Profile avatar
sloeschcke.bsky.social
Working on Efficient Training, Low-Rank Methods, and Quantization. PhD at the University of Copenhagen πŸ‡©πŸ‡° Member of @belongielab.org, Danish Data Science Academy, and Pioneer Centre for AI πŸ€– πŸ”— sebulo.github.io/
14 posts 281 followers 170 following
Regular Contributor

Thrilled to announce "Multimodality Helps Few-shot 3D Point Cloud Semantic Segmentation" is accepted as a Spotlight (5%) at #ICLR2025! Our model MM-FSS leverages 3D, 2D, & text modalities for robust few-shot 3D segmentationβ€”all without extra labeling cost. 🀩 arxiv.org/pdf/2410.22489 More detailsπŸ‘‡

β˜€οΈ Moved to Pasadena, California! β˜€οΈ For the next five months, I’ll be a Visiting Student Researcher at Anima Anandkumar's group at Caltech, collaborating with her team and Jean Kossaifi from NVIDIA on Efficient Machine Learning and AI4Science.

Recordings of the SSL4EO-2024 summer school are now released! This blog post summarizes what has been covered: langnico.github.io/posts/SSL4EO... Recordings: www.youtube.com/playlist?lis... Course website: ankitkariryaa.github.io/ssl4eo/ [1/3]

New Starter Pack: Pioneer Centre for AI researchers

Come by our poster session tomorrow! πŸ—“οΈ West Ballroom A-D #6104 πŸ•’ Thu, 12 Dec, 4:30 p.m. – 7:30 p.m. PST @madstoftrup.bsky.social and I are presenting LoQT: Low-Rank Adapters for Quantized Pretraining: arxiv.org/abs/2405.16528 #Neurips2024

Copenhagen University and Aarhus University meet-up in Vancouver πŸ‡©πŸ‡°πŸ‡¨πŸ‡¦ #NeurIPS2024

On my way to NeurIPS in Vancouver πŸ‡¨πŸ‡¦ Looking forward to reconnecting with friends and meeting new people. Let me know if you are interested in efficient training, quantization, or grabbing a coffee! #NeurIPS2024

Check out the work our lab in Copenhagen will be presenting at #NeurIPS2024 🌟 @neuripsconf.bsky.social @belongielab.org

Here’s a starter pack with members of our lab that have joined Bluesky

Pre-NeurIPS Poster Session in Copenhagen. Thanks to the Pioneer Centre for AI and @ellis.eu for sponsoring. @neuripsconf.bsky.social #neurips2024

Check out the ELLIS Pre-NeurIPS Fest event today in...πŸ‡©πŸ‡°Copenhagen! ELLIS Unit Copenhagen is holding their event at the Pioneer Center for AI showcasing #NeurIPS posters and other Denmark-affiliated papers in #AI and #ML. More info: bit.ly/4fRFrAh

I'm recruiting 1-2 PhD students to work with me at the University of Colorado Boulder! Looking for creative students with interests in #NLP and #CulturalAnalytics. Boulder is a lovely college town 30 minutes from Denver and 1 hour from Rocky Mountain National Park 😎 Apply by December 15th!

Join us for the 𝗣𝗿𝗲-π—‘π—²π˜‚π—Ώπ—œπ—£π—¦ π—£π—Όπ˜€π˜π—²π—Ώ π—¦π—²π˜€π˜€π—Άπ—Όπ—» in Copenhagen! πŸ—“οΈ π—ͺ𝗡𝗲𝗻: 16:00–18:00, Nov. 22, 2024 πŸ“ π—ͺ𝗡𝗲𝗿𝗲: Entrance Hall, Gefion, Øster Voldgade 10, 1350 KΓΈbenhavn K. Present or explore European contributions to NeurIPS 2024 and connect with colleagues. πŸ‘‰ π—œπ—»π—³π—Ό & π˜€π—Άπ—΄π—»-π˜‚π—½: www.aicentre.dk/events/pre-n...

Ever wanted to train your own 13B Llama2 model from scratch on a 24GB GPU? Or fine-tune one without compromising performance compared to full training? πŸ¦™ You now can, with LoQT: Low-Rank Adapters for Quantized Pretaining! arxiv.org/abs/2405.16528 1/4

A new approach to training models in memory-constrained settings, LoQT allows for the pre-training of a 13B LLM on a 24GB GPU without model parallelism, checkpointing, or offloading strategies during training Code: github.com/sebulo/LoQT

Logging on! πŸ§‘β€πŸ’»πŸ¦‹ We're the Belongie Lab led by @sergebelongie.bsky.social. We study Computer Vision and Machine Learning, located at the University of Copenhagen and Pioneer Centre for AI. Follow along to hear about our research past and present! www.belongielab.org