{"total":102,"rows":[{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711,"area":null},{"id":"2405.09818","title":"Chameleon: Mixed-Modal Early-Fusion Foundation Models","created":"2024-05-16","cited_by_count":927,"area":null},{"id":"2311.04400","title":"LRM: Large Reconstruction Model for Single Image to 3D","created":"2023-11-08","cited_by_count":849,"area":null},{"id":"2106.13884","title":"Multimodal Few-Shot Learning with Frozen Language Models","created":"2021-06-25","cited_by_count":661,"area":null},{"id":"2310.09478","title":"MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning","created":"2023-10-14","cited_by_count":625,"area":null},{"id":"2206.08155","title":"Zero-Shot Video Question Answering via Frozen Bidirectional Language Models","created":"2022-06-16","cited_by_count":229,"area":null},{"id":"2310.05694","title":"A Survey of Large Language Models for Healthcare: from Data, Technology, and Applications to Accountability and Ethics","created":"2023-10-09","cited_by_count":163,"area":null},{"id":"2411.04996","title":"Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models","created":"2024-11-07","cited_by_count":163,"area":null},{"id":"2206.06565","title":"LIFT: Language-Interfaced Fine-Tuning for Non-Language Machine Learning Tasks","created":"2022-06-14","cited_by_count":148,"area":null},{"id":"2305.18703","title":"Domain Specialization as the Key to Make Large Language Models Disruptive: A Comprehensive Survey","created":"2023-05-30","cited_by_count":135,"area":null},{"id":"2201.05273","title":"Pretrained Language Models for Text Generation: A Survey","created":"2022-01-14","cited_by_count":122,"area":null},{"id":"2209.03430","title":"Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questions","created":"2022-09-07","cited_by_count":116,"area":null},{"id":"2305.13292","title":"VideoLLM: Modeling Video Sequence with Large Language Models","created":"2023-05-22","cited_by_count":116,"area":null},{"id":"2205.02655","title":"Language Models Can See: Plugging Visual Controls in Text Generation","created":"2022-05-05","cited_by_count":90,"area":null},{"id":"2210.08773","title":"Plug-and-Play VQA: Zero-shot VQA by Conjoining Large Pretrained Models with Zero Training","created":"2022-10-17","cited_by_count":88,"area":null},{"id":"2303.06594","title":"ChatGPT Asks, BLIP-2 Answers: Automatic Questioning Towards Enriched Visual Descriptions","created":"2023-03-12","cited_by_count":86,"area":null},{"id":"2304.06708","title":"Verbs in Action: Improving verb understanding in video-language models","created":"2023-04-13","cited_by_count":76,"area":null},{"id":"2308.01399","title":"Learning to Model the World with Language","created":"2023-07-31","cited_by_count":68,"area":null},{"id":"2403.00839","title":"ToolNet: Connecting Large Language Models with Massive Tools via Tool Graph","created":"2024-02-29","cited_by_count":60,"area":null},{"id":"2303.15935","title":"When Brain-inspired AI Meets AGI","created":"2023-03-28","cited_by_count":54,"area":null},{"id":"2203.02113","title":"FS-COCO: Towards Understanding of Freehand Sketches of Common Objects in Context","created":"2022-03-04","cited_by_count":49,"area":null},{"id":"2307.14901","title":"Text-guided Foundation Model Adaptation for Pathological Image Classification","created":"2023-07-27","cited_by_count":47,"area":null},{"id":"2304.04227","title":"Video ChatCaptioner: Towards Enriched Spatiotemporal Descriptions","created":"2023-04-09","cited_by_count":42,"area":null},{"id":"2210.07179","title":"MAPL: Parameter-Efficient Adaptation of Unimodal Pre-Trained Models for Vision-Language Few-Shot Prompting","created":"2022-10-13","cited_by_count":41,"area":null},{"id":"2311.13627","title":"Vamos: Versatile Action Models for Video Understanding","created":"2023-11-22","cited_by_count":40,"area":null},{"id":"2407.15838","title":"MMInstruct: A High-Quality Multi-Modal Instruction Tuning Dataset with Extensive Diversity","created":"2024-07-22","cited_by_count":38,"area":null},{"id":"2303.11403","title":"eP-ALM: Efficient Perceptual Augmentation of Language Models","created":"2023-03-20","cited_by_count":34,"area":null},{"id":"2405.20305","title":"Can't make an Omelette without Breaking some Eggs: Plausible Action Anticipation using Large Video-Language Models","created":"2024-05-30","cited_by_count":33,"area":null},{"id":"2306.05480","title":"Artificial General Intelligence for Medical Imaging Analysis","created":"2023-06-08","cited_by_count":32,"area":null},{"id":"2207.00422","title":"Personalized Showcases: Generating Multi-Modal Explanations for Recommendations","created":"2022-06-30","cited_by_count":30,"area":null},{"id":"2302.00902","title":"Language Quantized AutoEncoders: Towards Unsupervised Text-Image Alignment","created":"2023-02-02","cited_by_count":29,"area":null},{"id":"2304.04920","title":"Advancing Medical Imaging with Language Models: A Journey from N-grams to ChatGPT","created":"2023-04-11","cited_by_count":28,"area":null},{"id":"2206.00790","title":"Efficient Self-supervised Vision Pretraining with Local Masked Reconstruction","created":"2022-06-01","cited_by_count":27,"area":null},{"id":"2306.11732","title":"Retrieving-to-Answer: Zero-Shot Video Question Answering with Frozen Large Language Models","created":"2023-06-15","cited_by_count":27,"area":null},{"id":"2312.02252","title":"StoryGPT-V: Large Language Models as Consistent Story Visualizers","created":"2023-12-04","cited_by_count":25,"area":null},{"id":"2406.16386","title":"Automatically Generating UI Code from Screenshot: A Divide-and-Conquer-Based Approach","created":"2024-06-24","cited_by_count":24,"area":null},{"id":"2308.12462","title":"Overcoming Generic Knowledge Loss with Selective Parameter Update","created":"2023-08-23","cited_by_count":23,"area":null},{"id":"2106.13871","title":"Transflower: probabilistic autoregressive dance generation with multimodal attention","created":"2021-06-25","cited_by_count":22,"area":null},{"id":"2403.18383","title":"Generative Multi-modal Models are Good Class-Incremental Learners","created":"2024-03-27","cited_by_count":22,"area":null},{"id":"2206.01843","title":"Visual Clues: Bridging Vision and Language Foundations for Image Paragraph Captioning","created":"2022-06-03","cited_by_count":21,"area":null},{"id":"2209.13983","title":"Medical Image Captioning via Generative Pretrained Transformers","created":"2022-09-28","cited_by_count":20,"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":"2312.01191","title":"Bootstrapping Interactive Image-Text Alignment for Remote Sensing Image Captioning","created":"2023-12-02","cited_by_count":18,"area":null},{"id":"2404.09941","title":"Evolving Interpretable Visual Classifiers with Large Language Models","created":"2024-04-15","cited_by_count":18,"area":null},{"id":"2502.03304","title":"Harmony in Divergence: Towards Fast, Accurate, and Memory-efficient Zeroth-order LLM Fine-tuning","created":"2025-02-05","cited_by_count":18,"area":null},{"id":"2211.10780","title":"ArtELingo: A Million Emotion Annotations of WikiArt with Emphasis on Diversity over Language and Culture","created":"2022-11-19","cited_by_count":17,"area":null},{"id":"2510.16990","title":"Graph4MM: Weaving Multimodal Learning with Structural Information","created":"2025-10-19","cited_by_count":17,"area":null},{"id":"2307.10757","title":"Vesper: A Compact and Effective Pretrained Model for Speech Emotion Recognition","created":"2023-07-20","cited_by_count":16,"area":null},{"id":"2504.11199","title":"Video Summarization with Large Language Models","created":"2025-04-15","cited_by_count":16,"area":null},{"id":"2303.09117","title":"Cross-Modal Causal Intervention for Medical Report Generation","created":"2023-03-16","cited_by_count":15,"area":null},{"id":"2403.03790","title":"Popeye: A Unified Visual-Language Model for Multi-Source Ship Detection from Remote Sensing Imagery","created":"2024-03-06","cited_by_count":14,"area":null},{"id":"2411.17261","title":"HEIE: MLLM-Based Hierarchical Explainable AIGC Image Implausibility Evaluator","created":"2024-11-26","cited_by_count":13,"area":null},{"id":"2303.06338","title":"Learning Combinatorial Prompts for Universal Controllable Image Captioning","created":"2023-03-11","cited_by_count":12,"area":null},{"id":"2307.12775","title":"Is attention all you need in medical image analysis? A review","created":"2023-07-24","cited_by_count":12,"area":null},{"id":"2311.06791","title":"InfMLLM: A Unified Framework for Visual-Language Tasks","created":"2023-11-12","cited_by_count":11,"area":null},{"id":"2306.00450","title":"Exploring Open-Vocabulary Semantic Segmentation without Human Labels","created":"2023-06-01","cited_by_count":10,"area":null},{"id":"2307.04251","title":"ChatGPT in the Age of Generative AI and Large Language Models: A Concise Survey","created":"2023-07-09","cited_by_count":10,"area":null},{"id":"2402.18157","title":"From Summary to Action: Enhancing Large Language Models for Complex Tasks with Open World APIs","created":"2024-02-28","cited_by_count":8,"area":null},{"id":"2404.18397","title":"ViOCRVQA: Novel Benchmark Dataset and Vision Reader for Visual Question Answering by Understanding Vietnamese Text in Images","created":"2024-04-29","cited_by_count":8,"area":null},{"id":"2410.00905","title":"Removing Distributional Discrepancies in Captions Improves Image-Text Alignment","created":"2024-10-01","cited_by_count":8,"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":"2407.08947","title":"Constructing Concept-based Models to Mitigate Spurious Correlations with Minimal Human Effort","created":"2024-07-12","cited_by_count":7,"area":null},{"id":"2408.07422","title":"LLMI3D: MLLM-based 3D Perception from a Single 2D Image","created":"2024-08-14","cited_by_count":7,"area":null},{"id":"2410.13901","title":"SoK: Prompt Hacking of Large Language Models","created":"2024-10-16","cited_by_count":7,"area":null},{"id":"2508.04062","title":"PET2Rep: Towards Vision-Language Model-Drived Automated Radiology Report Generation for Positron Emission Tomography","created":"2025-08-06","cited_by_count":7,"area":null},{"id":"2508.09560","title":"WeatherPrompt: Multi-modality Representation Learning for All-Weather Drone Visual Geo-Localization","created":"2025-08-13","cited_by_count":7,"area":null},{"id":"2208.12259","title":"Pix4Point: Image Pretrained Standard Transformers for 3D Point Cloud Understanding","created":"2022-08-25","cited_by_count":6,"area":null},{"id":"2211.15378","title":"Aesthetically Relevant Image Captioning","created":"2022-11-25","cited_by_count":6,"area":null},{"id":"2312.06718","title":"Large Scale Foundation Models for Intelligent Manufacturing Applications: A Survey","created":"2023-12-11","cited_by_count":6,"area":null},{"id":"2401.02651","title":"Benchmarking PathCLIP for Pathology Image Analysis","created":"2024-01-05","cited_by_count":6,"area":null},{"id":"2401.11851","title":"BETA: Binarized Energy-Efficient Transformer Accelerator at the Edge","created":"2024-01-22","cited_by_count":6,"area":null},{"id":"2208.11671","title":"Interpreting Song Lyrics with an Audio-Informed Pre-trained Language Model","created":"2022-08-24","cited_by_count":5,"area":null},{"id":"2412.01233","title":"Best Practices for Large Language Models in Radiology","created":"2024-12-02","cited_by_count":5,"area":null},{"id":"2505.18886","title":"KerZOO: Kernel Function Informed Zeroth-Order Optimization for Accurate and Accelerated LLM Fine-Tuning","created":"2025-05-24","cited_by_count":5,"area":null},{"id":"2303.10863","title":"Decomposed Prototype Learning for Few-Shot Scene Graph Generation","created":"2023-03-20","cited_by_count":4,"area":null},{"id":"2306.16991","title":"Integrating Large Pre-trained Models into Multimodal Named Entity Recognition with Evidential Fusion","created":"2023-06-29","cited_by_count":4,"area":null},{"id":"2405.01090","title":"Learning Multiple Object States from Actions via Large Language Models","created":"2024-05-02","cited_by_count":4,"area":null},{"id":"2407.14242","title":"Continual Panoptic Perception: Towards Multi-modal Incremental Interpretation of Remote Sensing Images","created":"2024-07-19","cited_by_count":4,"area":null},{"id":"2307.00519","title":"Image Background Serves as Good Proxy for Out-of-distribution Data","created":"2023-07-02","cited_by_count":3,"area":null},{"id":"2410.07981","title":"MolMix: A Simple Yet Effective Baseline for Multimodal Molecular Representation Learning","created":"2024-10-10","cited_by_count":3,"area":null},{"id":"2305.07176","title":"Automatic Radiology Report Generation by Learning with Increasingly Hard Negatives","created":"2023-05-11","cited_by_count":2,"area":null},{"id":"2306.00693","title":"GPT4Image: Large Pre-trained Models Help Vision Models Learn Better on Perception Task","created":"2023-06-01","cited_by_count":2,"area":null},{"id":"2310.12147","title":"InViG: Benchmarking Interactive Visual Grounding with 500K Human-Robot Interactions","created":"2023-10-18","cited_by_count":2,"area":null},{"id":"2406.14343","title":"IWISDM: Assessing instruction following in multimodal models at scale","created":"2024-06-20","cited_by_count":2,"area":null},{"id":"2503.23453","title":"Semantic-Spatial Feature Fusion with Dynamic Graph Refinement for Remote Sensing Image Captioning","created":"2025-03-30","cited_by_count":2,"area":null},{"id":"2510.18228","title":"Towards Fast LLM Fine-tuning through Zeroth-Order Optimization with Projected Gradient-Aligned Perturbations","created":"2025-10-21","cited_by_count":2,"area":null},{"id":"2310.06879","title":"The Solution for the CVPR2023 NICE Image Captioning Challenge","created":"2023-10-10","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":"2404.18976","title":"Foundations of Multisensory Artificial Intelligence","created":"2024-04-29","cited_by_count":1,"area":null},{"id":"2406.06211","title":"iMotion-LLM: Instruction-Conditioned Trajectory Generation","created":"2024-06-10","cited_by_count":1,"area":null},{"id":"2408.04909","title":"Surveying the Landscape of Image Captioning Evaluation: A Comprehensive Taxonomy, Trends and Metrics Analysis","created":"2024-08-09","cited_by_count":1,"area":null},{"id":"2606.12065","title":"Automating Geometry-Intensive Compliance Checking in BIM: Graph-Based Semantic Reasoning Framework","created":"2026-06-10","cited_by_count":1,"area":null},{"id":"2606.26734","title":"Robust Onion: Peeling Open Vocab Object Detectors Under Noise","created":"2026-06-25","cited_by_count":1,"area":null},{"id":"2211.06276","title":"One-Time Model Adaptation to Heterogeneous Clients: An Intra-Client and Inter-Image Attention Design","created":"2022-11-11","cited_by_count":0,"area":null},{"id":"2309.01202","title":"MAGMA: Music Aligned Generative Motion Autodecoder","created":"2023-09-03","cited_by_count":0,"area":null},{"id":"2403.01756","title":"Attention Guidance Mechanism for Handwritten Mathematical Expression Recognition","created":"2024-03-04","cited_by_count":0,"area":null},{"id":"2405.16098","title":"Lateralization MLP: A Simple Brain-inspired Architecture for Diffusion","created":"2024-05-25","cited_by_count":0,"area":null},{"id":"2504.02496","title":"Group-based Distinctive Image Captioning with Memory Difference Encoding and Attention","created":"2025-04-03","cited_by_count":0,"area":null},{"id":"2507.21353","title":"Group Relative Augmentation for Data Efficient Action Detection","created":"2025-07-28","cited_by_count":0,"area":null},{"id":"2509.18177","title":"A Framework for Generating Artificial Datasets to Validate Absolute and Relative Position Concepts","created":"2025-09-17","cited_by_count":0,"area":null}],"next_cursor":"100"}