| Date | Moderator | Moderator Link | Topic | To Read |
| 20.09.2024 | Adam Harmanec | YOLOv10: Real-Time End-to-End Object Detection | 
 |
| 19.07.2024 | Adam Harmanec | Trackastra: Transformer-based cell tracking for live-cell microscopy | 
|
| 07.06.2024 | Tomas Karella | Making Convolutional Networks Shift-Invariant Again | 
|
| 24.05.2024 | Michal Bartos | Plug-and-Play Image Restoration with Deep Denoiser Prior | 
|
| 26.04.2024 | Tomas Karella | Deep Networks with Stochastic Depth | 
|
| 12.04.2024 | Jan Kotera | Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture | 
|
| 15.03.2024 | Adam Harmanec | TrackFormer: Multi-Object Tracking with Transformers | 
|
| 25.02.2024 | Tomas Karella | CoAtNet: Marrying Convolution and Attention for All Data Sizes | 
|
| 16.02.2024 | Adam Novozamsky | Learning Continuous Image Representation with Local Implicit Image Function | 
|
| 19.01.2024 | Tomas Kerepecky | NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis | 
|
| 05.01.2024 | Tomas Karella | ImageBind: One Embedding Space To Bind Them All | 
|
| 15.12.2023 | Adam Harmanec | DETR: End-to-End Object Detection with Transformers | 
|
| 10.11.2023 | Tomas Karella | BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding | 
|
| 20.10.2023 | Adam Harmanec | Progressive Distillation for Fast Sampling of Diffusion Models | 
|
| 08.08.2023 | Vaclav Kosik | LORA: Low-Rank Adaptation of Large Language Models | 
|
| 18.08.2023 | Antonie Brozova | A Unified Framework for U-Net Design and Analysis | 
|
| 14.07.2023 | Adam Harmanec | Space-Time Correspondence as a Contrastive Random Walk | 
|
| 29.06.2023 | Filip Sroubek | Amortised MAP Inference for Image Super-resolution | 
|
| 12.06.2023 | Tomas Karella | DINOv2: A Self-supervised Vision Transformer Model | 
|
| 02.06.2023 | Adam Harmanec | DINO: Emerging Properties in Self-Supervised Vision Transformers | 
|
| 19.05.2023 | Adam Novozamsky | CLIP: Learning Transferable Visual Models From Natural Language Supervision | 
|
| 05.05.2023 | Tomas Karella | SAM: Segment Anything | 
|
| 14.04.2023 | Tomas Karella | How Do Vision Transformers Work? | 
|
| 24.03.2023 | Tomas Karella | LDMs: High-Resolution Image Synthesis with Latent Diffusion Models | 
|
| 03.03.2023 | Tomas Kerepecky | DMs: Denoising Diffusion Probabilistic Models | 
|
| 14.02.2023 | Adam Harmanec | ConvNeXt: A ConvNet for the 2020s | 
|
| 20.01.2023 | Tomas Karella | MaxViT: Multi-Axis Vision Transformer | 
|
| 02.12.2022 | Tomas Karella | A Survey of Visual Transformers | 
|