Sebastian Loeschcke
@sloeschcke.bsky.social
Working on Efficient Training, Low-Rank Methods, and Quantization.
PhD at the University of Copenhagen 🇩🇰
Member of @belongielab.org, Danish Data Science Academy, and Pioneer Centre for AI 🤖
🔗 sebulo.github.io/
PhD at the University of Copenhagen 🇩🇰
Member of @belongielab.org, Danish Data Science Academy, and Pioneer Centre for AI 🤖
🔗 sebulo.github.io/
🇳🇱 𝗤𝘂𝗮𝗹𝗰𝗼𝗺𝗺 𝗔𝗜 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 𝗜𝗻𝘁𝗲𝗿𝗻𝘀𝗵𝗶𝗽 🇳🇱
Excited to join @qualcomm.bsky.social in Amsterdam as a research intern in the Model Efficiency group, where I’ll be working on quantization and compression of machine learning models.
I’ll return to Copenhagen in December to start the final year of my PhD.
Excited to join @qualcomm.bsky.social in Amsterdam as a research intern in the Model Efficiency group, where I’ll be working on quantization and compression of machine learning models.
I’ll return to Copenhagen in December to start the final year of my PhD.
August 13, 2025 at 6:42 PM
🇳🇱 𝗤𝘂𝗮𝗹𝗰𝗼𝗺𝗺 𝗔𝗜 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 𝗜𝗻𝘁𝗲𝗿𝗻𝘀𝗵𝗶𝗽 🇳🇱
Excited to join @qualcomm.bsky.social in Amsterdam as a research intern in the Model Efficiency group, where I’ll be working on quantization and compression of machine learning models.
I’ll return to Copenhagen in December to start the final year of my PhD.
Excited to join @qualcomm.bsky.social in Amsterdam as a research intern in the Model Efficiency group, where I’ll be working on quantization and compression of machine learning models.
I’ll return to Copenhagen in December to start the final year of my PhD.
Reposted by Sebastian Loeschcke
📯 Best Paper Award at CVPR workshop on Visual concepts for our (@doneata.bsky.social + @delliott.bsky.social) paper on probing vision/lang/ vision+lang models for semantic norms!
TLDR: SSL vision models (swinV2, dinoV2) are surprisingly similar to LLM & VLMs even w/o lang 👀
arxiv.org/abs/2506.03994
TLDR: SSL vision models (swinV2, dinoV2) are surprisingly similar to LLM & VLMs even w/o lang 👀
arxiv.org/abs/2506.03994
June 13, 2025 at 3:15 PM
📯 Best Paper Award at CVPR workshop on Visual concepts for our (@doneata.bsky.social + @delliott.bsky.social) paper on probing vision/lang/ vision+lang models for semantic norms!
TLDR: SSL vision models (swinV2, dinoV2) are surprisingly similar to LLM & VLMs even w/o lang 👀
arxiv.org/abs/2506.03994
TLDR: SSL vision models (swinV2, dinoV2) are surprisingly similar to LLM & VLMs even w/o lang 👀
arxiv.org/abs/2506.03994
Check out our new preprint 𝐓𝐞𝐧𝐬𝐨𝐫𝐆𝐑𝐚𝐃.
We use a robust decomposition of the gradient tensors into low-rank + sparse parts to reduce optimizer memory for Neural Operators by up to 𝟕𝟓%, while matching the performance of Adam, even on turbulent Navier–Stokes (Re 10e5).
We use a robust decomposition of the gradient tensors into low-rank + sparse parts to reduce optimizer memory for Neural Operators by up to 𝟕𝟓%, while matching the performance of Adam, even on turbulent Navier–Stokes (Re 10e5).
June 3, 2025 at 3:17 AM
Check out our new preprint 𝐓𝐞𝐧𝐬𝐨𝐫𝐆𝐑𝐚𝐃.
We use a robust decomposition of the gradient tensors into low-rank + sparse parts to reduce optimizer memory for Neural Operators by up to 𝟕𝟓%, while matching the performance of Adam, even on turbulent Navier–Stokes (Re 10e5).
We use a robust decomposition of the gradient tensors into low-rank + sparse parts to reduce optimizer memory for Neural Operators by up to 𝟕𝟓%, while matching the performance of Adam, even on turbulent Navier–Stokes (Re 10e5).
Reposted by Sebastian Loeschcke
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)
NeurIPS participation in Europe
We seek to understand if there is interest in being able to attend NeurIPS in Europe, i.e. without travelling to San Diego, US. In the following, assume that it is possible to present accepted papers ...
docs.google.com
March 30, 2025 at 6:04 PM
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)
Visited the beautiful UC Santa Barbara yesterday.
March 8, 2025 at 5:41 PM
Visited the beautiful UC Santa Barbara yesterday.
Reposted by Sebastian Loeschcke
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 segmentation—all without extra labeling cost. 🤩
arxiv.org/pdf/2410.22489
More details👇
Our model MM-FSS leverages 3D, 2D, & text modalities for robust few-shot 3D segmentation—all without extra labeling cost. 🤩
arxiv.org/pdf/2410.22489
More details👇
February 11, 2025 at 5:49 PM
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 segmentation—all without extra labeling cost. 🤩
arxiv.org/pdf/2410.22489
More details👇
Our model MM-FSS leverages 3D, 2D, & text modalities for robust few-shot 3D segmentation—all without extra labeling cost. 🤩
arxiv.org/pdf/2410.22489
More details👇
☀️ Moved to Pasadena, California! ☀️
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.
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.
January 28, 2025 at 3:57 PM
☀️ Moved to Pasadena, California! ☀️
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.
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.
Reposted by Sebastian Loeschcke
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]
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]
January 24, 2025 at 3:32 PM
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]
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]
Reposted by Sebastian Loeschcke
New Starter Pack: Pioneer Centre for AI researchers
December 16, 2024 at 5:42 PM
New Starter Pack: Pioneer Centre for AI researchers
Come by our poster session tomorrow!
🗓️ West Ballroom A-D #6104
🕒 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
🗓️ West Ballroom A-D #6104
🕒 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
December 12, 2024 at 5:02 AM
Come by our poster session tomorrow!
🗓️ West Ballroom A-D #6104
🕒 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
🗓️ West Ballroom A-D #6104
🕒 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 🇩🇰🇨🇦
#NeurIPS2024
#NeurIPS2024
December 11, 2024 at 7:27 AM
Copenhagen University and Aarhus University meet-up in Vancouver 🇩🇰🇨🇦
#NeurIPS2024
#NeurIPS2024
On my way to NeurIPS in Vancouver 🇨🇦
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
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
December 8, 2024 at 4:08 AM
On my way to NeurIPS in Vancouver 🇨🇦
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
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
@neuripsconf.bsky.social @belongielab.org
With @neuripsconf.bsky.social right around the corner, we’re excited to be presenting our work soon! Here’s an overview
(1/5)
(1/5)
December 3, 2024 at 11:49 AM
Check out the work our lab in Copenhagen will be presenting at #NeurIPS2024 🌟
@neuripsconf.bsky.social @belongielab.org
@neuripsconf.bsky.social @belongielab.org
Reposted by Sebastian Loeschcke
Here’s a starter pack with members of our lab that have joined Bluesky
Belongie Lab
Join the conversation
go.bsky.app
November 25, 2024 at 10:42 AM
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
Thanks to the Pioneer Centre for AI and @ellis.eu for sponsoring.
@neuripsconf.bsky.social
#neurips2024
November 22, 2024 at 7:00 PM
Pre-NeurIPS Poster Session in Copenhagen.
Thanks to the Pioneer Centre for AI and @ellis.eu for sponsoring.
@neuripsconf.bsky.social
#neurips2024
Thanks to the Pioneer Centre for AI and @ellis.eu for sponsoring.
@neuripsconf.bsky.social
#neurips2024
Reposted by Sebastian Loeschcke
Check out the ELLIS Pre-NeurIPS Fest event today in...🇩🇰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
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
ELLIS Pre-NeurIPS Fest 2024: Celebrate, Connect, Collaborate
The ELLIS mission is to create a diverse European network that promotes research excellence and advances breakthroughs in AI, as well as a pan-European PhD program to educate the next generation of AI...
bit.ly
November 22, 2024 at 7:56 AM
Check out the ELLIS Pre-NeurIPS Fest event today in...🇩🇰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
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
Reposted by Sebastian Loeschcke
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!
Boulder is a lovely college town 30 minutes from Denver and 1 hour from Rocky Mountain National Park 😎
Apply by December 15th!
November 19, 2024 at 10:38 AM
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!
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-𝗡𝗲𝘂𝗿𝗜𝗣𝗦 𝗣𝗼𝘀𝘁𝗲𝗿 𝗦𝗲𝘀𝘀𝗶𝗼𝗻 in Copenhagen!
🗓️ 𝗪𝗵𝗲𝗻: 16:00–18:00, Nov. 22, 2024
📍 𝗪𝗵𝗲𝗿𝗲: Entrance Hall, Gefion, Øster Voldgade 10, 1350 København K.
Present or explore European contributions to NeurIPS 2024 and connect with colleagues.
👉 𝗜𝗻𝗳𝗼 & 𝘀𝗶𝗴𝗻-𝘂𝗽: www.aicentre.dk/events/pre-n...
🗓️ 𝗪𝗵𝗲𝗻: 16:00–18:00, Nov. 22, 2024
📍 𝗪𝗵𝗲𝗿𝗲: Entrance Hall, Gefion, Øster Voldgade 10, 1350 København K.
Present or explore European contributions to NeurIPS 2024 and connect with colleagues.
👉 𝗜𝗻𝗳𝗼 & 𝘀𝗶𝗴𝗻-𝘂𝗽: www.aicentre.dk/events/pre-n...
November 19, 2024 at 8:58 AM
Join us for the 𝗣𝗿𝗲-𝗡𝗲𝘂𝗿𝗜𝗣𝗦 𝗣𝗼𝘀𝘁𝗲𝗿 𝗦𝗲𝘀𝘀𝗶𝗼𝗻 in Copenhagen!
🗓️ 𝗪𝗵𝗲𝗻: 16:00–18:00, Nov. 22, 2024
📍 𝗪𝗵𝗲𝗿𝗲: Entrance Hall, Gefion, Øster Voldgade 10, 1350 København K.
Present or explore European contributions to NeurIPS 2024 and connect with colleagues.
👉 𝗜𝗻𝗳𝗼 & 𝘀𝗶𝗴𝗻-𝘂𝗽: www.aicentre.dk/events/pre-n...
🗓️ 𝗪𝗵𝗲𝗻: 16:00–18:00, Nov. 22, 2024
📍 𝗪𝗵𝗲𝗿𝗲: Entrance Hall, Gefion, Øster Voldgade 10, 1350 København K.
Present or explore European contributions to NeurIPS 2024 and connect with colleagues.
👉 𝗜𝗻𝗳𝗼 & 𝘀𝗶𝗴𝗻-𝘂𝗽: 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? 🦙
You now can, with LoQT: Low-Rank Adapters for Quantized Pretaining! arxiv.org/abs/2405.16528
1/4
You now can, with LoQT: Low-Rank Adapters for Quantized Pretaining! arxiv.org/abs/2405.16528
1/4
November 18, 2024 at 9:29 AM
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? 🦙
You now can, with LoQT: Low-Rank Adapters for Quantized Pretaining! arxiv.org/abs/2405.16528
1/4
You now can, with LoQT: Low-Rank Adapters for Quantized Pretaining! arxiv.org/abs/2405.16528
1/4
Reposted by Sebastian Loeschcke
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
Code: github.com/sebulo/LoQT
GitHub - sebulo/LoQT
Contribute to sebulo/LoQT development by creating an account on GitHub.
github.com
November 17, 2024 at 9:16 PM
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
Code: github.com/sebulo/LoQT
Reposted by Sebastian Loeschcke
Logging on! 🧑💻🦋 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
Belongie Lab - Home
Belongie Lab -- Home.
www.belongielab.org
November 17, 2024 at 12:36 PM
Logging on! 🧑💻🦋 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