{"list":"other","total":52,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"1605.08803","title":"Density estimation using Real NVP","created":"2016-05-27","cited_by_count":2042},{"id":"2205.10625","title":"Least-to-Most Prompting Enables Complex Reasoning in Large Language Models","created":"2022-05-21","cited_by_count":1407},{"id":"1806.01261","title":"Relational inductive biases, deep learning, and graph networks","created":"2018-06-04","cited_by_count":1360},{"id":"2210.03350","title":"Measuring and Narrowing the Compositionality Gap in Language Models","created":"2022-10-07","cited_by_count":1075},{"id":"1609.09106","title":"HyperNetworks","created":"2016-09-27","cited_by_count":1027},{"id":"1805.00932","title":"Exploring the Limits of Weakly Supervised Pretraining","created":"2018-05-02","cited_by_count":605},{"id":"2410.05229","title":"GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models","created":"2024-10-07","cited_by_count":550},{"id":"2305.18654","title":"Faith and Fate: Limits of Transformers on Compositionality","created":"2023-05-29","cited_by_count":503},{"id":"2309.12288","title":"The Reversal Curse: LLMs trained on \"A is B\" fail to learn \"B is A\"","created":"2023-09-21","cited_by_count":407},{"id":"1511.02799","title":"Neural Module Networks","created":"2015-11-09","cited_by_count":376},{"id":"2310.15916","title":"In-Context Learning Creates Task Vectors","created":"2023-10-24","cited_by_count":312},{"id":"2002.04486","title":"Implicit Bias of Gradient Descent for Wide Two-layer Neural Networks Trained with the Logistic Loss","created":"2020-02-11","cited_by_count":268},{"id":"2402.16837","title":"Do Large Language Models Latently Perform Multi-Hop Reasoning?","created":"2024-02-26","cited_by_count":169},{"id":"2108.12284","title":"The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers","created":"2021-08-26","cited_by_count":117},{"id":"1902.05040","title":"How do infinite width bounded norm networks look in function space?","created":"2019-02-13","cited_by_count":106},{"id":"2212.10537","title":"Does CLIP Bind Concepts? Probing Compositionality in Large Image Models","created":"2022-12-20","cited_by_count":102},{"id":"2007.08970","title":"Compositional Generalization in Semantic Parsing: Pre-training vs. Specialized Architectures","created":"2020-07-17","cited_by_count":95},{"id":"2310.09336","title":"Compositional Abilities Emerge Multiplicatively: Exploring Diffusion Models on a Synthetic Task","created":"2023-10-13","cited_by_count":93},{"id":"2206.00939","title":"Gradient flow dynamics of shallow ReLU networks for square loss and orthogonal inputs","created":"2022-06-02","cited_by_count":76},{"id":"2307.02129","title":"How Deep Neural Networks Learn Compositional Data: The Random Hierarchy Model","created":"2023-07-05","cited_by_count":71},{"id":"2307.05596","title":"Compositional Generalization from First Principles","created":"2023-07-10","cited_by_count":64},{"id":"2408.14339","title":"ConceptMix: A Compositional Image Generation Benchmark with Controllable Difficulty","created":"2024-08-26","cited_by_count":61},{"id":"2503.02113","title":"Deep Learning is Not So Mysterious or Different","created":"2025-03-03","cited_by_count":56},{"id":"2205.12253","title":"Evaluating the Impact of Model Scale for Compositional Generalization in Semantic Parsing","created":"2022-05-24","cited_by_count":50},{"id":"2301.10884","title":"Break It Down: Evidence for Structural Compositionality in Neural Networks","created":"2023-01-26","cited_by_count":44},{"id":"2310.05327","title":"Provable Compositional Generalization for Object-Centric Learning","created":"2023-10-09","cited_by_count":41},{"id":"2402.01103","title":"Compositional Generative Modeling: A Single Model is Not All You Need","created":"2024-02-02","cited_by_count":41},{"id":"2407.15720","title":"Do Large Language Models Have Compositional Ability? An Investigation into Limitations and Scalability","created":"2024-07-22","cited_by_count":40},{"id":"2310.19956","title":"The Impact of Depth on Compositional Generalization in Transformer Language Models","created":"2023-10-30","cited_by_count":38},{"id":"2410.01748","title":"Not All LLM Reasoners Are Created Equal","created":"2024-10-02","cited_by_count":30},{"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":"2411.07784","title":"Interaction Asymmetry: A General Principle for Learning Composable Abstractions","created":"2024-11-12","cited_by_count":20},{"id":"2501.09240","title":"Task Vectors in In-Context Learning: Emergence, Formation, and Benefit","created":"2025-01-16","cited_by_count":20},{"id":"2301.01413","title":"Attribute-Centric Compositional Text-to-Image Generation","created":"2023-01-04","cited_by_count":19},{"id":"2402.18361","title":"Why Do Animals Need Shaping? A Theory of Task Composition and Curriculum Learning","created":"2024-02-28","cited_by_count":16},{"id":"2410.22330","title":"Vision-Language Models Create Cross-Modal Task Representations","created":"2024-10-29","cited_by_count":15},{"id":"2409.14981","title":"On The Specialization of Neural Modules","created":"2024-09-23","cited_by_count":14},{"id":"2406.05816","title":"Attention as a Hypernetwork","created":"2024-06-09","cited_by_count":13},{"id":"2408.13256","title":"How Diffusion Models Learn to Factorize and Compose","created":"2024-08-23","cited_by_count":13},{"id":"2410.14817","title":"A Complexity-Based Theory of Compositionality","created":"2024-10-18","cited_by_count":13},{"id":"2502.15277","title":"Analyzing the Inner Workings of Transformers in Compositional Generalization","created":"2025-02-21","cited_by_count":6},{"id":"2109.15101","title":"Compositional generalization in semantic parsing with pretrained transformers","created":"2021-09-30","cited_by_count":5},{"id":"2409.05780","title":"Breaking Neural Network Scaling Laws with Modularity","created":"2024-09-09","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":"2410.08309","title":"Swing-by Dynamics in Concept Learning and Compositional Generalization","created":"2024-10-10","cited_by_count":5}],"next_cursor":null}