{"total":14,"rows":[{"id":"2309.15112","title":"InternLM-XComposer: A Vision-Language Large Model for Advanced Text-image Comprehension and Composition","created":"2023-09-26","cited_by_count":297,"area":null},{"id":"2309.10020","title":"Multimodal Foundation Models: From Specialists to General-Purpose Assistants","created":"2023-09-18","cited_by_count":247,"area":null},{"id":"2405.09589","title":"A Comprehensive Survey of Hallucination in Large Language, Image, Video and Audio Foundation Models","created":"2024-05-15","cited_by_count":100,"area":null},{"id":"2404.15254","title":"UniMERNet: A Universal Network for Real-World Mathematical Expression Recognition","created":"2024-04-23","cited_by_count":42,"area":null},{"id":"2312.16602","title":"Visual Instruction Tuning towards General-Purpose Multimodal Model: A Survey","created":"2023-12-27","cited_by_count":29,"area":null},{"id":"2404.19752","title":"Visual Fact Checker: Enabling High-Fidelity Detailed Caption Generation","created":"2024-04-30","cited_by_count":28,"area":null},{"id":"2410.15359","title":"Hallucination in Multimodal Foundation Models: A Survey on Causes, Corrections, and Evaluations","created":"2024-10-20","cited_by_count":8,"area":null},{"id":"2410.02768","title":"Uncertainty-Guided Self-Questioning and Answering for Video-Language Alignment","created":"2024-09-17","cited_by_count":6,"area":null},{"id":"2409.00571","title":"Enhancing Source Code Security with LLMs: Demystifying The Challenges and Generating Reliable Repairs","created":"2024-09-01","cited_by_count":4,"area":null},{"id":"2407.08475","title":"Investigating Public Fine-Tuning Datasets: A Complex Review of Current Practices from a Construction Perspective","created":"2024-07-11","cited_by_count":3,"area":null},{"id":"2409.14484","title":"Effectively Enhancing Vision Language Large Models by Prompt Augmentation and Caption Utilization","created":"2024-09-22","cited_by_count":1,"area":null},{"id":"2505.12045","title":"FIGhost: Fluorescent Ink-based Stealthy and Flexible Backdoor Attacks on Physical Traffic Sign Recognition","created":"2025-05-17","cited_by_count":1,"area":null},{"id":"2512.15006","title":"Evaluating the Capability of Video Question Generation for Expert Knowledge Elicitation","created":"2025-12-17","cited_by_count":0,"area":null},{"id":"2607.23917","title":"Gaze-to-text Generation: Beyond Categorical Decoding of Human Attention","created":"2026-07-27","cited_by_count":0,"area":null}],"next_cursor":null}