paper-reading-group
Paper Reading Group
Notes for papers presented during our paper reading sessions
Papers:
MOPO: Model-based Offline Policy Optimization
DETR: End-to-End Object Detection with Transformers
Efficient Adaptation for End-to-End Vision-Based Robotic Manipulation
PipeDream: Generalized Pipeline Parallelism for DNN Training
Lottery Ticket Hypothesis
Assessing the Ability of LSTMs to Learn Syntax-Sensitive Dependencies (Tal Linzen, Emmanuel Dupoux, Yoav Goldberg)
Designing and Interpreting Probes with Control Tasks (John Hewitt & Percy Liang)
What Does BERT Learn about the Structure of Language? (Ganesh Jawahar, Benoît Sagot, Djamé Seddah)
GNN
Universal Adversarial Triggers
Confidence-Aware Learning for Deep Neural Networks (CRL)
A How-to-Model Guide for Neuroscience
Neural ODEs
Model based Reinforcement Learning
Learning to describe scenes with programs
DeepSynth: Automata Synthesis for Automatic Task Segmentation in RL
Model free conventions in MARL with Heterogeneous Preferences
Accelerating Reinforcement Learning with Learned Skill Priors
Progressive Domain Adaptation for Object Detection
Convolutional Networks with Adaptive inference Graphs