Research associate @ ELLIS Unit, LIT AI Lab, Institute for Machine Learning, JKU Linz. Collab with MIT-IBM Watson AI Lab. PhD@TU Graz
Graz, Austria
Joined January 2022
- Tweets74
- Following212
- Followers136
- Likes182
Wei Lin @ CVPR 2025 retweeted
Huge thanks to my amazing co-authors: @shyam__marjit @WeiLinCV @leokarlin @jmie_mirza
📄 Paper: arxiv.org/abs/2610.01687
🌐 Project: akshit21112002.github.io/Arc…
💻 Code: github.com/Akshit21112002/Ar…
Working on test-time scaling or VLMs? Would love to chat
Wei Lin @ CVPR 2025 retweeted
🚨 Our panel kicks off at 11:30 AM in Room 207 A–D (Level 2)!
Don't miss an amazing discussion with: Ludwig Schmidt, Andrew Owens, Arsha Nagrani, and Ani Kembhavi 🔥
Wei Lin @ CVPR 2025 retweeted
Thrilled to announce two new developments at JKU and NXAI that are released today:
- We scaled xLSTM to 7B parameters: linktr.ee/xlstm
- For the people caring about state tracking capabilities, there's the new FlashRNN library: arxiv.org/abs/2412.07752
Wei Lin @ CVPR 2025 retweeted
The Machine Learning for Molecules workshop 2024 will take place THIS FRIDAY, December 6.
Tickets for in-person participation are "SOLD" OUT.
We still have a few free tickets for online/virtual participation!
Registration link here: moleculediscovery.github.io/…
Wei Lin @ CVPR 2025 retweeted
Bio-xLSTM: Generative modeling, representation and in-context learning of biological and chemical sequences
xLSTM also shines for DNA, proteins and small molecules -- can handle large-range interactions and huge context!
P: arxiv.org/abs/2411.04165
Wei Lin @ CVPR 2025 retweeted
BREAKING NEWS
The Royal Swedish Academy of Sciences has decided to award the 2024 #NobelPrize in Physics to John J. Hopfield and Geoffrey E. Hinton “for foundational discoveries and inventions that enable machine learning with artificial neural networks.”
Wei Lin @ CVPR 2025 retweeted
ELLIS Machine Learning for Molecules workshop
December 6, 2024, HYBRID
Paper submission deadline: November 1st.
Program chairs: @fra_grisoni @jtmargraf an me
Webpage: moleculediscovery.github.io/…
We hope to see you all there!
Wei Lin @ CVPR 2025 retweeted
Panel starts now 🥳
@jcniebles @YejinChoinka Alexie A.Efros Antonio Torralba
Wei Lin @ CVPR 2025 retweeted
🚀 Just published on arXiv: SDLG – a novel method for enhancing trustworthiness in LLMs 💡
#SDLG #NeurIPS2024
🔍 SDLG improves uncertainty estimation in NLG – it detects whether an LLM is hallucinating by steering its text generation 💫
📜 Check it out: arxiv.org/pdf/2406.04306
Wei Lin @ CVPR 2025 retweeted
Introducing Vision-LSTM - making xLSTM read images 🧠It works ... pretty, pretty well 🚀🚀 But convince yourself :) We are happy to share code already!
📜: arxiv.org/abs/2406.04303
🖥️: nx-ai.github.io/vision-lstm/
All credits to my stellar PhD @benediktalkin
Wei Lin @ CVPR 2025 retweeted
Learning to remove noise from images yields fantastic image generators. Here's how you can use diffusion models to solve Combinatorial Optimization problems by removing noise from solutions that you don't even have! To be presented @ICML 2024, 🧵👇
Wei Lin @ CVPR 2025 retweeted
In case you haven't noticed, we have $10K winner prizes for the top teams!
🤑🤑🤑
Also, we extended the deadlines for Phase 1 and Phase 2 to June 5th.
Challenge: sites.google.com/view/2nd-mm…
Git: github.com/jmiemirza/MMFM-Ch…
@CVPR
Wei Lin @ CVPR 2025 retweeted
Really excited to announce Energy-based Hopfield Boosting. 🎉
Hopfield Boosting advances the state-of-the-art in OOD detection. 🚀
Our new energy function allows a model to focus on hard training examples close to the decision boundary between in-distribution and OOD samples. 🧵
Wei Lin @ CVPR 2025 retweeted
The #xLSTM is finally live! What an exciting day!
How far do we get in language modeling with the LSTM compared to State-of-the-Art LLMs?
I would say pretty, pretty far!
How? We extend the LSTM with Exponential Gating and parallelizable Matrix Memory!
arxiv.org/pdf/2405.04517
Wei Lin @ CVPR 2025 retweeted
I am so excited that xLSTM is out. LSTM is close to my heart - for more than 30 years now. With xLSTM we close the gap to existing state-of-the-art LLMs. With NXAI we have started to build our own European LLMs. I am very proud of my team. arxiv.org/abs/2405.04517
Wei Lin @ CVPR 2025 retweeted
We are very happy to receive a big grant of 33M€ for developing Artificial Intelligence methods in the next five years!!
JKU Linz teams up with TU Vienna, IST Austria, TU Graz, AAU Klagenfurt und WU Vienna.
We'll make it worth!
💡„Bilateral Artificial Intelligence“ - Die neue Dimension der KI entdecken
Wir gratulieren! 👏
#exzellenzinitiative #spitzenforschung
@jkulinz @tugraz @wu_vienna @ISTAustria @tu_wien
ALT Agata Ciabattoni, Christoph Lampert, Sepp Hochreiter, Gerhard Friedrich, Martina Seidl, Thomas Eiter, Axel Polleres. Foto: FWF/Daniel Novotny
Wei Lin @ CVPR 2025 retweeted
We have a cool challenge on understanding document images in our 2nd #CVPR2024 workshop on “What is Next in Multimodal Foundation Models?”, (sites.google.com/view/2nd-mm…). This is a great opportunity to showcase your work in front of a large audience (pic below from our 1st workshop)
