Notes on interesting papers I've read and everything else I find noteworthy, mostly for future reference.

- [Educational Researcher 1984] The Two Sigma Problem paper
- [NeurIPS 2023] Reflexion: Language Agents with Verbal Reinforcement Learning language-agents language-models paper
- [ICLR 2023] ReAct: Synergizing Reasoning and Acting in Language Models language-agents paper language-models
- [NeurIPS 2017] Thinking Fast and Slow with Deep Learning and Tree Search rl paper
- [arXiv 2016] Holophrasm: a neural Automated Theorem Prover for higher-order logic theorem-proving rl paper
- First-order Superposition logic theorem-proving
- [Science 2022] Competition-level code generation with AlphaCode language-models paper program-synthesis
- [arXiv 2022] Least-to-Most Prompting Enables Complex Reasoning in Large Language Models language-models paper
- [arXiv 2022] Compositional Semantic Parsing with Large Language Models language-models paper
- [PNAS 2020] Brain computation by assemblies of neurons theoretical-computer-science paper neuroscience
- [ICLR 2020] Deep Learning for Symbolic Mathematics deep-learning paper
- [NeurIPS 1998] Learning Macro-Actions in Reinforcement Learning rl paper
- [NeurIPS 2021] Subgoal Search For Complex Reasoning Tasks ml research paper
- [Computational Linguistics 1996] A maximum entropy approach to natural language processing ml nlp paper
- Monte Carlo Tree Search rl
- [arXiv 2022] HyperTree Proof Search for Neural Theorem Proving ml rl theorem-proving paper
- [arXiv 2021] Proving Theorems using Incremental Learning and Hindsight Experience Replay ml paper theorem-proving
- [arXiv 2022] Autoformalization with Large Language Models language-models theorem-proving paper
- [ICML 2022] Prioritized Training on Points that are Learnable, Worth Learning, and Not Yet Learnt ml paper
- [ICLR 2022] An Explanation of In-context Learning as Implicit Bayesian Inference bayesian-inference ml paper in-context-learning
- [arXiv 2022] Data Distributional Properties Drive Emergent In-Context Learning in Transformers ml paper in-context-learning
- [ICML 2009] Curriculum learning ml paper
- GTD
- [EDM 2020] Variational Item Response Theory: Fast, Accurate, and Expressive psychometrics ml paper irt
- [ICML 2019] Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations ml paper
- [Journal of Mathematical Psychology 2007] ‘Ideal learning’ of natural language: Positive results about learning from positive evidence paper linguistics
- [PNAS 2022] One model for the learning of language cogsci paper linguistics
- [ICML 2021] LIME: Learning Inductive Bias for Primitives of Mathematical Reasoning ml paper theorem-proving
- [NeurIPS 2020] Big Bird: Transformers for Longer Sequences paper
- [arXiv] Longformer: The Long-Document Transformer paper
- [ICLR 2022] Memorizing Transformers paper
- [ICLR 2022] Proof Artifact Co-training for Theorem Proving with Language Models theorem-proving paper ml
- GNU/Linux Reference linux
- [NeurIPS 2018] How Does Batch Normalization Help Optimization? ml paper
- [NeurIPS 2019] Adversarial Examples Are Not Bugs, They Are Features robustness ml paper
- [ICLR 2022] Natural Language Descriptions of Deep Visual Features interpretability ml paper
- [ICCV 2021] Curious Representation Learning for Embodied Intelligence ml representation-learning rl paper
- [SocArxiv 2021] The InterModel Vigorish (IMV): A flexible and portable approach for quantifying predictive accuracy with binary outcomes stats psychometrics paper
- [ICLR 2022] Increasing the Cost of Model Extraction with Calibrated Proof of Work ml security paper
- Energy-Based Models ml generative-models
- [ICML 2017] Wasserstein Generative Adversarial Networks ml generative-models paper
- [NeurIPS 2016] f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization ml generative-models paper
- [NeurIPS 2014] Generative Adversarial Nets paper
- [Cognitive Science 2020] Assessing Mathematics Misunderstandings via Bayesian Inverse Planning paper cogsci education bayesian-inference
- [ICLR 2015] Importance Weighted Autoencoders ml paper
- [ICLR 2017] beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework ml paper
- Evidence Lower Bound (ELBO) stats ml
- [ICLR 2014] Auto-Encoding Variational Bayes ml generative-models paper
- Experiment Pre-registration research
- Fixing the resolution of an external display arch-linux
- [ICLR 2020] Plug and Play Language Models: A Simple Approach to Controlled Text Generation paper
- [ICLR 2021] IsarStep: A Benchmark For High-Level Mathematical Reasoning paper
- [ACL 2016] Deep Reinforcement Learning with a Natural Language Action Space paper
- [Educational Psychology 2011] Practicing Versus Inventing With Contrasting Cases: The Effects of Telling First on Learning and Transfer paper
- [Science 2018] A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play paper
- [arXiv] Generative Language Modeling for Automated Theorem Proving paper
- [ICLR 2014] Auto-Encoding Variatonal Bayes paper
- [ICLR 2017] Categorical Reparameterization with Gumbel-Softmax paper
- [EMNLP 2020] Unsupervised Question Decomposition for Question Answering paper
- [NeurIPS 2019] Representation Learning with Contrastive Predictive Coding paper
- [Psychological Review 2007] Word Learning as Bayesian Inference paper
- [ICFP 2011] Parsing with Derivatives: A Functional Pearl paper
- [Cognition 2012] The communicative function of ambiguity in language paper
- [KDD 2016] "Why Should I Trust You?": Explaining the Predictions of Any Classifier paper
- [CHI 2020] An Interaction Design for Machine Teaching to Develop AI Tutors paper
- [TCS 2020] Anchoring Utterances paper
- [arXiv 2020] Program Synthesis with Pragmatic Communication paper
- [NeurIPS 2019] Write, Execute, Assess: Program Synthesis with a REPL paper
- [ICLR 2019] Execution-Guided Neural Program Synthesis paper
- [NeurIPS 2018] Learning to Infer Graphics Programs from Hand-Drawn Images paper
- [CVPR 2016] Neural Module Networks paper
- [BRMIC 2004] AutoTutor: A tutor with dialogue in natural language paper
- [CVPR 2020] ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks paper
- [arXiv 2020] Language Models are Few-Shot Learners paper
- [POPL 2004] Abstractions from proofs paper
- [ICCV 2017] Inferring and Executing Programs for Visual Reasoning paper
- [NeurIPS 2015] Exploring Models and Data for Image Question Answering paper
- [NeurIPS 2017] Attention is All You Need paper
- [ACL 2020] Interactive Classification by Asking Informative Questions paper
- [CogSci 2019] Asking goal-oriented questions and learning from answers paper
- [NeurIPS 2019] Zero-shot Learning via Simultaneous Generating and Learning paper