The AI@MIT club holds (nearly) weekly reading groups on topics in machine learning, from theory to computer vision to systems applications. Join the mailing list and Slack community to hear more + discuss!
Find paper PDFs, along with some slides and notes, in this repository.
| Date | Paper | Slides | Presenter |
|---|---|---|---|
| 4/7/2020 | Recent advances in contrastive learning | slides | Rumen Dangovski |
| 3/31/2020 | Online Learning and Regret Minimization | slides | Max Fishelson |
| 3/24/2020 | Fixing Data Augmentation to Improve Adversarial Robustness | slides | Kristian Georgiev |
| 3/17/2021 | Contrastive Text Generation | slides | Darsh Shah |
| Date | Paper | Slides | Presenter |
|---|---|---|---|
| 11/20/2020 | Train simultaneously, generalize better: Stability of gradient-based minimax learners | Kristian Georgiev | |
| 11/13/2020 | Deep Learning for Symbolic Mathematics | slides | Shayda Moezzi |
| 10/30/2020 | Tailoring: encoding inductive biases by optimizing unsupervised objectives at prediction time | slides | Farren Alet |
| 10/23/2020 | Denoising Diffusion Probabilistic Models | slides | Ajay Jain |
| 10/9/2020 | Robust Encodings: A Framework for Combating Adversarial Typos | annotated paper | Raj Movva |
| 4/7/2020 | Meta-Learning Symmetries by Reparameterization | Kristian Georgiev | |
| 3/4/2020 | What Do Neural Networks Learn When Trained With Random Labels? | slides | Kaveri Nadhamuni |
| Date | Paper | Slides | Presenter |
|---|---|---|---|
| 4/15/2020 | Fractal AI: A Fragile Theory of Intelligence | slides | Tony Wang |
| 4/7/2020 | A Unified Analysis of Extra-gradient and Optimistic Gradient Methods for Saddle Point Problems: Proximal Point Approach | Kristian Georgiev | |
| 3/4/2020 | Invertible Residual Networks | slides | Kaveri Nadhamuni |
| 2/19/2020 | Towards Learned Algorithms, Data Structures, and Systems | slides | Prof. Tim Kraska |
| Date | Paper | Slides | Presenter |
|---|---|---|---|
| 5/6/2019 | Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments | slides | Rose Wang |
| 4/29/2019 | Learning Latent Permutations with Gumbel-Sinkhorn Networks | slides | Ajay Jain |
| 4/19/2019 | Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models | slides | Kaveri Nadhamuni |
| 4/10/2019 | A Brief Introduction to Hyperbolic Geometry for Machine Learning | slides | Justin Chen |
| 4/3/2019 | Sampling Matters in Deep Embedding Learning | Samson Timoner | |
| 3/13/2019 | Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation | Sualeh Asif | |
| 3/6/2019 | A Style-Based Generator Architecture for Generative Adversarial Networks (video) | slides | Abhinav Venigalla |
| 2/25/2019 | Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks | slides | Ajay Jain |
| Date | Paper | Presenter |
|---|---|---|
| 11/28/2018 | BAGAN: Data Augmentation with Balancing GAN | Kaveri Nadhamuni |
| 11/14/2018 | BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding | Sree Harsha Nelaturu |
| 10/31/2018 | How Does Batch Normalization Help Optimization? | Moin Nadeem |
| 10/24/2018 | Annotating the World Wide Web using Natural Language, Omnibase: Uniform Access to Heterogeneous Data for Question Answering | Michael Silver |
| 10/17/2018 | Learning to Compose Neural Networks for Question Answering | Sree Harsha Nelaturu |
| 10/10/2018 | Neural Turing Machines (blog post) | Nate Foss |
| 10/3/2018 | Bring your own paper! | -- |
| 9/26/2018 | Variational Inference with Normalizing Flows | Ajay Jain |
| Date | Paper | Presenter |
|---|---|---|
| 5/2/18 | DeepCoder: Learning to Write Programs | Nate Foss |
| 4/25/18 | Guest speaker: GAN overview, CycleGAN, BicycleGAN | Jun-Yan Zhu (MIT CSAIL) |
| 4/11/18 | Toward Multimodal Image-to-Image Translation | Tieshun Roquerre |
| 4/4/18 | Stochastic Program Optimization | Ajay Jain |
| 3/14/18 | Learned Index Structures | Kristian Georgiev |
| 3/7/18 | Rationalizing Neural Predictions | Collaborative read |
| 2/28/18 | Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks | Parth Shah |
| 2/21/18 | Overview: Adversarial Examples | Bristy Sikder |
| 2/14/18 | Large Scale Distributed Deep Networks | Ajay Jain & Justin Chen |
| Date | Paper | Presenter |
|---|---|---|
| 12/7/2017 | Movie screening: AlphaGo | -- |
| 12/6/2017 | Guest speakers: Robust Adversarial Examples | Anish Athalye & Logan Engstrom (MIT) |
| 11/29/2017 | Improved Training of Wasserstein GANs | Isaac Wolverton |
| 11/15/2017 | Mastering the game of Go without human knowledge (AlphaGo Zero) | Jeremy Nixon |
| 11/8/2017 | Decoupled Neural Interfaces using Synthetic Gradients | Andrew Luo |
| 10/26/2017 | Playing Atari with Deep Reinforcement Learning | Tim Plump |
| 10/19/2017 | One/Few shot learning | Matthew Feng & Parth Shah |
| 10/12/2017 | Skip thought vectors | Nikhil Murthy |
| 10/6/2017 | DeepFace and FaceNet | Ajay Jain |
| 9/28/2017 | DenseNet, ResNet and HighwayNet | Tim Plump |
| 9/18/2017 | Guest speaker: Object detection and recognition | Paras Jain (DeepScale) |
| 9/14/2017 | Feature Pyramid Networks for Object Detection | Andrew Luo |
| Date | Paper | Presenter |
|---|---|---|
| 11/7/2016 | Adam - A method for stochastic optimization | Hassan Kane |
| 10/31/2016 | Learning to Protect Communications with Adversarial Neural Cryptography | Simanta Gautam |
| 10/24/2016 | Show, Attend and Tell: Neural Image Caption Generation with Visual Attention | Nick |
| 10/17/2016 | Human-level control through deep reinforcement learning | Ali-Amir Aldan |
| 10/3/2016 | Generative Adversarial Networks | Prafulla Dhariwal |