Reading Group

The reading group in the WiSe24/25 will be every week on Monday evenings, starting on the 21st of October. We meet at 7pm in MAR 0.015 .

Down below you find the list of papers with their respective date. Please read the paper before attending as we will use the time to discuss the contents.

We will use the semester to explore LLMs and mechanistic interpretability. At first, we are going to learn the basics of natural language processing and the transformer architecture. Then we will have a look at scaling these models, modern trainign techniques and self improvement. Afterwards, we will switch topics and focus on mechanistic interpretability. For this part, we are still working on the details.

Upcoming

December 16, 2024

A Mathematical Framework for Transformer Circuits

Nelson Elhage, Neel Nanda, Catherine Olsson, Tom Henighan†, Nicholas Joseph†, Ben Mann†, Amanda Askell, Yuntao Bai, Anna Chen, Tom Conerly, Nova DasSarma, Dawn Drain, Deep Ganguli, Zac Hatfield-Dodds, Danny Hernandez, Andy Jones, Jackson Kernion, Liane Lovitt, Kamal Ndousse, Dario Amodei, Tom Brown, Jack Clark, Jared Kaplan, Sam McCandlish, Chris Olah

January 13, 2025

Toy Models of Superposition

Nelson Elhage, Tristan Hume, Catherine Olsson, Nicholas Schiefer, Tom Henighan, Shauna Kravec, Zac Hatfield-Dodds, Robert Lasenby, Dawn Drain, Carol Chen, Roger Grosse, Sam McCandlish, Jared Kaplan, Dario Amodei, Martin Wattenberg, Christopher Olah

January 20, 2025

Steering Llama 2 via Contrastive Activation Addition

Nina Rimsky, Nick Gabrieli, Julian Schulz, Meg Tong, Evan Hubinger, Alexander Matt Turner

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

February 3, 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, Carson Denison, Amanda Askell, Robert Lasenby, Yifan Wu, Shauna Kravec, Nicholas Schiefer, Tim Maxwell, Nicholas Joseph, Alex Tamkin, Karina Nguyen, Brayden McLean, Josiah E Burke, Tristan Hume, Shan Carter, Tom Henighan, Chris Olah

February 10, 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, Emmanuel Ameisen, Andy Jones, Hoagy Cunningham, Nicholas L Turner, Callum McDougall, Monte MacDiarmid, Alex Tamkin, Esin Durmus, Tristan Hume, Francesco Mosconi, C. Daniel Freeman, Theodore R. Sumers, Edward Rees, Joshua Batson, Adam Jermyn, Shan Carter, Chris Olah, Tom Henighan

Past

December 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, Colton Bishop, Rebecca Roelofs, Lei M Zhang, Kay McKinney, Disha Shrivastava, Cosmin Paduraru, George Tucker, Doina Precup, Feryal Behbahani, Aleksandra Faust

December 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, Katarina Slama, Alex Ray, John Schulman, Jacob Hilton, Fraser Kelton, Luke Miller, Maddie Simens, Amanda Askell, Peter Welinder, Paul Christiano, Jan Leike, Ryan Lowe

November 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

November 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, Johannes Welbl, Aidan Clark, Tom Hennigan, Eric Noland, Katie Millican, George van den Driessche, Bogdan Damoc, Aurelia Guy, Simon Osindero, Karen Simonyan, Erich Elsen, Jack W. Rae, Oriol Vinyals, Laurent Sifre

November 11, 2024

A Formal Perspective on Byte-Pair Encoding

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

November 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, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel M. Ziegler, Jeffrey Wu, Clemens Winter, Christopher Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, Dario Amodei

October 28, 2024

Formal Algorithms for Transformers

Mary Phuong, Marcus Hutter

October 21, 2024

Natural Language Processing, Chapter 6

Jacob Eisenstein

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

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, Zhaohan Daniel Guo, Mohammad Gheshlaghi Azar, Bilal Piot, Koray Kavukcuoglu, Rémi Munos, Michal Valko

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, Adam Roberts, Marco Tagliasacchi, Matt Sharifi, Neil Zeghidour, Christian Frank

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

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, Mohammad Azar, David Silver

November 24, 2023

Noisy Networks for Exploration

Meire Fortunato, Mohammad Gheshlaghi Azar, Bilal Piot, Jacob Menick, Ian Osband, Alex Graves, Vlad Mnih, Remi Munos, Demis Hassabis, Olivier Pietquin, Charles Blundell, Shane Legg

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, A. Fidjeland, Georg Ostrovski, Stig Petersen, Charlie Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, D. Kumaran, Daan Wierstra, S. Legg, D. Hassabis