{"total":34,"rows":[{"id":"2307.03601","title":"GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest","created":"2023-07-07","cited_by_count":302,"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":"2311.04219","title":"OtterHD: A High-Resolution Multi-modality Model","created":"2023-11-07","cited_by_count":72,"area":null},{"id":"2307.02869","title":"MomentDiff: Generative Video Moment Retrieval from Random to Real","created":"2023-07-06","cited_by_count":58,"area":null},{"id":"2404.04346","title":"Koala: Key frame-conditioned long video-LLM","created":"2024-04-05","cited_by_count":57,"area":null},{"id":"2412.19806","title":"Vitron: A Unified Pixel-level Vision LLM for Understanding, Generating, Segmenting, Editing","created":"2024-10-08","cited_by_count":49,"area":null},{"id":"2308.16632","title":"3D-STMN: Dependency-Driven Superpoint-Text Matching Network for End-to-End 3D Referring Expression Segmentation","created":"2023-08-31","cited_by_count":36,"area":null},{"id":"2409.14457","title":"Large Model Based Agents: State-of-the-Art, Cooperation Paradigms, Security and Privacy, and Future Trends","created":"2024-09-22","cited_by_count":26,"area":null},{"id":"2305.11768","title":"Generating Visual Spatial Description via Holistic 3D Scene Understanding","created":"2023-05-19","cited_by_count":16,"area":null},{"id":"2402.17128","title":"OSCaR: Object State Captioning and State Change Representation","created":"2024-02-27","cited_by_count":16,"area":null},{"id":"2305.12260","title":"Cross2StrA: Unpaired Cross-lingual Image Captioning with Cross-lingual Cross-modal Structure-pivoted Alignment","created":"2023-05-20","cited_by_count":15,"area":null},{"id":"2308.05081","title":"Constructing Holistic Spatio-Temporal Scene Graph for Video Semantic Role Labeling","created":"2023-08-09","cited_by_count":15,"area":null},{"id":"2308.04502","title":"Revisiting Disentanglement and Fusion on Modality and Context in Conversational Multimodal Emotion Recognition","created":"2023-08-08","cited_by_count":13,"area":null},{"id":"2310.04991","title":"Video-Teller: Enhancing Cross-Modal Generation with Fusion and Decoupling","created":"2023-10-08","cited_by_count":12,"area":null},{"id":"2602.01851","title":"How Well Do Models Follow Visual Instructions? VIBE: A Systematic Benchmark for Visual Instruction-Driven Image Editing","created":"2026-02-02","cited_by_count":12,"area":null},{"id":"2312.12273","title":"VQA4CIR: Boosting Composed Image Retrieval with Visual Question Answering","created":"2023-12-19","cited_by_count":11,"area":null},{"id":"2405.19098","title":"Efficient Black-box Adversarial Attacks via Bayesian Optimization Guided by a Function Prior","created":"2024-05-29","cited_by_count":11,"area":null},{"id":"2512.00752","title":"Charts Are Not Images: On the Challenges of Scientific Chart Editing","created":"2025-11-30","cited_by_count":11,"area":null},{"id":"2601.07185","title":"Defenses Against Prompt Attacks Learn Surface Heuristics","created":"2026-01-12","cited_by_count":11,"area":null},{"id":"2402.02503","title":"GeReA: Question-Aware Prompt Captions for Knowledge-based Visual Question Answering","created":"2024-02-04","cited_by_count":9,"area":null},{"id":"2310.05867","title":"Domain-wise Invariant Learning for Panoptic Scene Graph Generation","created":"2023-10-09","cited_by_count":7,"area":null},{"id":"2312.06363","title":"MMICT: Boosting Multi-Modal Fine-Tuning with In-Context Examples","created":"2023-12-11","cited_by_count":7,"area":null},{"id":"2406.01601","title":"Backpropagation-Free Multi-modal On-Device Model Adaptation via Cloud-Device Collaboration","created":"2024-05-21","cited_by_count":5,"area":null},{"id":"2501.17261","title":"NUS-Emo at SemEval-2024 Task 3: Instruction-Tuning LLM for Multimodal Emotion-Cause Analysis in Conversations","created":"2024-08-22","cited_by_count":5,"area":null},{"id":"2508.11936","title":"M3OOD: Automatic Selection of Multimodal OOD Detectors","created":"2025-08-16","cited_by_count":5,"area":null},{"id":"2308.06668","title":"Large Language Models and Foundation Models in Smart Agriculture: Basics, Opportunities, and Challenges","created":"2023-08-13","cited_by_count":4,"area":null},{"id":"2308.14149","title":"Examining User-Friendly and Open-Sourced Large GPT Models: A Survey on Language, Multimodal, and Scientific GPT Models","created":"2023-08-27","cited_by_count":4,"area":null},{"id":"2410.10212","title":"Large Language Model-Enhanced Reinforcement Learning for Generic Bus Holding Control Strategies","created":"2024-10-14","cited_by_count":4,"area":null},{"id":"2308.04424","title":"A Bi-directional Multi-hop Inference Model for Joint Dialog Sentiment Classification and Act Recognition","created":"2023-08-08","cited_by_count":2,"area":null},{"id":"2308.10354","title":"Imaginations of WALL-E : Reconstructing Experiences with an Imagination-Inspired Module for Advanced AI Systems","created":"2023-08-20","cited_by_count":2,"area":null},{"id":"2308.04498","title":"DialogRE^C+: An Extension of DialogRE to Investigate How Much Coreference Helps Relation Extraction in Dialogs","created":"2023-08-08","cited_by_count":1,"area":null},{"id":"2405.02933","title":"Relay Decoding: Concatenating Large Language Models for Machine Translation","created":"2024-05-05","cited_by_count":1,"area":null},{"id":"2410.05767","title":"Grounding is All You Need? Dual Temporal Grounding for Video Dialog","created":"2024-10-08","cited_by_count":1,"area":null},{"id":"2409.19454","title":"See Where You Read with Eye Gaze Tracking and Large Language Model","created":"2024-09-28","cited_by_count":0,"area":null}],"next_cursor":null}