{"total":25,"rows":[{"id":"2307.13721","title":"Foundational Models Defining a New Era in Vision: A Survey and Outlook","created":"2023-07-25","cited_by_count":110,"area":null},{"id":"2310.09291","title":"Vision-by-Language for Training-Free Compositional Image Retrieval","created":"2023-10-13","cited_by_count":103,"area":null},{"id":"2407.00952","title":"SplitLoRA: A Split Parameter-Efficient Fine-Tuning Framework for Large Language Models","created":"2024-07-01","cited_by_count":62,"area":null},{"id":"2311.14332","title":"GATGPT: A Pre-trained Large Language Model with Graph Attention Network for Spatiotemporal Imputation","created":"2023-11-24","cited_by_count":35,"area":null},{"id":"2401.14192","title":"How Can Large Language Models Understand Spatial-Temporal Data?","created":"2024-01-25","cited_by_count":33,"area":null},{"id":"2403.05854","title":"LTGC: Long-tail Recognition via Leveraging LLMs-driven Generated Content","created":"2024-03-09","cited_by_count":33,"area":null},{"id":"2403.07369","title":"Textual Knowledge Matters: Cross-Modality Co-Teaching for Generalized Visual Class Discovery","created":"2024-03-12","cited_by_count":31,"area":null},{"id":"2405.10313","title":"How Far Are We From AGI: Are LLMs All We Need?","created":"2024-05-16","cited_by_count":31,"area":null},{"id":"2401.13837","title":"Democratizing Fine-grained Visual Recognition with Large Language Models","created":"2024-01-24","cited_by_count":25,"area":null},{"id":"2411.03769","title":"No Culture Left Behind: ArtELingo-28, a Benchmark of WikiArt with Captions in 28 Languages","created":"2024-11-06","cited_by_count":19,"area":null},{"id":"2404.15790","title":"Leveraging Large Language Models for Multimodal Search","created":"2024-04-24","cited_by_count":11,"area":null},{"id":"2312.02916","title":"MIND: Multi-Task Incremental Network Distillation","created":"2023-12-05","cited_by_count":8,"area":null},{"id":"2411.12174","title":"Just KIDDIN: Knowledge Infusion and Distillation for Detection of INdecent Memes","created":"2024-11-19","cited_by_count":8,"area":null},{"id":"2404.18311","title":"Towards Incremental Learning in Large Language Models: A Critical Review","created":"2024-04-28","cited_by_count":6,"area":null},{"id":"2310.20633","title":"Defining a New NLP Playground","created":"2023-10-31","cited_by_count":4,"area":null},{"id":"2309.10783","title":"Language as the Medium: Multimodal Video Classification through text only","created":"2023-09-19","cited_by_count":3,"area":null},{"id":"2406.04844","title":"Multi-Granularity Language-Guided Training for Multi-Object Tracking","created":"2024-06-07","cited_by_count":2,"area":null},{"id":"2310.00845","title":"Application of frozen large-scale models to multimodal task-oriented dialogue","created":"2023-10-02","cited_by_count":1,"area":null},{"id":"2402.01352","title":"Describing Images $\\textit{Fast and Slow}$: Quantifying and Predicting the Variation in Human Signals during Visuo-Linguistic Processes","created":"2024-02-02","cited_by_count":1,"area":null},{"id":"2402.15746","title":"Intelligent Director: An Automatic Framework for Dynamic Visual Composition using ChatGPT","created":"2024-02-24","cited_by_count":1,"area":null},{"id":"2405.06319","title":"Decoding Emotions in Abstract Art: Cognitive Plausibility of CLIP in Recognizing Color-Emotion Associations","created":"2024-05-10","cited_by_count":1,"area":null},{"id":"2406.13093","title":"RITA: A Real-time Interactive Talking Avatars Framework","created":"2024-06-18","cited_by_count":1,"area":null},{"id":"2604.05087","title":"Document Optimization for Black-Box Retrieval via Reinforcement Learning","created":"2026-04-06","cited_by_count":1,"area":null},{"id":"2607.22016","title":"EVL-MCoT: Enhanced Vision-Language Multi-CoT for Harmful Meme Detection","created":"2026-07-24","cited_by_count":1,"area":null},{"id":"2503.09361","title":"Deep Learning for Climate Action: Computer Vision Analysis of Visual Narratives on X","created":"2025-03-12","cited_by_count":0,"area":null}],"next_cursor":null}