image Retrieval 🔎 Given a [query image] + [query text], retrieve the particular object after the change — not just any similar object. 🛢 New dataset on HF: i-CIR huggingface.co/datasets/bil... 📄 Project page: vrg.fel.cvut.cz/icir/

021

Reposted by Bill Psomas

David Picard @davidpicard.eurosky.social · 11/03/2026

This is such a good illustration! Too bad I didn't have the idea when I wrote that silly little paper a few years ago. Anyway, remember folks: torch.manual_seed(3407) is all you need No other seed had been subject to as much scrutiny as this one And it's all yours for free!

2265

Bill Psomas @billpsomas.bsky.social · 12/03/2026

🤖 Thrilled to share the Call for Papers for Greeks in AI 2026! 🇬🇷 Greeks in AI 2026 📍 Eugenides Foundation, Athens, Greece 📅 15–17 July 2026 We invite submissions presenting recent advances, ongoing research, and emerging ideas in Artificial Intelligence and Machine Learning.

131

Bill Psomas @billpsomas.bsky.social · 09/03/2026

1/n #CVPR2026 Accepted Paper🚀 𝑨𝒓𝒆 𝒂 𝑭𝒆𝒘 𝑬𝒙𝒂𝒎𝒑𝒍𝒆𝒔 𝑬𝒏𝒐𝒖𝒈𝒉 𝒕𝒐 𝑩𝒓𝒊𝒅𝒈𝒆 𝒕𝒉𝒆 𝑺𝒖𝒑𝒆𝒓𝒗𝒊𝒔𝒊𝒐𝒏 𝑮𝒂𝒑 𝒊𝒏 𝑶𝒑𝒆𝒏-𝑽𝒐𝒄𝒂𝒃𝒖𝒍𝒂𝒓𝒚 𝑺𝒆𝒈𝒎𝒆𝒏𝒕𝒂𝒕𝒊𝒐𝒏? 𝑹𝒆𝒕𝒓𝒊𝒆𝒗𝒆 𝒂𝒏𝒅 𝑺𝒆𝒈𝒎𝒆𝒏𝒕 (𝑹𝑵𝑺) answers this question. Paper/code at the end👇🏼

182

Reposted by Bill Psomas

Dmytro Mishkin @ducha-aiki.bsky.social · 27/02/2026

Retrieve and Segment: Are a Few Examples Enough to Bridge the Supervision Gap in Open-Vocabulary Segmentation? Tilemachos Aravanis @stojnicv.xyz @billpsomas.bsky.social Nikos Komodakis @gtolias.bsky.social tl;dr: almost yes if use 1-3 images, no if more(fig 6) arxiv.org/abs/2602.23339 #CVPR2026

073

Reposted by Bill Psomas

Tong Wei @weitong8591.bsky.social · 26/02/2026

Excited to share that our paper "Global-Aware Edge Prioritization for Pose Graph Initialization" has been accepted to CVPR 2026! #CVPR2026 See you soon in Denver!🥳🥳 Code is coming soon🚧 ❓How would you do an accurate and efficient pose graph initialization in a global manner? arxiv.org/abs/2602.21963

arxiv.org

Global-Aware Edge Prioritization for Pose Graph Initialization

The pose graph is a core component of Structure-from-Motion (SfM), where images act as nodes and edges encode relative poses. Since geometric verification is expensive, SfM pipelines restrict the pose...

193

Reposted by Bill Psomas

Zhenjun Zhao @ericzzj.bsky.social · 26/02/2026

Global-Aware Edge Prioritization for Pose Graph Initialization @weitong8591.bsky.social, @gtolias.bsky.social, Jiri Matas, @danielbarath.bsky.social tl;dr: rank pose graph edges->global consistency->improve SfM arxiv.org/abs/2602.21963

192

Reposted by Bill Psomas

Kosta Derpanis @csprofkgd.bsky.social · 20/02/2026

Sleeping while waiting on an “anywhere in the world” paper decision release. #CVPR2026

2171

Bill Psomas @billpsomas.bsky.social · 20/02/2026

1/n Attention, Please! 🚀 Our work “Revisiting Attentive Probing Through the Lens of Efficiency” has been accepted at #ICLR2026. We introduce Efficient Probing (EP) — a lightweight, multi-query attentive probing method for frozen encoders. Paper + code at the end 👇

1124

Reposted by Bill Psomas

Dmytro Mishkin @ducha-aiki.bsky.social · 03/02/2026

BBoxMaskPose v2: Expanding Mutual Conditioning to 3D Miroslav Purkrabek, Constantin Kolomiiets, Jiri Matas tl;dr: sota in human pose estimations, especially for the hard cases arxiv.org/abs/2601.15200

0121

Reposted by Bill Psomas

Giorgos Tolias @gtolias.bsky.social · 08/01/2026

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

euraxess.cz

Postdoctoral research position in Instance-level visual generation

Czech Technical University in Prague (CTU) offers a fellowship program, the CTU Global Postdoc Fellowship. This new and attractive two-year fellowship-program offers excellent researchers who have rec...

21210

Bill Psomas @billpsomas.bsky.social · 06/01/2026

🚀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!

0125

Bill Psomas @billpsomas.bsky.social · 27/12/2025

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👇

1144

Reposted by Bill Psomas

European Space Agency @esa.int · 24/12/2025

✨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

8410112

Reposted by Bill Psomas

Evangelos Kazakos @ekazakos.bsky.social · 24/12/2025

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!

051

Bill Psomas @billpsomas.bsky.social · 20/12/2025

📣 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

huggingface.co

billpsomas/icir · Datasets at Hugging Face

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

051

Reposted by Bill Psomas

Christian Wolf @chriswolfvision.bsky.social · 04/12/2025

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

261

Bill Psomas @billpsomas.bsky.social · 04/12/2025

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!

000

Bill Psomas @billpsomas.bsky.social · 11/11/2025

🤞🏾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

032