{"total":55,"rows":[{"id":"2407.06581","title":"Vision language models are blind: Failing to translate detailed visual features into words","created":"2024-07-09","cited_by_count":147,"area":"mllm"},{"id":"2411.00238","title":"Understanding the Limits of Vision Language Models Through the Lens of the Binding Problem","created":"2024-10-31","cited_by_count":75,"area":"mllm"},{"id":"2311.16093","title":"Visual cognition in multimodal large language models","created":"2023-11-27","cited_by_count":38,"area":"mllm"},{"id":"2409.01374","title":"H-ARC: A Robust Estimate of Human Performance on the Abstraction and Reasoning Corpus Benchmark","created":"2024-09-02","cited_by_count":33,"area":null},{"id":"2502.04381","title":"Limitations of Large Language Models in Clinical Problem-Solving Arising from Inflexible Reasoning","created":"2025-02-05","cited_by_count":31,"area":"lr"},{"id":"2404.13591","title":"MARVEL: Multidimensional Abstraction and Reasoning through Visual Evaluation and Learning","created":"2024-04-21","cited_by_count":30,"area":"lr"},{"id":"2407.17773","title":"KiVA: Kid-inspired Visual Analogies for Testing Large Multimodal Models","created":"2024-07-25","cited_by_count":24,"area":"lr"},{"id":"2401.12117","title":"The Curious Case of Nonverbal Abstract Reasoning with Multi-Modal Large Language Models","created":"2024-01-22","cited_by_count":17,"area":"lr"},{"id":"2402.03507","title":"Neural networks for abstraction and reasoning: Towards broad generalization in machines","created":"2024-02-05","cited_by_count":13,"area":"lr"},{"id":"2506.15871","title":"Visual symbolic mechanisms: Emergent symbol processing in vision language models","created":"2025-06-18","cited_by_count":13,"area":"mllm"},{"id":"2410.06405","title":"Tackling the Abstraction and Reasoning Corpus with Vision Transformers: the Importance of 2D Representation, Positions, and Objects","created":"2024-10-08","cited_by_count":10,"area":"lr"},{"id":"2403.05789","title":"ItD: Large Language Models Can Teach Themselves Induction through Deduction","created":"2024-03-09","cited_by_count":8,"area":null},{"id":"2407.09502","title":"From Text to Life: On the Reciprocal Relationship between Artificial Life and Large Language Models","created":"2024-06-14","cited_by_count":8,"area":null},{"id":"2412.07322","title":"ConceptSearch: Towards Efficient Program Search Using LLMs for Abstraction and Reasoning Corpus (ARC)","created":"2024-12-10","cited_by_count":8,"area":"lr"},{"id":"2403.09734","title":"Do Large Language Models Solve ARC Visual Analogies Like People Do?","created":"2024-03-13","cited_by_count":7,"area":"lr"},{"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":"2407.20806","title":"ARCLE: The Abstraction and Reasoning Corpus Learning Environment for Reinforcement Learning","created":"2024-07-30","cited_by_count":7,"area":null},{"id":"2410.17218","title":"Creativity in AI: Progresses and Challenges","created":"2024-10-22","cited_by_count":7,"area":null},{"id":"2410.18077","title":"ALTA: Compiler-Based Analysis of Transformers","created":"2024-10-23","cited_by_count":7,"area":null},{"id":"2411.15645","title":"MC-NEST: Enhancing Mathematical Reasoning in Large Language Models leveraging a Monte Carlo Self-Refine Tree","created":"2024-11-23","cited_by_count":7,"area":"lr"},{"id":"2412.05586","title":"Towards Learning to Reason: Comparing LLMs with Neuro-Symbolic on Arithmetic Relations in Abstract Reasoning","created":"2024-12-07","cited_by_count":7,"area":"lr"},{"id":"2506.02537","title":"VisuRiddles: Fine-grained Perception is a Primary Bottleneck for Multimodal Large Language Models in Abstract Visual Reasoning","created":"2025-06-03","cited_by_count":7,"area":"lr"},{"id":"2506.14276","title":"Don't throw the baby out with the bathwater: How and why deep learning for ARC","created":"2025-06-17","cited_by_count":7,"area":null},{"id":"2312.05468","title":"Image and Data Mining in Reticular Chemistry Using GPT-4V","created":"2023-12-09","cited_by_count":6,"area":null},{"id":"2411.05943","title":"Quantifying artificial intelligence through algorithmic generalization","created":"2024-11-08","cited_by_count":5,"area":null},{"id":"2503.11207","title":"Can Large Reasoning Models do Analogical Reasoning under Perceptual Uncertainty?","created":"2025-03-14","cited_by_count":5,"area":"lr"},{"id":"2503.23125","title":"Evaluating Compositional Scene Understanding in Multimodal Generative Models","created":"2025-03-29","cited_by_count":5,"area":"mllm"},{"id":"2507.07544","title":"Position: We Need An Algorithmic Understanding of Generative AI","created":"2025-07-10","cited_by_count":5,"area":null},{"id":"2401.11725","title":"Speak It Out: Solving Symbol-Related Problems with Symbol-to-Language Conversion for Language Models","created":"2024-01-22","cited_by_count":4,"area":null},{"id":"2403.04400","title":"Exploring Continual Learning of Compositional Generalization in NLI","created":"2024-03-07","cited_by_count":4,"area":null},{"id":"2405.06399","title":"Program Synthesis using Inductive Logic Programming for the Abstraction and Reasoning Corpus","created":"2024-05-10","cited_by_count":4,"area":"lr"},{"id":"2406.11061","title":"A-I-RAVEN and I-RAVEN-Mesh: Two New Benchmarks for Abstract Visual Reasoning","created":"2024-06-16","cited_by_count":4,"area":"lr"},{"id":"2411.00264","title":"TurtleBench: A Visual Programming Benchmark in Turtle Geometry","created":"2024-10-31","cited_by_count":4,"area":null},{"id":"2510.17496","title":"I-RAVEN-X: Benchmarking Generalization and Robustness of Analogical and Mathematical Reasoning in Large Language and Reasoning Models","created":"2025-10-20","cited_by_count":4,"area":"lr"},{"id":"2312.03042","title":"Inherent limitations of LLMs regarding spatial information","created":"2023-12-05","cited_by_count":3,"area":null},{"id":"2408.15244","title":"Misrepresented Technological Solutions in Imagined Futures: The Origins and Dangers of AI Hype in the Research Community","created":"2024-08-08","cited_by_count":3,"area":null},{"id":"2402.03618","title":"Comparing Abstraction in Humans and Large Language Models Using Multimodal Serial Reproduction","created":"2024-02-06","cited_by_count":2,"area":null},{"id":"2403.00820","title":"Retrieval Augmented Generation Systems: Automatic Dataset Creation, Evaluation and Boolean Agent Setup","created":"2024-02-26","cited_by_count":2,"area":"rag"},{"id":"2501.04424","title":"NSA: Neuro-symbolic ARC Challenge","created":"2025-01-08","cited_by_count":2,"area":"lr"},{"id":"2507.22457","title":"What is an \"Abstract Reasoner\"? Revisiting Experiments and Arguments about Large Language Models","created":"2025-07-30","cited_by_count":2,"area":"lr"},{"id":"2508.10057","title":"Large Language Models Show Signs of Alignment with Human Neurocognition During Abstract Reasoning","created":"2025-08-12","cited_by_count":2,"area":"lr"},{"id":"2509.20645","title":"Anticipatory Evaluation of Language Models: Predicting LLM Benchmark Scores from Descriptions","created":"2025-09-25","cited_by_count":2,"area":null},{"id":"2402.05307","title":"Three Pathways to Neurosymbolic Reinforcement Learning with Interpretable Model and Policy Networks","created":"2024-02-07","cited_by_count":1,"area":"deeprl"},{"id":"2402.18426","title":"A Relational Inductive Bias for Dimensional Abstraction in Neural Networks","created":"2024-02-28","cited_by_count":1,"area":null},{"id":"2504.15903","title":"Impact of Noise on LLM-Models Performance in Abstraction and Reasoning Corpus (ARC) Tasks with Model Temperature Considerations","created":"2025-04-22","cited_by_count":1,"area":"lr"},{"id":"2511.08747","title":"Vector Symbolic Algebras for the Abstraction and Reasoning Corpus","created":"2025-11-11","cited_by_count":1,"area":null},{"id":"2502.02315","title":"Shuttle Between the Instructions and the Parameters of Large Language Models","created":"2025-02-04","cited_by_count":0,"area":null},{"id":"2509.14171","title":"AssoCiAm: A Benchmark for Evaluating Association Thinking while Circumventing Ambiguity","created":"2025-09-17","cited_by_count":0,"area":"lr"},{"id":"2601.11866","title":"Advances in LLM Reasoning Enable Flexibility in Clinical Problem-Solving","created":"2026-01-17","cited_by_count":0,"area":"lr"},{"id":"2603.09113","title":"PM-Nav: Priori-Map Guided Embodied Navigation in Functional Buildings","created":"2026-03-10","cited_by_count":0,"area":null},{"id":"2604.14437","title":"LLMs taking shortcuts in test generation: A study with SAP HANA and LevelDB","created":"2026-04-15","cited_by_count":0,"area":null},{"id":"2605.23141","title":"VisAnalog: A Diagnostic Suite for Visual Concept Transfer on Natural Images","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2605.25427","title":"Binding Visual Features Point by Point","created":"2026-05-25","cited_by_count":0,"area":"mllm"},{"id":"2607.11696","title":"Think Through a Bottleneck: Hourglass Reasoning for Rigorous Induction","created":"2026-07-13","cited_by_count":0,"area":"lr"},{"id":"2610.07646","title":"Matching Object or Relation? Tracing Abstract Reasoning Inside VLMs","created":"2026-10-06","cited_by_count":0,"area":"lr"}],"next_cursor":null}