{"total":108,"rows":[{"id":"2212.07796","title":"CREPE: Can Vision-Language Foundation Models Reason Compositionally?","created":"2022-12-13","cited_by_count":181,"area":"mllm"},{"id":"2112.00826","title":"Inducing Causal Structure for Interpretable Neural Networks","created":"2021-12-01","cited_by_count":110,"area":null},{"id":"2209.15003","title":"Compositional Semantic Parsing with Large Language Models","created":"2022-09-29","cited_by_count":95,"area":null},{"id":"2107.02794","title":"Improving Coherence and Consistency in Neural Sequence Models with Dual-System, Neuro-Symbolic Reasoning","created":"2021-07-06","cited_by_count":85,"area":null},{"id":"2307.08689","title":"COLLIE: Systematic Construction of Constrained Text Generation Tasks","created":"2023-07-17","cited_by_count":70,"area":null},{"id":"2404.03622","title":"Mind's Eye of LLMs: Visualization-of-Thought Elicits Spatial Reasoning in Large Language Models","created":"2024-04-04","cited_by_count":66,"area":"lr"},{"id":"2307.07696","title":"Coupling Large Language Models with Logic Programming for Robust and General Reasoning from Text","created":"2023-07-15","cited_by_count":59,"area":"lr"},{"id":"2205.12443","title":"Generating Natural Language Proofs with Verifier-Guided Search","created":"2022-05-25","cited_by_count":52,"area":null},{"id":"2310.03249","title":"Can Large Language Models be Good Path Planners? A Benchmark and Investigation on Spatial-temporal Reasoning","created":"2023-10-05","cited_by_count":49,"area":"lr"},{"id":"2106.00188","title":"PIGLeT: Language Grounding Through Neuro-Symbolic Interaction in a 3D World","created":"2021-06-01","cited_by_count":47,"area":null},{"id":"2407.02511","title":"LLM-A*: Large Language Model Enhanced Incremental Heuristic Search on Path Planning","created":"2024-06-20","cited_by_count":45,"area":null},{"id":"2206.05379","title":"A Benchmark for Compositional Visual Reasoning","created":"2022-06-11","cited_by_count":43,"area":"lr"},{"id":"2207.10430","title":"The Neural Race Reduction: Dynamics of Abstraction in Gated Networks","created":"2022-07-21","cited_by_count":37,"area":null},{"id":"2103.14232","title":"ACRE: Abstract Causal REasoning Beyond Covariation","created":"2021-03-26","cited_by_count":30,"area":null},{"id":"2109.01156","title":"Challenges in Generalization in Open Domain Question Answering","created":"2021-09-02","cited_by_count":30,"area":null},{"id":"2107.12580","title":"Pointer Value Retrieval: A new benchmark for understanding the limits of neural network generalization","created":"2021-07-27","cited_by_count":29,"area":null},{"id":"2201.05899","title":"Unobserved Local Structures Make Compositional Generalization Hard","created":"2022-01-15","cited_by_count":29,"area":null},{"id":"2109.10613","title":"COVR: A test-bed for Visually Grounded Compositional Generalization with real images","created":"2021-09-22","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":"2511.15722","title":"Spatial Reasoning in Multimodal Large Language Models: A Survey of Tasks, Benchmarks and Methods","created":"2025-11-14","cited_by_count":23,"area":"lr"},{"id":"2109.08994","title":"ReaSCAN: Compositional Reasoning in Language Grounding","created":"2021-09-18","cited_by_count":19,"area":null},{"id":"2109.15256","title":"Inducing Transformer's Compositional Generalization Ability via Auxiliary Sequence Prediction Tasks","created":"2021-09-30","cited_by_count":19,"area":null},{"id":"2502.12435","title":"A Survey on Large Language Models for Automated Planning","created":"2025-02-18","cited_by_count":17,"area":null},{"id":"2106.08170","title":"How Modular Should Neural Module Networks Be for Systematic Generalization?","created":"2021-06-15","cited_by_count":15,"area":null},{"id":"2109.12243","title":"Systematic Generalization on gSCAN: What is Nearly Solved and What is Next?","created":"2021-09-25","cited_by_count":15,"area":null},{"id":"2204.11167","title":"RelViT: Concept-guided Vision Transformer for Visual Relational Reasoning","created":"2022-04-24","cited_by_count":15,"area":null},{"id":"2406.08787","title":"A Survey on Compositional Learning of AI Models: Theoretical and Experimental Practices","created":"2024-06-13","cited_by_count":15,"area":null},{"id":"2409.14981","title":"On The Specialization of Neural Modules","created":"2024-09-23","cited_by_count":14,"area":null},{"id":"2112.03204","title":"Quantifying Adaptability in Pre-trained Language Models with 500 Tasks","created":"2021-12-06","cited_by_count":13,"area":null},{"id":"2202.10745","title":"Improving Systematic Generalization Through Modularity and Augmentation","created":"2022-02-22","cited_by_count":13,"area":null},{"id":"2208.08195","title":"Benchmarking Compositionality with Formal Languages","created":"2022-08-17","cited_by_count":12,"area":null},{"id":"2210.01603","title":"Neural-Symbolic Recursive Machine for Systematic Generalization","created":"2022-10-04","cited_by_count":12,"area":null},{"id":"2310.17514","title":"The Validity of Evaluation Results: Assessing Concurrence Across Compositionality Benchmarks","created":"2023-10-26","cited_by_count":12,"area":null},{"id":"2110.10661","title":"SILG: The Multi-environment Symbolic Interactive Language Grounding Benchmark","created":"2021-10-20","cited_by_count":11,"area":null},{"id":"2210.12786","title":"When Can Transformers Ground and Compose: Insights from Compositional Generalization Benchmarks","created":"2022-10-23","cited_by_count":11,"area":null},{"id":"2407.13729","title":"Baba Is AI: Break the Rules to Beat the Benchmark","created":"2024-07-18","cited_by_count":10,"area":null},{"id":"2108.03509","title":"Compositional Generalization in Multilingual Semantic Parsing over Wikidata","created":"2021-08-07","cited_by_count":9,"area":null},{"id":"2403.16394","title":"Skews in the Phenomenon Space Hinder Generalization in Text-to-Image Generation","created":"2024-03-25","cited_by_count":8,"area":null},{"id":"2505.21828","title":"SAGE-Eval: Evaluating LLMs for Systematic Generalizations of Safety Facts","created":"2025-05-27","cited_by_count":8,"area":null},{"id":"2106.08858","title":"Grounding Spatio-Temporal Language with Transformers","created":"2021-06-16","cited_by_count":7,"area":null},{"id":"2107.00956","title":"SocialAI: Benchmarking Socio-Cognitive Abilities in Deep Reinforcement Learning Agents","created":"2021-07-02","cited_by_count":7,"area":null},{"id":"2112.00086","title":"Dyna-bAbI: unlocking bAbI's potential with dynamic synthetic benchmarking","created":"2021-11-30","cited_by_count":7,"area":null},{"id":"2405.15164","title":"From Frege to chatGPT: Compositionality in language, cognition, and deep neural networks","created":"2024-05-24","cited_by_count":7,"area":null},{"id":"2406.12000","title":"Look Further Ahead: Testing the Limits of GPT-4 in Path Planning","created":"2024-06-17","cited_by_count":7,"area":null},{"id":"2103.01403","title":"A Minimalist Dataset for Systematic Generalization of Perception, Syntax, and Semantics","created":"2021-03-02","cited_by_count":6,"area":null},{"id":"2108.02319","title":"Generalization in Multimodal Language Learning from Simulation","created":"2021-08-03","cited_by_count":6,"area":null},{"id":"2203.04806","title":"One-Shot Learning from a Demonstration with Hierarchical Latent Language","created":"2022-03-09","cited_by_count":6,"area":null},{"id":"2302.11978","title":"Does Deep Learning Learn to Abstract? A Systematic Probing Framework","created":"2023-02-23","cited_by_count":6,"area":null},{"id":"2311.09064","title":"Imagine the Unseen World: A Benchmark for Systematic Generalization in Visual World Models","created":"2023-11-15","cited_by_count":6,"area":"wm"},{"id":"2109.10935","title":"Robust Generalization of Quadratic Neural Networks via Function Identification","created":"2021-09-22","cited_by_count":5,"area":null},{"id":"2109.14115","title":"Visually Grounded Concept Composition","created":"2021-09-29","cited_by_count":5,"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":"2206.03139","title":"Intra-agent speech permits zero-shot task acquisition","created":"2022-06-07","cited_by_count":5,"area":null},{"id":"2210.11431","title":"Counterfactual Recipe Generation: Exploring Compositional Generalization in a Realistic Scenario","created":"2022-10-20","cited_by_count":5,"area":null},{"id":"2304.14511","title":"Visual Referential Games Further the Emergence of Disentangled Representations","created":"2023-04-27","cited_by_count":5,"area":null},{"id":"2411.05943","title":"Quantifying artificial intelligence through algorithmic generalization","created":"2024-11-08","cited_by_count":5,"area":null},{"id":"2110.06843","title":"Compositional Generalization in Dependency Parsing","created":"2021-10-13","cited_by_count":4,"area":null},{"id":"2111.10756","title":"TraVLR: Now You See It, Now You Don't! A Bimodal Dataset for Evaluating Visio-Linguistic Reasoning","created":"2021-11-21","cited_by_count":4,"area":null},{"id":"2207.02518","title":"Compositional Generalization in Grounded Language Learning via Induced Model Sparsity","created":"2022-07-06","cited_by_count":4,"area":null},{"id":"2301.03238","title":"MAQA: A Multimodal QA Benchmark for Negation","created":"2023-01-09","cited_by_count":4,"area":null},{"id":"2509.16590","title":"Question Answering with LLMs and Learning from Answer Sets","created":"2025-09-20","cited_by_count":4,"area":"lr"},{"id":"2602.15183","title":"Seeing to Generalize: How Visual Data Corrects Binding Shortcuts","created":"2026-02-16","cited_by_count":4,"area":"mllm"},{"id":"2201.11766","title":"Recursive Decoding: A Situated Cognition Approach to Compositional Generation in Grounded Language Understanding","created":"2022-01-27","cited_by_count":3,"area":null},{"id":"2202.09717","title":"Understanding Robust Generalization in Learning Regular Languages","created":"2022-02-20","cited_by_count":3,"area":null},{"id":"2209.01352","title":"Improving Compositional Generalization in Math Word Problem Solving","created":"2022-09-03","cited_by_count":3,"area":null},{"id":"2209.10926","title":"Equivariant Transduction through Invariant Alignment","created":"2022-09-22","cited_by_count":3,"area":null},{"id":"2211.07727","title":"Logical Tasks for Measuring Extrapolation and Rule Comprehension","created":"2022-11-14","cited_by_count":3,"area":"lr"},{"id":"2211.11033","title":"On the Complexity of Bayesian Generalization","created":"2022-11-20","cited_by_count":3,"area":null},{"id":"2306.09890","title":"Studying Generalization on Memory-Based Methods in Continual Learning","created":"2023-06-16","cited_by_count":3,"area":null},{"id":"2105.05069","title":"Zero-Shot Generalization using Intrinsically Motivated Compositional Emergent Protocols","created":"2021-05-11","cited_by_count":2,"area":null},{"id":"2207.08012","title":"Meta-Referential Games to Learn Compositional Learning Behaviours","created":"2022-07-16","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":"2312.04736","title":"Is Feedback All You Need? Leveraging Natural Language Feedback in Goal-Conditioned Reinforcement Learning","created":"2023-12-07","cited_by_count":2,"area":null},{"id":"2403.08425","title":"Specification Overfitting in Artificial Intelligence","created":"2024-03-13","cited_by_count":2,"area":null},{"id":"2403.12201","title":"Compositional learning of functions in humans and machines","created":"2024-03-18","cited_by_count":2,"area":null},{"id":"2411.13981","title":"On the Fairness, Diversity and Reliability of Text-to-Image Generative Models","created":"2024-11-21","cited_by_count":2,"area":null},{"id":"2601.18858","title":"Representational Homomorphism Predicts and Improves Compositional Generalization In Transformer Language Model","created":"2026-01-26","cited_by_count":2,"area":null},{"id":"2605.03413","title":"Learning to Theorize the World from Observation","created":"2026-05-05","cited_by_count":2,"area":null},{"id":"2607.04926","title":"Input Pathways Shape Few-Shot, Not Zero-Shot, Binding in Tiny Transformers: A Fully-Enumerable Study","created":"2026-07-06","cited_by_count":2,"area":null},{"id":"2607.18921","title":"Circuit Claims Depend on What Is Extracted and How It Is Compared","created":"2026-07-21","cited_by_count":2,"area":null},{"id":"2105.03943","title":"gComm: An environment for investigating generalization in Grounded Language Acquisition","created":"2021-05-09","cited_by_count":1,"area":null},{"id":"2205.08288","title":"Measuring Alignment Bias in Neural Seq2Seq Semantic Parsers","created":"2022-05-17","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":"2305.15087","title":"Pento-DIARef: A Diagnostic Dataset for Learning the Incremental Algorithm for Referring Expression Generation from Examples","created":"2023-05-24","cited_by_count":1,"area":null},{"id":"2311.04364","title":"Syntax-Guided Transformers: Elevating Compositional Generalization and Grounding in Multimodal Environments","created":"2023-11-07","cited_by_count":1,"area":null},{"id":"2312.15815","title":"Compositional Generalization in Spoken Language Understanding","created":"2023-12-25","cited_by_count":1,"area":null},{"id":"2404.12013","title":"Sequential Compositional Generalization in Multimodal Models","created":"2024-04-18","cited_by_count":1,"area":null},{"id":"2409.20259","title":"Learning to Ground Existentially Quantified Goals","created":"2024-09-30","cited_by_count":1,"area":null},{"id":"2501.19182","title":"A Compressive-Expressive Communication Framework for Compositional Representations","created":"2025-01-31","cited_by_count":1,"area":null},{"id":"2511.02627","title":"DecompSR: A dataset for decomposed analyses of compositional multihop spatial reasoning","created":"2025-11-04","cited_by_count":1,"area":"lr"},{"id":"2604.04825","title":"Plausibility as Commonsense Reasoning: Humans Succeed, Large Language Models Do not","created":"2026-04-06","cited_by_count":1,"area":"lr"},{"id":"2605.07078","title":"Test-Time Compositional Generalization in Diffusion Models via Concept Discovery","created":"2026-05-08","cited_by_count":1,"area":"diffusion"},{"id":"2606.02556","title":"HERO'S JOURNEY: Testing Complex Rule Induction with Text Games","created":"2026-06-01","cited_by_count":1,"area":null},{"id":"2102.04225","title":"Concepts, Properties and an Approach for Compositional Generalization","created":"2021-02-08","cited_by_count":0,"area":null},{"id":"2102.05602","title":"Systematic Generalization in Neural Networks-based Multivariate Time Series Forecasting Models","created":"2021-02-10","cited_by_count":0,"area":null},{"id":"2211.11956","title":"A Short Survey of Systematic Generalization","created":"2022-11-22","cited_by_count":0,"area":null},{"id":"2309.15991","title":"Targeted Image Data Augmentation Increases Basic Skills Captioning Robustness","created":"2023-09-27","cited_by_count":0,"area":null},{"id":"2411.19787","title":"CAREL: Instruction-guided reinforcement learning with cross-modal auxiliary objectives","created":"2024-11-29","cited_by_count":0,"area":"deeprl"},{"id":"2502.20499","title":"Data Distributional Properties As Inductive Bias for Systematic Generalization","created":"2025-02-27","cited_by_count":0,"area":null}],"next_cursor":"100"}