{"total":43,"rows":[{"id":"2306.02858","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","created":"2023-06-05","cited_by_count":1471,"area":"mllm"},{"id":"2308.01390","title":"OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models","created":"2023-08-02","cited_by_count":565,"area":"mllm"},{"id":"2307.02499","title":"mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding","created":"2023-07-04","cited_by_count":168,"area":"mllm"},{"id":"2502.21257","title":"RoboBrain: A Unified Brain Model for Robotic Manipulation from Abstract to Concrete","created":"2025-02-28","cited_by_count":135,"area":"mllm"},{"id":"2210.09263","title":"Vision-Language Pre-training: Basics, Recent Advances, and Future Trends","created":"2022-10-17","cited_by_count":117,"area":"mllm"},{"id":"2211.01335","title":"Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese","created":"2022-11-02","cited_by_count":109,"area":"mllm"},{"id":"2311.01477","title":"FaithScore: Fine-grained Evaluations of Hallucinations in Large Vision-Language Models","created":"2023-11-02","cited_by_count":46,"area":"mllm"},{"id":"2410.10855","title":"Core Knowledge Deficits in Multi-Modal Language Models","created":"2024-10-06","cited_by_count":38,"area":"mllm"},{"id":"2306.04362","title":"Youku-mPLUG: A 10 Million Large-scale Chinese Video-Language Dataset for Pre-training and Benchmarks","created":"2023-06-07","cited_by_count":36,"area":"mllm"},{"id":"2312.01571","title":"How to Configure Good In-Context Sequence for Visual Question Answering","created":"2023-12-04","cited_by_count":33,"area":"mllm"},{"id":"2306.02080","title":"Benchmarking Robustness of Adaptation Methods on Pre-trained Vision-Language Models","created":"2023-06-03","cited_by_count":31,"area":"mllm"},{"id":"2410.06699","title":"Break the Visual Perception: Adversarial Attacks Targeting Encoded Visual Tokens of Large Vision-Language Models","created":"2024-10-09","cited_by_count":27,"area":"mllm"},{"id":"2311.17095","title":"Emergent Open-Vocabulary Semantic Segmentation from Off-the-shelf Vision-Language Models","created":"2023-11-28","cited_by_count":15,"area":"mllm"},{"id":"2507.05056","title":"INTER: Mitigating Hallucination in Large Vision-Language Models by Interaction Guidance Sampling","created":"2025-07-07","cited_by_count":10,"area":"mllm"},{"id":"2503.20502","title":"MLLM-Selector: Necessity and Diversity-driven High-Value Data Selection for Enhanced Visual Instruction Tuning","created":"2025-03-26","cited_by_count":9,"area":"mllm"},{"id":"2209.06954","title":"Correlation Information Bottleneck: Towards Adapting Pretrained Multimodal Models for Robust Visual Question Answering","created":"2022-09-14","cited_by_count":7,"area":"mllm"},{"id":"2508.11011","title":"Are Large Pre-trained Vision Language Models Effective Construction Safety Inspectors?","created":"2025-08-14","cited_by_count":7,"area":"mllm"},{"id":"2308.16689","title":"ViLTA: Enhancing Vision-Language Pre-training through Textual Augmentation","created":"2023-08-31","cited_by_count":6,"area":"mllm"},{"id":"2410.02773","title":"Mind the Uncertainty in Human Disagreement: Evaluating Discrepancies between Model Predictions and Human Responses in VQA","created":"2024-09-17","cited_by_count":6,"area":"mllm"},{"id":"2504.18856","title":"Multi-Resolution Pathology-Language Pre-training Model with Text-Guided Visual Representation","created":"2025-04-26","cited_by_count":6,"area":"mllm"},{"id":"2307.03254","title":"Vision Language Transformers: A Survey","created":"2023-07-06","cited_by_count":5,"area":"mllm"},{"id":"2307.08504","title":"BUS:Efficient and Effective Vision-language Pre-training with Bottom-Up Patch Summarization","created":"2023-07-17","cited_by_count":5,"area":"mllm"},{"id":"2308.03475","title":"COPA: Efficient Vision-Language Pre-training Through Collaborative Object- and Patch-Text Alignment","created":"2023-08-07","cited_by_count":5,"area":"mllm"},{"id":"2412.06461","title":"Ranked from Within: Ranking Large Multimodal Models Without Labels","created":"2024-12-09","cited_by_count":5,"area":"mllm"},{"id":"2507.03262","title":"Investigating Redundancy in Multimodal Large Language Models with Multiple Vision Encoders","created":"2025-07-04","cited_by_count":5,"area":"mllm"},{"id":"2401.02137","title":"SyCoCa: Symmetrizing Contrastive Captioners with Attentive Masking for Multimodal Alignment","created":"2024-01-04","cited_by_count":4,"area":"mllm"},{"id":"2409.10921","title":"KALE: An Artwork Image Captioning System Augmented with Heterogeneous Graph","created":"2024-09-17","cited_by_count":4,"area":"mllm"},{"id":"2307.07341","title":"PiTL: Cross-modal Retrieval with Weakly-supervised Vision-language Pre-training via Prompting","created":"2023-07-14","cited_by_count":3,"area":"mllm"},{"id":"2312.08846","title":"TiMix: Text-aware Image Mixing for Effective Vision-Language Pre-training","created":"2023-12-14","cited_by_count":3,"area":"mllm"},{"id":"2503.09445","title":"Astrea: A MOE-based Visual Understanding Model with Progressive Alignment","created":"2025-03-12","cited_by_count":3,"area":"mllm"},{"id":"2505.12217","title":"HyperCap: Hyperspectral Land Cover Captioning Dataset for Vision Language Models","created":"2025-05-18","cited_by_count":3,"area":"mllm"},{"id":"2312.10613","title":"p-Laplacian Adaptation for Generative Pre-trained Vision-Language Models","created":"2023-12-17","cited_by_count":1,"area":"mllm"},{"id":"2403.00249","title":"Semantics-enhanced Cross-modal Masked Image Modeling for Vision-Language Pre-training","created":"2024-03-01","cited_by_count":1,"area":"mllm"},{"id":"2403.08433","title":"An Empirical Study of Parameter Efficient Fine-tuning on Vision-Language Pre-train Model","created":"2024-03-13","cited_by_count":1,"area":"mllm"},{"id":"2408.13898","title":"Evaluating Attribute Comprehension in Large Vision-Language Models","created":"2024-08-25","cited_by_count":1,"area":"mllm"},{"id":"2503.18034","title":"Expanding the Boundaries of Vision Prior Knowledge in Multi-modal Large Language Models","created":"2025-03-23","cited_by_count":1,"area":"mllm"},{"id":"2510.11295","title":"Human Uncertainty-Aware Data Selection and Automatic Labeling in Visual Question Answering","created":"2025-10-13","cited_by_count":1,"area":"mllm"},{"id":"2510.16290","title":"Cerberus: Real-Time Video Anomaly Detection via Cascaded Vision-Language Models","created":"2025-10-18","cited_by_count":1,"area":"mllm"},{"id":"2210.14558","title":"Compressing And Debiasing Vision-Language Pre-Trained Models for Visual Question Answering","created":"2022-10-26","cited_by_count":0,"area":"mllm"},{"id":"2411.08840","title":"Multimodal Instruction Tuning with Hybrid State Space Models","created":"2024-11-13","cited_by_count":0,"area":"mllm"},{"id":"2412.08110","title":"The ART of Composition: Attention-Regularized Training for Compositional Visual Grounding","created":"2024-12-11","cited_by_count":0,"area":"mllm"},{"id":"2608.28218","title":"Focus Where It Counts: A Salience-Driven Vision-Language Model for Low Vision Assistance","created":"2026-08-28","cited_by_count":0,"area":"mllm"},{"id":"2610.14976","title":"Metric-Driven Reinforcement Learning for Object Hallucination Reduction in LVLM-Based Image Captioning","created":"2026-10-10","cited_by_count":0,"area":"mllm"}],"next_cursor":null}