|
1 | 1 | # Materials from the weekly seminar of the MI^2 group <img src="prezentacja.png" align="right" width="300"/> |
2 | 2 |
|
3 | | -We meet every Monday, at 10 AM in MI^2 DataLab (room 044, Faculty of Mathematics and Information Science, Warsaw University of Technology) or online. |
| 3 | +We meet every Monday, at 10 AM in **room 5.04 at Rektorska 4**, Warsaw University of Technology - or online. |
4 | 4 |
|
5 | 5 | Join us at https://meet.drwhy.ai. |
6 | 6 |
|
7 | | -## Year 2024/2025 |
8 | | - |
9 | | -### Spring semester |
10 | | - |
11 | | -* 24.02 - [Tracking information flow in biosystems from high-throughput data](https://github.com/MI2DataLab/MI2DataLab_Seminarium/tree/master/2025/2025_02_24_tracking_information_flow) - Miron Kursa |
12 | | -* 03.03 - Introduction to Sparse Autoencoders SAE with [ReLU](https://transformer-circuits.pub/2024/scaling-monosemanticity/) (Anthropic; Blog; 21.05.2024), [TopK](https://openreview.net/forum?id=tcsZt9ZNKD) (OpenAI; ICLR 2025; 06.06.2025) and [JumpReLU](https://openreview.net/forum?id=XkMrWOJhNd) (DeepMind; 09.08.2024; EMNLP 2024 Workshop) - (advising Vladimir) |
13 | | -* 10.03 - [Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models](https://openreview.net/forum?id=I4e82CIDxv) (Northeastern University; ICLR 2025; 31.03.2025) - (advising Vladimir) |
14 | | -* 17.03 - [Sparse Autoencoders Do Not Find Canonical Units of Analysis](https://openreview.net/forum?id=9ca9eHNrdH) (Durham University/Independent; ICLR 2025; 07.02.2025) - (advising Vladimir) |
15 | | -* 24.03 - [Interpreting CLIP with Hierarchical Sparse Autoencoders](https://arxiv.org/abs/2502.20578) (My paper; Under Review; 30.01.2025) - Vladimir Zaigrajew |
16 | | -* 31.03 - [ProtoViT: Interpretable image classification with adaptive prototype-based vision transformers](https://openreview.net/forum?id=hjhpCJfbFG) - Paweł Gelar |
17 | | -* 07.04 - [PIP-Net: Patch-based intuitive prototypes for interpretable image classification](https://openaccess.thecvf.com/content/CVPR2023/html/Nauta_PIP-Net_Patch-Based_Intuitive_Prototypes_for_Interpretable_Image_Classification_CVPR_2023_paper.html) - Karol Dobiczek |
18 | | -* 14.04 - [Birds look like cars: Adversarial analysis of intrinsically interpretable deep learning](https://arxiv.org/abs/2503.08636) - Hubert Baniecki |
19 | | -* 28.04 - Vlad (ICLR) |
20 | | -* 05.05 - [Explaining in Diffusion: Explaining a Classifier Through Hierarchical Semantics with Text-to-Image Diffusion Models](https://arxiv.org/abs/2412.18604) - Jakub Świstak |
21 | | -* 12.05 - [Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model](https://github.com/MI2DataLab/MI2DataLab_Seminarium/tree/master/2025/2025_05_12_denoising_diffusion_null_space_models) - Jakub Grzywaczewski |
22 | | -* 19.05 - [Diffusion Posterior Sampling for General Noisy Inverse Problems](https://arxiv.org/abs/2209.14687) - Tymoteusz Kwieciński |
23 | | -* 26.05 - [DiG-IN: Diffusion Guidance for Investigating Networks -- Uncovering Classifier Differences Neuron Visualisations and Visual Counterfactual Explanations](https://arxiv.org/abs/2311.17833) - Dawid Płudowski |
24 | | -* 31.05 - Wyjazd zespołu do Wilgi |
25 | | -* 02.06 |
26 | | -* 09.06 |
| 7 | +## Year 2025/2026 |
27 | 8 |
|
28 | 9 | ### Fall semester |
29 | 10 |
|
30 | | -#### Schedule for the first half of the semester (track: Context matters in Deep Learning Models - Computer Vision): |
31 | | - |
32 | | -* 07.10 - guest lecture by nadkom. dr Paweł Olber |
33 | | -* 14.10 - Do Not Explain Vision Models without Context - Paulina Tomaszewska |
34 | | -* 21.10 - [Positional Label for Self-Supervised Vision Transformer](https://github.com/MI2DataLab/MI2DataLab_Seminarium/tree/master/2024/2024_10_21_Positional_Label_for_Self-Supervised_Vision_Transformer) - Filip Kołodziejczyk |
35 | | -* 28.10 - [Adversarial examples vs. context consistency defense for object detection](https://github.com/MI2DataLab/MI2DataLab_Seminarium/tree/master/2024/2024_10_28_Adversarial_attacks_against_object_detection.md) - Hubert Baniecki |
36 | | -* 04.11 - [Unlocking the Power of Spatial and Temporal Information in Medical Multimodal Pre-training](https://github.com/MI2DataLab/MI2DataLab_Seminarium/tree/master/2024/2024_11_04_Unlocking_the_Power_of_Spatial_and_Temporal_Information_in_Medical_Multimodal_Pre-training) - Bartosz Kochański |
37 | | -* 18.11 - User study: Visual Counterfactual Explanations for Improved Model Understanding - Bartek Sobieski |
38 | | -* 25.11 - [Vision Transformers provably learn spatial structure](https://github.com/MI2DataLab/MI2DataLab_Seminarium/tree/master/2024/2024_11_25_Vision_Transformers_provably_learn_spatial_structure) - Vladimir Zaigrajew |
39 | | -* 02.12 - [Null-text Inversion for Editing Real Images using Guided Diffusion Models](https://github.com/MI2DataLab/MI2DataLab_Seminarium/tree/master/2024/2024_12_02_Null_text_optimization_for_editing_real_images) - Dawid Płudowski |
40 | | -* 09.12 - [Diffusion-Based Scene Graph to Image Generation with Masked Contrastive Pre-Training](https://github.com/MI2DataLab/MI2DataLab_Seminarium/tree/master/2024/2024_12_09_Diffusion_Based_Scene_Graph_to_Image_Generation_with_Masked_Contrastive_Pre_Training) - Tymoteusz Kwieciński |
41 | | -* 16.12 - [Rethinking Visual Counterfactual Explanations Through Region Constraint](https://github.com/MI2DataLab/MI2DataLab_Seminarium/tree/master/2024/2024_12_16_rethinking_visual_counterfactual_explanations_through_region_constraint) - Bartek Sobieski |
42 | | -* 13.01 - [Controlling The World by Sleight of Hand](https://github.com/MI2DataLab/MI2DataLab_Seminarium/tree/master/2025/2025_01_13_controlling_the_world_by_sleight_of_hand) - Jakub Świstak |
43 | | -* 20.01 - Connecting counterfactual and attributions modes of explanation - Jan Jakubik |
44 | | - |
45 | | -## Year 2023/2024 |
46 | | - |
47 | | -### Summer semester |
48 | | - |
49 | | -#### Schedule |
50 | | - |
51 | | -* 19.02.2024 - PhD Thesis discussion Explanation methods for sequential data model |
52 | | -* 26.02.2024 - PhD Thesis discussion Modele rekomendacyjne wspólnej filtracji w serwisach ogłoszeniowych |
53 | | -* 04.02.2024 - PhD Thesis presentation Modele rekomendacyjne wspólnej filtracji w serwisach ogłoszeniowych |
54 | | -* 11.03.2024 - PhD Thesis discussion Analysis and texture recognition of digital images for computer aided skin lesions diagnostics |
55 | | -* 18.03.2024 - PhD Thesis presentation Analysis and texture recognition of digital images for computer aided skin lesions diagnostics |
56 | | -* 25.03.2024 - Law in AI - Andrzej Porębski |
57 | | -* 08.04.2024 - [Introduction to counterfactual explanations track](https://github.com/MI2DataLab/MI2DataLab_Seminarium/tree/master/2024/2024_04_08_Intro_to_CEs) - Mateusz Krzyziński, Bartek Sobieski |
58 | | -* 15.04.2024 - [The Privacy Issue of Counterfactual Explanations: Explanation Linkage Attacks](https://github.com/HubertR21/MI2DataLab_Seminarium/tree/master/2024/2024_04_15_explanation_linkage_attacks) - Mikołaj Spytek |
59 | | -* 22.04.2024 - [Text-to-Image Models for Counterfactual Explanations: A Black-Box Approach](https://github.com/MI2DataLab/MI2DataLab_Seminarium/tree/master/2024/2024_04_22_TIME_Text-To-Image_For_Counterfactual_Explanations) - Tymoteusz Kwieciński |
60 | | -* 06.05.2024 - [GLOBE-CE: A Translation Based Approach for Global Counterfactual Explanations](https://github.com/MI2DataLab/MI2DataLab_Seminarium/tree/master/2024/2024_05_06_GLOBE-CE) - Piotr Wilczyński |
61 | | -* 13.05.2024 - [Introduction to ViT and transformer attributions](https://github.com/MI2DataLab/MI2DataLab_Seminarium/tree/master/2024/2024_05_13_Introduction_to_Visual_Transformers_and_Transformer_Attributions/) - Filip Kołodziejczyk |
62 | | -* 20.05.2024 - MI^2 PhD thesis presentations - Weronika Guzik, Katarzyna Kobylińska, Katarzyna Woźnica. |
63 | | -* 27.05.2024 - [AtMan: Understanding Transformer Predictions Through Memory Efficient Attention Manipulation](https://github.com/MI2DataLab/MI2DataLab_Seminarium/tree/master/2024/2024_06_03_AtMan) - Maciej Chrabąszcz |
64 | | -* 03.06.2024 - [Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet](https://github.com/MI2DataLab/MI2DataLab_Seminarium/tree/master/2024/2024_06_03_Scaling_Monosemanticity) - Vladimir Zaigrajew |
65 | | -* 10.06.2024 - Semester summary and discussion. |
66 | | - |
67 | | -### Winter semester |
68 | | - |
69 | 11 | #### Schedule |
70 | 12 |
|
71 | | -* 09.10.2023 - [Organizational matters](https://github.com/MI2DataLab/MI2DataLab_Seminarium/tree/master/2023/2023_10_09_Organizational_matters_winter_edition) - Hubert Baniecki, Maciej Chrabąszcz, Bartek Sobieski |
72 | | -* 16.10.2023 - [On Minimizing the Impact of Dataset Shifts on Actionable Explanations](https://github.com/MI2DataLab/MI2DataLab_Seminarium/blob/master/2023/2023_10_16_impact_of_dataset_shifts_on_actionable_eplanations.txt) - Hubert Baniecki |
73 | | -* 23.10.2023 - [On the Robustness of Removal-Based Feature Attributions](https://github.com/MI2DataLab/MI2DataLab_Seminarium/tree/master/2023/2023_10_23_removal_based_attributions_robustness) - Mateusz Krzyziński |
74 | | -* 30.10.2023 - Discussion - AdvXAI: Robustness of explanations |
75 | | -* 06.11.2023 - [Representation Engineering](https://github.com/maciejchrabaszcz/MI2DataLab_Seminarium/tree/master/2023/2023_11_06_Representation_Engineering) - Maciej Chrabąszcz |
76 | | -* 13.11.2023 - [Adaptive Testing of Computer Vision Models](https://github.com/MI2DataLab/MI2DataLab_Seminarium/tree/master/2023/2023_11_13_Adaptive_Testing_of_Computer_Vision_Models) - Mikołaj Spytek |
77 | | -* 20.11.2023 - [Red Teaming Language Models with Language Models](https://github.com/MI2DataLab/MI2DataLab_Seminarium/tree/master/2023/2023_11_20_Red_Teaming_Language_Models_with_Language_Models) - Piotr Wilczyński |
78 | | -* 27.11.2023 - [Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned](https://github.com/MI2DataLab/MI2DataLab_Seminarium/tree/master/2023/2023_11_27_Red_Teaming_Language_Models_to_Reduce_Harms) - Vladimir Zaigrajew |
79 | | -* 04.12.2023 - Discussion - RedTeaming of foundation models |
80 | | -* 11.12.2023 - [Introduction to Diffusion Models](https://github.com/MI2DataLab/MI2DataLab_Seminarium/tree/master/2023/2023_12_11_intro_to_diffusion_models) - Bartek Sobieski |
81 | | -* 18.12.2023 - [Glaze: Protecting artists from style mimicry by text-to-image model](https://github.com/MI2DataLab/MI2DataLab_Seminarium/tree/master/2023/2023_12_18_glaze_protecting_artists_from_style_mimicry) - Tymoteusz Kwieciński |
82 | | -* 08.01.2023 - [FLIRT: Feedback Loop In-context Red Teaming](https://github.com/HubertR21/MI2DataLab_Seminarium/tree/patch-2/2024/2024_01_08_FLIRT_Feedback_Loop_In-context_Red_Teaming) - Hubert Ruczyński |
83 | | -* 15.01.2024 - [Red-Teaming the Stable Diffusion Safety Filter](https://github.com/MI2DataLab/MI2DataLab_Seminarium/tree/master/2023/2024_01_15_red_teaming_stable_diffusion_safety_filter) - Mateusz Grzyb |
84 | | -* 22.01.2024 - Discussion - Diffusion models for XAI |
| 13 | +* 06.10 - organizational meeting |
| 14 | +* 13.10 - Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models - Bartosz Kochański |
| 15 | +* 20.10 - Michał Włodarczyk |
| 16 | +* 27.10 - Monthly sync meeting (Hubert Baniecki, Dawid Płudowski, Julian Sienkiewicz) |
| 17 | +* 03.11 - Jakub Grzywaczewski |
| 18 | +* 17.11 - Bartek Sobieski |
| 19 | +* 24.11 - Monthly sync meeting (Paulina Tomaszewska, Paweł Struski, Vladimir Zaigrajew) |
| 20 | +* 01.12 - Dawid Płudowski |
| 21 | +* 08.12 - Kamil Książek |
| 22 | +* 15.12 - Monthly sync meeting (Bartek Sobieski, Jakub Grzywaczewski, Michał Włodarczyk) |
| 23 | +* 12.01 - Agata Kaczmarek |
| 24 | +* 19.01 - Monthly sync meeting (Kamil Książek, Bartosz Kochański, Agata Kaczmarek) |
| 25 | +* 19.01 - Retro meeting |
85 | 26 |
|
86 | 27 | **Overviews of previous editions** |
| 28 | +[2024/2025](https://github.com/MI2DataLab/MI2DataLab_Seminarium/blob/master/README_ARCHIVE_24_25.md) |
| 29 | +[2023/2024](https://github.com/MI2DataLab/MI2DataLab_Seminarium/blob/master/README_ARCHIVE_23_24.md) |
87 | 30 | [2022/2023](https://github.com/MI2DataLab/MI2DataLab_Seminarium/blob/master/README_ARCHIVE_22_23.md) |
88 | | -[2021/2022](https://github.com/MI2DataLab/MI2DataLab_Seminarium/blob/master/README_ARCHIVE.md) |
| 31 | +[2021/2022 and prior](https://github.com/MI2DataLab/MI2DataLab_Seminarium/blob/master/README_ARCHIVE.md) |
0 commit comments