• Home
• Blog
• Paper reviews

Paper Reviews

Brief notes on papers I read, mostly for future reference.

• [ACL 2016] Deep Reinforcement Learning with a Natural Language Action Space
• [Educational Psychology 2011] Practicing Versus Inventing With Contrasting Cases: The Effects of Telling First on Learning and Transfer
• [Science 2018] A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play
• [arXiv] Generative Language Modeling for Automated Theorem Proving
• [ICLR 2014] Auto-Encoding Variatonal Bayes
• [ICLR 2017] Categorical Reparameterization with Gumbel-Softmax
• [EMNLP 2020] Unsupervised Question Decomposition for Question Answering
• [NeurIPS 2019] Representation Learning with Contrastive Predictive Coding
• [Psychological Review 2007] Word Learning as Bayesian Inference
• [ICFP 2011] Parsing with Derivatives: A Functional Pearl
• [Cognition 2012] The communicative function of ambiguity in language
• [KDD 2016] "Why Should I Trust You?": Explaining the Predictions of Any Classifier
• [CHI 2020] An Interaction Design for Machine Teaching to Develop AI Tutors
• [TCS 2020] Anchoring Utterances
• [arXiv 2020] Program Synthesis with Pragmatic Communication
• [NeurIPS 2019] Write, Execute, Assess: Program Synthesis with a REPL
• [ICLR 2019] Execution-Guided Neural Program Synthesis
• [NeurIPS 2018] Learning to Infer Graphics Programs from Hand-Drawn Images
• [CVPR 2016] Neural Module Networks
• [BRMIC 2004] AutoTutor: A tutor with dialogue in natural language
• [CVPR 2020] ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks
• [arXiv 2020] Language Models are Few-Shot Learners
• [POPL 2004] Abstractions from proofs
• [ICCV 2017] Inferring and Executing Programs for Visual Reasoning
• [NeurIPS 2015] Exploring Models and Data for Image Question Answering
• [NeurIPS 2017] Attention is All You Need
• [ACL 2020] Interactive Classification by Asking Informative Questions
• [CogSci 2019] Asking goal-oriented questions and learning from answers
• [NeurIPS 2019] Zero-shot Learning via Simultaneous Generating and Learning