AI Reading Group | BLISS Berlin

Summer Semester 2023
Tue, June 6, 2023Reading Group
Meta-Learning the Inductive Biases of Simple Neural Circuits
William Dorrell, Maria Yuffa, Peter Latham
Paper
Tue, June 13, 2023Reading Group
Dopamine and temporal difference learning - A fruitful relationship between neuroscience and AI
Will Dabney, Zeb Kurth-Nelson
Paper
Tue, June 20, 2023Reading Group
Pattern-Based Music Generation with Wasserstein Autoencoders and PRC Descriptions
Valentijn Borghuis, Luca Angioloni, Lorenzo Brusci, Paolo Frasconi
Paper
Tue, June 27, 2023Reading Group
Bytes is all you need
Maxwell Horton, Sachin Mehta, Ali Farhadi, Mohammad Rastegari
Paper
Tue, July 11, 2023Reading Group
Masked Autoencoders Are Scalable Vision Learners
Kaiming He, Xinlei Chen, Saining Xie, Yanghao Li, Piotr Dollár et al.
Paper
Winter Semester 2023/24
Sun, October 22, 2023Reading Group
Human-level Control through Deep Reinforcement Learning
Volodymyr Mnih, K. Kavukcuoglu, David Silver, Andrei A. Rusu, J. Veness et al.
Paper
Hosted by Jarek Liesen. Introduction to deep reinforcement learning through exploration of many relevant and foundational papers.
Mon, October 30, 2023Reading Group
Dueling Network Architectures for Deep Reinforcement Learning
Ziyu Wang, Tom Schaul, Matteo Hessel, Hado van Hasselt, Marc Lanctot et al.
Paper
Hosted by Jarek Liesen. Introduction to deep reinforcement learning through exploration of many relevant and foundational papers.
Wed, November 1, 2023Reading Group
Deep Reinforcement Learning with Double Q-learning
Hado van Hasselt, Arthur Guez, David Silver
Paper
Hosted by Jarek Liesen. Introduction to deep reinforcement learning through exploration of many relevant and foundational papers.
Tue, November 7, 2023Reading Group
Prioritized Experience Replay
Tom Schaul, John Quan, Ioannis Antonoglou, David Silver
Paper
Hosted by Jarek Liesen. Introduction to deep reinforcement learning through exploration of many relevant and foundational papers.
Wed, November 15, 2023Reading Group
A Distributional Perspective on Reinforcement Learning
Marc G. Bellemare, Will Dabney, Rémi Munos
Paper
Hosted by Jarek Liesen. Introduction to deep reinforcement learning through exploration of many relevant and foundational papers.
Fri, November 24, 2023Reading Group
Noisy Networks for Exploration
Meire Fortunato, Mohammad Gheshlaghi Azar, Bilal Piot, Jacob Menick, Ian Osband et al.
Paper
Hosted by Jarek Liesen. Introduction to deep reinforcement learning through exploration of many relevant and foundational papers.
Tue, December 5, 2023Reading Group
Rainbow: Combining Improvements in Deep Reinforcement Learning
Matteo Hessel, Joseph Modayil, Hado van Hasselt, Tom Schaul, Georg Ostrovski et al.
Paper
Hosted by Jarek Liesen. Introduction to deep reinforcement learning through exploration of many relevant and foundational papers.
Tue, December 12, 2023Reading Group
Agent57: Outperforming the Atari Human Benchmark
Adrià Puigdomènech Badia, Bilal Piot, Steven Kapturowski, Pablo Sprechmann, Alex Vitvitskyi et al.
Paper
Hosted by Jarek Liesen. Introduction to deep reinforcement learning through exploration of many relevant and foundational papers.
Tue, December 19, 2023Reading Group
RL-Duet - Online Music Accompaniment Generation Using Deep Reinforcement Learning
Nan Jiang, Sheng Jin, Zhiyao Duan, Changshui Zhang
Paper
Hosted by Leo Pinetzki. We explore many audio-related papers at the intersection of AI and sound.
Tue, January 9, 2024Reading Group
Neural Discrete Representation Learning
Aaron van den Oord, Oriol Vinyals, Koray Kavukcuoglu
Paper
Hosted by Leo Pinetzki. We explore many audio-related papers at the intersection of AI and sound.
Tue, January 16, 2024Reading Group
Jukebox A Generative Model for Music
Prafulla Dhariwal, Heewoo Jun, Christine Payne, Jong Wook Kim, Alec Radford et al.
Paper
Hosted by Leo Pinetzki. We explore many audio-related papers at the intersection of AI and sound.
Tue, January 23, 2024Reading Group
High Fidelity Neural Audio Compression
Alexandre Défossez, Jade Copet, Gabriel Synnaeve, Yossi Adi
Paper
Hosted by Leo Pinetzki. We explore many audio-related papers at the intersection of AI and sound.
Tue, January 30, 2024Reading Group
MusicLM: Generating Music From Text
Andrea Agostinelli, Timo I. Denk, Zalán Borsos, Jesse Engel, Mauro Verzetti et al.
Paper
Hosted by Leo Pinetzki. We explore many audio-related papers at the intersection of AI and sound.
Tue, February 6, 2024Reading Group
MT3 Multi-Task Multitrack Music Transcription
Josh Gardner, Ian Simon, Ethan Manilow, Curtis Hawthorne, Jesse Engel
Paper
Hosted by Leo Pinetzki. We explore many audio-related papers at the intersection of AI and sound.
Tue, February 13, 2024Reading Group
Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale
Matthew Le, Apoorv Vyas, Bowen Shi, Brian Karrer, Leda Sari et al.
Paper
Hosted by Leo Pinetzki. We explore many audio-related papers at the intersection of AI and sound.
Summer Semester 2024
Tue, April 23, 2024Reading Group
2 papers: Intriguing Properties of Contrastive Losses, Bootstrap your own latent: A new approach to self-supervised Learning
Reading group session
Hosted by Jakob Hackstein. Self-supervised learning is highly effective for learning representations from unlabeled data.
Tue, May 7, 2024Reading Group
2 papers: Emerging Properties in Self-Supervised Vision Transformers, Vision Transformers Need Registers
Reading group session
Hosted by Jakob Hackstein. Self-supervised learning is highly effective for learning representations from unlabeled data.
Tue, May 21, 2024Reading Group
2 papers: Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture, What do Self Supervised Vision Transformers Learn?
Reading group session
Hosted by Jakob Hackstein. Self-supervised learning is highly effective for learning representations from unlabeled data.
Tue, June 4, 2024Reading Group
2 papers: Revealing the Dark Secrets of Masked Image Modeling, Can We Break Free from Strong Data Augmentations in Self-Supervised Learning?
Reading group session
Hosted by Jakob Hackstein. Self-supervised learning is highly effective for learning representations from unlabeled data.
Tue, June 18, 2024Reading Group
2 papers: Stochastic Gradient Descend, Adding Gradient Noise Improves Learning for Very Deep Networks
Reading group session
Hosted by Jarek Liesen. We read papers about optimizers and their properties to learn how to optimize even further.
Mon, July 1, 2024Reading Group
2 papers: On the importance of initialization and momentum in deep learning, Adam: A Method for Stochastic Optimization
Reading group session
Hosted by Jarek Liesen. We read papers about optimizers and their properties to learn how to optimize even further.
Sat, September 21, 2024Reading Group
Natural Language Processing, Chapter 6
Jacob Eisenstein
Paper
Hosted by Raphael Reinauer. We explore the basics of natural language processing and the transformer architecture, scaling language models, modern training techniques, and self-improvement.
Location: MAR 0.015, TU Berlin (Marchstraße 23, 10587 Berlin)
Time: Every Monday, 7pm
Sat, September 28, 2024Reading Group
Formal Algorithms for Transformers
Mary Phuong, Marcus Hutter
Paper
Hosted by Raphael Reinauer. We explore the basics of natural language processing and the transformer architecture, scaling language models, modern training techniques, and self-improvement.
Location: MAR 0.015, TU Berlin (Marchstraße 23, 10587 Berlin)
Time: Every Monday, 7pm
Winter Semester 2024/25
Fri, October 4, 2024Reading Group
Language Models are Few-Shot Learners, Chapter 3
Tom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan et al.
Paper
Hosted by Raphael Reinauer. We explore the basics of natural language processing and the transformer architecture, scaling language models, modern training techniques, and self-improvement.
Location: MAR 0.015, TU Berlin (Marchstraße 23, 10587 Berlin)
Time: Every Monday, 7pm
Fri, October 11, 2024Reading Group
A Formal Perspective on Byte-Pair Encoding
Vilém Zouhar, Clara Meister, Juan Luis Gastaldi, Li Du, Tim Vieira et al.
Paper
Hosted by Raphael Reinauer. We explore the basics of natural language processing and the transformer architecture, scaling language models, modern training techniques, and self-improvement.
Location: MAR 0.015, TU Berlin (Marchstraße 23, 10587 Berlin)
Time: Every Monday, 7pm
Fri, October 18, 2024Reading Group
Training Compute-Optimal Large Language Models
Jordan Hoffmann, Sebastian Borgeaud, Arthur Mensch, Elena Buchatskaya, Trevor Cai et al.
Paper
Hosted by Raphael Reinauer. We explore the basics of natural language processing and the transformer architecture, scaling language models, modern training techniques, and self-improvement.
Location: MAR 0.015, TU Berlin (Marchstraße 23, 10587 Berlin)
Time: Every Monday, 7pm
Fri, October 25, 2024Reading Group
Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism
Mohammad Shoeybi, Mostofa Patwary, Raul Puri, Patrick LeGresley, Jared Casper et al.
Paper
Hosted by Raphael Reinauer. We explore the basics of natural language processing and the transformer architecture, scaling language models, modern training techniques, and self-improvement.
Location: MAR 0.015, TU Berlin (Marchstraße 23, 10587 Berlin)
Time: Every Monday, 7pm
Sat, November 2, 2024Reading Group
Training language models to follow instructions with human feedback
Long Ouyang, Jeff Wu, Xu Jiang, Diogo Almeida, Carroll L. Wainwright et al.
Paper
Hosted by Raphael Reinauer. We explore the basics of natural language processing and the transformer architecture, scaling language models, modern training techniques, and self-improvement.
Location: MAR 0.015, TU Berlin (Marchstraße 23, 10587 Berlin)
Time: Every Monday, 7pm
Sat, November 9, 2024Reading Group
Training Language Models to Self-Correct via Reinforcement Learning
Aviral Kumar, Vincent Zhuang, Rishabh Agarwal, Yi Su, JD Co-Reyes et al.
Paper
Hosted by Raphael Reinauer. We explore the basics of natural language processing and the transformer architecture, scaling language models, modern training techniques, and self-improvement.
Location: MAR 0.015, TU Berlin (Marchstraße 23, 10587 Berlin)
Time: Every Monday, 7pm
Sat, November 16, 2024Reading Group
A Mathematical Framework for Transformer Circuits
Nelson Elhage, Neel Nanda, Catherine Olsson, Tom Henighan†, Nicholas Joseph† et al.
Paper
Hosted by Lorenz Hufe. A deep dive into understanding the internal mechanisms of language models.
Location: MAR 0.015, TU Berlin (Marchstraße 23, 10587 Berlin)
Time: Every Monday, 7pm
Mon, January 13, 2025Reading Group
Toy Models of Superposition
Nelson Elhage, Tristan Hume, Catherine Olsson, Nicholas Schiefer, Tom Henighan et al.
Paper
Hosted by Lorenz Hufe. A deep dive into understanding the internal mechanisms of language models.
Location: MAR 0.015, TU Berlin (Marchstraße 23, 10587 Berlin)
Time: Every Monday, 7pm
Mon, January 20, 2025Reading Group
Towards Monosemanticity: Decomposing Language Models With Dictionary Learning
Trenton Bricken, Adly Templeton, Joshua Batson, Brian Chen, Adam Jermyn et al.
Paper
Hosted by Lorenz Hufe. A deep dive into understanding the internal mechanisms of language models.
Location: MAR 0.015, TU Berlin (Marchstraße 23, 10587 Berlin)
Time: Every Monday, 7pm
Mon, January 27, 2025Reading Group
Refusal in Language Models Is Mediated by a Single Direction
Andy Arditi, Oscar Obeso, Aaquib Syed, Daniel Paleka, Nina Panickssery et al.
Paper
Hosted by Lorenz Hufe. A deep dive into understanding the internal mechanisms of language models.
Location: MAR 0.015, TU Berlin (Marchstraße 23, 10587 Berlin)
Time: Every Monday, 7pm
Mon, February 3, 2025Reading Group
Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet
Adly Templeton, Tom Conerly, Jonathan Marcus, Jack Lindsey, Trenton Bricken et al.
Paper
Hosted by Lorenz Hufe. A deep dive into understanding the internal mechanisms of language models.
Location: MAR 0.015, TU Berlin (Marchstraße 23, 10587 Berlin)
Time: Every Monday, 7pm
Mon, February 10, 2025Reading Group
Efficient Dictionary Learning with Switch Sparse Autoencoders
Anish Mudide, Joshua Engels, Eric J. Michaud, Max Tegmark, Christian Schroeder de Witt
Paper
Hosted by Lorenz Hufe. A deep dive into understanding the internal mechanisms of language models.
Location: MAR 0.015, TU Berlin (Marchstraße 23, 10587 Berlin)
Time: Every Monday, 7pm
Mon, February 17, 2025Reading Group
Monet: Mixture of Monosemantic Experts for Transformers
Jungwoo Park, Young Jin Ahn, Kee-Eung Kim, Jaewoo Kang
Paper
Hosted by Lorenz Hufe. A deep dive into understanding the internal mechanisms of language models.
Location: MAR 0.015, TU Berlin (Marchstraße 23, 10587 Berlin)
Time: Every Monday, 7pm
Mon, March 3, 2025Reading Group
Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models
Samuel Marks, Can Rager, Eric J. Michaud, Yonatan Belinkov, David Bau et al.
Paper
Hosted by Lorenz Hufe. A deep dive into understanding the internal mechanisms of language models.
Location: MAR 0.015, TU Berlin (Marchstraße 23, 10587 Berlin)
Time: Every Monday, 7pm
Mon, March 10, 2025Reading Group
Transcoders Find Interpretable LLM Feature Circuits
Jacob Dunefsky, Philippe Chlenski, Neel Nanda
Paper
Hosted by Lorenz Hufe. A deep dive into understanding the internal mechanisms of language models.
Location: MAR 0.015, TU Berlin (Marchstraße 23, 10587 Berlin)
Time: Every Monday, 7pm
Mon, March 17, 2025Reading Group
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition
Dan Braun, Lucius Bushnaq, Stefan Heimersheim, Jake Mendel, Lee Sharkey
Paper
Hosted by Lorenz Hufe. A deep dive into understanding the internal mechanisms of language models.
Location: MAR 0.015, TU Berlin (Marchstraße 23, 10587 Berlin)
Time: Every Monday, 7pm
Summer Semester 2025
Mon, April 28, 2025Reading Group
A foundation model for clinical-grade computational pathology and rare cancers detection
Eugene Vorontsov, Alican Bozkurt, Adam Casson, George Shaikovski, Michal Zelechowski et al.
Paper
Hosted by Tom Neuhäuser. A deep dive into the world of multimodal foundation models for histopathology.
Location: Merantix AI Campus (Max-Urich-Straße 3, 13355 Berlin)
Time: Every Monday, 6:45pm
Mon, May 5, 2025Reading Group
A visual-language foundation model for computational pathology
Ming Y. Lu, Bowen Chen, Drew F. K. Williamson, Richard J. Chen, Ivy Liang et al.
Paper
Hosted by Tom Neuhäuser. A deep dive into the world of multimodal foundation models for histopathology.
Location: Merantix AI Campus (Max-Urich-Straße 3, 13355 Berlin)
Time: Every Monday, 6:45pm
Mon, May 12, 2025Reading Group
Transmil: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classification
Zhuchen Shao, Hao Bian, Yang Chen, Yifeng Wang, Jian Zhang et al.
Paper
Hosted by Tom Neuhäuser. A deep dive into the world of multimodal foundation models for histopathology.
Location: Merantix AI Campus (Max-Urich-Straße 3, 13355 Berlin)
Time: Every Monday, 6:45pm
Mon, May 19, 2025Reading Group
A multimodal generative AI copilot for human pathology
Ming Y. Lu, Bowen Chen, Drew F. K. Williamson, Richard J. Chen, Melissa Zhao et al.
Paper
Hosted by Tom Neuhäuser. A deep dive into the world of multimodal foundation models for histopathology.
Location: Merantix AI Campus (Max-Urich-Straße 3, 13355 Berlin)
Time: Every Monday, 6:45pm
Mon, May 26, 2025Reading Group
Scaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised Learning
Richard J. Chen, Chengkuan Chen, Yicong Li, Tiffany Y. Chen, Andrew D. Trister et al.
Paper
Hosted by Tom Neuhäuser. A deep dive into the world of multimodal foundation models for histopathology.
Location: Merantix AI Campus (Max-Urich-Straße 3, 13355 Berlin)
Time: Every Monday, 6:45pm
Mon, June 2, 2025Reading Group
PRISM: A Multi-Modal Generative Foundation Model for Slide-Level Histopathology
George Shaikovski, Adam Casson, Kristen Severson, Eric Zimmermann, Yi Kan Wang et al.
Paper
Hosted by Tom Neuhäuser. A deep dive into the world of multimodal foundation models for histopathology.
Location: Merantix AI Campus (Max-Urich-Straße 3, 13355 Berlin)
Time: Every Monday, 6:45pm
Mon, June 16, 2025Reading Group
Neural Message Passing for Quantum Chemistry
Justin Gilmer, Samuel S. Schoenholz, Patrick F. Riley, Oriol Vinyals, George E. Dahl
Paper
Hosted by Gregor Lied. This reading group investigated the theoretical foundations and architectural design space of Geometric Graph Neural Networks for 3D atomic systems.
Location: Merantix AI Campus (Max-Urich-Straße 3, 13355 Berlin)
Time: Every Monday, 6:45pm
Mon, June 23, 2025Reading Group
Directional Message Passing for Molecular Graphs
Johannes Gasteiger, Janek Groß, Stephan Günnemann
Paper
Hosted by Gregor Lied. This reading group investigated the theoretical foundations and architectural design space of Geometric Graph Neural Networks for 3D atomic systems.
Location: Merantix AI Campus (Max-Urich-Straße 3, 13355 Berlin)
Time: Every Monday, 6:45pm
Mon, June 30, 2025Reading Group
E(n) Equivariant Graph Neural Networks
Victor Garcia Satorras, Emiel Hoogeboom, Max Welling
Paper
Hosted by Gregor Lied. This reading group investigated the theoretical foundations and architectural design space of Geometric Graph Neural Networks for 3D atomic systems.
Location: Merantix AI Campus (Max-Urich-Straße 3, 13355 Berlin)
Time: Every Monday, 6:45pm
Mon, July 7, 2025Reading Group
ForceNet: A Graph Neural Network for Large-Scale Quantum Calculations
Weihua Hu, Muhammed Shuaibi, Abhishek Das, Siddharth Goyal, Anuroop Sriram et al.
Paper
Hosted by Gregor Lied. This reading group investigated the theoretical foundations and architectural design space of Geometric Graph Neural Networks for 3D atomic systems.
Location: Merantix AI Campus (Max-Urich-Straße 3, 13355 Berlin)
Time: Every Monday, 6:45pm
Mon, July 14, 2025Reading Group
On the Expressive Power of Geometric Graph Neural Networks
Chaitanya K. Joshi, Cristian Bodnar, Simon V. Mathis, Taco Cohen, Pietro Liò
Paper
Hosted by Gregor Lied. This reading group investigated the theoretical foundations and architectural design space of Geometric Graph Neural Networks for 3D atomic systems.
Location: Merantix AI Campus (Max-Urich-Straße 3, 13355 Berlin)
Time: Every Monday, 6:45pm
Winter Semester 2025/26
Mon, October 20, 2025Reading Group
U-Net: Convolutional Networks for Biomedical Image Segmentation
Olaf Ronneberger, Philipp Fischer, Thomas Brox
Paper
Tillmann Rheude, Leonhard Kohleick, and Benjamin Wild from Berlin Institute of Health at Charité co-hosted this reading group on the variety of machine learning in healthcare, covering medical image segmentation, timeseries learning, multimodal representations, and more.
Location: Merantix AI Campus (Max-Urich-Straße 3, 13355 Berlin)
Time: Every Monday, 6:45pm
Mon, October 27, 2025Reading Group
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 et al.
Paper
Tillmann Rheude, Leonhard Kohleick, and Benjamin Wild from Berlin Institute of Health at Charité co-hosted this reading group on the variety of machine learning in healthcare, covering medical image segmentation, timeseries learning, multimodal representations, and more.
Location: Merantix AI Campus (Max-Urich-Straße 3, 13355 Berlin)
Time: Every Monday, 6:45pm
Mon, November 3, 2025Reading Group
A foundation model for clinician-centered drug repurposing
Kexin Huang, Payal Chandak, Qianwen Wang, Shreyas Havaldar, Akhil Vaid et al.
Paper
Tillmann Rheude, Leonhard Kohleick, and Benjamin Wild from Berlin Institute of Health at Charité co-hosted this reading group on the variety of machine learning in healthcare, covering medical image segmentation, timeseries learning, multimodal representations, and more.
Location: Merantix AI Campus (Max-Urich-Straße 3, 13355 Berlin)
Time: Every Monday, 6:45pm
Mon, November 10, 2025Reading Group
Large Language Models are Powerful Electronic Health Record Encoders
Stefan Hegselmann, Georg von Arnim, Tillmann Rheude, Noel Kronenberg, David Sontag et al.
Paper
Tillmann Rheude, Leonhard Kohleick, and Benjamin Wild from Berlin Institute of Health at Charité co-hosted this reading group on the variety of machine learning in healthcare, covering medical image segmentation, timeseries learning, multimodal representations, and more.
Location: Merantix AI Campus (Max-Urich-Straße 3, 13355 Berlin)
Time: Every Monday, 6:45pm
Mon, November 17, 2025Reading Group
JanusDNA: A Powerful Bi-directional Hybrid DNA Foundation Model
Qihao Duan, Bingding Huang, Zhenqiao Song, Irina Lehmann, Lei Gu et al.
Paper
Tillmann Rheude, Leonhard Kohleick, and Benjamin Wild from Berlin Institute of Health at Charité co-hosted this reading group on the variety of machine learning in healthcare, covering medical image segmentation, timeseries learning, multimodal representations, and more.
Location: Merantix AI Campus (Max-Urich-Straße 3, 13355 Berlin)
Time: Every Monday, 6:45pm
Mon, November 24, 2025Reading Group
Beyond Sensor Data: Foundation Models of Behavioral Data from Wearables Improve Health Predictions
Eray Erturk, Fahad Kamran, Salar Abbaspourazad, Sean Jewell, Harsh Sharma et al.
Paper
Tillmann Rheude, Leonhard Kohleick, and Benjamin Wild from Berlin Institute of Health at Charité co-hosted this reading group on the variety of machine learning in healthcare, covering medical image segmentation, timeseries learning, multimodal representations, and more.
Location: Merantix AI Campus (Max-Urich-Straße 3, 13355 Berlin)
Time: Every Monday, 6:45pm
Mon, December 1, 2025Reading Group
Contrasting with Symile: Simple Model-Agnostic Representation Learning for Unlimited Modalities
Adriel Saporta, Aahlad Puli, Mark Goldstein, Rajesh Ranganath
Paper
Tillmann Rheude, Leonhard Kohleick, and Benjamin Wild from Berlin Institute of Health at Charité co-hosted this reading group on the variety of machine learning in healthcare, covering medical image segmentation, timeseries learning, multimodal representations, and more.
Location: Merantix AI Campus (Max-Urich-Straße 3, 13355 Berlin)
Time: Every Monday, 6:45pm
Mon, December 8, 2025Reading Group
Training Language Models to Follow Instructions with Human Feedback
Long Ouyang, Jeff Wu, Xu Jiang, Diogo Almeida, Carroll L. Wainwright et al.
Register Paper
Craig Dickson hosted this reading group on technical alignment in AI, covering state of the art research on aligning large language models — including RLHF, constitutional AI, adversarial training, goal misgeneralization, and more.
Location: Merantix AI Campus (Max-Urich-Straße 3, 13355 Berlin)
Time: Every Monday, 6:45pm
Mon, December 15, 2025Reading Group
Constitutional AI: Harmlessness from AI Feedback
Yuntao Bai, Saurav Kadavath, Sandipan Kundu, Amanda Askell, Jackson Kernion et al.
Register Paper
Craig Dickson hosted this reading group on technical alignment in AI, covering state of the art research on aligning large language models — including RLHF, constitutional AI, adversarial training, goal misgeneralization, and more.
Location: Merantix AI Campus (Max-Urich-Straße 3, 13355 Berlin)
Time: Every Monday, 6:45pm
Mon, January 12, 2026Reading Group
Adversarial Training for High-Stakes Reliability
Daniel M. Ziegler, Seraphina Nix, Lawrence Chan, Tim Bauman, Peter Schmidt-Nielsen et al.
Register Paper
Craig Dickson hosted this reading group on technical alignment in AI, covering state of the art research on aligning large language models — including RLHF, constitutional AI, adversarial training, goal misgeneralization, and more.
Location: Merantix AI Campus (Max-Urich-Straße 3, 13355 Berlin)
Time: Every Monday, 6:45pm
Mon, January 19, 2026Reading Group
Goal Misgeneralization in Deep Reinforcement Learning
Lauro Langosco, Jack Koch, Lee Sharkey, Jacob Pfau, Laurent Orseau et al.
Register Paper
Craig Dickson hosted this reading group on technical alignment in AI, covering state of the art research on aligning large language models — including RLHF, constitutional AI, adversarial training, goal misgeneralization, and more.
Location: Merantix AI Campus (Max-Urich-Straße 3, 13355 Berlin)
Time: Every Monday, 6:45pm
Mon, January 26, 2026Reading Group
TruthfulQA: Measuring How Models Mimic Human Falsehoods
Stephanie Lin, Jacob Hilton, Owain Evans
Register Paper
Craig Dickson hosted this reading group on technical alignment in AI, covering state of the art research on aligning large language models — including RLHF, constitutional AI, adversarial training, goal misgeneralization, and more.
Location: Merantix AI Campus (Max-Urich-Straße 3, 13355 Berlin)
Time: Every Monday, 6:45pm
Mon, February 2, 2026Reading Group
Alignment Faking in Large Language Models
Ryan Greenblatt, Carson Denison, Benjamin Wright, Fabien Roger, Monte MacDiarmid et al.
Register Paper
Craig Dickson hosted this reading group on technical alignment in AI, covering state of the art research on aligning large language models — including RLHF, constitutional AI, adversarial training, goal misgeneralization, and more.
Location: Merantix AI Campus (Max-Urich-Straße 3, 13355 Berlin)
Time: Every Monday, 6:45pm
Mon, February 9, 2026Reading Group
Emergent Misalignment
Jan Betley, Daniel Tan, Niels Warncke, Anna Sztyber-Betley, Xuchan Bao et al.
Register Paper
Craig Dickson hosted this reading group on technical alignment in AI, covering state of the art research on aligning large language models — including RLHF, constitutional AI, adversarial training, goal misgeneralization, and more.
Location: Merantix AI Campus (Max-Urich-Straße 3, 13355 Berlin)
Time: Every Monday, 6:45pm
Summer Semester 2026
Mon, April 27, 2026Reading Group
Persona Features Control Emergent Misalignment
Miles Wang, Tom Dupre la Tour, Olivia Watkins, Aleksandar Makelov, Ryan Andrew Chi et al.
Register Paper
This summer semester we are hosting a BLISSful AI reading group. Various BLISS members will present papers related to their research.
Location: Merantix AI Campus (Max-Urich-Straße 3, 13355 Berlin)
Time: Every Monday, 6:45pm
Mon, May 4, 2026Reading Group
Tell me about yourself: LLMs are aware of their learned behaviors
Jan Betley, Xuchan Bao, Martín Soto, Anna Sztyber-Betley, James Chua et al.
Register Paper
This summer semester we are hosting a BLISSful AI reading group. Various BLISS members will present papers related to their research.
Location: Merantix AI Campus (Max-Urich-Straße 3, 13355 Berlin)
Time: Every Monday, 6:45pm
Mon, May 11, 2026Reading Group
Getting aligned on representational alignment
Ilia Sucholutsky, Lukas Muttenthaler, Adrian Weller, Andi Peng, Andreea Bobu et al.
Register Paper
This summer semester we are hosting a BLISSful AI reading group. Various BLISS members will present papers related to their research.
Location: Merantix AI Campus (Max-Urich-Straße 3, 13355 Berlin)
Time: Every Monday, 6:45pm
Mon, May 18, 2026Reading Group
Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
Julian Schrittwieser, Ioannis Antonoglou, Thomas Hubert, Karen Simonyan, Laurent Sifre et al.
Register Paper
This summer semester we are hosting a BLISSful AI reading group. Various BLISS members will present papers related to their research.
Location: Merantix AI Campus (Max-Urich-Straße 3, 13355 Berlin)
Time: Every Monday, 6:45pm
Mon, June 1, 2026Reading Group
Genie: Generative Interactive Environments
Jake Bruce, Michael Dennis, Ashley Edwards, Jack Parker-Holder, Yuge Shi et al.
Register Paper
This summer semester we are hosting a BLISSful AI reading group. Various BLISS members will present papers related to their research.
Location: Merantix AI Campus (Max-Urich-Straße 3, 13355 Berlin)
Time: Every Monday, 6:45pm
Mon, June 8, 2026Reading Group
How Far is Video Generation from World Model: A Physical Law Perspective
Bingyi Kang, Yang Yue, Rui Lu, Zhijie Lin, Yang Zhao et al.
Register Paper
This summer semester we are hosting a BLISSful AI reading group. Various BLISS members will present papers related to their research.
Location: Merantix AI Campus (Max-Urich-Straße 3, 13355 Berlin)
Time: Every Monday, 6:45pm
Mon, June 15, 2026Reading Group
Dyslexify: A Mechanistic Defense Against Typographic Attacks in CLIP
Lorenz Hufe, Constantin Venhoff, Erblina Purelku, Maximilian Dreyer, Sebastian Lapuschkin et al.
Register Paper
This summer semester we are hosting a BLISSful AI reading group. Various BLISS members will present papers related to their research.
Location: Merantix AI Campus (Max-Urich-Straße 3, 13355 Berlin)
Time: Every Monday, 6:45pm
Mon, June 22, 2026CancelledReading Group
Token Sparse Attention: Efficient Long-Context Inference with Interleaved Token Selection
Dongwon Jo, Beomseok Kang, Jiwon Song, Jae-Joon Kim
Paper
This summer semester we are hosting a BLISSful AI reading group. Various BLISS members will present papers related to their research.
Location: Merantix AI Campus (Max-Urich-Straße 3, 13355 Berlin)
Time: Every Monday, 6:45pm
Mon, June 29, 2026Reading Group
SonicBoom: Contact Localization Using Array of Microphones
Moonyoung Lee, Uksang Yoo, Jean Oh, Jeffrey Ichnowski, George Kantor et al.
Register Paper
This summer semester we are hosting a BLISSful AI reading group. Various BLISS members will present papers related to their research.
Location: Merantix AI Campus (Max-Urich-Straße 3, 13355 Berlin)
Time: Every Monday, 6:45pm
Mon, July 6, 2026Reading Group
DexForce: Extracting Force-informed Actions from Kinesthetic Demonstrations for Dexterous Manipulation
Claire Chen, Zhongchun Yu, Hojung Choi, Mark Cutkosky, Jeannette Bohg
Register Paper
This summer semester we are hosting a BLISSful AI reading group. Various BLISS members will present papers related to their research.
Location: Merantix AI Campus (Max-Urich-Straße 3, 13355 Berlin)
Time: Every Monday, 6:45pm
Mon, July 13, 2026Reading Group
Coupled Particle Filters for Robust Affordance Estimation
Patrick Lowin, Vito Mengers, Oliver Brock
Register Paper
This summer semester we are hosting a BLISSful AI reading group. Various BLISS members will present papers related to their research.
Location: Merantix AI Campus (Max-Urich-Straße 3, 13355 Berlin)
Time: Every Monday, 6:45pm
More events are being planned — stay tuned!