{"total":35,"rows":[{"id":"2309.10020","title":"Multimodal Foundation Models: From Specialists to General-Purpose Assistants","created":"2023-09-18","cited_by_count":247,"area":null},{"id":"2312.08168","title":"Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifiers","created":"2023-12-13","cited_by_count":175,"area":null},{"id":"2308.08769","title":"Chat-3D: Data-efficiently Tuning Large Language Model for Universal Dialogue of 3D Scenes","created":"2023-08-17","cited_by_count":129,"area":null},{"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":"2406.15704","title":"video-SALMONN: Speech-Enhanced Audio-Visual Large Language Models","created":"2024-06-22","cited_by_count":102,"area":null},{"id":"2404.07973","title":"Ferret-v2: An Improved Baseline for Referring and Grounding with Large Language Models","created":"2024-04-11","cited_by_count":97,"area":null},{"id":"2410.18325","title":"AVHBench: A Cross-Modal Hallucination Benchmark for Audio-Visual Large Language Models","created":"2024-10-23","cited_by_count":56,"area":null},{"id":"2412.20206","title":"Toward Visual Grounding: A Survey","created":"2024-12-28","cited_by_count":52,"area":null},{"id":"2310.20381","title":"A Systematic Evaluation of GPT-4V's Multimodal Capability for Medical Image Analysis","created":"2023-10-31","cited_by_count":37,"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":"2408.06627","title":"WorldScribe: Towards Context-Aware Live Visual Descriptions","created":"2024-08-13","cited_by_count":27,"area":null},{"id":"2412.18619","title":"Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey","created":"2024-12-16","cited_by_count":27,"area":null},{"id":"2412.11694","title":"From Specific-MLLMs to Omni-MLLMs: A Survey on MLLMs Aligned with Multi-modalities","created":"2024-12-16","cited_by_count":22,"area":null},{"id":"2310.08884","title":"Extending Multi-modal Contrastive Representations","created":"2023-10-13","cited_by_count":21,"area":null},{"id":"2310.18709","title":"Audio-Visual Instance Segmentation","created":"2023-10-28","cited_by_count":21,"area":null},{"id":"2405.17927","title":"The Evolution of Multimodal Model Architectures","created":"2024-05-28","cited_by_count":21,"area":null},{"id":"2402.02555","title":"High-Quality Entity Segmentation and Grounding","created":"2024-02-04","cited_by_count":13,"area":null},{"id":"2407.04928","title":"CLIPVQA:Video Quality Assessment via CLIP","created":"2024-07-06","cited_by_count":11,"area":null},{"id":"2311.08400","title":"Towards Open-Ended Visual Recognition with Large Language Model","created":"2023-11-14","cited_by_count":8,"area":null},{"id":"2402.11265","title":"Beyond Literal Descriptions: Understanding and Locating Open-World Objects Aligned with Human Intentions","created":"2024-02-17","cited_by_count":8,"area":null},{"id":"2506.07643","title":"Synthetic Visual Genome","created":"2025-06-09","cited_by_count":6,"area":null},{"id":"2503.10781","title":"Large-scale Pre-training for Grounded Video Caption Generation","created":"2025-03-13","cited_by_count":5,"area":null},{"id":"2505.17994","title":"Segment Anyword: Mask Prompt Inversion for Open-Set Grounded Segmentation","created":"2025-05-23","cited_by_count":4,"area":null},{"id":"2403.16539","title":"Data-Efficient 3D Visual Grounding via Order-Aware Referring","created":"2024-03-25","cited_by_count":3,"area":null},{"id":"2404.08915","title":"PM2: A New Prompting Multi-modal Model Paradigm for Few-shot Medical Image Classification","created":"2024-04-13","cited_by_count":3,"area":null},{"id":"2603.28757","title":"SonoWorld: From One Image to a 3D Audio-Visual Scene","created":"2026-03-30","cited_by_count":3,"area":null},{"id":"2404.13530","title":"Listen Then See: Video Alignment with Speaker Attention","created":"2024-04-21","cited_by_count":2,"area":null},{"id":"2502.12623","title":"DeepResonance: Enhancing Multimodal Music Understanding via Music-centric Multi-way Instruction Tuning","created":"2025-02-18","cited_by_count":2,"area":null},{"id":"2503.15176","title":"A Review on Large Language Models for Visual Analytics","created":"2025-03-19","cited_by_count":1,"area":null},{"id":"2509.04606","title":"Sample-efficient Integration of New Modalities into Large Language Models","created":"2025-09-04","cited_by_count":1,"area":null},{"id":"2509.19731","title":"CAMILA: Context-Aware Masking for Image Editing with Language Alignment","created":"2025-09-24","cited_by_count":1,"area":null},{"id":"2411.07584","title":"Grounded Video Caption Generation","created":"2024-11-12","cited_by_count":0,"area":null},{"id":"2511.06991","title":"CoLM: Collaborative Large Models via A Client-Server Paradigm","created":"2025-11-10","cited_by_count":0,"area":null},{"id":"2606.00592","title":"Through the PRISM: Principle-Aware, Interpretable, and Multi-Scale Evaluation of Visual Designs","created":"2026-05-30","cited_by_count":0,"area":null},{"id":"2609.19143","title":"PANORAMA: Panoptic Grounded Captioning via Mask Proposal Selection","created":"2026-09-16","cited_by_count":0,"area":null}],"next_cursor":null}