Luca Eyring
@lucaeyring.bsky.social
ELLIS PhD student at TU Munich & Helmholtz AI
Generative Modeling - Optimal Transport - Representation Learning
https://lucaeyring.com/
Generative Modeling - Optimal Transport - Representation Learning
https://lucaeyring.com/
Pinned
Luca Eyring
@lucaeyring.bsky.social
· Dec 11
Can we enhance the performance of T2I models without any fine-tuning?
We show that with our ReNO, Reward-based Noise Optimization, one-step models consistently surpass the performance of all current open-source Text-to-Image models within the computational budget of 20-50 sec!
#NeurIPS2024
We show that with our ReNO, Reward-based Noise Optimization, one-step models consistently surpass the performance of all current open-source Text-to-Image models within the computational budget of 20-50 sec!
#NeurIPS2024
Reposted by Luca Eyring
3/
Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Models
@lucaeyring.bsky.social , @shyamgopal.bsky.social , Alexey Dosovitskiy, @natanielruiz.bsky.social , @zeynepakata.bsky.social
[Paper]: arxiv.org/abs/2508.09968
[Code]: github.com/ExplainableM...
Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Models
@lucaeyring.bsky.social , @shyamgopal.bsky.social , Alexey Dosovitskiy, @natanielruiz.bsky.social , @zeynepakata.bsky.social
[Paper]: arxiv.org/abs/2508.09968
[Code]: github.com/ExplainableM...
October 13, 2025 at 2:44 PM
3/
Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Models
@lucaeyring.bsky.social , @shyamgopal.bsky.social , Alexey Dosovitskiy, @natanielruiz.bsky.social , @zeynepakata.bsky.social
[Paper]: arxiv.org/abs/2508.09968
[Code]: github.com/ExplainableM...
Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Models
@lucaeyring.bsky.social , @shyamgopal.bsky.social , Alexey Dosovitskiy, @natanielruiz.bsky.social , @zeynepakata.bsky.social
[Paper]: arxiv.org/abs/2508.09968
[Code]: github.com/ExplainableM...
Reposted by Luca Eyring
🎓PhD Spotlight: Karsten Roth
Celebrate @confusezius.bsky.social , who defended his PhD on June 24th summa cum laude!
🏁 His next stop: Google DeepMind in Zurich!
Join us in celebrating Karsten's achievements and wishing him the best for his future endeavors! 🥳
Celebrate @confusezius.bsky.social , who defended his PhD on June 24th summa cum laude!
🏁 His next stop: Google DeepMind in Zurich!
Join us in celebrating Karsten's achievements and wishing him the best for his future endeavors! 🥳
August 4, 2025 at 2:11 PM
🎓PhD Spotlight: Karsten Roth
Celebrate @confusezius.bsky.social , who defended his PhD on June 24th summa cum laude!
🏁 His next stop: Google DeepMind in Zurich!
Join us in celebrating Karsten's achievements and wishing him the best for his future endeavors! 🥳
Celebrate @confusezius.bsky.social , who defended his PhD on June 24th summa cum laude!
🏁 His next stop: Google DeepMind in Zurich!
Join us in celebrating Karsten's achievements and wishing him the best for his future endeavors! 🥳
Reposted by Luca Eyring
From cell lines to full embryos, drug treatments to genetic perturbations, neuron engineering to virtual organoid screens — odds are there’s something in it for you!
Built on flow matching, CellFlow can help guide your next phenotypic screen: biorxiv.org/content/10.1101/2025.04.11.648220v1
Built on flow matching, CellFlow can help guide your next phenotypic screen: biorxiv.org/content/10.1101/2025.04.11.648220v1
April 23, 2025 at 9:26 AM
From cell lines to full embryos, drug treatments to genetic perturbations, neuron engineering to virtual organoid screens — odds are there’s something in it for you!
Built on flow matching, CellFlow can help guide your next phenotypic screen: biorxiv.org/content/10.1101/2025.04.11.648220v1
Built on flow matching, CellFlow can help guide your next phenotypic screen: biorxiv.org/content/10.1101/2025.04.11.648220v1
Reposted by Luca Eyring
(4/4) Disentangled Representation Learning with the Gromov-Monge Gap
@lucaeyring.bsky.social will present GMG, a novel regularizer that matches prior distributions with minimal geometric distortion.
📍 Hall 3 + Hall 2B #603
🕘 Sat Apr 26, 10:00 a.m.–12:30 p.m.
@lucaeyring.bsky.social will present GMG, a novel regularizer that matches prior distributions with minimal geometric distortion.
📍 Hall 3 + Hall 2B #603
🕘 Sat Apr 26, 10:00 a.m.–12:30 p.m.
April 22, 2025 at 1:52 PM
(4/4) Disentangled Representation Learning with the Gromov-Monge Gap
@lucaeyring.bsky.social will present GMG, a novel regularizer that matches prior distributions with minimal geometric distortion.
📍 Hall 3 + Hall 2B #603
🕘 Sat Apr 26, 10:00 a.m.–12:30 p.m.
@lucaeyring.bsky.social will present GMG, a novel regularizer that matches prior distributions with minimal geometric distortion.
📍 Hall 3 + Hall 2B #603
🕘 Sat Apr 26, 10:00 a.m.–12:30 p.m.
Reposted by Luca Eyring
(3/4) Disentangled Representation Learning with the Gromov-Monge Gap
A fantastic work contributed by Theo Uscidda and @lucaeyring.bsky.social , with @confusezius.bsky.social , @fabiantheis.bsky.social , @zeynepakata.bsky.social , and Marco Cuturi.
📖 [Paper]: arxiv.org/abs/2407.07829
A fantastic work contributed by Theo Uscidda and @lucaeyring.bsky.social , with @confusezius.bsky.social , @fabiantheis.bsky.social , @zeynepakata.bsky.social , and Marco Cuturi.
📖 [Paper]: arxiv.org/abs/2407.07829
Disentangled Representation Learning with the Gromov-Monge Gap
Learning disentangled representations from unlabelled data is a fundamental challenge in machine learning. Solving it may unlock other problems, such as generalization, interpretability, or fairness. ...
arxiv.org
April 7, 2025 at 9:34 AM
(3/4) Disentangled Representation Learning with the Gromov-Monge Gap
A fantastic work contributed by Theo Uscidda and @lucaeyring.bsky.social , with @confusezius.bsky.social , @fabiantheis.bsky.social , @zeynepakata.bsky.social , and Marco Cuturi.
📖 [Paper]: arxiv.org/abs/2407.07829
A fantastic work contributed by Theo Uscidda and @lucaeyring.bsky.social , with @confusezius.bsky.social , @fabiantheis.bsky.social , @zeynepakata.bsky.social , and Marco Cuturi.
📖 [Paper]: arxiv.org/abs/2407.07829
Reposted by Luca Eyring
Happy to share that we have 4 papers to be presented in the coming #ICLR2025 in the beautiful city of #Singapore . Check out our website for more details: eml-munich.de/publications. We will introduce the talented authors with their papers very soon, stay tuned😉
March 19, 2025 at 11:54 AM
Happy to share that we have 4 papers to be presented in the coming #ICLR2025 in the beautiful city of #Singapore . Check out our website for more details: eml-munich.de/publications. We will introduce the talented authors with their papers very soon, stay tuned😉
Reposted by Luca Eyring
Thrilled to announce that four papers from our group have been accepted to #CVPR2025 in Nashville! 🎉 Congrats to all authors & collaborators.
Our work spans multimodal pre-training, model merging, and more.
📄 Papers & codes: eml-munich.de#publications
See threads for highlights in each paper.
#CVPR
Our work spans multimodal pre-training, model merging, and more.
📄 Papers & codes: eml-munich.de#publications
See threads for highlights in each paper.
#CVPR
April 2, 2025 at 11:36 AM
Thrilled to announce that four papers from our group have been accepted to #CVPR2025 in Nashville! 🎉 Congrats to all authors & collaborators.
Our work spans multimodal pre-training, model merging, and more.
📄 Papers & codes: eml-munich.de#publications
See threads for highlights in each paper.
#CVPR
Our work spans multimodal pre-training, model merging, and more.
📄 Papers & codes: eml-munich.de#publications
See threads for highlights in each paper.
#CVPR
Reposted by Luca Eyring
📄 Disentangled Representation Learning with the Gromov-Monge Gap
with Théo Uscidda, Luca Eyring, @confusezius.bsky.social, Fabian J Theis, Marco Cuturi
📄 Decoupling Angles and Strength in Low-rank Adaptation
with Massimo Bini, Leander Girrbach
with Théo Uscidda, Luca Eyring, @confusezius.bsky.social, Fabian J Theis, Marco Cuturi
📄 Decoupling Angles and Strength in Low-rank Adaptation
with Massimo Bini, Leander Girrbach
January 24, 2025 at 8:02 PM
📄 Disentangled Representation Learning with the Gromov-Monge Gap
with Théo Uscidda, Luca Eyring, @confusezius.bsky.social, Fabian J Theis, Marco Cuturi
📄 Decoupling Angles and Strength in Low-rank Adaptation
with Massimo Bini, Leander Girrbach
with Théo Uscidda, Luca Eyring, @confusezius.bsky.social, Fabian J Theis, Marco Cuturi
📄 Decoupling Angles and Strength in Low-rank Adaptation
with Massimo Bini, Leander Girrbach
Reposted by Luca Eyring
Missing the deep learning part? go check out the follow up work @neuripsconf.bsky.social (tinyurl.com/yvf72kzf) and @iclr-conf.bsky.social (tinyurl.com/4vh8vuzk)
January 23, 2025 at 8:45 AM
Missing the deep learning part? go check out the follow up work @neuripsconf.bsky.social (tinyurl.com/yvf72kzf) and @iclr-conf.bsky.social (tinyurl.com/4vh8vuzk)
Reposted by Luca Eyring
Good to see moscot-tools.org published in @nature.com ! We made existing Optimal Transport (OT) applications in single-cell genomics scalable and multimodal, added a novel spatiotemporal trajectory inference method and found exciting new biology in the pancreas! tinyurl.com/33zuwsep
Mapping cells through time and space with moscot - Nature
Moscot is an optimal transport approach that overcomes current limitations of similar methods to enable multimodal, scalable and consistent single-cell analyses of datasets across spatial and temporal...
tinyurl.com
January 23, 2025 at 8:42 AM
Good to see moscot-tools.org published in @nature.com ! We made existing Optimal Transport (OT) applications in single-cell genomics scalable and multimodal, added a novel spatiotemporal trajectory inference method and found exciting new biology in the pancreas! tinyurl.com/33zuwsep
Reposted by Luca Eyring
Today is a great day for optimal transport 🎉! Lots of gratitude 🙏 for all folks who contributed to ott-jax.readthedocs.io and pushed for the MOSCOT (now @ nature!) paper, from visionaries @dominik1klein.bsky.social, G. Palla, Z. Piran to the magician, Michal Klein! ❤️
www.nature.com/articles/s41...
www.nature.com/articles/s41...
January 22, 2025 at 10:18 PM
Today is a great day for optimal transport 🎉! Lots of gratitude 🙏 for all folks who contributed to ott-jax.readthedocs.io and pushed for the MOSCOT (now @ nature!) paper, from visionaries @dominik1klein.bsky.social, G. Palla, Z. Piran to the magician, Michal Klein! ❤️
www.nature.com/articles/s41...
www.nature.com/articles/s41...
Reposted by Luca Eyring
This is maybe my favorite thing I've seen out of #NeurIPS2024.
Head over to HuggingFace and play with this thing. It's quite extraordinary.
Head over to HuggingFace and play with this thing. It's quite extraordinary.
Thanks to @fffiloni.bsky.social and @natanielruiz.bsky.social, we have a running live Demo of ReNO, play around with it here:
🤗: huggingface.co/spaces/fffil...
We are excited to present ReNO at #NeurIPS2024 this week!
Join us tomorrow from 11am-2pm at East Exhibit Hall A-C #1504!
🤗: huggingface.co/spaces/fffil...
We are excited to present ReNO at #NeurIPS2024 this week!
Join us tomorrow from 11am-2pm at East Exhibit Hall A-C #1504!
December 14, 2024 at 7:32 PM
This is maybe my favorite thing I've seen out of #NeurIPS2024.
Head over to HuggingFace and play with this thing. It's quite extraordinary.
Head over to HuggingFace and play with this thing. It's quite extraordinary.
Reposted by Luca Eyring
ReNO shows that some initial noise are better for some prompts! This is great to improve image generation, but i think it also shows a deeper property of diffusion models.
Can we enhance the performance of T2I models without any fine-tuning?
We show that with our ReNO, Reward-based Noise Optimization, one-step models consistently surpass the performance of all current open-source Text-to-Image models within the computational budget of 20-50 sec!
#NeurIPS2024
We show that with our ReNO, Reward-based Noise Optimization, one-step models consistently surpass the performance of all current open-source Text-to-Image models within the computational budget of 20-50 sec!
#NeurIPS2024
December 12, 2024 at 11:23 AM
ReNO shows that some initial noise are better for some prompts! This is great to improve image generation, but i think it also shows a deeper property of diffusion models.
Can we enhance the performance of T2I models without any fine-tuning?
We show that with our ReNO, Reward-based Noise Optimization, one-step models consistently surpass the performance of all current open-source Text-to-Image models within the computational budget of 20-50 sec!
#NeurIPS2024
We show that with our ReNO, Reward-based Noise Optimization, one-step models consistently surpass the performance of all current open-source Text-to-Image models within the computational budget of 20-50 sec!
#NeurIPS2024
December 11, 2024 at 11:05 PM
Can we enhance the performance of T2I models without any fine-tuning?
We show that with our ReNO, Reward-based Noise Optimization, one-step models consistently surpass the performance of all current open-source Text-to-Image models within the computational budget of 20-50 sec!
#NeurIPS2024
We show that with our ReNO, Reward-based Noise Optimization, one-step models consistently surpass the performance of all current open-source Text-to-Image models within the computational budget of 20-50 sec!
#NeurIPS2024
Reposted by Luca Eyring
After a break of over 2 years, I'm attending a conference again! Excited to attend NeurIPS, even more so to be presenting ReNO, getting inference-time scaling and preference optimization to work for text-to-image generation.
Do reach out if you'd like to chat!
Do reach out if you'd like to chat!
December 9, 2024 at 9:27 PM
After a break of over 2 years, I'm attending a conference again! Excited to attend NeurIPS, even more so to be presenting ReNO, getting inference-time scaling and preference optimization to work for text-to-image generation.
Do reach out if you'd like to chat!
Do reach out if you'd like to chat!