Advertisement Β· 728 Γ— 90

Posts by Michael Dorkenwald

Preview
Elastic ViTs from Pretrained Models without Retraining Vision foundation models achieve remarkable performance but are only available in a limited set of pre-determined sizes, forcing sub-optimal deployment choices under real-world constraints. We introdu...

This was a great collaboration with Walter Simoncini (equal contribution), Tijmen Blankevoort, @cgmsnoek.bsky.social and @yukimasano.bsky.social
Website: elastic.ashita.nl
Paper: arxiv.org/abs/2510.17700
Code: github.com/WalterSimonc...

4 months ago 0 0 0 0
Post image

Pretrained ViTs usually come in rigid sizes (S, B, L, H). But your hardware constraints don't

We built a way to make DINO or CLIP fully elastic in <5 mins without any retraining ⚑️

Get the exact model size you need, not just what was released

Find Walter at #NeurIPS Poster 4709 | Thu 4:30-7:30 PM

4 months ago 5 2 1 0

✨ The VIS Lab at the #University of #Amsterdam is proud and excited to announce it has #TWELVE papers πŸš€ accepted for the leading #AI-#makers conference on representation learning ( #ICLR2025 ) in Singapore πŸ‡ΈπŸ‡¬. 1/n
πŸ‘‡πŸ‘‡πŸ‘‡ @ellisamsterdam.bsky.social

1 year ago 17 4 1 0
Post image

Fuck it, today we're open-sourcing the codebase used to train SmolVLM from scratch on 256 H100s πŸ”₯
Inspired by our team's effort to open-source DeepSeek's R1, we are releasing the training and evaluation code on top of the weights 🫑
Now you can train any SmolVLMβ€”or create your own custom VLMs!

1 year ago 25 5 2 0
Post image Post image Post image

πŸ€” Can you turn your vision-language model from a great zero-shot model into a great-at-any-shot generalist?

Turns out you can, and here is how: arxiv.org/abs/2411.15099

Really excited to this work on multimodal pretraining for my first bluesky entry!

🧡 A short and hopefully informative thread:

1 year ago 134 24 2 7
Video

Introducing β€œMAGiC-SLAM: Multi-Agent Gaussian Globally Consistent SLAM”! We do SLAM with novel view synthesis capabilities on multiple simultaneously operating agents!

vladimiryugay.github.io/magic_slam/i...
1/7

1 year ago 51 17 3 1

Nice πŸ‘! We love small (M)LLMs :) will training code also be released?

1 year ago 3 1 0 0

Amazing, congrats! Well deserved!

1 year ago 1 0 0 0
Advertisement

The ✨ML Internship Feed✨ is here!

@serge.belongie.com and I created this feed to compile internship opportunities in AI, ML, CV, NLP, and related areas.

The feed is rule-based. Please help us improve the rules by sharing feedback 🧑

πŸ”— Link to the feed: bsky.app/profile/did:...

1 year ago 63 16 7 1

Here we grow again. Introducing my 2nd AWESOME #ComputerVision Starter Pack.

Missed you? Let me know in the thread.

go.bsky.app/Gjcs339

1 year ago 79 19 45 6
Video

Academic faculty comparing their research output πŸ˜…

1 year ago 10 1 0 0
Video

Hi πŸ‘‹ We're glad to be here on @bsky.app and looking forward to engaging in this community. But first, learn a little more about us...

#ELLISforEurope #AI #ML #CrossBorderCollab #PhD

1 year ago 122 19 3 1

Welcome @mdorkenw.bsky.social to the other side!

1 year ago 3 1 1 0

Thanks from the other side!

1 year ago 1 0 0 0