{"total":31,"rows":[{"id":"2311.17946","title":"DreamSync: Aligning Text-to-Image Generation with Image Understanding Feedback","created":"2023-11-29","cited_by_count":58,"area":null},{"id":"2302.12313","title":"Testing AI on language comprehension tasks reveals insensitivity to underlying meaning","created":"2023-02-23","cited_by_count":45,"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":"2302.03675","title":"Auditing Gender Presentation Differences in Text-to-Image Models","created":"2023-02-07","cited_by_count":22,"area":null},{"id":"2312.03766","title":"Mismatch Quest: Visual and Textual Feedback for Image-Text Misalignment","created":"2023-12-05","cited_by_count":18,"area":null},{"id":"2404.14883","title":"Language in Vivo vs. in Silico: Size Matters but Larger Language Models Still Do Not Comprehend Language on a Par with Humans Due to Impenetrable Semantic Reference","created":"2024-04-23","cited_by_count":15,"area":null},{"id":"2408.06518","title":"Does Liking Yellow Imply Driving a School Bus? Semantic Leakage in Language Models","created":"2024-08-12","cited_by_count":15,"area":null},{"id":"2211.08371","title":"Pragmatics in Language Grounding: Phenomena, Tasks, and Modeling Approaches","created":"2022-11-15","cited_by_count":12,"area":null},{"id":"2405.09426","title":"Global-Local Image Perceptual Score (GLIPS): Evaluating Photorealistic Quality of AI-Generated Images","created":"2024-05-15","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":"2409.20556","title":"Inverse Painting: Reconstructing The Painting Process","created":"2024-09-30","cited_by_count":6,"area":null},{"id":"2305.01788","title":"Vision Meets Definitions: Unsupervised Visual Word Sense Disambiguation Incorporating Gloss Information","created":"2023-05-02","cited_by_count":5,"area":null},{"id":"2308.14740","title":"Total Selfie: Generating Full-Body Selfies","created":"2023-08-28","cited_by_count":5,"area":null},{"id":"2410.22592","title":"GRADE: Quantifying Sample Diversity in Text-to-Image Models","created":"2024-10-29","cited_by_count":5,"area":null},{"id":"2412.10604","title":"EvalGIM: A Library for Evaluating Generative Image Models","created":"2024-12-13","cited_by_count":5,"area":null},{"id":"2503.23011","title":"Geometrical Properties of Text Token Embeddings for Strong Semantic Binding in Text-to-Image Generation","created":"2025-03-29","cited_by_count":5,"area":null},{"id":"2305.15026","title":"Transferring Visual Attributes from Natural Language to Verified Image Generation","created":"2023-05-24","cited_by_count":4,"area":null},{"id":"2504.01137","title":"Follow the Flow: On Information Flow Across Textual Tokens in Text-to-Image Models","created":"2025-04-01","cited_by_count":4,"area":null},{"id":"2409.06725","title":"DefectTwin: When LLM Meets Digital Twin for Railway Defect Inspection","created":"2024-08-26","cited_by_count":3,"area":null},{"id":"2302.09742","title":"Affect-Conditioned Image Generation","created":"2023-02-20","cited_by_count":2,"area":null},{"id":"2501.06638","title":"Scaling Down Semantic Leakage: Investigating Associative Bias in Smaller Language Models","created":"2025-01-11","cited_by_count":2,"area":null},{"id":"2510.15015","title":"DeLeaker: Dynamic Inference-Time Reweighting For Semantic Leakage Mitigation in Text-to-Image Models","created":"2025-10-16","cited_by_count":2,"area":null},{"id":"2310.11146","title":"The Quo Vadis of the Relationship between Language and Large Language Models","created":"2023-10-17","cited_by_count":1,"area":null},{"id":"2401.14212","title":"Explicitly Representing Syntax Improves Sentence-to-layout Prediction of Unexpected Situations","created":"2024-01-25","cited_by_count":1,"area":null},{"id":"2410.03505","title":"Classification-Denoising Networks","created":"2024-10-04","cited_by_count":1,"area":null},{"id":"2602.00570","title":"GLAD: Generative Language-Assisted Visual Tracking for Low-Semantic Templates","created":"2026-01-31","cited_by_count":1,"area":null},{"id":"2410.18085","title":"TextureMeDefect: LLM-based Defect Texture Generation for Railway Components on Mobile Devices","created":"2024-10-07","cited_by_count":0,"area":null},{"id":"2512.24687","title":"Quantum Visual Word Sense Disambiguation: Unraveling Ambiguities Through Quantum Inference Model","created":"2025-12-31","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},{"id":"2610.03512","title":"ProgressNet: Sketching and Prompting with a Frozen Text-to-Image Model","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}