Thrilled to share our latest work on SciVid, to appear at #ICCV2025! 🎉
SciVid offers cross-domain evaluation of video models in scientific applications, including medical CV, animal behavior, & weather forecasting 🧪🌍📽️🪰🐭🫀🌦️
📝 Check out our paper: arxiv.org/abs/2507.03578
[1/4]🧵

Painting process!
A time lapse of me painting a fanart of Lycoris Recoil, Chisato, onto a Chopstick

This is the whole pair! Cuties💕
Took me around 3hours to make them. There is a light firework in the background and if you hold them closer they really form the heart with their hands:-)

#Fanart
#LycorisRecoil
#ChisatoXTakina
#PaintingOnChopsticks

The prototype of Chopsticks with motifs of Julie Valesque @julievasques.bsky.social are ready!
😍🤩😍
I am looking forward for the real ones. Just some small adjustments to go! So happy to have this prototype now in my kitchen as cooking sticks🤗🤗 hope they arrive in Brazilia soon then, too!

Would you present your next NeurIPS paper in Europe instead of traveling to San Diego (US) if this was an option? Søren Hauberg (DTU) and I would love to hear the answer through this poll: (1/6)

🔥Excited to introduce RINS - a technique that boosts model performance by recursively applying early layers during inference without increasing model size or training compute flops! Not only does it significantly improve LMs, but also multimodal systems like SigLIP.
(1/N)

TRecViT: A Recurrent Video Transformer
arxiv.org/abs/2412.14294

Causal, 3× fewer parameters, 12× less memory, 5× higher FLOPs than (non-causal) ViViT, matching / outperforming on Kinetics & SSv2 action recognition.

Code and checkpoints out soon.

Check out @tkipf.bsky.social's post on MooG, the latest in our line of research on self-supervised neural scene representations learned from raw pixels:

SRT: srt-paper.github.io
OSRT: osrt-paper.github.io
RUST: rust-paper.github.io
DyST: dyst-paper.github.io
MooG: moog-paper.github.io

🤔 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:

Woo hoo! 1K new followers, welcome to 💙🦋!

For science-minded folks, there are some very cool tricks 🚀…

If you use any of these emojis: 👩‍🔬|👩🏻‍🔬|👩🏼‍🔬|👩🏽‍🔬|👩🏾‍🔬|👩🏿‍🔬 your post will index on a Women in STEM feed

If you use 🧪 a Science feed

If you use 🧠 a Neuroscience feed

Go get it 🚀🧪🧠👩‍🔬💙🎊