{"total":59,"rows":[{"id":"2210.01936","title":"When and why vision-language models behave like bags-of-words, and what to do about it?","created":"2022-10-04","cited_by_count":610,"area":"mllm"},{"id":"2302.08399","title":"Large Language Models Fail on Trivial Alterations to Theory-of-Mind Tasks","created":"2023-02-16","cited_by_count":292,"area":null},{"id":"2212.07796","title":"CREPE: Can Vision-Language Foundation Models Reason Compositionally?","created":"2022-12-13","cited_by_count":181,"area":"mllm"},{"id":"2306.08877","title":"Linguistic Binding in Diffusion Models: Enhancing Attribute Correspondence through Attention Map Alignment","created":"2023-06-15","cited_by_count":171,"area":"diffusion"},{"id":"2311.04287","title":"Holistic Evaluation of Text-To-Image Models","created":"2023-11-07","cited_by_count":160,"area":null},{"id":"2404.19753","title":"DOCCI: Descriptions of Connected and Contrasting Images","created":"2024-04-30","cited_by_count":132,"area":null},{"id":"2306.12672","title":"From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thought","created":"2023-06-22","cited_by_count":119,"area":"wm"},{"id":"2210.02438","title":"DALL-E-Bot: Introducing Web-Scale Diffusion Models to Robotics","created":"2022-10-05","cited_by_count":106,"area":"diffusion"},{"id":"2308.08708","title":"Consciousness in Artificial Intelligence: Insights from the Science of Consciousness","created":"2023-08-17","cited_by_count":104,"area":null},{"id":"2212.10015","title":"Benchmarking Spatial Relationships in Text-to-Image Generation","created":"2022-12-20","cited_by_count":97,"area":null},{"id":"2310.09336","title":"Compositional Abilities Emerge Multiplicatively: Exploring Diffusion Models on a Synthetic Task","created":"2023-10-13","cited_by_count":93,"area":"diffusion"},{"id":"2404.04125","title":"No \"Zero-Shot\" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance","created":"2024-04-04","cited_by_count":75,"area":null},{"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":"2210.10606","title":"DALLE-2 is Seeing Double: Flaws in Word-to-Concept Mapping in Text2Image Models","created":"2022-10-19","cited_by_count":51,"area":null},{"id":"2310.08753","title":"CompA: Addressing the Gap in Compositional Reasoning in Audio-Language Models","created":"2023-10-12","cited_by_count":43,"area":"lr"},{"id":"2310.07972","title":"Interpretable Diffusion via Information Decomposition","created":"2023-10-12","cited_by_count":37,"area":"diffusion"},{"id":"2306.12105","title":"Mass-Producing Failures of Multimodal Systems with Language Models","created":"2023-06-21","cited_by_count":36,"area":null},{"id":"2406.19370","title":"Emergence of Hidden Capabilities: Exploring Learning Dynamics in Concept Space","created":"2024-06-27","cited_by_count":35,"area":null},{"id":"2210.12889","title":"DALL-E 2 Fails to Reliably Capture Common Syntactic Processes","created":"2022-10-23","cited_by_count":31,"area":null},{"id":"2209.08891","title":"Exploiting Cultural Biases via Homoglyphs in Text-to-Image Synthesis","created":"2022-09-19","cited_by_count":29,"area":"diffusion"},{"id":"2309.16115","title":"Compositional Sculpting of Iterative Generative Processes","created":"2023-09-28","cited_by_count":27,"area":"diffusion"},{"id":"2302.03675","title":"Auditing Gender Presentation Differences in Text-to-Image Models","created":"2023-02-07","cited_by_count":22,"area":null},{"id":"2311.03354","title":"CoVLM: Composing Visual Entities and Relationships in Large Language Models Via Communicative Decoding","created":"2023-11-06","cited_by_count":20,"area":null},{"id":"2404.07389","title":"Object-Conditioned Energy-Based Attention Map Alignment in Text-to-Image Diffusion Models","created":"2024-04-10","cited_by_count":18,"area":"diffusion"},{"id":"2306.00503","title":"MEWL: Few-shot multimodal word learning with referential uncertainty","created":"2023-06-01","cited_by_count":17,"area":null},{"id":"2405.05409","title":"Initialization is Critical to Whether Transformers Fit Composite Functions by Reasoning or Memorizing","created":"2024-05-08","cited_by_count":17,"area":null},{"id":"2406.05191","title":"DiffusionPID: Interpreting Diffusion via Partial Information Decomposition","created":"2024-06-07","cited_by_count":16,"area":"diffusion"},{"id":"2405.19708","title":"Text Guided Image Editing with Automatic Concept Locating and Forgetting","created":"2024-05-30","cited_by_count":12,"area":"diffusion"},{"id":"2403.04321","title":"Discriminative Probing and Tuning for Text-to-Image Generation","created":"2024-03-07","cited_by_count":11,"area":null},{"id":"2406.14481","title":"Revealing Vision-Language Integration in the Brain with Multimodal Networks","created":"2024-06-20","cited_by_count":11,"area":null},{"id":"2303.03761","title":"Graph Neural Networks in Vision-Language Image Understanding: A Survey","created":"2023-03-07","cited_by_count":10,"area":null},{"id":"2411.17066","title":"Relations, Negations, and Numbers: Looking for Logic in Generative Text-to-Image Models","created":"2024-11-26","cited_by_count":9,"area":null},{"id":"2404.05783","title":"A Survey on Responsible Generative AI: What to Generate and What Not","created":"2024-04-08","cited_by_count":8,"area":null},{"id":"2405.20759","title":"Information Theoretic Text-to-Image Alignment","created":"2024-05-31","cited_by_count":8,"area":"diffusion"},{"id":"2209.13696","title":"What Does DALL-E 2 Know About Radiology?","created":"2022-09-27","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":"2410.17218","title":"Creativity in AI: Progresses and Challenges","created":"2024-10-22","cited_by_count":7,"area":null},{"id":"2411.07664","title":"Evaluating the Generation of Spatial Relations in Text and Image Generative Models","created":"2024-11-12","cited_by_count":6,"area":null},{"id":"2410.08309","title":"Swing-by Dynamics in Concept Learning and Compositional Generalization","created":"2024-10-10","cited_by_count":5,"area":"diffusion"},{"id":"2503.23125","title":"Evaluating Compositional Scene Understanding in Multimodal Generative Models","created":"2025-03-29","cited_by_count":5,"area":"mllm"},{"id":"2402.08919","title":"Interpretable Measures of Conceptual Similarity by Complexity-Constrained Descriptive Auto-Encoding","created":"2024-02-14","cited_by_count":4,"area":null},{"id":"2210.10684","title":"Language Models Understand Us, Poorly","created":"2022-10-19","cited_by_count":3,"area":null},{"id":"2309.06680","title":"STUPD: A Synthetic Dataset for Spatial and Temporal Relation Reasoning","created":"2023-09-13","cited_by_count":3,"area":"lr"},{"id":"2410.10596","title":"Overcoming classic challenges for artificial neural networks by providing incentives and practice","created":"2024-10-14","cited_by_count":3,"area":null},{"id":"2507.18616","title":"SynC: Synthetic Image Caption Dataset Refinement with One-to-many Mapping for Zero-shot Image Captioning","created":"2025-07-24","cited_by_count":3,"area":null},{"id":"2601.06338","title":"Circuit Mechanisms for Spatial Relation Generation in Diffusion Transformers","created":"2026-01-09","cited_by_count":3,"area":"diffusion"},{"id":"2406.07699","title":"CUPID: Contextual Understanding of Prompt-conditioned Image Distributions","created":"2024-06-11","cited_by_count":2,"area":null},{"id":"2505.13281","title":"Computer Vision Models Show Human-Like Sensitivity to Geometric and Topological Concepts","created":"2025-05-19","cited_by_count":2,"area":"mllm"},{"id":"2405.12538","title":"Bridging the Intent Gap: Knowledge-Enhanced Visual Generation","created":"2024-05-21","cited_by_count":1,"area":null},{"id":"2410.03505","title":"Classification-Denoising Networks","created":"2024-10-04","cited_by_count":1,"area":null},{"id":"2505.03530","title":"A Multi-Level Causal Intervention Framework for Mechanistic Interpretability in Variational Autoencoders","created":"2025-05-06","cited_by_count":1,"area":"mechinterp"},{"id":"2210.01797","title":"Ten Years after ImageNet: A 360{\\deg} Perspective on AI","created":"2022-10-01","cited_by_count":0,"area":null},{"id":"2305.18485","title":"Autoencoding Conditional Neural Processes for Representation Learning","created":"2023-05-29","cited_by_count":0,"area":null},{"id":"2401.09193","title":"GNN-LoFI: a Novel Graph Neural Network through Localized Feature-based Histogram Intersection","created":"2024-01-17","cited_by_count":0,"area":null},{"id":"2509.16141","title":"AcT2I: Evaluating and Improving Action Depiction in Text-to-Image Models","created":"2025-09-19","cited_by_count":0,"area":null},{"id":"2602.04911","title":"A logical re-conception of neural networks: Hamiltonian bitwise part-whole architecture","created":"2026-02-04","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":"2606.19941","title":"Compositionality Emerges in a Narrow Depth-Connectivity Regime: Architecture Constraints and Solution Manifolds","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2608.00410","title":"Where did the ambiguity go? Examining how multimodal models interpret polysemous words","created":"2026-08-01","cited_by_count":0,"area":null}],"next_cursor":null}