[go: up one dir, main page]

Direkt zum Inhalt springen
Computer Vision Group
TUM School of Computation, Information and Technology
Technical University of Munich
Technical University of Munich Menu

Links

Informatik IX
Computer Vision Group

Boltzmannstrasse 3
85748 Garching info@vision.in.tum.de

Follow us on:

YouTube X / Twitter Facebook

News

24.10.2024

LSD SLAM received the ECCV 2024 Koenderink Award for standing the Test of Time.

03.07.2024

We have seven papers accepted to ECCV 2024. Check our publication page for more details.

09.06.2024
GCPR / VMV 2024

GCPR / VMV 2024

We are organizing GCPR / VMV 2024 this fall.

04.03.2024

We have twelve papers accepted to CVPR 2024. Check our publication page for more details.

18.07.2023

We have four papers accepted to ICCV 2023. Check out our publication page for more details.

More



Seminar: Deep Learning for the Natural Sciences (5 ECTS)

Winter Semester 2024

Organiser: Karnik Ram (karnik.ram@tum.de)

Preliminary meeting : 11.07.24. Slides

Description

Following its success in computer vision and language processing, deep learning is now being increasingly used to augment and accelerate research in the natural sciences. Examples include electro-catalyst discovery for energy storage, fast PDE solvers for weather forecasting, discovery of new anti-biotics, and many other advances that were not possible using traditional methods alone. In this seminar, we will discuss relevant papers in this new area, with an emphasis on the deep learning techniques powering these approaches such as geometric deep learning, generative models, and self-supervised learning.

Format
  • Students are expected to study one paper in depth, and present and lead a discussion on it. Apart from the presentation and report, students are also expected to periodically submit one-paragraph summaries of the papers discussed, and participate in the discussions.
  • Sessions will be held in-person (with a remote attendance option) once every two weeks, on Tuesday afternoon (14:30 - 16:30). There will be two paper presentations in every session. There will also be a catch-up lecture on certain relevant topics from deep learning (eg. diffusion models, graph learning) at the start based on interest.
  • All class-related communications are over Discord, and the summaries, presentation, and report are managed on Gradescope.
Prerequisites

A good understanding of machine learning techniques (esp. deep learning), linear algebra, and calculus. Undergraduate students are requested to check with the organizer before enrolling.

Schedule
List of potential papers
No. Paper
1 Continuous PDE Dynamics Forecasting with Implicit Neural Representations
2 Neural Operator: Learning Maps Between Function Spaces
3 Equivariant Graph Neural Operator for Modeling 3D Dynamics
4 E(3)-equivariant graph neural networks for data-efficient and accurate interatomic potentials
5 Learning Local Equivariant Representations for Large-Scale Atomistic Dynamics
6 Action Matching: Learning Stochastic Dynamics from Samples
7 ClimODE: Climate and Weather Forecasting with Physics-informed Neural ODEs
8 GenCast: Diffusion-based ensemble forecasting for medium-range weather
9 Aurora: A Foundation Model of the Atmosphere
10 Fine-Tuned Language Models Generate Stable Inorganic Materials as Text
11 FlowMM: Generating Materials with Riemannian Flow Matching
12 Spherical Channels for Modeling Atomic Interactions
13 MatterGen: a generative model for inorganic materials design
14 MatterSim: A Deep Learning Atomistic Model Across Elements, Temperatures and Pressures
15 Scaling deep learning for materials discovery
16 Highly accurate protein structure prediction with AlphaFold 2
17 Accurate structure prediction of biomolecular interactions with AlphaFold 3
18 DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking
19 AlphaFold Meets Flow Matching for Generating Protein Ensembles
20 Real-time gravitational-wave science with neural posterior estimation
21 All-in-one simulation-based inference
22 LVM-Med: Learning Large-Scale Self-Supervised Vision Models for Medical Imaging via Second-order Graph Matching
23 BioCLIP: A Vision Foundation Model for the Tree of Life
24 KAN 2.0: Kolmogorov-Arnold Networks Meet Science
25 Discovering Symbolic Models from Deep Learning with Inductive Biases
26 Locality-Sensitive Hashing-Based Efficient Point Transformer with Applications in High-Energy Physics
Additional Resources

Rechte Seite

Informatik IX
Computer Vision Group

Boltzmannstrasse 3
85748 Garching info@vision.in.tum.de

Follow us on:

YouTube X / Twitter Facebook

News

24.10.2024

LSD SLAM received the ECCV 2024 Koenderink Award for standing the Test of Time.

03.07.2024

We have seven papers accepted to ECCV 2024. Check our publication page for more details.

09.06.2024
GCPR / VMV 2024

GCPR / VMV 2024

We are organizing GCPR / VMV 2024 this fall.

04.03.2024

We have twelve papers accepted to CVPR 2024. Check our publication page for more details.

18.07.2023

We have four papers accepted to ICCV 2023. Check out our publication page for more details.

More