{"total":54,"rows":[{"id":"2212.10015","title":"Benchmarking Spatial Relationships in Text-to-Image Generation","created":"2022-12-20","cited_by_count":97,"area":null},{"id":"2310.14735","title":"Unleashing the potential of prompt engineering for large language models","created":"2023-10-23","cited_by_count":72,"area":null},{"id":"2208.00005","title":"Testing Relational Understanding in Text-Guided Image Generation","created":"2022-07-29","cited_by_count":59,"area":null},{"id":"2303.13367","title":"ChatGPT and a New Academic Reality: Artificial Intelligence-Written Research Papers and the Ethics of the Large Language Models in Scholarly Publishing","created":"2023-03-21","cited_by_count":52,"area":null},{"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":"2211.00768","title":"Why is Winoground Hard? Investigating Failures in Visuolinguistic Compositionality","created":"2022-11-01","cited_by_count":44,"area":null},{"id":"2211.14666","title":"Synergies between Disentanglement and Sparsity: Generalization and Identifiability in Multi-Task Learning","created":"2022-11-26","cited_by_count":44,"area":null},{"id":"2206.00169","title":"Discovering the Hidden Vocabulary of DALLE-2","created":"2022-06-01","cited_by_count":43,"area":null},{"id":"2305.18339","title":"A Survey on ChatGPT: AI-Generated Contents, Challenges, and Solutions","created":"2023-05-25","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":"2304.06470","title":"Qualitative Failures of Image Generation Models and Their Application in Detecting Deepfakes","created":"2023-03-29","cited_by_count":31,"area":null},{"id":"2412.16211","title":"Is Your World Simulator a Good Story Presenter? A Consecutive Events-Based Benchmark for Future Long Video Generation","created":"2024-12-17","cited_by_count":30,"area":null},{"id":"2306.02295","title":"A Mathematical Abstraction for Balancing the Trade-off Between Creativity and Reality in Large Language Models","created":"2023-06-04","cited_by_count":29,"area":null},{"id":"2306.17525","title":"MeLM, a generative pretrained language modeling framework that solves forward and inverse mechanics problems","created":"2023-06-30","cited_by_count":29,"area":null},{"id":"2303.12003","title":"Artificial muses: Generative Artificial Intelligence Chatbots Have Risen to Human-Level Creativity","created":"2023-03-21","cited_by_count":24,"area":null},{"id":"2205.02007","title":"A Computational Inflection for Scientific Discovery","created":"2022-05-04","cited_by_count":23,"area":null},{"id":"2501.08537","title":"Complexity Control Facilitates Reasoning-Based Compositional Generalization in Transformers","created":"2025-01-15","cited_by_count":20,"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":"2403.11821","title":"A Survey on Quality Metrics for Text-to-Image Generation","created":"2024-03-18","cited_by_count":18,"area":null},{"id":"2310.15144","title":"DEsignBench: Exploring and Benchmarking DALL-E 3 for Imagining Visual Design","created":"2023-10-23","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":"2310.11685","title":"Why Softmax Attention Outperforms Linear Attention","created":"2023-10-18","cited_by_count":15,"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":"2308.16316","title":"Ten Years of Generative Adversarial Nets (GANs): A survey of the state-of-the-art","created":"2023-08-30","cited_by_count":14,"area":null},{"id":"2308.04553","title":"From Fake to Real: Pretraining on Balanced Synthetic Images to Prevent Spurious Correlations in Image Recognition","created":"2023-08-08","cited_by_count":12,"area":null},{"id":"2312.02338","title":"A Contrastive Compositional Benchmark for Text-to-Image Synthesis: A Study with Unified Text-to-Image Fidelity Metrics","created":"2023-12-04","cited_by_count":12,"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":"2209.13696","title":"What Does DALL-E 2 Know About Radiology?","created":"2022-09-27","cited_by_count":7,"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":"2504.12320","title":"Has the Creativity of Large-Language Models peaked? An analysis of inter- and intra-LLM variability","created":"2025-04-10","cited_by_count":6,"area":null},{"id":"2310.10605","title":"ForceGen: End-to-end de novo protein generation based on nonlinear mechanical unfolding responses using a protein language diffusion model","created":"2023-10-16","cited_by_count":5,"area":null},{"id":"2305.17262","title":"Im-Promptu: In-Context Composition from Image Prompts","created":"2023-05-26","cited_by_count":4,"area":null},{"id":"2410.10291","title":"Evaluating Semantic Variation in Text-to-Image Synthesis: A Causal Perspective","created":"2024-10-14","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":"2302.03531","title":"Structured Generative Models for Scene Understanding","created":"2023-02-07","cited_by_count":3,"area":null},{"id":"2405.15406","title":"A Misleading Gallery of Fluid Motion by Generative Artificial Intelligence","created":"2024-05-24","cited_by_count":3,"area":null},{"id":"2208.10760","title":"How good are deep models in understanding the generated images?","created":"2022-08-23","cited_by_count":2,"area":null},{"id":"2305.14410","title":"Image Manipulation via Multi-Hop Instructions -- A New Dataset and Weakly-Supervised Neuro-Symbolic Approach","created":"2023-05-23","cited_by_count":2,"area":null},{"id":"2308.16611","title":"Detecting Out-of-Context Image-Caption Pairs in News: A Counter-Intuitive Method","created":"2023-08-31","cited_by_count":2,"area":null},{"id":"2402.06501","title":"Scalable Interactive Machine Learning for Future Command and Control","created":"2024-02-09","cited_by_count":2,"area":null},{"id":"2403.12294","title":"A Comparative Investigation of Compositional Syntax and Semantics in DALL-E 2","created":"2024-03-18","cited_by_count":2,"area":null},{"id":"2412.11594","title":"VersaGen: Unleashing Versatile Visual Control for Text-to-Image Synthesis","created":"2024-12-16","cited_by_count":2,"area":null},{"id":"2509.26524","title":"TAP: Two-Stage Adaptive Personalization of Multi-Task and Multi-Modal Foundation Models in Federated Learning","created":"2025-09-30","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":"2504.17234","title":"Scene Perceived Image Perceptual Score (SPIPS): combining global and local perception for image quality assessment","created":"2025-04-24","cited_by_count":1,"area":null},{"id":"2510.03678","title":"Towards Sampling Data Structures for Tensor Products in Turnstile Streams","created":"2025-10-04","cited_by_count":1,"area":null},{"id":"2308.06807","title":"Neural Networks for Programming Quantum Annealers","created":"2023-08-13","cited_by_count":0,"area":null},{"id":"2309.08851","title":"Enhancing Visual Perception in Novel Environments via Incremental Data Augmentation Based on Style Transfer","created":"2023-09-16","cited_by_count":0,"area":null},{"id":"2508.16643","title":"From Classical Probabilistic Latent Variable Models to Modern Generative AI: A Unified Perspective","created":"2025-08-18","cited_by_count":0,"area":null},{"id":"2511.04776","title":"Quantifying the Climate Risk of Generative AI: Region-Aware Carbon Accounting with G-TRACE and the AI Sustainability Pyramid","created":"2025-11-06","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":"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}