Example post 1
+ +Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua.
+diff --git a/preview/pr-3/2019/01/07/example-post-1.html b/preview/pr-3/2019/01/07/example-post-1.html new file mode 100644 index 00000000..ff660712 --- /dev/null +++ b/preview/pr-3/2019/01/07/example-post-1.html @@ -0,0 +1,637 @@ + + +
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua.
+Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua.
+Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua.
+Try searching the whole site for the content you want:
+ + +Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. +Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat.
++ Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. + +
++ Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. + +
++ Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. + +
+Barbara Werner
+Lab Manager
+Room 4.306
+Im Neuenheimer Feld 205
+69120 Heidelberg
We develop principled AI methods to solve hard problems from the natural sciences. Our expertise are fundamental algorithms and their application to complex problems with spatial structure.
+Geometric Machine Learning in Quantum Chemistry
+ + +Predicting molecular properties is important for a huge range of problems, from biochemistry to drug development.
+ +The most universal approach to such predictions relies on quantum mechanics. We aim to dramatically speed up these quantum calculations using machine learning methods that respect the fundamental symmetries of the problem.
+ + + + +Our Team
+ + +The team is everything! Our maxime: 1. Be Nice and 2. Do Great Science :-)
+ + + + +Our Network
+ + +We learn a lot from our colleagues! We are proud members of, and help shape the future of, our excellence cluster, our ellis unit and our department.
+ + +Home, Sweet Home
+ + +IWR is a central institute of our university, and a fantastic place where scientists from maths, CS, physics and more meet to develop methods that address some of the hardest problems out there.
+ + +Machine Learning in Heidelberg
+ + +Heidelberg is home to a vibrant ML community. The MLAI page is the portal to all talks and events in the area.
+ + + + +I am a physics master’s student in the Scientific AI lab. Currently, I am working on the application of equivariant machine learning methods to the problem of density functional theory.
+ +In addition to my studies, I also serve as a Teaching Assistant for the bachelor lecture “Einführung ins Maschinelle Lernen”. This position provides me the opportunity to assist other students in their learning process, while concurrently solidifying my own understanding of the topics.
+ +When I’m not immersed in my studies, I enjoy staying active with swimming and biking. I also participate in a student choir and enjoy playing the piano.
+ + + + + + + + + + + +From October 2023 to March 2024 I am a visiting professor (Vertretungsprofessor) taking over Fred Hamprecht’s teaching duties. I am teaching a BSc course Einführung ins Machinelle Lernen and a MSc seminar Transformers, large language models, and their use in physics.
+ +Other then that, I am a research scientist and a group leader in the Berens lab at Tübingen University, Germany.
+ +I am interested in self-supervised and unsupervised learning, in particular contrastive learning, manifold learning, and dimensionality reduction for 2D visualization of scientific datasets. I am working with image data, text data, graph data, and single-cell RNA-seq data in neuroscience contexts.
+ +Please see my personal website https://dkobak.github.io for more details.
+ + + + + + + + + + + +I am writing my Physics Master’s thesis in the Scientific AI lab. Since my Bachelor’s thesis in Stochastic Dynamics I developed a greater interest in Theoretical Physics, Differential Geometry and Machine Learning.
+ +Currently, I am working on Machine Learning applications to Density Functional Theory. Generally, I am interested in the theoretical underpinnings of Machine Learning. That is, how can theory (Math, Physics, Chemistry, you name it) guide our understanding of and yield appropriate inductive biases for Machine Learning.
+ +I previously studied and worked in Sport Sciences, aiming to understand how the human body moves, develops and adapts. Writing a thesis on energy conservation in human movement sparked my interest in Physics leading to my eventual switching of gears. The urge to understand the behavior of systems on a most fundamental level lead me from the human body to Physics and Machine Learning.
+The love for sports remains. Primarily, I am engaged in Brazilian Jiu-Jitsu and Boxing. My gentler side likes books (old), movies (semi-old), cooking (Italian) and my dog Chewie (cute).
I am a PhD student in Fred Hamprecht’s Scientific AI lab. Previously, I studied Mathematics at the University of Valencia and Scientific Computing at Heidelberg University. I am principally interested in the development and understanding of methods for the analysis of data (specifically modelled by graphs) with a well founded theory.
+ +A list of my publications can be found here.
+ + + + + + + + + + + + +In my current physics Bachelor’s thesis at the Scientific AI lab I’m working on better understanding the loss landscapes of dimension reduction techniques such as t-SNE and UMAP.
+ +When I have the time I enjoy physical challenges of a different kind like bouldering, dancing and mountainbiking. Afterwards, I take delight in reading or playing the piano.
+ + + + + + + + + + + +Hi!
+ +I develop machine learning algorithms for complex problems endowed with spatial structure.
+ +For twenty years, I had fun (and luckily some success) solving problems from image analysis. More recently, I have decided to dedicate myself entirely to the study of a long-standing problem from quantum chemistry: In the framewok of density functional theory, I try to learn the kinetic energy functional using, and expanding, the latest technology from geometric machine learning.
+ +What has not changed is my love for methods that have a sound mathematical background such as combinatorial optimization or algebraic graph theory, while being widely applicable and useful in practice.
+ +I enjoy, and feel most privileged, to be able to work on things unknown, and to teach the next generation of scientists and engineers. Luckily, I am blessed with a fantastic lab whose members happen to be both extremely gifted and nice.
+ +I am proud that several former PhD students continue to serve in research and education, including
+ +I am a master’s student in physics and currently working in the Scientific AI lab on the DFT project.
+ +After I wrote my bachelor’s thesis in mathematical physics, where I researched the mathematical structure of the path integral in quantum mechanics, I discovered my passion for structural insight in the sciences. And what better tool to discover structures in data than machine learning?
+ +My main interest lies in bridging the gap between the natural sciences and machine learning research, with the goal of using machine learning techniques to accelerate research and discover new facts about our physical world.
+ +In my free time, I enjoy cooking and exploring food from all around the world. You will also find me playing video games, watching movies, and most importantly, engaging in never-ending discussions about them.
+ + + + + + + + + + + +In the Scientific AI lab, I am a PhD student working with machine learning in +quantum chemistry, specifically the DFT project. Before this, I studied +information geometry and Bayesian inference for my Master’s thesis.
+ +Including machine learning, I am interested in algorithms in general and how +the theoretical understanding of both their objectives and inner workings may +help us improve their performance.
+ +My free time is mostly filled with music – I enjoy playing the piano both in +a classical and Jazz setting.
+ + + + + + + + + + + +I am a Master student in the Scientific AI lab currently writing my Master’s thesis in physics. I did a dual Bachelor’s degree in physics and mathematics with a specialization on string theory and information theory.
+ +In my Master’s thesis I am interested in machine learning architecture and theory. I am working on the density functional theory project.
+ +In my free time I like to play ice hockey, go running or play chess. I am a huge coffee nerd, so on the weekend, you might have a high chance to meet me in a nice café.
+ + + + + + + + + + + +Hi! I am Lorenzo, and I am currently a PostDoc in the sciAI lab! +I am passionate about applying advanced and principled machine learning techniques to solve real-world problems (at scale!).
+ +My favorite playground is life sciences; I have worked on a variety of projects at the intersection of computer vision and biomedical research. To name some, I developed deep learning pipelines, for instance, segmentation using convolutional neural networks, cell detection and tracking using transformers, assembling large-scale datasets for bio-medical computer vision applications, generative models for synthetic training data generation, and cell/tissue classification using graph neural networks.
+ +I studied Physics (bachelor’s in Rome Tor Vergata and master’s in Heidelberg). My old-time passions are chaotic dynamical systems and statistical mechanics.
+ +I am not very good with languages, but my Python is better than my English! I love anything related to coding and trying new, exciting programming languages!
+ +My big passions are Dogs, food, photography, and mountain bikes!
+ + + + + + + + + + + +I am currently working on my physics master thesis in the Scientific AI lab. Before going to Heidelberg, I studied physics and computer science at TU Darmstadt and FSU Jena. My research interests include machine learning and its applications in physics, which is why I am currently working on applying equivariant machine learning to density functional theory.
+ +In addition, I also have a deep interest in theoretical physics, which was my main focus next to machine learning during my studies.
+ +In my free time I enjoy playing the guitar, reading and going for long walks. If I find the time, I also like to bind books from scratch.
+ + + + + + + + + + + +I am a physics PhD student in the Scientific AI lab. Before joining the group I studied physics in Heidelberg and did my master’s thesis on medical object detection. I am interested in quantum mechanics and applying neural networks to computational physics simulations. For my PhD, I am working on the orbital-free density functional theory project.
+ +When I am not working, you might find me running or biking on the Heidelberger trails.
+ + + + + + + + + + + +I am a research assistant in Fred Hamprecht’s Scientific AI Lab. I am currently working on computational techniques for Single Cell Data Analysis. More broadly, I am interested in applying ML techniques to problems in Healthcare and Life Sciences.
+ +I obtained my Master’s from the Computational and Data Sciences Department at the Indian Institute of Science, Bangalore in 2020. I worked under Dr. Phaneendra Yalavarthy in the Medical Imaging Group. +I did my Bachelor’s in Production and Industrial Engineering from the Indian Institute of Technology, Delhi (2013-2017).
+ +I love listening to music and have been trained in Indian classical singing for a few years. I am also fond of playing guitar and have been trying to progress beyond the amateur level for years (someday it will happen)! +Another amateur pursuit of mine is Photography. +I can also have endless discussions on Lord of the Rings, Stormlight Archive, Wheel of Time, Fullmetal Alchemist, Code Geass… and the list goes on.
+ + + + + + + + + + + +I am a PhD student in Fred Hamprecht’s Image Analysis and Learning lab. Before, I have studied Physics at Heidelberg University and at Imperial College London. My research interests range from developing principled methods to analyze structured data (let there be graphs) to more applied problems, in particular 3D computer vision.
+ +In my free time I love doing sports, riding my bike up the Heidelberg Hills or going bouldering. I sing in a student choir and always enjoy playing the guitar in the occasional jam session.
+ +Feel free to get in touch with me or catch me in person at our weekly journal club where we come together to discuss the latest and the greatest in the machine learning paper jungle.
+ + + + + + + + + + + +To me, an exiting aspect of machine learning research is how great ideas can be successfully applied in countless domains, +in particular other sciences. +As a member of the scientific AI lab, I had the chance to do so in a biological, technical and most recently chemical context:
+ +Currently, my main research interest is geometric machine learning, particularly its application to molecular systems. +As one of the initial members of the orbital-free DFT project, I am exited to see how the team is growing and evolving.
+ +In my free time, I enjoy climbing and origami.
+ + + + + + + + + + + +I am a physics Bachelor’s student in the Scientific AI lab. In my studies I am mostly interested +in computer physics and computer science. I am currently doing my Bachelor’s thesis with the topic of spatial statistics +on the distribution of neural stem cells.
+ +In my free time I like to cook and test out new recipes. As a contrast to the long work on the computer I love to work out or have a run in the forest.
+ + + + + + + + + + + +I support the group by administering the workstations and servers. I am particularly interested in the group’s systems and tools, work processes and GreenIT.
+ +When I’m not working on the computer, you’ll find me at the chessboard, on my bike or in the climbing gym.
+ + + + + + + + + + + +I am currently pursuing my master’s degree in physics at the Scientific AI Lab. For my master’s thesis, I contribute to a team focusing on the application of equivariant machine learning models to density functional theory. This approach has the potential to accelerate quantum chemical simulations.
+ +Beyond my academic pursuits, I have a passion for teaching. This semester marks my fifth term as a tutor for theoretical physics, this time for theoretical physics III.
+ +During my leisure time, I like to engage in various sports such as tennis, bouldering, and courses offered by the uni-sports program. Additionally, I find joy in hiking and cooking.
+ + + + + + + + + + + +We offer a supportive environment, and MINT-minorities are welcome!
+BSc and MSc students are full team members and have a working place in the lab. Science is infinite (hence we always have a long list of open questions) but unfortunately lab space isn’t. As a consequence, we can only offer a finite number of theses at any one time.
+ +Without exception, our thesis topics are connected to our own research, and by extension to things unknown. The ideal topic has a down-to-earth part (less exciting, but with very high chance of success) and a freestyle part (more difficult and higher risk, but also more exciting and with more space for creative contributions).
+ +Besides the advising PI, most undergraduate students are also mentored by a PhD student in day to day work.
+ +We try and find a good match between person and topic: To let you build on your strengths and experience, but also let you learn new things and give you space to grow. To apply, write to Fred Hamprecht with a short description of your interests plus CV and transcripts. MINT minorities (including female students and first-generation students) are particularly welcome!
+We work on making quantum chemical predictions with chemical accuracy, without orbitals and at a fraction of the cost.
+ + + + +Now headed by Anna Kreshuk at EMBL, ilastik facilitates quantitative image analysis and has many users in biology.
+ + + + +One decade of work from exactly solving the multicut problem, to the fast mutex watershed and the generalized gasp heuristic.
+ + + + +PlantSeg is a deep learning tool for cell instance segmentation tailored to the needs of plant biologists.
+ + + + +Most of our publications are found under +Fred’s Google Scholar Profile
+Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. +Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat.
+The Research Seminar: Advanced Machine Learning is a weekly reading group. The focus is on discussing current research papers and results in machine learning. The target audience is active researchers (postdocs, phd students and advanced master students) in the field who want to discuss and stay up to date with recent developments.
+ +Contact Peter Lippmann (peter.lippmann [at] iwr.uni-heidelberg.de) for further details.
+ +Next Seminar: 04.12.2023 in INF 205, SR 4.300 starting at 1:00pm
+Paper to be discussed:
Progress measures for grokking via mechanistic interpretability
+Neel Nanda, Lawrence Chan, Tom Lieberum, Jess Smith, Jacob Steinhardt
+https://arxiv.org/abs/2301.05217
Recently discussed papers:
+ +27.11.23
+GraphCast: Learning skillful medium-range global weather forecasting
+Remi Lam, Alvaro Sanchez-Gonzalez, Matthew Willson et al.
+https://arxiv.org/abs/2212.12794
13.11.23
+Transformers are efficient hierarchical chemical graph learners
+Zihan Pengmei, Zimu Li, Chih-chan Tien, Risi Kondor, Aaron R. Dinner
+https://arxiv.org/abs/2310.01704
06.11.23
+Free-form Flows: Make Any Architecture a Normalizing Flow
+Felix Draxler, Sorrenson, Peter Rangi, Rousselot, Armand Louis Amedee, Zimmermann, Lea, Ullrich Köthe
+https://arxiv.org/abs/2310.16624
30.10.23
+Nougat: Neural Optical Understanding for Academic Documents
+Lukas Blecher, Guillem Cucurull, Thomas Scialom, Robert Stojnic
+https://arxiv.org/abs/2308.13418
23.10.23
+White-Box Transformers via Sparse Rate Reduction
+Yaodong Yu, Sam Buchanan, Druv Pai, Tianzhe Chu, Ziyang Wu, Shengbang Tong, Benjamin D. Haeffele, Yi Ma
+https://arxiv.org/abs/2306.01129
16.10.23
+Emergence of Segmentation with Minimalistic White-Box Transformers
+Yaodong Yu, Tianzhe Chu, Shengbang Tong, Ziyang Wu, Druv Pai, Sam Buchanan, Yi Ma
+https://arxiv.org/abs/2308.16271
09.10.23
+Large Language Models as Optimizers
+Chengrun Yang, Xuezhi Wang, Yifeng Lu, Hanxiao Liu, Quoc V. Le, Denny Zhou, Xinyun Chen
+https://arxiv.org/abs/2309.03409
02.10.23
+PointLLM: Empowering Large Language Models to Understand Point Clouds
+Runsen Xu, Xiaolong Wang, Tai Wang, Yilun Chen, Jiangmiao Pang, Dahua Lin
+https://arxiv.org/abs/2308.16911
25.09.23
+Loss of Plasticity in Deep Continual Learning
+Shibhansh Dohare, J. Fernando Hernandez-Garcia, Parash Rahman, Richard S. Sutton, A. Rupam Mahmood
+https://arxiv.org/abs/2306.13812
18.09.23
+Tuning Computer Vision Models With Task Rewards
+André Susano Pinto, Alexander Kolesnikov, Yuge Shi, Lucas Beyer, Xiaohua Zhai
+https://openreview.net/forum?id=zzOooeAqtT
11.09.23
+Deep Learning on Implicit Neural Representations of Shapes
+Luca De Luigi, Adriano Cardace, Riccardo Spezialetti, Pierluigi Zama Ramirez, Samuele Salti, Luigi Di Stefano
+https://arxiv.org/abs/2302.05438
28.08.23
+Equivariant Diffusion for Molecule Generation in 3D
+Emiel Hoogeboom, Victor Garcia Satorras, Clément Vignac, Max Welling
+https://arxiv.org/abs/2203.17003
21.08.23
+Fourier Neural Operator for Parametric Partial Differential Equations
+Zongyi Li, Nikola Kovachki, Kamyar Azizzadenesheli, Burigede Liu, Kaushik Bhattacharya, Andrew Stuart, Anima Anandkumar
+https://arxiv.org/abs/2010.08895
14.08.23
+Equivariant Architectures for Learning in Deep Weight Spaces
+Aviv Navon, Aviv Shamsian, Idan Achituve, Ethan Fetaya, Gal Chechik, Haggai Maron
+https://openreview.net/forum?id=SCU1xlr9Y4
07.08.23
+VectorAdam for Rotation Equivariant Geometry Optimization
+Selena Ling, Nicholas Sharp, Alec Jacobson
+https://openreview.net/forum?id=df1g_KeEjQ
31.07.23
+Adding Conditional Control to Text-to-Image Diffusion Models
+Lvmin Zhang and Maneesh Agrawala
+https://arxiv.org/pdf/2302.05543.pdf
24.07.23
+DeepSea: An efficient deep learning model for single-cell segmentation and tracking of time-lapse microscopy images
+Zargari, Abolfazl, et al.
+https://www.biorxiv.org/content/10.1101/2021.03.10.434806v2.abstract
17.07.23
+Track Anything: Segment Anything Meets Videos
+Jinyu Yang, Mingqi Gao, Zhe Li, Shang Gao, Fangjing Wang, Feng Zheng
+https://arxiv.org/abs/2304.11968
10.07.23
+Trans-Dimensional Generative Modeling via Jump Diffusion Models
+Andrew Campbell, William Harvey, Christian Weilbach, Valentin De Bortoli, Tom Rainforth, Arnaud Doucet
+https://arxiv.org/abs/2305.16261
03.07.23
+Scaling Transformer to 1M tokens and beyond with RMT
+Aydar Bulatov, Yuri Kuratov, Mikhail S. Burtsev
+https://arxiv.org/abs/2304.11062
26.06.23
+Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold
+Xingang Pan, Ayush Tewari, Thomas Leimkühler, Lingjie Liu, Abhimitra Meka, Christian Theobalt
+https://arxiv.org/abs/2305.10973
19.06.23
+Seeing is Believing: Brain-Inspired Modular Training for Mechanistic Interpretability
+Ziming Liu, Eric Gan, Max Tegmark
+https://arxiv.org/abs/2305.08746
12.06.23
+Supervised Training of Conditional Monge Maps
+Charlotte Bunne, Andreas Krause, Marco Cuturi
+https://arxiv.org/abs/2206.14262
05.06.23
+Causal Reasoning and Large Language Models: Opening a New Frontier for Causality
+Emre Kıcıman, Robert Ness, Amit Sharma, Chenhao Tan
+https://arxiv.org/abs/2305.00050
22.05.23
+How Attentive are Graph Attention Networks?
+Shaked Brody, Uri Alon, Eran Yahav
+https://arxiv.org/abs/2105.14491
15.05.23
+Sparks of Artificial General Intelligence: Early experiments with GPT-4
+Sébastien Bubeck, Varun Chandrasekaran, Ronen Eldan et al
+https://arxiv.org/abs/2303.12712
08.05.23
+Discrete Variational Autoencoders
+Jason Tyler Rolfe
+https://arxiv.org/abs/1609.02200
24.04.23
+Is the Performance of My Deep Network Too Good to Be True? A Direct Approach to Estimating the Bayes Error in Binary Classification
+Takashi Ishida, Ikko Yamane, Nontawat Charoenphakdee, Gang Niu, Masashi Sugiyama
+https://openreview.net/forum?id=FZdJQgy05rz
17.04.23
+Image as Set of Points
+Xu Ma, Yuqian Zhou, Huan Wang, Can Qin, Bin Sun, Chang Liu, Yun Fu
+https://openreview.net/forum?id=awnvqZja69
03.04.23
+Advancing mathematics by guiding human intuition with AI
+Davies, A., Veličković, P., Buesing, L., Blackwell, S., Zheng, D., Tomašev, N., … & Kohli, P
+https://www.nature.com/articles/s41586-021-04086-x
27.03.23
+DreamFusion: Text-to-3D using 2D Diffusion
+Ben Poole, Ajay Jain, Jonathan T. Barron, Ben Mildenhall
+https://openreview.net/forum?id=FjNys5c7VyY
20.03.23
+Flow Matching for Generative Modeling
+Yaron Lipman, Ricky T. Q. Chen, Heli Ben-Hamu, Maximilian Nickel, Matt Le
+https://arxiv.org/pdf/2210.02747.pdf
Name | +Role | +
---|---|
Fahimeh Moafian | +Postdoctoral Researcher | +
We are physicists, mathematicians, computer scientists and engineers, united by the 💗 for science. One of us originally studied languages, and one is a chemist gone astray.
+ +Name | +Role | +
---|---|
Lennart Bürger | +MSc Student | +