🚨 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! 🌴

Retrieve and Segment: Are a Few Examples Enough to Bridge the Supervision Gap in Open-Vocabulary Segmentation? Open-vocabulary segmentation (OVS) extends the zero-shot recognition capabilities of vision-language models (VLMs) to pixel-level prediction, enabling segmentation of arbitrary categories specified by text prompts. Despite recent progress, OVS lags behind fully supervised approaches due to two challenges: the coarse image-level supervision used to train VLMs and the semantic ambiguity of natural language. We address these limitations by introducing a few-shot setting that augments textual prompts with a support set of pixel-annotated images. Building on this, we propose a retrieval-augmented test-time adapter that learns a lightweight, per-image classifier by fusing textual and visual support features. Unlike prior methods relying on late, hand-crafted fusion, our approach performs learned, per-query fusion, achieving stronger synergy between modalities. The method supports continually expanding support sets, and applies to fine-grained tasks such as personalized segmentation. Experiments show that we significantly narrow the gap between zero-shot and supervised segmentation while preserving open-vocabulary ability.

🤜🤛 Grateful to @tim-arav.bsky.social, @stojnicv.xyz, Nikos Komodakis, and @gtolias.bsky.social

📝 Paper: arxiv.org/abs/2602.23339
💻 Code: github.com/TilemahosAra...

#CVPR2026 #ComputerVision #AI #MSCA #MSCAPF #RAG #DL #ML

🎉 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.

🚀 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

🚀 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/

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!

OpenReview link: openreview.net/group?id=gre...

#GreeksInAI #AI #ArtificialIntelligence #MachineLearning #DeepLearning #NLP #ComputerVision #Robotics #MultimodalAI #TrustworthyAI #AIResearch #Innovation #Greece #Athens

Important dates
📝 Submission deadline: 25 May 2026
📩 Notification of acceptance: 1 June 2026
🎤 Dates of the event: 15–17 July 2026

This is a great opportunity to share your work, meet the Greek AI community, and help strengthen the AI ecosystem in Greece and beyond.

Submissions may include work submitted or accepted within the last year, and accepted papers will be presented as posters or spotlight talks.

All submissions will be through OpenReview:

Topics include, among others:
• Machine Learning
• Natural Language Processing
• Computer Vision
• Robotics and Autonomous Systems
• Reinforcement Learning
• Multimodal AI
• Trustworthy, Fair, and Explainable AI
• AI for Science, Healthcare, and Climate
• AI Applications

🤖 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.

Retrieve and Segment: Are a Few Examples Enough to Bridge the Supervision Gap in Open-Vocabulary Segmentation? Open-vocabulary segmentation (OVS) extends the zero-shot recognition capabilities of vision-language models (VLMs) to pixel-level prediction, enabling segmentation of arbitrary categories specified by...

7/7 Resources 📄

Paper: arxiv.org/abs/2602.23339
Code: github.com/TilemahosAra...

Joint work with: @tim-arav.bsky.social, @stojnicv.xyz, Nikos Komodakis, and @gtolias.bsky.social.

We thank @noagarciad.bsky.social, @skamalas.bsky.social, @ekazakos.bsky.social for the feedback.

See you @ #CVPR2026

6/n 𝑷𝒆𝒓𝒔𝒐𝒏𝒂𝒍𝒊𝒛𝒆𝒅 𝑺𝒆𝒈𝒎𝒆𝒏𝒕𝒂𝒕𝒊𝒐𝒏

🥤 𝑹𝑵𝑺 can easily be employed for fine-grained tasks like 𝒑𝒆𝒓𝒔𝒐𝒏𝒂𝒍𝒊𝒛𝒆𝒅 𝒔𝒆𝒈𝒎𝒆𝒏𝒕𝒂𝒕𝒊𝒐𝒏 by simply expanding the support set with a few examples of a specific instance, letting it 𝒔𝒆𝒑𝒂𝒓𝒂𝒕𝒆 𝒕𝒉𝒂𝒕 𝒊𝒏𝒔𝒕𝒂𝒏𝒄𝒆 𝒇𝒓𝒐𝒎 𝒊𝒕𝒔 𝒃𝒓𝒐𝒂𝒅𝒆𝒓 𝒄𝒍𝒂𝒔𝒔.

5/n 𝑩𝒓𝒊𝒅𝒈𝒊𝒏𝒈 𝒕𝒉𝒆 𝑮𝒂𝒑

⚡ 𝑹𝑵𝑺 improves over different kinds of OVS approaches 𝒃𝒚 14.1% 𝒐𝒏 𝒂𝒗𝒆𝒓𝒂𝒈𝒆, while maintaining open-vocabulary generalization.

4/n 𝑫𝒚𝒏𝒂𝒎𝒊𝒄 𝑭𝒆𝒘-𝒔𝒉𝒐𝒕 𝑺𝒄𝒆𝒏𝒂𝒓𝒊𝒐𝒔

We investigate multiple 𝒇𝒆𝒘-𝒔𝒉𝒐𝒕 settings where visual or textual information may be missing for some test classes.

🎉 We consistently improve respective baselines, making 𝑹𝑵𝑺 a 𝒑𝒓𝒂𝒄𝒕𝒊𝒄𝒂𝒍 and 𝒐𝒑𝒆𝒏-𝒘𝒐𝒓𝒍𝒅 𝑶𝑽𝑺 method.

3/n 𝑯𝒐𝒘 it works?

💾 𝑹𝑵𝑺 stores 𝑽𝑳𝑴 𝒇𝒆𝒂𝒕𝒖𝒓𝒆𝒔 from visual and textual examples in a 𝒎𝒆𝒎𝒐𝒓𝒚-𝒆𝒇𝒇𝒊𝒄𝒊𝒆𝒏𝒕 manner.

🖼️ At test time, it 𝒓𝒆𝒕𝒓𝒊𝒆𝒗𝒆𝒔 𝒕𝒆𝒔𝒕 𝒊𝒎𝒂𝒈𝒆 𝒓𝒆𝒍𝒆𝒗𝒂𝒏𝒕 𝒆𝒙𝒂𝒎𝒑𝒍𝒆𝒔 to train a linear classifier on both modalities.

2/n Zero-shot open-vocabulary segmentation (OVS) is significantly underperforming fully supervised.

🌉 𝑹𝑵𝑺 𝒃𝒓𝒊𝒅𝒈𝒆𝒔 𝒕𝒉𝒊𝒔 𝒈𝒂𝒑 using a few pixel-level annotated visual examples along with class names.

With a few adaptation steps on each test image, we improve zero-shot 𝒃𝒚 up to 34% on average.

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👇🏼

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

🎉🎉🎉

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

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

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

Attention, Please! Revisiting Attentive Probing Through the Lens of Efficiency As fine-tuning becomes impractical at scale, probing is emerging as the preferred evaluation protocol. However, standard linear probing can understate the capability of models whose pre-training optim...

8/8 Resources 📄

Paper: arxiv.org/abs/2506.10178
Code: github.com/billpsomas/e...

Joint work with: Dionysis Christopoulos,@eirinibaltzi.bsky.social,@ikakogeorgiou.bsky.social, @tim-arav.bsky.social,Nikos Komodakis,Konstantinos Karantzalos,Yannis Avrithis,@gtolias.bsky.social.

See you @ ICLR 2026🇧🇷

7/n Take-home messages 💡

EP:
- Plug-and-play.
- Compatible with all pre-training families.
- Unlocks the potential of encoders optimized for local representations.
- Complementary with PEFT.
- Better to have it, than not to have it. 👀

6/n EP + PEFT = 🔥

- EP captures information that LoRA alone does not, and vice versa.
- LoRA+EP improves over both pure EP and pure LoRA.

📌 Example: a LoRA+EP configuration with 250K params reaches 72%, 4.3% above linear probing (67.7%), while using over 3× fewer parameters.

5/n Interpretability 🔍

- EP queries specialize in distinct spatial regions.
- Attention maps are complementary.
- Semantic correspondences emerge (e.g. tails, feet).
- Verified quantitatively too.

4/n Designed for local representations🧩

📊 Across ImageNet-1K:

- Consistent gains over k-NN and Linear Probing (LP).
- Particularly strong improvements for MIM, VL, and generative.
- Minimal overhead.

3/n Core observation ⚙️

Prior attentive probing uses redundant projections.

🔍 Introducing Efficient Probing (EP):

📌 Multi-query cross-attention.
🔌 Plug-and-play on top of frozen encoders.
💸 Lightweight and parameter-efficient.