{"total":32,"rows":[{"id":"2310.07064","title":"Large Language Models can Learn Rules","created":"2023-10-10","cited_by_count":69,"area":null},{"id":"2210.05062","title":"Relational Attention: Generalizing Transformers for Graph-Structured Tasks","created":"2022-10-11","cited_by_count":41,"area":null},{"id":"2305.19302","title":"Smooth, exact rotational symmetrization for deep learning on point clouds","created":"2023-05-30","cited_by_count":39,"area":null},{"id":"2407.09777","title":"Graph Transformers: A Survey","created":"2024-07-13","cited_by_count":32,"area":null},{"id":"2212.10769","title":"Uncontrolled Lexical Exposure Leads to Overestimation of Compositional Generalization in Pretrained Models","created":"2022-12-21","cited_by_count":26,"area":null},{"id":"2311.09817","title":"Neural-Logic Human-Object Interaction Detection","created":"2023-11-16","cited_by_count":25,"area":null},{"id":"2303.13716","title":"ReCOGS: How Incidental Details of a Logical Form Overshadow an Evaluation of Semantic Interpretation","created":"2023-03-24","cited_by_count":24,"area":null},{"id":"2501.19215","title":"Strassen Attention, Split VC Dimension and Compositionality in Transformers","created":"2025-01-31","cited_by_count":12,"area":null},{"id":"2401.10119","title":"Towards Principled Graph Transformers","created":"2024-01-18","cited_by_count":11,"area":null},{"id":"2503.01431","title":"How simple can you go? An off-the-shelf transformer approach to molecular dynamics","created":"2025-03-03","cited_by_count":10,"area":null},{"id":"2507.02754","title":"Fast and Simplex: 2-Simplicial Attention in Triton","created":"2025-07-03","cited_by_count":8,"area":null},{"id":"2502.15277","title":"Analyzing the Inner Workings of Transformers in Compositional Generalization","created":"2025-02-21","cited_by_count":6,"area":null},{"id":"2201.11316","title":"Transformer Module Networks for Systematic Generalization in Visual Question Answering","created":"2022-01-27","cited_by_count":5,"area":null},{"id":"2302.09458","title":"Learning Language Representations with Logical Inductive Bias","created":"2023-02-19","cited_by_count":5,"area":null},{"id":"2403.11834","title":"Towards Understanding the Relationship between In-context Learning and Compositional Generalization","created":"2024-03-18","cited_by_count":5,"area":null},{"id":"2407.17396","title":"Systematic Relational Reasoning With Epistemic Graph Neural Networks","created":"2024-07-24","cited_by_count":4,"area":null},{"id":"2410.11865","title":"Automatic Screening for Children with Speech Disorder using Automatic Speech Recognition: Opportunities and Challenges","created":"2024-10-07","cited_by_count":3,"area":null},{"id":"2305.04346","title":"Laziness Is a Virtue When It Comes to Compositionality in Neural Semantic Parsing","created":"2023-05-07","cited_by_count":2,"area":null},{"id":"2309.08798","title":"D3: Data Diversity Design for Systematic Generalization in Visual Question Answering","created":"2023-09-15","cited_by_count":2,"area":null},{"id":"2311.01580","title":"MetaReVision: Meta-Learning with Retrieval for Visually Grounded Compositional Concept Acquisition","created":"2023-11-02","cited_by_count":2,"area":null},{"id":"2410.11331","title":"SHAKTI: A 2.5 Billion Parameter Small Language Model Optimized for Edge AI and Low-Resource Environments","created":"2024-10-15","cited_by_count":2,"area":null},{"id":"2510.23532","title":"When No Paths Lead to Rome: Benchmarking Systematic Neural Relational Reasoning","created":"2025-10-27","cited_by_count":2,"area":null},{"id":"2210.05723","title":"Embeddings as Epistemic States: Limitations on the Use of Pooling Operators for Accumulating Knowledge","created":"2022-10-11","cited_by_count":1,"area":null},{"id":"2305.09948","title":"HICO-DET-SG and V-COCO-SG: New Data Splits for Evaluating the Systematic Generalization Performance of Human-Object Interaction Detection Models","created":"2023-05-17","cited_by_count":1,"area":null},{"id":"2601.19094","title":"FloydNet: A Learning Paradigm for Global Relational Reasoning","created":"2026-01-27","cited_by_count":1,"area":null},{"id":"2608.06834","title":"Graph Machine: Exploring Edge Mechanisms as an Inductive Bias","created":"2026-08-07","cited_by_count":1,"area":null},{"id":"2211.11956","title":"A Short Survey of Systematic Generalization","created":"2022-11-22","cited_by_count":0,"area":null},{"id":"2302.10043","title":"Friend Ranking in Online Games via Pre-training Edge Transformers","created":"2023-02-20","cited_by_count":0,"area":null},{"id":"2501.09451","title":"Scaling Graph-Based Dependency Parsing with Arc Vectorization and Attention-Based Refinement","created":"2025-01-16","cited_by_count":0,"area":null},{"id":"2605.18674","title":"Efficient Lookahead Encoding and Abstracted Width for Learning General Policies in Classical Planning","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2606.28122","title":"Higher-Order Fourier Neural Operator: Explicit Mode Mixer for Nonlinear PDEs","created":"2026-06-26","cited_by_count":0,"area":null},{"id":"2608.09307","title":"Linearized 2-Simplicial Attention","created":"2026-08-10","cited_by_count":0,"area":null}],"next_cursor":null}