Max Burg
@maxfburg.bsky.social
Reposted by Max Burg
🚨 New paper alert! 🚨
We’ve just launched openretina, an open-source framework for collaborative retina modeling across datasets and species.
A 🧵👇 (1/9)
We’ve just launched openretina, an open-source framework for collaborative retina modeling across datasets and species.
A 🧵👇 (1/9)
March 14, 2025 at 9:41 AM
🚨 New paper alert! 🚨
We’ve just launched openretina, an open-source framework for collaborative retina modeling across datasets and species.
A 🧵👇 (1/9)
We’ve just launched openretina, an open-source framework for collaborative retina modeling across datasets and species.
A 🧵👇 (1/9)
Reposted by Max Burg
Deadline extended to March 19 for the EVAL-FoMo workshop @cvprconference.bsky.social! We welcome submissions (incl. published papers) analyzing emerging capabilities & limits in visual foundation models.
Details: sites.google.com/view/eval-fo...
#CVPR2025
Details: sites.google.com/view/eval-fo...
#CVPR2025
March 12, 2025 at 12:20 PM
Deadline extended to March 19 for the EVAL-FoMo workshop @cvprconference.bsky.social! We welcome submissions (incl. published papers) analyzing emerging capabilities & limits in visual foundation models.
Details: sites.google.com/view/eval-fo...
#CVPR2025
Details: sites.google.com/view/eval-fo...
#CVPR2025
Reposted by Max Burg
New preprint out! 🎉
How does LLM training loss translate to downstream performance?
We show that pretraining data and tokenizer shape loss-to-loss scaling, while architecture and other factors play a surprisingly minor role!
brendel-group.github.io/llm-line/ 🧵1/8
How does LLM training loss translate to downstream performance?
We show that pretraining data and tokenizer shape loss-to-loss scaling, while architecture and other factors play a surprisingly minor role!
brendel-group.github.io/llm-line/ 🧵1/8
February 18, 2025 at 2:09 PM
New preprint out! 🎉
How does LLM training loss translate to downstream performance?
We show that pretraining data and tokenizer shape loss-to-loss scaling, while architecture and other factors play a surprisingly minor role!
brendel-group.github.io/llm-line/ 🧵1/8
How does LLM training loss translate to downstream performance?
We show that pretraining data and tokenizer shape loss-to-loss scaling, while architecture and other factors play a surprisingly minor role!
brendel-group.github.io/llm-line/ 🧵1/8
Reposted by Max Burg
🧠 Meet LAMINR: Where neurons meet their match—finding common patterns that keep them excited 🔥💘
LAMINR learns & aligns invariance manifolds of sensory neurons to reveal shared properties.
🌟 #ICLR2025 Oral
📝 Paper: shorturl.at/08968
💻 Code: github.com/sinzlab/laminr
LAMINR learns & aligns invariance manifolds of sensory neurons to reveal shared properties.
🌟 #ICLR2025 Oral
📝 Paper: shorturl.at/08968
💻 Code: github.com/sinzlab/laminr
February 17, 2025 at 4:51 PM
🧠 Meet LAMINR: Where neurons meet their match—finding common patterns that keep them excited 🔥💘
LAMINR learns & aligns invariance manifolds of sensory neurons to reveal shared properties.
🌟 #ICLR2025 Oral
📝 Paper: shorturl.at/08968
💻 Code: github.com/sinzlab/laminr
LAMINR learns & aligns invariance manifolds of sensory neurons to reveal shared properties.
🌟 #ICLR2025 Oral
📝 Paper: shorturl.at/08968
💻 Code: github.com/sinzlab/laminr
Reposted by Max Burg
CuratedThoughts: Data Curation for RL Datasets 🚀
Since DeepSeek-R1 introduced reasoning-based RL, datasets like Open-R1 & OpenThoughts emerged for fine-tuning & GRPO. Our deep dive found major flaws — 25% of OpenThoughts needed elimination by data curation.
Here's why 👇🧵
Since DeepSeek-R1 introduced reasoning-based RL, datasets like Open-R1 & OpenThoughts emerged for fine-tuning & GRPO. Our deep dive found major flaws — 25% of OpenThoughts needed elimination by data curation.
Here's why 👇🧵
February 17, 2025 at 6:22 PM
CuratedThoughts: Data Curation for RL Datasets 🚀
Since DeepSeek-R1 introduced reasoning-based RL, datasets like Open-R1 & OpenThoughts emerged for fine-tuning & GRPO. Our deep dive found major flaws — 25% of OpenThoughts needed elimination by data curation.
Here's why 👇🧵
Since DeepSeek-R1 introduced reasoning-based RL, datasets like Open-R1 & OpenThoughts emerged for fine-tuning & GRPO. Our deep dive found major flaws — 25% of OpenThoughts needed elimination by data curation.
Here's why 👇🧵
Reposted by Max Burg
After a long journey, Segment Anything for Microscopy is now published in Nature Methods! We significantly improve SAM for interactive and automatic segmentation in light and electron microscopy and build a user-friendly tool.
www.nature.com/articles/s41...
www.nature.com/articles/s41...
February 12, 2025 at 11:41 AM
After a long journey, Segment Anything for Microscopy is now published in Nature Methods! We significantly improve SAM for interactive and automatic segmentation in light and electron microscopy and build a user-friendly tool.
www.nature.com/articles/s41...
www.nature.com/articles/s41...
Reposted by Max Burg
🚀 We’re hiring! Join Bernhard Schölkopf & me at @ellisinsttue.bsky.social to push the frontier of #AI in education!
We’re building cutting-edge, open-source AI tutoring models for high-quality, adaptive learning for all pupils with support from the Hector Foundation.
👉 forms.gle/sxvXbJhZSccr...
We’re building cutting-edge, open-source AI tutoring models for high-quality, adaptive learning for all pupils with support from the Hector Foundation.
👉 forms.gle/sxvXbJhZSccr...
February 11, 2025 at 4:34 PM
🚀 We’re hiring! Join Bernhard Schölkopf & me at @ellisinsttue.bsky.social to push the frontier of #AI in education!
We’re building cutting-edge, open-source AI tutoring models for high-quality, adaptive learning for all pupils with support from the Hector Foundation.
👉 forms.gle/sxvXbJhZSccr...
We’re building cutting-edge, open-source AI tutoring models for high-quality, adaptive learning for all pupils with support from the Hector Foundation.
👉 forms.gle/sxvXbJhZSccr...