Reading Group

Get ready for Winter Semester 2025/26!

In the second half of this semester, Craig Dickson will host a reading group on Technical Alignment in AI. Join us for discussions about state of the art research on aligning large language models, including RLHF, constitutional AI, adversarial training, goal misgeneralization, and more!

📍 Merantix AI Campus (Max-Urich-Straße 3, 13355 Berlin)

🕖 Every Monday, 18:45 (Add to Calendar)

Upcoming

January 12, 2026

Adversarial Training for High-Stakes Reliability

Daniel M. Ziegler, Seraphina Nix, Lawrence Chan, Tim Bauman, Peter Schmidt-Nielsen, Tao Lin, Adam Scherlis, Noa Nabeshima et al.

January 19, 2026

Goal Misgeneralization in Deep Reinforcement Learning

Lauro Langosco, Jack Koch, Lee Sharkey, Jacob Pfau, Laurent Orseau, David Krueger

January 26, 2026

TruthfulQA: Measuring How Models Mimic Human Falsehoods

Stephanie Lin, Jacob Hilton, Owain Evans

February 2, 2026

Alignment Faking in Large Language Models

Ryan Greenblatt, Carson Denison, Benjamin Wright, Fabien Roger, Monte MacDiarmid, Sam Marks, Johannes Treutlein, Tim Belonax et al.

February 9, 2026

Emergent Misalignment

Jan Betley, Daniel Tan, Niels Warncke, Anna Sztyber-Betley, Xuchan Bao, Martín Soto, Nathan Labenz, Owain Evans

Past Papers

Technical Alignment in AI

by Craig Dickson, 2025 - 2026

A tour through the alignment of large language models.

December 15, 2025

Constitutional AI: Harmlessness from AI Feedback

Yuntao Bai, Saurav Kadavath, Sandipan Kundu, Amanda Askell, Jackson Kernion, Andy Jones, Anna Chen, Anna Goldie et al.

December 8, 2025

Training Language Models to Follow Instructions with Human Feedback

Long Ouyang, Jeff Wu, Xu Jiang, Diogo Almeida, Carroll L. Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal et al.

Variety of Machine Learning in Healthcare

by Tillmann Rheude und Leonhard Kohleick, 2025

A tour through the variety of machine learning in healthcare, from images and cells to genes and multimodal data.

December 1, 2025

Contrasting with Symile: Simple Model-Agnostic Representation Learning for Unlimited Modalities

Adriel Saporta, Aahlad Puli, Mark Goldstein, Rajesh Ranganath

November 24, 2025

Beyond Sensor Data: Foundation Models of Behavioral Data from Wearables Improve Health Predictions

Eray Erturk, Fahad Kamran, Salar Abbaspourazad, Sean Jewell, Harsh Sharma, Yujie Li, Sinead Williamson, Nicholas J. Foti, Joseph Futoma

November 17, 2025

JanusDNA: A Powerful Bi-directional Hybrid DNA Foundation Model

Qihao Duan, Bingding Huang, Zhenqiao Song, Irina Lehmann, Lei Gu, Roland Eils, Benjamin Wild

November 10, 2025

Large Language Models are Powerful Electronic Health Record Encoders

Stefan Hegselmann, Georg von Arnim, Tillmann Rheude, Noel Kronenberg, David Sontag, Gerhard Hindricks, Roland Eils, Benjamin Wild

November 3, 2025

A foundation model for clinician-centered drug repurposing

Kexin Huang, Payal Chandak, Qianwen Wang, Shreyas Havaldar, Akhil Vaid, Jure Leskovec, Girish Nadkarni, Benjamin S. Glicksberg et al.

October 27, 2025

Biologically Guided Variational Inference for Interpretable Multimodal Single-Cell Integration and Mechanistic Discovery

Lucas Arnoldt, Julius Upmeier zu Belzen, Luis Herrmann, Khue Nguyen, Fabian Theis, Benjamin Wild, Roland Eils

October 20, 2025

U-Net: Convolutional Networks for Biomedical Image Segmentation

Olaf Ronneberger, Philipp Fischer, Thomas Brox

Geometric Graph Neural Network

by Gregor Lied, 2025

This reading group investigates the theoretical foundations and architectural design space of Geometric Graph Neural Networks for 3D atomic systems.

July 14, 2025

On the Expressive Power of Geometric Graph Neural Networks

Chaitanya K. Joshi, Cristian Bodnar, Simon V. Mathis, Taco Cohen, Pietro Liò

July 7, 2025

ForceNet: A Graph Neural Network for Large-Scale Quantum Calculations

Weihua Hu, Muhammed Shuaibi, Abhishek Das, Siddharth Goyal, Anuroop Sriram, Jure Leskovec, Devi Parikh, C. Lawrence Zitnick

June 30, 2025

E(n) Equivariant Graph Neural Networks

Victor Garcia Satorras, Emiel Hoogeboom, Max Welling

June 23, 2025

Directional Message Passing for Molecular Graphs

Johannes Gasteiger, Janek Groß, Stephan Günnemann

June 16, 2025

Neural Message Passing for Quantum Chemistry

Justin Gilmer, Samuel S. Schoenholz, Patrick F. Riley, Oriol Vinyals, George E. Dahl

AI in Medicine

by Tom Neuhäuser, 2025

A deep dive into the world of multimodal foundation models for histopathology.

June 2, 2025

PRISM: A Multi-Modal Generative Foundation Model for Slide-Level Histopathology

George Shaikovski, Adam Casson, Kristen Severson, Eric Zimmermann, Yi Kan Wang, Jeremy D. Kunz, Juan A. Retamero, Gerard Oakley et al.

May 26, 2025

Scaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised Learning

Richard J. Chen, Chengkuan Chen, Yicong Li, Tiffany Y. Chen, Andrew D. Trister, Rahul G. Krishnan, Faisal Mahmood

May 19, 2025

A multimodal generative AI copilot for human pathology

Ming Y. Lu, Bowen Chen, Drew F. K. Williamson, Richard J. Chen, Melissa Zhao, Aaron K. Chow, Kenji Ikemura, Ahrong Kim et al.

May 12, 2025

Transmil: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classification

Zhuchen Shao, Hao Bian, Yang Chen, Yifeng Wang, Jian Zhang, Xiangyang Ji, Yongbing Zhang

May 5, 2025

A visual-language foundation model for computational pathology

Ming Y. Lu, Bowen Chen, Drew F. K. Williamson, Richard J. Chen, Ivy Liang, Tong Ding, Guillaume Jaume, Igor Odintsov et al.

April 28, 2025

A foundation model for clinical-grade computational pathology and rare cancers detection

Eugene Vorontsov, Alican Bozkurt, Adam Casson, George Shaikovski, Michal Zelechowski, Kristen Severson, Eric Zimmermann, James Hall et al.

Mechanistic Interpretability

by Lorenz Hufe, 2024 - 2025

Sometimes everybody needs to know what is going on inside a (language) model

March 17, 2025

Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition

Dan Braun, Lucius Bushnaq, Stefan Heimersheim, Jake Mendel, Lee Sharkey

March 10, 2025

Transcoders Find Interpretable LLM Feature Circuits

Jacob Dunefsky, Philippe Chlenski, Neel Nanda

March 3, 2025

Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models

Samuel Marks, Can Rager, Eric J. Michaud, Yonatan Belinkov, David Bau, Aaron Mueller

February 17, 2025

Monet: Mixture of Monosemantic Experts for Transformers

Jungwoo Park, Young Jin Ahn, Kee-Eung Kim, Jaewoo Kang

February 10, 2025

Efficient Dictionary Learning with Switch Sparse Autoencoders

Anish Mudide, Joshua Engels, Eric J. Michaud, Max Tegmark, Christian Schroeder de Witt

February 3, 2025

Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet

Adly Templeton, Tom Conerly, Jonathan Marcus, Jack Lindsey, Trenton Bricken, Brian Chen, Adam Pearce, Craig Citro et al.

January 27, 2025

Refusal in Language Models Is Mediated by a Single Direction

Andy Arditi, Oscar Obeso, Aaquib Syed, Daniel Paleka, Nina Panickssery, Wes Gurnee, Neel Nanda

January 20, 2025

Towards Monosemanticity: Decomposing Language Models With Dictionary Learning

Trenton Bricken, Adly Templeton, Joshua Batson, Brian Chen, Adam Jermyn, Tom Conerly, Nicholas L Turner, Cem Anil et al.

January 13, 2025

Toy Models of Superposition

Nelson Elhage, Tristan Hume, Catherine Olsson, Nicholas Schiefer, Tom Henighan, Shauna Kravec, Zac Hatfield-Dodds, Robert Lasenby et al.

November 16, 2024

A Mathematical Framework for Transformer Circuits

Nelson Elhage, Neel Nanda, Catherine Olsson, Tom Henighan†, Nicholas Joseph†, Ben Mann†, Amanda Askell, Yuntao Bai et al.

LLMs and Language Modeling

by Raphael Reinauer, 2024

Long story short, we read papers about language models and language modeling

November 9, 2024

Training Language Models to Self-Correct via Reinforcement Learning

Aviral Kumar, Vincent Zhuang, Rishabh Agarwal, Yi Su, JD Co-Reyes, Avi Singh, Kate Baumli, Shariq Iqbal et al.

November 2, 2024

Training language models to follow instructions with human feedback

Long Ouyang, Jeff Wu, Xu Jiang, Diogo Almeida, Carroll L. Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal et al.

October 25, 2024

Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism

Mohammad Shoeybi, Mostofa Patwary, Raul Puri, Patrick LeGresley, Jared Casper, Bryan Catanzaro

October 18, 2024

Training Compute-Optimal Large Language Models

Jordan Hoffmann, Sebastian Borgeaud, Arthur Mensch, Elena Buchatskaya, Trevor Cai, Eliza Rutherford, Diego de Las Casas, Lisa Anne Hendricks et al.

October 11, 2024

A Formal Perspective on Byte-Pair Encoding

Vilém Zouhar, Clara Meister, Juan Luis Gastaldi, Li Du, Tim Vieira, Mrinmaya Sachan, Ryan Cotterell

October 4, 2024

Language Models are Few-Shot Learners, Chapter 3

Tom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam et al.

September 28, 2024

Formal Algorithms for Transformers

Mary Phuong, Marcus Hutter

September 21, 2024

Natural Language Processing, Chapter 6

Jacob Eisenstein

Optimizers

by Jarek Liesen, 2024

We read papers about optimizers and their properties to learn how to optimize even further

July 1, 2024

On the importance of initialization and momentum in deep learning

Ilya Sutskever, James Martens, George Dahl, Geoffrey Hinton

July 1, 2024

Adam: A Method for Stochastic Optimization

Diederik P. Kingma, Jimmy Ba

June 18, 2024

Stochastic Gradient Descend

appliedprobability

June 18, 2024

Adding Gradient Noise Improves Learning for Very Deep Networks

Arvind Neelakantan, Luke Vilnis, Quoc V. Le, Ilya Sutskever, Lukasz Kaiser, Karol Kurach, James Martens

Self-Supervised Learning

by Jakob Hackstein, 2024

Something students should know about. Its super effective in learning representations from unlabeled data.

June 4, 2024

Revealing the Dark Secrets of Masked Image Modeling

Zhenda Xie, Zigang Geng, Jingcheng Hu, Zheng Zhang, Han Hu, Yue Cao

June 4, 2024

Can We Break Free from Strong Data Augmentations in Self-Supervised Learning?

Shruthi Gowda1, Elahe Arani, Bahram Zonooz

May 21, 2024

Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture

Mahmoud Assran, Quentin Duval, Ishan Misra, Piotr Bojanowski, Pascal Vincent, Michael Rabbat, Yann LeCun, Nicolas Ballas

May 21, 2024

What do Self Supervised Vision Transformers Learn?

Namuk Park, Wonjae Kim, Byeongho Heo, Taekyung Kim, Sangdoo Yun

May 7, 2024

Emerging Properties in Self-Supervised Vision Transformers

Mathilde Caron, Hugo Touvron, Ishan Misra, Hervé Jégou, Julien Mairal, Piotr Bojanowski, Armand Joulin

May 7, 2024

Vision Transformers Need Registers

Timothée Darcet, Maxime Oquab, Julien Mairal, Piotr Bojanowski

April 23, 2024

Intriguing Properties of Contrastive Losses

Ting Chen, Calvin Luo, Lala Li

April 23, 2024

Bootstrap your own latent: A new approach to self-supervised Learning

Jean-Bastien Grill, Florian Strub, Florent Altché, Corentin Tallec, Pierre H. Richemond, Elena Buchatskaya, Carl Doersch, Bernardo Avila Pires et al.

Audio and AI

by Leo Pinetzki, 2023 - 2024

We Heard You Like AI so here we explored many audio related papers

February 13, 2024

Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale

Matthew Le, Apoorv Vyas, Bowen Shi, Brian Karrer, Leda Sari, Rashel Moritz, Mary Williamson, Vimal Manohar et al.

February 6, 2024

MT3 Multi-Task Multitrack Music Transcription

Josh Gardner, Ian Simon, Ethan Manilow, Curtis Hawthorne, Jesse Engel

January 30, 2024

MusicLM: Generating Music From Text

Andrea Agostinelli, Timo I. Denk, Zalán Borsos, Jesse Engel, Mauro Verzetti, Antoine Caillon, Qingqing Huang, Aren Jansen et al.

January 23, 2024

High Fidelity Neural Audio Compression

Alexandre Défossez, Jade Copet, Gabriel Synnaeve, Yossi Adi

January 16, 2024

Jukebox A Generative Model for Music

Prafulla Dhariwal, Heewoo Jun, Christine Payne, Jong Wook Kim, Alec Radford, Ilya Sutskever

January 9, 2024

Neural Discrete Representation Learning

Aaron van den Oord, Oriol Vinyals, Koray Kavukcuoglu

December 19, 2023

RL-Duet - Online Music Accompaniment Generation Using Deep Reinforcement Learning

Nan Jiang, Sheng Jin, Zhiyao Duan, Changshui Zhang

Deep Q-Learning

by Jarek Liesen, 2023

Introduction to deep reinforcement learning by exploration of many relevant and foundational papers

December 12, 2023

Agent57: Outperforming the Atari Human Benchmark

Adrià Puigdomènech Badia, Bilal Piot, Steven Kapturowski, Pablo Sprechmann, Alex Vitvitskyi, Daniel Guo, Charles Blundell

December 5, 2023

Rainbow: Combining Improvements in Deep Reinforcement Learning

Matteo Hessel, Joseph Modayil, Hado van Hasselt, Tom Schaul, Georg Ostrovski, Will Dabney, Dan Horgan, Bilal Piot et al.

November 24, 2023

Noisy Networks for Exploration

Meire Fortunato, Mohammad Gheshlaghi Azar, Bilal Piot, Jacob Menick, Ian Osband, Alex Graves, Vlad Mnih, Remi Munos et al.

November 15, 2023

A Distributional Perspective on Reinforcement Learning

Marc G. Bellemare, Will Dabney, Rémi Munos

November 7, 2023

Prioritized Experience Replay

Tom Schaul, John Quan, Ioannis Antonoglou, David Silver

November 1, 2023

Deep Reinforcement Learning with Double Q-learning

Hado van Hasselt, Arthur Guez, David Silver

October 30, 2023

Dueling Network Architectures for Deep Reinforcement Learning

Ziyu Wang, Tom Schaul, Matteo Hessel, Hado van Hasselt, Marc Lanctot, Nando de Freitas

October 22, 2023

Human-level Control through Deep Reinforcement Learning

Volodymyr Mnih, K. Kavukcuoglu, David Silver, Andrei A. Rusu, J. Veness, Marc G. Bellemare, Alex Graves, Martin A. Riedmiller et al.

Unstructured Papers

by Jarek Liesen, 2023

We read papers based on proposals from the group

July 11, 2023

Masked Autoencoders Are Scalable Vision Learners

Kaiming He, Xinlei Chen, Saining Xie, Yanghao Li, Piotr Dollár, Ross Girshick

June 27, 2023

Bytes is all you need

Maxwell Horton, Sachin Mehta, Ali Farhadi, Mohammad Rastegari

June 20, 2023

Pattern-Based Music Generation with Wasserstein Autoencoders and PRC Descriptions

Valentijn Borghuis, Luca Angioloni, Lorenzo Brusci, Paolo Frasconi

June 13, 2023

Dopamine and temporal difference learning - A fruitful relationship between neuroscience and AI

Will Dabney, Zeb Kurth-Nelson

June 6, 2023

Meta-Learning the Inductive Biases of Simple Neural Circuits

William Dorrell, Maria Yuffa, Peter Latham