{"list":"other","total":62,"rows":[{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"1308.3432","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","created":"2013-08-15","cited_by_count":2079},{"id":"1906.00446","title":"Generating Diverse High-Fidelity Images with VQ-VAE-2","created":"2019-06-02","cited_by_count":1387},{"id":"2207.04672","title":"No Language Left Behind: Scaling Human-Centered Machine Translation","created":"2022-07-11","cited_by_count":1312},{"id":"2006.15055","title":"Object-Centric Learning with Slot Attention","created":"2020-06-26","cited_by_count":876},{"id":"2004.09813","title":"Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation","created":"2020-04-21","cited_by_count":593},{"id":"2106.04399","title":"Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation","created":"2021-06-08","cited_by_count":392},{"id":"1511.02799","title":"Neural Module Networks","created":"2015-11-09","cited_by_count":376},{"id":"2111.09266","title":"GFlowNet Foundations","created":"2021-11-17","cited_by_count":290},{"id":"2011.15091","title":"Inductive Biases for Deep Learning of Higher-Level Cognition","created":"2020-11-30","cited_by_count":275},{"id":"1908.08351","title":"Compositionality decomposed: how do neural networks generalise?","created":"2019-08-22","cited_by_count":265},{"id":"2006.08381","title":"DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning","created":"2020-06-15","cited_by_count":161},{"id":"2107.10098","title":"Disentanglement via Mechanism Sparsity Regularization: A New Principle for Nonlinear ICA","created":"2021-07-21","cited_by_count":160},{"id":"2203.16437","title":"Weakly supervised causal representation learning","created":"2022-03-30","cited_by_count":140},{"id":"2202.03169","title":"CITRIS: Causal Identifiability from Temporal Intervened Sequences","created":"2022-02-07","cited_by_count":133},{"id":"2103.15949","title":"Transformer visualization via dictionary learning: contextualized embedding as a linear superposition of transformer factors","created":"2021-03-29","cited_by_count":108},{"id":"1709.08568","title":"The Consciousness Prior","created":"2017-09-25","cited_by_count":107},{"id":"2212.10537","title":"Does CLIP Bind Concepts? Probing Compositionality in Large Image Models","created":"2022-12-20","cited_by_count":102},{"id":"2310.04363","title":"Amortizing intractable inference in large language models","created":"2023-10-06","cited_by_count":97},{"id":"1902.07181","title":"Measuring Compositionality in Representation Learning","created":"2019-02-19","cited_by_count":84},{"id":"2302.11529","title":"Modular Deep Learning","created":"2023-02-22","cited_by_count":83},{"id":"2002.01365","title":"Compositional Languages Emerge in a Neural Iterated Learning Model","created":"2020-02-04","cited_by_count":75},{"id":"2103.01937","title":"Neural Production Systems: Learning Rule-Governed Visual Dynamics","created":"2021-03-02","cited_by_count":75},{"id":"1802.07044","title":"The Description Length of Deep Learning Models","created":"2018-02-20","cited_by_count":72},{"id":"1906.02403","title":"Ease-of-Teaching and Language Structure from Emergent Communication","created":"2019-06-06","cited_by_count":65},{"id":"2206.01101","title":"Weakly Supervised Representation Learning with Sparse Perturbations","created":"2022-06-02","cited_by_count":65},{"id":"2307.05596","title":"Compositional Generalization from First Principles","created":"2023-07-10","cited_by_count":64},{"id":"2304.05366","title":"The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learning","created":"2023-04-11","cited_by_count":63},{"id":"2307.02598","title":"Additive Decoders for Latent Variables Identification and Cartesian-Product Extrapolation","created":"2023-07-05","cited_by_count":58},{"id":"2005.08520","title":"Robust Training of Vector Quantized Bottleneck Models","created":"2020-05-18","cited_by_count":54},{"id":"1808.05563","title":"Learning Invariances using the Marginal Likelihood","created":"2018-08-16","cited_by_count":51},{"id":"2006.16225","title":"Object Files and Schemata: Factorizing Declarative and Procedural Knowledge in Dynamical Systems","created":"2020-06-29","cited_by_count":48},{"id":"2302.14383","title":"Linear Spaces of Meanings: Compositional Structures in Vision-Language Models","created":"2023-02-28","cited_by_count":48},{"id":"2211.14666","title":"Synergies between Disentanglement and Sparsity: Generalization and Identifiability in Multi-Task Learning","created":"2022-11-26","cited_by_count":44},{"id":"2301.10884","title":"Break It Down: Evidence for Structural Compositionality in Neural Networks","created":"2023-01-26","cited_by_count":44},{"id":"2202.10638","title":"Invariance Learning in Deep Neural Networks with Differentiable Laplace Approximations","created":"2022-02-22","cited_by_count":42},{"id":"2310.05327","title":"Provable Compositional Generalization for Object-Centric Learning","created":"2023-10-09","cited_by_count":41},{"id":"2302.06576","title":"GFlowNet-EM for learning compositional latent variable models","created":"2023-02-13","cited_by_count":40},{"id":"2202.00155","title":"Fortuitous Forgetting in Connectionist Networks","created":"2022-02-01","cited_by_count":39},{"id":"2211.01177","title":"Neural Systematic Binder","created":"2022-11-02","cited_by_count":37},{"id":"2206.02713","title":"Is a Modular Architecture Enough?","created":"2022-06-06","cited_by_count":36},{"id":"2204.00616","title":"Simplicial Embeddings in Self-Supervised Learning and Downstream Classification","created":"2022-04-01","cited_by_count":24},{"id":"2312.15001","title":"Discovering modular solutions that generalize compositionally","created":"2023-12-22","cited_by_count":23},{"id":"2405.16391","title":"When does compositional structure yield compositional generalization? A kernel theory","created":"2024-05-26","cited_by_count":20},{"id":"2202.04895","title":"Diffusion bridges vector quantized Variational AutoEncoders","created":"2022-02-10","cited_by_count":16},{"id":"2202.12439","title":"Learning Invariant Weights in Neural Networks","created":"2022-02-25","cited_by_count":16},{"id":"2310.18777","title":"Improving Compositional Generalization Using Iterated Learning and Simplicial Embeddings","created":"2023-10-28","cited_by_count":15},{"id":"2409.14981","title":"On The Specialization of Neural Modules","created":"2024-09-23","cited_by_count":14},{"id":"2210.07931","title":"Sequential Learning Of Neural Networks for Prequential MDL","created":"2022-10-14","cited_by_count":13},{"id":"2110.09419","title":"Compositional Attention: Disentangling Search and Retrieval","created":"2021-10-18","cited_by_count":12},{"id":"2402.01203","title":"Neural Language of Thought Models","created":"2024-02-02","cited_by_count":9},{"id":"2010.09602","title":"End-to-End Text-to-Speech using Latent Duration based on VQ-VAE","created":"2020-10-19","cited_by_count":7},{"id":"2302.06403","title":"Sources of Richness and Ineffability for Phenomenally Conscious States","created":"2023-02-13","cited_by_count":7},{"id":"2402.05309","title":"Investigating Generalization Behaviours of Generative Flow Networks","created":"2024-02-07","cited_by_count":6},{"id":"2405.02350","title":"What makes Models Compositional? A Theoretical View: With Supplement","created":"2024-05-02","cited_by_count":5},{"id":"2409.09626","title":"Understanding Simplicity Bias towards Compositional Mappings via Learning Dynamics","created":"2024-09-15","cited_by_count":5},{"id":"2110.03498","title":"On the relationship between disentanglement and multi-task learning","created":"2021-10-07","cited_by_count":4},{"id":"2407.11249","title":"Disentangling Representations through Multi-task Learning","created":"2024-07-15","cited_by_count":4},{"id":"1804.06955","title":"Disentangling Controllable and Uncontrollable Factors of Variation by Interacting with the World","created":"2018-04-19","cited_by_count":3}],"next_cursor":null}