└── README.md /README.md: -------------------------------------------------------------------------------- 1 | # Machine Learning 2 | 3 | Seminarium magisterskie MIMUW 4 | 5 | ## Plan spotkań 2024/2025 6 | * 2024-10-03 spotkanie organizacyjne 7 | * 2024-10-10 spotkanie organizacyjne 8 | * 2024-10-17 Kamil Ciebiera - [Mamba 2](https://docs.google.com/presentation/d/1VExGaY-5wygUkxQIdU8cHCvwcba20_5Gn6DA2ZfXEBc/edit?usp=sharing) , Ewa Dobrowolska - [Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problem](https://arxiv.org/abs/2402.02868) 9 | * 2024-10-24 Stanisław Świątkowski - [On the Measure of Intelligence](https://arxiv.org/abs/1911.01547), Paweł Narkiewicz - [LiPO: Listwise Preference Optimization through 10 | Learning-to-Rank](https://arxiv.org/pdf/2402.01878) 11 | * 2024-10-31 Piotr Kamiński - [Physics of Language Models](https://physics.allen-zhu.com) 12 | * 2024-11-07 Przełożone ze względu na MLinPL 13 | * 2024-11-14 Paweł Wojciechowski - [Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)](https://arxiv.org/abs/2402.10376), Maciej Raczuk - [Multi-turn Reinforcement Learning from Preference Human Feedback](https://arxiv.org/abs/2405.14655) 14 | * 2024-11-21 Jakub Kołaczyński - [Diffusion Models Are Real-Time Game Engines](https://arxiv.org/abs/2408.14837) 15 | * 2024-11-28 Julian Kwiatkowski - [Let's Verify Step by Step](https://arxiv.org/abs/2305.20050) 16 | * 2024-12-05 Rafał Powalski (Ingenix.ai) - [Drug Design Topics](https://docs.google.com/presentation/d/1GPxgm4NwPHDxmaNDQQNRItk0W08skOBw/edit#slide=id.g308c4833079_1_1) 17 | * 2024-12-12 - 18 | * 2024-12-19 Bartłomiej Sadlej, Przemysław Pietrzak [Simulating 500 million years of evolution with a language model 19 | ](https://www.biorxiv.org/content/10.1101/2024.07.01.600583v1) 20 | * 2024-01-16- 21 | * 2024-01-23- Mikołaj Garstecki [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://arxiv.org/pdf/2305.10601#cite.wei2022chain) 22 | * 2025-03-06 Kamil Ciebiera, Przemysław Pietrzak: Deepseek 23 | * 2025-03-13 Paweł Siwak [LIMO: Less is More for Reasoning](https://arxiv.org/abs/2502.03387) 24 | * 2025-03-27 Jakub Kołaczyński [Diffusion Models already have a Semantic Latent Space](https://arxiv.org/abs/2210.10960) 25 | * 2025-04-03 Bartłomiej Sadlej [Rethinking Visual Counterfactual Explanations Through Region Constraint](https://arxiv.org/abs/2410.12591) 26 | * 2025-05-15 Julian Kwiatkowski [Learn Beyond The Answer: Training Language Models with Reflection for Mathematical Reasoning](https://arxiv.org/pdf/2406.12050) 27 | * 2025-05-29 Łukasz Smoliński [Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solvers](https://arxiv.org/abs/2408.06195), Maksym Matviienko [Self-Reflection in LLM Agents: Effects on Problem-Solving Performance](https://arxiv.org/abs/2405.06682) 28 | * 2025-06-05 Ignacy Stępniewski [Large Language Diffusion Models](https://arxiv.org/abs/2502.09992) 29 | * 2025-06-12 Marek Lisowski [Open-Endedness is Essential for Artificial Superhuman Intelligence](https://arxiv.org/pdf/2406.04268) 30 | 31 | ## Plan spotkań 2023/2024 32 | * 2023-10-05 spotkanie organizacyjne 33 | * 2023-10-12 przykłady projektów magisterskich 34 | * 2023-10-19 Maksymilian Grochowski [VOYAGER: An Open-Ended Embodied Agent with Large Language Models](https://voyager.minedojo.org/assets/documents/voyager.pdf) 35 | * 2023-10-26 - 36 | * 2023-11-09 Władek Pałucki [Reward Design with Language Models](https://arxiv.org/abs/2303.00001), Maciej Sygnowski [ProAgent: Building Proactive Cooperative AI with Large Language Models](https://arxiv.org/pdf/2308.11339.pdf) 37 | * 2023-11-16 Witold Drzewakowski ([Eureka](https://arxiv.org/abs/2310.12931)), Mateusz Boruń ([Universal Approximation Theorem for MLP](http://neuralnetworksanddeeplearning.com/chap4.html)) 38 | * 2023-11-23 Franciszek Szarwacki (Can Large Language Models Reason about Program Invariants? [Paper](https://openreview.net/pdf?id=mXv2aVqUGG), [Slides](https://docs.google.com/presentation/d/1zMHMt7krLMO23OAEOgdxfXisUP0jWJA2vetFk_8IZd8/edit?usp=sharing)) 39 | * 2023-11-30 Ewa Dobrowolska [Code as Policies: Language Model Programs for Embodied Control](https://arxiv.org/pdf/2209.07753.pdf), Kamil Jonak ([LLM as General Pattern Machines](https://arxiv.org/abs/2307.04721?fbclid=IwAR2iP7irl2dvT_NhlsgmyzFDuHuSm2Hk4oN11AfKNl747SJgFnVrToCM4fU)) 40 | * 2023-12-07 Kamil Ciebiera [LLMs and the Abstraction and Reasoning Corpus](https://arxiv.org/pdf/2305.18354.pdf), Krystian Król [Low-Resource Languages Jailbreak GPT-4](https://arxiv.org/pdf/2310.02446.pdf) 41 | * 2023-12-14 Bartłomiej Sadlej [Autogen](https://github.com/microsoft/autogen#autogen) 42 | * 2023-12-21 43 | * 2024-01-11 Przemysław Pietrzak [ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate](https://arxiv.org/abs/2308.07201) [slides](https://docs.google.com/presentation/d/1knu42Xzg2iO_6q9jpmXeXhemzNsTox04vGxcOniWazg/edit?usp=sharing) 44 | * 2024-01-18 Maciej Białobrzeski [The Reversal Curse:LLMs trained on “A is B” fail to learn “B is A”](https://arxiv.org/pdf/2309.12288.pdf) 45 | * 2024-01-25 Mikael Jaworowski (zastosowania Random Matrix Theory w przewidywaniu siły wiązania się potencjalnych leków do wybranych receptorów), Maciej Raczuk [Discovering faster matrix multiplication algorithms with reinforcement learning](https://www.nature.com/articles/s41586-022-05172-4)([slides](https://www.overleaf.com/read/kvdgghytxynm#b74bb7)) 46 | * 2024-02-29 spotkanie organizacyjne - semestr letni 47 | * 2024-03-07 Kamil Ciebiera + Krystian Król: MoE-Mamba + background (Mamba/Switch) [Slajdy](https://docs.google.com/presentation/d/1SYMUzSjQqSCP7CrRar7diUb4pSHJ-sf5iykRr4RTefo/edit?usp=sharing) 48 | * 2024-03-14 Bartłomiej Sadlej i Stanisław Świątkowski - Consistency Models https://arxiv.org/abs/2303.01469 49 | * 2024-03-21 50 | * 2024-03-26 Krzysztof Tomala [Solving olympiad geometry without human demonstrations](https://www.nature.com/articles/s41586-023-06747-5) 51 | * 2024-04-04 Ewa Dobrowolska [Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking](https://arxiv.org/pdf/2403.09629.pdf) 52 | * 2024-04-11 Przemysław Pietrzak i Paweł Wojciechowski [AttnLRP: Attention-Aware Layer-wise Relevance Propagation 53 | for Transformers](https://arxiv.org/abs/2402.05602) [Slides](https://drive.google.com/file/d/1NTL_eIe7O5-mX3kbXfvEOIk3ch_Ldpvt/view?usp=sharing) 54 | * 2024-04-18 55 | * 2024-04-25 Franciszek Szarwacki [Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding](https://arxiv.org/abs/2310.05424) ([Slides](https://docs.google.com/presentation/d/1LKpSUQcF0M-lNA5ygNayAwov-RqrpCBcQYfmaD8N170/edit?usp=sharing)) 56 | * 2024-05-09 Michał Sala [Musika! Fast Infinite Waveform Music Generation](https://arxiv.org/abs/2208.08706) 57 | * 2024-05-16 Radosław Jurczak [Evaluating the Moral Beliefs Encoded in LLMs](https://arxiv.org/abs/2307.14324) [slides](https://drive.google.com/file/d/1x221bbDbYvJMhOH1MbQNkhEXVDTv71my/view?usp=sharing), Piotr Kamiński [GPT-4 IS TOO SMART TO BE SAFE: STEALTHY CHAT WITH LLMS VIA CIPHER](https://arxiv.org/pdf/2308.06463) 58 | * 2024-05-23 Witold Drzewakowski [NLHF](https://arxiv.org/abs/2312.00886), Mateusz Szymański [VampNet: Music Generation via Masked Acoustic Token Modeling](https://arxiv.org/pdf/2307.04686) 59 | * 2024-06-06 Władek Pałucki [Contrastive Reinforcement Learning](https://arxiv.org/abs/2206.07568), Maks Grochowski [Learning Curricula in Open-Ended Worlds](https://arxiv.org/abs/2312.03126) 60 | * 2024-06-13 Szymon Sadkowski [Efficient Streaming Language Models with Attention Sinks](https://arxiv.org/abs/2309.17453), Maciej Raczuk [Language models can explain neurons in language models](https://openaipublic.blob.core.windows.net/neuron-explainer/paper/index.html) 61 | 62 | ## Plan spotkań 2022/2023 63 | * 2022-10-20 Łukasz Kuciński, Research topics in RL and Deep Learning. 64 | * 2022-11-03 Maciej Wojtala, [Best First Search-based planning algorithms in the Rubik's Cube environment](https://drive.google.com/file/d/1bKyHVG1-am4BWJyINcTnDEZ77D_UNCED/view?usp=sharing) 65 | * 2022-11-17 Szymon Tworkowski & Szymon Antoniak, [Formal Premise Selection With Language Models](http://aitp-conference.org/2022/abstract/AITP_2022_paper_32.pdf) 66 | * 2022-12-01 Bartłomiej Krzepkowski, [A Global Past-Future Early Exit Method for Accelerating Inference of Pre-trained Language Models](https://drive.google.com/file/d/1Mf92lcW6FY8n-x6wi9ZP13MFWi2P8zsp/view?usp=share_link); Aleksandra Mysiak, [Transformer probing](https://docs.google.com/presentation/d/1mr5UVhS1tsrWtrwgWXkaFrE58nLaWyMSoK446cLt6d8/edit?usp=sharing) 67 | * 2022-12-15 Franciszek Szarwacki [Make-a-video: Text-to-Video Generation without Text-Video Data](https://docs.google.com/presentation/d/1c0TwM3tIzS6dfeGyYCJUjnOx-fskSq9YLxyDGuG7L1k/edit?usp=sharing); Philip Smolenski-Jensen [Bayesian Neural Networks](https://docs.google.com/presentation/d/14lpvmYIvpAKMLDLfvVbRdevw7FnfSjYPjs3Ry9-_Pt8/edit?usp=sharing) 68 | * 2023-01-12 Jakub Modrzewski ???; Krzysztof Tomala [Structural re-parametrization of neural networks](https://docs.google.com/presentation/d/1q8otxsEFhjjR48jGu_PTXs5IQxwlZRkAAW8jcIdAWtE/edit?usp=sharing) 69 | * 2023-01-26 Krystian Król, [State of knowledge on Automatic Music Transcription](https://docs.google.com/presentation/d/16uN9rRvy2ha68rwnBOE0AxLfaEKMOon-PeP2TF13zpI/edit?usp=sharing); Szymon Sadkowski [How Close is ChatGPT to Human Experts](https://docs.google.com/presentation/d/1DJhOMivto5mZ5rs78lvZyvGxRvIfH_KlWwsGXBnpM-o/edit?usp=sharing) 70 | * 2023-03-09 Spotkanie organizacyjne 71 | * 2023-03-23 Jakub Modrzewski [ConvNeXt - A ConvNet for the 2020s](https://docs.google.com/presentation/d/1-1Qo4vSGC1MA6DJp4BaiEhdH21etNnfn/edit?usp=sharing&ouid=104896128149293750407&rtpof=true&sd=true); Propozycje tematów [Transformers for ML Seminar](https://docs.google.com/document/d/1I9dvYzXPYusY4QwgOkorWVihBznbv53XbjcjscF3aOw/edit) 72 | * 2023-04-13 Igor Witkowski, Learning to Play Atari with the Help of Instruction Manuals 73 | * 2023-05-04 Mateusz Kaluzny, A Mathematical Framework for Transformer Circuits 74 | * 2023-05-11 Michał Sala ??? 75 | * 2023-05-18 Michał Tyrolski (Fast and Precise: Adjusting Planning Horizon with Adaptive Subgoal Search) 76 | * 2023-05-25 77 | * 2023-06-01 Witold Drzewakowski (TBA) 78 | * 2023-06-15 Radosław Jurczak (Transformers on protein sequences: how & why); Alek Leśniak (TBA) 79 | 80 | ## Plan spotkań 2021/2022 81 | * 2021-10-07 Spotkanie organizacyjne. Łukasz Kuciński : [Prezentacja tematów z RL-a](https://docs.google.com/presentation/d/1BnoASprAroK6n2UCzSbqcyEXufNhYh9Lq6HW5MtycOI/edit?usp=sharing) 82 | * 2021-10-14 NCBJ NOMATEN Stefanos Papanikolaou : [Prezentacja tematów](https://www.dropbox.com/s/wag10f11bjbh32i/AlavaPapanikolaou_RecruitingPresentation.pdf?dl=0) 83 | * 2021-10-21 TCL - [Prezentacja tematów](https://drive.google.com/file/d/1Bn6iVKbIiNiqYBjJCF4rsuyWgX8UBMZe/view?usp=sharing) 84 | * 2021-11-04 Zuzanna Opała "[Extreme Classification](https://docs.google.com/presentation/d/1B3ppmO2JY_WdJkVQvDTkSOHWYtMkpvDUgHCmqhg5V5g/edit?usp=sharing)", Maciej Wojtala "[AlphaStar Algorithm](https://drive.google.com/file/d/1PSHdt_jXXo_i_uw7--nwsoWwhNKWZzSI/view?usp=sharing) and [Its Adaptation in Portfolio Optimisation](https://drive.google.com/file/d/1cUd63C6uNxoGfPhO9_jB8sLs_XJ87Sg7/view?usp=sharing)" 85 | * 2021-11-18 Zuzanna Kwiatkowska, "[State of Audio](https://drive.google.com/file/d/1tRz6MztkVQ0YiqvsI785lmPpagOiB7gX/view?usp=sharing)" 86 | * 2021-12-02 Michał Raszkowski "[Hyperparameter optimisation](https://docs.google.com/presentation/d/17rIivNx2XnI3KyKVoLAPc33CMCYVjc6fNeDVbWNEgxM/edit?usp=sharing)", Szymon Tworkowski & Michał Tyrolski "[Hierarchical Transformers Are More Efficient Language Models](https://arxiv.org/abs/2110.13711)" 87 | * 2021-12-16 Maciej Mikuła [Enhancing Goal-Conditioned Reinforcement Learning agents via Planning](https://drive.google.com/file/d/1hilUngnJC8IteVkyhnuhfpiX9erWaM_S/view?usp=sharing), Szymon Haponiuk "[Neural ordinary differential equations](https://docs.google.com/presentation/d/1wlyJIgI2Ca3EW4weC925m5FgtZwWaVOgdTKP5VdsbY8/edit?usp=sharing)" 88 | * 2022-01-13 Paweł Gora "RL do optymalizacji strategii w modelach nowotworów" 89 | * 2022-01-27 Cancelled 90 | * 2022-03-03 Kałużny Mateusz Jakub "???" 91 | * 2022-03-17 Mysiak Aleksandra "[Dependency trees in NLP](https://docs.google.com/presentation/d/16syOIqXgYX9Zp5Lmif6uLCiiEyTrvfMOHKkWM7MZVBk/edit?usp=sharing)", Błajda Mateusz "[Style GAN](https://drive.google.com/file/d/1VNvvwcjxzHlTEVIqYQpKOYJt9mwE-ztJ/view?usp=sharing)" 92 | * 2022-03-31 Tomala Krzysztof Jakub, Antoniak Szymon "[A glimpse into the world of Meta Learning](https://docs.google.com/presentation/d/1q2OuQ0nsNzgID2o_a824x1X5NpP3nlq_qBkr4tWWGTA/edit?usp=sharing)" 93 | * 2022-04-21 Smolenski-Jensen Philip Alexander 94 | * 2022-05-05 Król Krystian Kamil "[All you need to know about DALL·E 2](https://drive.google.com/file/d/1NvseRe-Syasq8K6baDnpd3hcWQhDt7Td/view?usp=sharing)", Wierzbiński Marcin Józef 95 | * 2022-05-19 ~~Bochenek Maria Teresa~~, Mysiurska Marta 96 | * 2022-06-02 Modrzewski Jakub Maksymilian "[NAS - Neural Predictor Approach](https://docs.google.com/presentation/d/1l5r44Mj9uODmBVDDmG3IzHtV8mv6zb4K/edit?usp=sharing&ouid=104896128149293750407&rtpof=true&sd=true)" 97 | 98 | ## Plan spotkań 2020/2021 99 | 100 | * 2020-10-15; 101 | * 2020-10-22; 102 | * 2020-11-05; [Jacek Cyranka (tematy prac mgr.)](https://drive.google.com/file/d/1XFUEDCnoI4-x72ggKJsVabPx6HtVtgnj/view?usp=sharing), [Wojciech Jablonski, Neural Architecture Search for Segmentation](https://docs.google.com/presentation/d/1FSSwYVuJiw-klPlLC7rwq4ikZEC27jO0LAqpiMMbEVw/edit?usp=sharing) (na podstawie [DARTS](https://arxiv.org/pdf/1806.09055.pdf), [Auto-DeepLab](https://arxiv.org/pdf/1901.02985.pdf), [DCNAS](https://arxiv.org/pdf/2003.11883.pdf)), [Zuzanna Kwiatkowska, Deep Learning Based Open Set Acoustic Scene Classification](https://arxiv.org/abs/2008.07247) 103 | * 2020-11-19; Zuzanna Opala([Training a Cooperative Team in Google Football Environment Using Multi-Agent Reinforcement Learning](https://docs.google.com/presentation/d/19xMbID6WH39BsQHCsw8dXpGy-pi33oCd9gX3ZKz1Iq0/edit?usp=sharing)), Maciej Sypetkowski ([Latent space editing in GANs](https://docs.google.com/presentation/d/1H627AmDNepd2hBVDW5f7WJEBOjClY_SZhzoScpJ753M/edit?usp=sharing) & [PGGAN, StyleGAN paper scraps](https://docs.google.com/presentation/d/1m_KjRdKPiSv_eTGsaaqGDJgu9509avsJ-_SJJMswTw8/edit?usp=sharing)) 104 | * 2020-12-03; Jakub Modrzewski(COVID-19 AI Diagnosis using only Cough Recordings. [Presentation](https://drive.google.com/file/d/1-VZt9Z5zWh7QkGpL--St84gcwkab5Xpn/view?usp=sharing), [Article](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9208795)), Marta Mysiurska [Multi-objective counterfactual explanation](https://drive.google.com/file/d/1bwZoeUjN2SYPHchgMnTQaexSneA02rKf/view?usp=sharing) 105 | * 2020-12-17; Michal Raszkowski ([Computer Vision for Autonomous Vehicles](https://docs.google.com/presentation/d/1kHg7G0g5o1rDN22v0QfyWkIljnX7kwWC1kvJ1OSPLPc/edit?usp=sharing)), [Piotr Krzywicki: Deep Learning in robotic manipulation](https://docs.google.com/presentation/d/1rJdOh9QsfTebiLpjfYyYBOVDXnAPgrVcbWh0wbN4grY/edit?usp=sharing) 106 | * 2021-01-14; Karol Kowalski, Marcin Wierzbiński [Gravitational-wave detectors with machine learning)](https://drive.google.com/file/d/1zIEnw9WKEDvmCwSk2sTn3TFfeSdAbko0/view?usp=sharing) 107 | * 2021-01-28; Philip Smolenski-Jensen ([AlphaFold - state-of-the-art protein folding model 108 | ](https://docs.google.com/presentation/d/10RrCTM_N9LgCzYh_Xn-iXLz0jmfq3kCkwmt_zu0DuP4/edit?usp=sharing)), Maciej Mikula [Agent57- Outperforming the Atari Human Benchmark](https://drive.google.com/file/d/1q1i43zI8LF0aIoGw5yo__Prt6PfnzH0k/view?usp=sharing) 109 | * 2021-03-04 110 | * 2021-03-18; Marcin Wierzbiński - LSTM vs GRU; Zuzanna Opała ([Robust High-dimensional Memory-augmented Neural Networks](https://docs.google.com/presentation/d/1GR8FFrkQniRRWUHscVf8afW56Egsvua71pUskbxs8ww/edit?usp=sharing)) 111 | * 2021-04-08; Maciej Mikuła - [Relational inductive biases, deep learning, and graph networks](https://drive.google.com/file/d/1IQUVDIQk3q3TnDXYMStW3m9VzsBAYnI_/view?usp=sharing); Jakub Modrzewski - [Stock Market’s Price Movement Prediction With LSTM Neural Networks](https://drive.google.com/file/d/1Lv4nY9RqhMpgCyNHPOJTJhrbOmR9mPVt/view?usp=sharing) 112 | * 2021-04-29; Philip Smolenski-Jensen ([CURL - Contrastive Unsupervised Representations for Reinforcement Learning](https://docs.google.com/presentation/d/1FONAZ_LT_GsMWE4_IJtvV8mPzKHp06A7KBSQcQ_hO1Y/edit?usp=sharing)) 113 | * 2021-05-20; Zuzanna Kwiatkowska (On gradient-based saliency maps in deep learning: [presentation](https://drive.google.com/file/d/121vPple7ZBYjiaguEXh0qQlioRYLJOzL/view?usp=sharing), [paper](https://arxiv.org/pdf/1810.03292.pdf)); 114 | * 2021-06-10; Wojciech Jabłoński (TurboDARTS - better, faster, more efficient Neural Architecture Search); Jakub Jasiulewicz - Pretrained Transformers As Universal Computation Engines ([paper](https://arxiv.org/pdf/2103.05247.pdf), [paper](https://arxiv.org/pdf/2012.11995.pdf), [presentation](https://students.mimuw.edu.pl/~jj385649/um-sem/um-sem-2021.pdf)), Marta Mysiurska - ?; Piotr Krzywicki – [Lessons learned implementing real-world robot learning system](https://docs.google.com/presentation/d/e/2PACX-1vQTbghFdrALpNqaW7EoYBm-GDdzsgfLMo3PhJELmV3uYRpeYa7OGErozOoSF4y-Vn-PajFseqGLioqJ/pub?start=false&loop=false&delayms=3000&slide=id.p) 115 | 116 | ## Plan spotkań 2019/2020 117 | 118 | * 2019-10-03 119 | * 2019-10-10; Umair Rasheed - Volkswagen 120 | * 2019-10-17; [Michał Futrega (Neural Architecture Search)](https://docs.google.com/presentation/d/1cj2wUcqnuoo71X1Jp_aA0dqR815pmgyB3R5sq6c7tfs/edit?usp=sharing) + [Jacek Cyranka (prezentacja tematów prac magisterskich)](https://docs.google.com/presentation/d/1kbdybSmN78ItZX5sy471H-sm9DsfPRv-u4oQcuV2TEo/edit?usp=sharing) 121 | * 2019-10-24; Maciej Biernaczyk - [AutoGAN: Neural Architecture Search for Generative Adversarial Networks](https://docs.google.com/presentation/d/1JcYwfr6DXhcHFcXG-7wE0Yw4dvS7Fur3ypx7oxXlFZM/edit?usp=sharing) 122 | * 2019-10-31; Michał Zawalski - [Knowledge-free solving the Rubik’s cube](https://docs.google.com/presentation/d/1W3ajlSapeFFQH3h04tpOJ5SQgcI2B4Rgk2bYlfA4gus/edit?usp=sharing) 123 | * 2019-11-07; Krystian Koziatek - [Learning the Depths of Moving People by Watching Frozen People](https://docs.google.com/presentation/d/1w4kxk5tlTzR0tV-1mHTvqzMCvnhgG67V28BL54ZQzgE/edit?usp=sharing) + [Marek Cygan: prezentacja tematów prac magisterskich](https://docs.google.com/presentation/d/1Yzkp8nZifuY-VZ0V5c4eY_Zo4hhpZgv5-tCOr-dnVXM/edit?usp=sharing) 124 | * 2019-11-14; Mateusz Doliński - [NGBoost: Natural Gradient Boosting for Probabilistic Prediction](https://drive.google.com/file/d/1XniVuuDCZYpmL9pcwz4TpgF9cygCAoFM/view?usp=sharing) 125 | * 2019-11-21; Jakub Skorupski - [TossingBot: Learning to Throw Arbitrary Objects with Residual Physics](https://arxiv.org/abs/1903.11239) | [Prezentacja](https://drive.google.com/file/d/1mlgmSzErT-FVIy2kHpdborf4UUPPDa9o/view) 126 | * 2019-11-28; Michał Kukuła - [Graph-based sparse neural networks for traffic signal optimization](http://students.mimuw.edu.pl/~mk371127/seminarium-ml.pdf) + ([Paweł Gora: prezentacja tematów prac magisterskich](https://drive.google.com/file/d/0B_tQx3IvcEWmNTAySE0yQnh2WU94alpON2YwNjE4ZGsyRk9j/view?usp=sharing) 127 | * 2019-12-05 [Przemek Biecek: prezentacja tematów prac magisterskich](https://github.com/pbiecek/Talks/blob/master/2019/MachineLearningSeminarMIM2019.pdf) & [Piotr Miłoś: prezentacja tematów prac magisterskich](https://docs.google.com/presentation/d/15QF2qzwV3YwaEcpTuQksxccI-0SgI3nxfzPwLdYYMyM/edit?usp=sharing) 128 | * 2019-12-12; Mateusz Doliński - [Wild patterns: Ten years after the rise of adversarial machine learning](https://arxiv.org/abs/1712.03141) 129 | * 2019-12-19 Henryk Michalewski, Mateusz Malinowski - [Prezentacja tematów prac magisterskich](https://drive.google.com/open?id=0B_tQx3IvcEWmZ3h0Ml9NQ05OWFFNRHlyQVl5bW1FMEM3MkhF) 130 | * 2020-01-09 brak seminarium 131 | * 2020-01-16 Jakub Jasiulewicz - [Playing hard exploration games by watching YouTube](http://students.mimuw.edu.pl/~jj385649/um-sem/Playing%20hard%20exploration%20games%20by%20watching%20YouTube.pdf) ([paper](https://arxiv.org/abs/1805.11592)) 132 | * 2020-01-23 Kamil Faber - [Optymalizacja Hiperparametrów](http://students.mimuw.edu.pl/~kf209517/seminarium_kamil_faber.pdf), Tomasz Kurzelewski 133 | * 2020-02-27 Zuzanna Kwiatkowska - [Introduction to Topological Data Analysis](https://drive.google.com/file/d/1rHbAT81esPBSWN1JBRBaf03jf8K9cw4I/view?usp=sharing) 134 | * 2020-03-05 135 | * 2020-03-12 Jakub Sieroń - [Emergent Tool Use from Multi-Agent Interaction](https://openai.com/blog/emergent-tool-use/) 136 | * 2020-03-19 137 | * 2020-03-26 Maciej Sypetkowski -- [Presentation](http://students.mimuw.edu.pl/~ms386094/ml-sem-noisy-student-26-03-2020.pdf), [Self-training with Noisy Student improves ImageNet classification](https://arxiv.org/abs/1911.04252) 138 | * 2020-04-02 Jakub Sieroń 139 | * 2020-04-16 brak seminarium 140 | * 2020-04-23 brak seminarium 141 | * 2020-04-30 (10:15-13:15) Michał Kukuła, Jakub Skorupski, Kamil Tokarski - [Autoencoders](https://docs.google.com/presentation/d/18nieuWffjILfbDWrDXnUAXGWftGtTeIW1aeIKzfDP8w/edit?usp=sharing) 142 | * 2020-05-07 143 | * 2020-05-14 144 | * 2020-05-21 (10:15-13:15) Zuzanna Kwiatkowska ([AudioAI](https://drive.google.com/file/d/1O29x1GUHIcWjLoHh_qs92d2XVR6JE-Dy/view?usp=sharing)), Mieczysław Krawiarz ([ERASER](https://docs.google.com/presentation/d/1kIzjS9Hzu0dkMj7pKeEZRquArc7WSwf95qtZPJQUB6k/edit?usp=sharing)), Krystian Koziatek ([Skin cancer detection & ResNeSt](https://docs.google.com/presentation/d/1KVFTEit3wr8WKPI5N5RgAN-ERXXgu-2qRPI08Npb8IM/edit?usp=sharing)), Michał Futrega [Pruning](https://docs.google.com/presentation/d/1n4GUCmm-I8c4c0jwh3hejxtxSACRbQhar8lCP9l3eiQ/edit?usp=sharing) - DL for audio, NLP and video 145 | * 2020-05-28 Piotr Piękos - Mathematical tasks with nlp methods 146 | * 2020-06-04 147 | 148 | 149 | 150 | ## Plan spotkań 2018/2019 151 | 152 | * 2018-10-11; Zuzanna Pilat - Learning algorithms with neural gpu 153 | * 2018-10-18; [Bartosz Biskupski (TCL) - prezentacja tematów prac magisterskich](http://tcl-research.pl/files/2018.10_TCL_MimUW_Msc_thesis_videos.pdf) 154 | * 2018-10-25; (seminarium odwołane) Paweł Gora - prezentacja tematów prac magisterskich 155 | * 2018-11-08; Paweł Gora - prezentacja tematów prac magisterskich 156 | * 2018-11-15; Sebastian Jaszczur - [Distillation and privileged information](http://goo.gl/EC8V81) 157 | * 2018-11-22; Przemysław Sadownik - Tree-based Pipeline Optimization Tool for Automating Data Science 158 | * 2018-11-29; Marcin Papierzyński - [Opening the black box of Deep Neural Networks via Information](https://tinyurl.com/InformationBottleneck) 159 | * 2018-12-13; Piotr Biliński - prezentacja tematów prac magisterskich. 160 | * 2018-12-20; Michał Zawalski 161 | * 2018-01-10; Rafał Sadziak - [Adversarial attacks and defences](https://docs.google.com/presentation/d/1pmlocRcmmQXZAqCUCmyWFQybvm7whosHO9nV4ZxafU0/edit?usp=sharing) 162 | * 2018-01-17; Michał Łuszczyk - [Realistic Evaluation of Deep Semi-Supervised Learning Algorithms](http://papers.nips.cc/paper/7585-realistic-evaluation-of-deep-semi-supervised-learning-algorithms.pdf). 163 | * 2018-01-24; Wojciech Mańke - [Neural Architecture Search With Reinforcement Learning](https://arxiv.org/pdf/1611.01578.pdf) 164 | * 2019-01-31; 165 | * 2019-02-07; 166 | * 2019-02-28; Paweł Zięcik - [Large-Scale Study of Curiosity-Driven Learning](https://pathak22.github.io/large-scale-curiosity/resources/largeScaleCuriosity2018.pdf) 167 | * 2019-03-07; Michał Kukuła [Learning Optimal and Fair Decision Trees for Non-Discriminative Decision-Making](http://www-bcf.usc.edu/~vayanou/papers/2019/Fair_DT_AAAI_2019_CameraReady.pdf) 168 | * 2019-03-14; Jakub Sieroń [Thinking Fast and Slow with Deep Learning and Tree Search](https://arxiv.org/abs/1705.08439) 169 | * 2019-03-21; Maciej Biernaczyk 170 | * 2019-03-28; Adam Dobrakowski 171 | * 2019-04-04; Sebastian Jaszczur - [Concrete Problems in AI Safety](https://arxiv.org/abs/1606.06565) 172 | * 2019-04-11; Jakub Skorupski - [Generating Adversarial Malware Examples for Black-Box Attacks Based on GAN](https://arxiv.org/pdf/1702.05983.pdf) 173 | * 2019-04-18; 174 | * 2019-04-25; Mikołaj Błaż - [Single-Agent Policy Tree Search With Guarantees](https://arxiv.org/abs/1811.10928) 175 | * 2019-05-02; 176 | * 2019-05-09; Przemysław Sadownik "Layer-based AutoML with evolutionary algorithms" 177 | * 2019-05-16; Jacek Maksymiuk - [“What is Relevant in a Text Document?”: An Interpretable Machine Learning Approach](https://arxiv.org/pdf/1612.07843.pdf) 178 | * 2019-05-23; Mateusz Doliński - [doc2vec](http://proceedings.mlr.press/v32/le14.pdf) 179 | * 2019-05-30; Piotr Piękos - [Hindsight Experience Replay](https://arxiv.org/abs/1707.01495) 180 | * 2019-06-06; Paweł Zięcik - [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://arxiv.org/pdf/1810.04805.pdf) 181 | * 2019-06-13; Krystian Koziatek - Depth map prediction problem overview, 182 | Tomasz Kępa - [AutoAugment: Learning Augmentation Strategies from Data](https://arxiv.org/pdf/1805.09501.pdf) 183 | 184 | ## Plan spotkań 2017/2018 185 | 186 | * 2017-10-05; Spotkanie organizacyjne 187 | * 2017-10-12; Propozycje prac magisterskich - NVidia 188 | * 2017-10-19; [Propozycje prac magisterskich - Henryk Michalewski](https://docs.google.com/presentation/d/1mBW6-jCIZeqm-iSzO9sSvPozw8FmGi78ED-ZS4-OPUo/edit?usp=sharing) 189 | * 2017-10-26; Understanding deep learning requires rethinking generalization, https://arxiv.org/abs/1611.03530 , [prezentacja](https://docs.google.com/presentation/d/18CmBvLTApYklfpqKKoB3BDr-RE3m045WZnJHg7E-a9c/edit#slide=id.g292430808e_0_56) 190 | * 2017-11-02; Distilling the Knowledge in a Neural Network, https://arxiv.org/abs/1503.02531 191 | * 2017-11-09; "Why Should I Trust You?": Explaining the Predictions of Any Classifier, https://arxiv.org/abs/1602.04938 [prezentacja](https://docs.google.com/presentation/d/1-22dim5U_2jRyI2FcOM5dAjdkRs2Oj0BXKjhGlSXuOc/edit#slide=id.p) 192 | * 2017-11-16; Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images, https://arxiv.org/abs/1412.1897 193 | * 2017-11-23; Visualizing statistical models: Removing the blindfold, http://had.co.nz/stat645/model-vis.pdf 194 | * 2017-11-30; mlr: Machine Learning in R, http://jmlr.org/papers/v17/15-066.html 195 | * 2017-12-07 196 | * 2017-12-14; Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics, https://arxiv.org/pdf/1705.07115.pdf 197 | * 2017-12-21; Deep Reinforcement Learning: Pong from Pixels, http://karpathy.github.io/2016/05/31/rl/ https://docs.google.com/presentation/d/1lHvatcCaJXit7Uub4pBDOD_s32VZKq5NRZPpxcaDf8M/edit#slide=id.p3 198 | * 2018-01-11; Scikit-learn & Pandas 199 | * 2018-01-18; Visualizing and Understanding Convolutional Networks, https://arxiv.org/abs/1311.2901 200 | * 2018-01-25; A Critical Review of Recurrent Neural Networks for Sequence Learning https://arxiv.org/abs/1506.00019 201 | * 2018-03-01; A Unified Approach to Interpreting Model Predictions https://arxiv.org/abs/1705.07874 202 | * 2018-03-08 203 | * 2018-03-15; Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm https://arxiv.org/abs/1712.01815, Mastering the game of Go without human knowledge https://www.nature.com/articles/nature24270?sf123103138=1 204 | * 2018-03-22; Playing Atari with Deep Reinforcement Learning https://www.cs.toronto.edu/~vmnih/docs/dqn.pdf oraz Continuous control with deep reinforcement learning https://arxiv.org/abs/1509.02971 205 | * 2018-03-28; Paweł Góra, zaczynamy 10:45 206 | * 2018-04-05; brak seminarium 207 | * 2018-04-12; Dynamic Routing Between Capsules https://arxiv.org/abs/1710.09829 208 | * 2018-04-19 209 | * 2018-04-26; Matrix Capsules with EM Routing https://openreview.net/forum?id=HJWLfGWRb 210 | * 2018-05-10; GA2M - Interpretable Generalized Additive Models (+ applications) - Przemysław Horban 211 | * 2018-05-17; NeuroSAT - Learning a SAT Solver from Single-Bit Supervision https://arxiv.org/abs/1802.03685 212 | * 2018-05-24; Anchors: High-Precision Model-Agnostic Explanations https://homes.cs.washington.edu/~marcotcr/aaai18.pdf 213 | * 2018-06-07; Continuous control with deep reinforcement learning https://arxiv.org/abs/1509.02971 214 | --------------------------------------------------------------------------------