paper-reading-group

Paper Reading Group

Notes for papers presented during our paper reading sessions

Papers:

  1. MOPO: Model-based Offline Policy Optimization
  2. DETR: End-to-End Object Detection with Transformers
  3. Efficient Adaptation for End-to-End Vision-Based Robotic Manipulation
  4. PipeDream: Generalized Pipeline Parallelism for DNN Training
  5. Lottery Ticket Hypothesis
  6. Assessing the Ability of LSTMs to Learn Syntax-Sensitive Dependencies (Tal Linzen, Emmanuel Dupoux, Yoav Goldberg)
  7. Designing and Interpreting Probes with Control Tasks (John Hewitt & Percy Liang)
  8. What Does BERT Learn about the Structure of Language? (Ganesh Jawahar, Benoît Sagot, Djamé Seddah)
  9. GNN
  10. Universal Adversarial Triggers
  11. Confidence-Aware Learning for Deep Neural Networks (CRL)
  12. A How-to-Model Guide for Neuroscience
  13. Neural ODEs
  14. Model based Reinforcement Learning
  15. Learning to describe scenes with programs
  16. DeepSynth: Automata Synthesis for Automatic Task Segmentation in RL
  17. Model free conventions in MARL with Heterogeneous Preferences
  18. Accelerating Reinforcement Learning with Learned Skill Priors
  19. Progressive Domain Adaptation for Object Detection
  20. Convolutional Networks with Adaptive inference Graphs