{"total":25,"rows":[{"id":"2106.13884","title":"Multimodal Few-Shot Learning with Frozen Language Models","created":"2021-06-25","cited_by_count":661,"area":null},{"id":"2205.12548","title":"RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning","created":"2022-05-25","cited_by_count":366,"area":null},{"id":"2201.09873","title":"Transformers in Medical Imaging: A Survey","created":"2022-01-24","cited_by_count":245,"area":null},{"id":"2304.08295","title":"Interactive and Explainable Region-guided Radiology Report Generation","created":"2023-04-17","cited_by_count":140,"area":null},{"id":"2209.03430","title":"Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questions","created":"2022-09-07","cited_by_count":116,"area":null},{"id":"2101.00828","title":"Transformer-based Conditional Variational Autoencoder for Controllable Story Generation","created":"2021-01-04","cited_by_count":44,"area":null},{"id":"2401.02412","title":"LLM Augmented LLMs: Expanding Capabilities through Composition","created":"2024-01-04","cited_by_count":35,"area":null},{"id":"2302.00902","title":"Language Quantized AutoEncoders: Towards Unsupervised Text-Image Alignment","created":"2023-02-02","cited_by_count":29,"area":null},{"id":"2103.11070","title":"Attribute Alignment: Controlling Text Generation from Pre-trained Language Models","created":"2021-03-20","cited_by_count":27,"area":null},{"id":"2205.15608","title":"Weakly-supervised Action Transition Learning for Stochastic Human Motion Prediction","created":"2022-05-31","cited_by_count":26,"area":null},{"id":"2209.13983","title":"Medical Image Captioning via Generative Pretrained Transformers","created":"2022-09-28","cited_by_count":20,"area":null},{"id":"2108.04812","title":"Continual Learning for Grounded Instruction Generation by Observing Human Following Behavior","created":"2021-08-10","cited_by_count":19,"area":null},{"id":"2211.08682","title":"Parameter-Efficient Tuning on Layer Normalization for Pre-trained Language Models","created":"2022-11-16","cited_by_count":19,"area":null},{"id":"2209.13171","title":"RepsNet: Combining Vision with Language for Automated Medical Reports","created":"2022-09-27","cited_by_count":14,"area":null},{"id":"2106.03717","title":"Diverse Pretrained Context Encodings Improve Document Translation","created":"2021-06-07","cited_by_count":13,"area":null},{"id":"2408.11965","title":"CT-AGRG: Automated Abnormality-Guided Report Generation from 3D Chest CT Volumes","created":"2024-08-21","cited_by_count":10,"area":null},{"id":"2101.00822","title":"Outline to Story: Fine-grained Controllable Story Generation from Cascaded Events","created":"2021-01-04","cited_by_count":8,"area":null},{"id":"2109.01229","title":"Multimodal Conditionality for Natural Language Generation","created":"2021-09-02","cited_by_count":6,"area":null},{"id":"2109.06807","title":"A Temporal Variational Model for Story Generation","created":"2021-09-14","cited_by_count":5,"area":null},{"id":"2207.03777","title":"Hidden Schema Networks","created":"2022-07-08","cited_by_count":4,"area":null},{"id":"2404.18976","title":"Foundations of Multisensory Artificial Intelligence","created":"2024-04-29","cited_by_count":1,"area":null},{"id":"2405.14113","title":"Multi-modality Regional Alignment Network for Covid X-Ray Survival Prediction and Report Generation","created":"2024-05-23","cited_by_count":1,"area":null},{"id":"2511.12945","title":"APT: Affine Prototype-Timestamp For Time Series Forecasting Under Distribution Shift","created":"2025-11-17","cited_by_count":1,"area":null},{"id":"2202.08124","title":"XFBoost: Improving Text Generation with Controllable Decoders","created":"2022-02-16","cited_by_count":0,"area":null},{"id":"2601.04563","title":"A Vision for Multisensory Intelligence: Sensing, Science, and Synergy","created":"2026-01-08","cited_by_count":0,"area":null}],"next_cursor":null}