@lciernik

PhD student at ML Group @TUBerlin @bifoldberlin @HFA_academy @ELLISforEurope | MSc thesis at Boeva Lab, @ETH_en

Joined September 2023
  • Tweets32
  • Following148
  • Followers93
8Media
Laure Ciernik retweeted
Luca Eyring
@LucaEyringJul 7
I‘m at ICML this week and we’re presenting Diamond Maps at Hall A #2713 today at 2pm @electronickale, @zeynepakata, @peholderrieth! Also, feel free to DM if you wanna chat about diffusion/flows/reward alignment/etc.
Luca Eyring
@LucaEyringApr 22
Accurate reward guidance in diffusion models has been a long-standing challenge. We propose Diamond Maps 💎, through stochastic flow maps we make reward guidance both accurate and scalable.
2
8
61
6,700
✨Tomorrow's the day! Excited to present this work with @LucaEyring at ICML in HALL A #2711 at 10:30 am✨ If you're interested in extracting knowledge from vision transformers for downstream tasks, come by! Looking forward to great discussions and new research ideas.
Laure Ciernik@lciernikJan 16
Why you should probe more than just the final layer of your Vision Transformer to maximize performance. 🧵👇
1
1
5
1,888
Why you should probe more than just the final layer of your Vision Transformer to maximize performance. 🧵👇
1
3
3
11
2,902
more replies
7/ Huge thanks to my shared first author, Marco Morik, and all great co-authors: @lukas_thede, @LucaEyring, Shinichi Nakajima, @zeynepakata, and @lukas_mut 🙏
1
3
274
Large thanks for the vital support: @bifoldberlin, @HFA_academy, @uni_tue, Tübingen AI Center, @HelmholtzMunich, @MunichCenterML, and @AIgnostics. We couldn't have done it without this ecosystem🚀
3
157
🎉 Update: This work got accepted to #icml2025!! Huge thanks to my amazing co-authors @LorenzLinhardt, Marco Morik, @jdppel, @skornblith, and @lukas_mut for their great work and to all collaborators! 🙏 📄 Paper: arxiv.org/abs/2411.05561 💻 Code: github.com/lciernik/similari… 🧵1/3
Laure Ciernik@lciernik11 Nov 2024
If two models are more similar to each other than a third on ImageNet, will this hold for medical/ satellite images? Our preprint analyzes how vision model similarities generalize across datasets, the factors that influence them, and their link to downstream task behavior. 🧵1/7
1
4
1
15
1,148
During the rebuttal, we've added: improved local structure measurements, a CKA stability analysis, and additional dataset observations. 🧵2/3
1
3
129
The core message remains: Training objective drives the consistency of pairwise representational similarities, and similarity-performance correlations depend on the dataset structure. 🧵3/3
3
117
Laure Ciernik retweeted
Fabian Theis
@fabian_theis12 Dec 2024
1/🚀 Excited to share RegVelo, our new computational model combining RNA velocity with gene regulatory network (GRN) dynamics to model cellular changes and predict in silico perturbations. Here's how it works and why it matters! 🧵👇
biorxiv.org/content/10.1101/…
8
98
3
402
67,310
Laure Ciernik retweeted
Valentina Boeva
@val_boeva26 Nov 2024
🚀 New preprint from our lab, @ekrym2 and @fabian_theis : UniversalEPI, an attention-based method to predict enhancer-promoter interactions from DNA sequence and ATAC-seq🌟 🔬 Key Highlights: - Predicts chromatin interactions across unseen cell types with no retraining. - Outperforms state-of-the-art models like C.Origami and ChromaFold with Spearman’s Rho > 0.92 in unseen cell types. - Tracks chromatin dynamics in processes like macrophage reprogramming and cancer transcriptional states. - Scalable for both bulk and single-cell chromatin accessibility data. 🧬UseUniversalEPI for in-silico 3D chromatin modeling in your favorite model! Examples of applications: studies on genetic diseases, cell differentiation, and the regulatory impacts of non-coding variants. 📄 Read the full preprint: doi.org/10.1101/2024.11.22.6… by @AayushGrover8 @ekrym2 @ilibarra @fabian_theis et al.
1
30
3
126
19,376
Laure Ciernik retweeted
Fabian Theis
@fabian_theis20 Nov 2024
1/ 🧬 Single-cell genomics reveals biological variations beyond cell types. Unveiling these in separate latent dimensions is known as disentanglement. Led by @AmirAliMoinfar, we introduce DRVI to learn nonlinear, disentangled & interpretable latent spaces. biorxiv.org/content/10.1101/…
2
50
199
21,544
Laure Ciernik retweeted
Julius Hense@hense9612 Nov 2024
❓ Do histopathological foundation models eliminate batch effects? ❓ The surprisingly clear answer is: they do not! Find out more in our new paper that we will present at the AIM-FM Workshop at @NeurIPSConf. Link: arxiv.org/abs/2411.05489
1
3
13
614
If two models are more similar to each other than a third on ImageNet, will this hold for medical/ satellite images? Our preprint analyzes how vision model similarities generalize across datasets, the factors that influence them, and their link to downstream task behavior. 🧵1/7
1
14
5
57
14,323
more replies
2nd key insight: The link between model similarity & behavior varies by dataset. Single-domain sets show strong correlations, while some multi-domain ones have high-performing, dissimilar models. Thus, the Platonic Representation Hypothesis may depend on the dataset's nature. 6/7
1
6
599
Want to learn more? Read our new preprint:arxiv.org/abs/2411.05561 ✨ Deeply grateful to @LorenzLinhardt, Marco Morik, @jdppel, @skornblith, and @lukas_mut for their rigorous work and dedication throughout this project. Each contribution was essential to make this possible! 🙏 7/7
2
12
787
Load more