{"total":90,"rows":[{"id":"2309.05519","title":"NExT-GPT: Any-to-Any Multimodal LLM","created":"2023-09-11","cited_by_count":615,"area":"mllm"},{"id":"2305.16355","title":"PandaGPT: One Model To Instruction-Follow Them All","created":"2023-05-25","cited_by_count":334,"area":null},{"id":"2209.03320","title":"What does a platypus look like? Generating customized prompts for zero-shot image classification","created":"2022-09-07","cited_by_count":267,"area":null},{"id":"2306.09093","title":"Macaw-LLM: Multi-Modal Language Modeling with Image, Audio, Video, and Text Integration","created":"2023-06-15","cited_by_count":172,"area":"mllm"},{"id":"2212.10505","title":"DePlot: One-shot visual language reasoning by plot-to-table translation","created":"2022-12-20","cited_by_count":160,"area":"lr"},{"id":"2205.10747","title":"Language Models with Image Descriptors are Strong Few-Shot Video-Language Learners","created":"2022-05-22","cited_by_count":117,"area":null},{"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":"2211.00575","title":"Text-Only Training for Image Captioning using Noise-Injected CLIP","created":"2022-11-01","cited_by_count":91,"area":null},{"id":"2301.00184","title":"Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?","created":"2022-12-31","cited_by_count":90,"area":null},{"id":"2303.03032","title":"DeCap: Decoding CLIP Latents for Zero-Shot Captioning via Text-Only Training","created":"2023-03-06","cited_by_count":84,"area":null},{"id":"2303.00855","title":"Grounded Decoding: Guiding Text Generation with Grounded Models for Embodied Agents","created":"2023-03-01","cited_by_count":67,"area":"agents"},{"id":"2210.14140","title":"Contrastive Search Is What You Need For Neural Text Generation","created":"2022-10-25","cited_by_count":59,"area":null},{"id":"2406.02030","title":"Multimodal Reasoning with Multimodal Knowledge Graph","created":"2024-06-04","cited_by_count":44,"area":"lr"},{"id":"2305.01795","title":"Multimodal Procedural Planning via Dual Text-Image Prompting","created":"2023-05-02","cited_by_count":40,"area":null},{"id":"2305.18010","title":"Test-Time Adaptation with CLIP Reward for Zero-Shot Generalization in Vision-Language Models","created":"2023-05-29","cited_by_count":38,"area":"mllm"},{"id":"2403.03715","title":"MeaCap: Memory-Augmented Zero-shot Image Captioning","created":"2024-03-06","cited_by_count":35,"area":null},{"id":"2307.16525","title":"Transferable Decoding with Visual Entities for Zero-Shot Image Captioning","created":"2023-07-31","cited_by_count":34,"area":null},{"id":"2303.02437","title":"ConZIC: Controllable Zero-shot Image Captioning by Sampling-Based Polishing","created":"2023-03-04","cited_by_count":33,"area":null},{"id":"2210.03765","title":"Visualize Before You Write: Imagination-Guided Open-Ended Text Generation","created":"2022-10-07","cited_by_count":30,"area":null},{"id":"2401.08567","title":"Connect, Collapse, Corrupt: Learning Cross-Modal Tasks with Uni-Modal Data","created":"2024-01-16","cited_by_count":27,"area":null},{"id":"2211.09778","title":"I Can't Believe There's No Images! Learning Visual Tasks Using only Language Supervision","created":"2022-11-17","cited_by_count":26,"area":null},{"id":"2207.11100","title":"Zero-Shot Video Captioning with Evolving Pseudo-Tokens","created":"2022-07-22","cited_by_count":25,"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":"2208.13628","title":"Efficient Vision-Language Pretraining with Visual Concepts and Hierarchical Alignment","created":"2022-08-29","cited_by_count":19,"area":"mllm"},{"id":"2307.16686","title":"Guiding Image Captioning Models Toward More Specific Captions","created":"2023-07-31","cited_by_count":17,"area":null},{"id":"2211.10797","title":"An Empirical Study On Contrastive Search And Contrastive Decoding For Open-ended Text Generation","created":"2022-11-19","cited_by_count":14,"area":null},{"id":"2303.12208","title":"MAGVLT: Masked Generative Vision-and-Language Transformer","created":"2023-03-21","cited_by_count":14,"area":null},{"id":"2312.08865","title":"Improving Cross-modal Alignment with Synthetic Pairs for Text-only Image Captioning","created":"2023-12-14","cited_by_count":14,"area":null},{"id":"2308.13218","title":"MultiCapCLIP: Auto-Encoding Prompts for Zero-Shot Multilingual Visual Captioning","created":"2023-08-25","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":"2401.02347","title":"Mining Fine-Grained Image-Text Alignment for Zero-Shot Captioning via Text-Only Training","created":"2024-01-04","cited_by_count":12,"area":null},{"id":"2304.13273","title":"From Association to Generation: Text-only Captioning by Unsupervised Cross-modal Mapping","created":"2023-04-26","cited_by_count":11,"area":"mllm"},{"id":"2305.14053","title":"Parts of Speech-Grounded Subspaces in Vision-Language Models","created":"2023-05-23","cited_by_count":11,"area":"mllm"},{"id":"2311.08396","title":"Zero-shot audio captioning with audio-language model guidance and audio context keywords","created":"2023-11-14","cited_by_count":11,"area":null},{"id":"2409.00547","title":"Data Augmentation for Image Classification using Generative AI","created":"2024-08-31","cited_by_count":11,"area":null},{"id":"2409.18046","title":"IFCap: Image-like Retrieval and Frequency-based Entity Filtering for Zero-shot Captioning","created":"2024-09-26","cited_by_count":11,"area":null},{"id":"2308.01126","title":"Beyond Generic: Enhancing Image Captioning with Real-World Knowledge using Vision-Language Pre-Training Model","created":"2023-08-02","cited_by_count":10,"area":"mllm"},{"id":"2308.12045","title":"CgT-GAN: CLIP-guided Text GAN for Image Captioning","created":"2023-08-23","cited_by_count":10,"area":null},{"id":"2602.07026","title":"Modality Gap-Driven Subspace Alignment Training Paradigm For Multimodal Large Language Models","created":"2026-02-02","cited_by_count":10,"area":"mllm"},{"id":"2208.01815","title":"Effidit: Your AI Writing Assistant","created":"2022-08-03","cited_by_count":8,"area":null},{"id":"2211.07275","title":"Zero-shot Image Captioning by Anchor-augmented Vision-Language Space Alignment","created":"2022-11-14","cited_by_count":8,"area":null},{"id":"2305.19108","title":"DisCLIP: Open-Vocabulary Referring Expression Generation","created":"2023-05-30","cited_by_count":8,"area":null},{"id":"2502.16427","title":"Fine-Grained Captioning of Long Videos through Scene Graph Consolidation","created":"2025-02-23","cited_by_count":8,"area":"mllm"},{"id":"2305.16944","title":"Learning to Imagine: Visually-Augmented Natural Language Generation","created":"2023-05-26","cited_by_count":7,"area":null},{"id":"2305.18072","title":"Image Captioning with Multi-Context Synthetic Data","created":"2023-05-29","cited_by_count":7,"area":"diffusion"},{"id":"2311.17315","title":"Explaining CLIP's performance disparities on data from blind/low vision users","created":"2023-11-29","cited_by_count":7,"area":"mllm"},{"id":"2501.00437","title":"Unleashing Text-to-Image Diffusion Prior for Zero-Shot Image Captioning","created":"2024-12-31","cited_by_count":7,"area":"diffusion"},{"id":"2411.09439","title":"Spider: Any-to-Many Multimodal LLM","created":"2024-11-14","cited_by_count":6,"area":"mllm"},{"id":"2507.04976","title":"Can Video LLMs Refuse to Answer? Alignment for Answerability in Video Large Language Models","created":"2025-07-07","cited_by_count":6,"area":"mllm"},{"id":"2212.05093","title":"Plug-and-Play Recipe Generation with Content Planning","created":"2022-12-09","cited_by_count":5,"area":null},{"id":"2303.07519","title":"Architext: Language-Driven Generative Architecture Design","created":"2023-03-13","cited_by_count":5,"area":null},{"id":"2306.16649","title":"ZeroGen: Zero-shot Multimodal Controllable Text Generation with Multiple Oracles","created":"2023-06-29","cited_by_count":5,"area":null},{"id":"2405.07046","title":"RETTA: Retrieval-Enhanced Test-Time Adaptation for Zero-Shot Video Captioning","created":"2024-05-11","cited_by_count":5,"area":null},{"id":"2501.12231","title":"InsTALL: Context-aware Instructional Task Assistance with Multi-modal Large Language Models","created":"2025-01-21","cited_by_count":5,"area":"mllm"},{"id":"2212.02175","title":"Momentum Decoding: Open-ended Text Generation As Graph Exploration","created":"2022-12-05","cited_by_count":4,"area":null},{"id":"2303.06458","title":"ZeroNLG: Aligning and Autoencoding Domains for Zero-Shot Multimodal and Multilingual Natural Language Generation","created":"2023-03-11","cited_by_count":4,"area":null},{"id":"2402.17298","title":"ArcSin: Adaptive ranged cosine Similarity injected noise for Language-Driven Visual Tasks","created":"2024-02-27","cited_by_count":4,"area":null},{"id":"2405.18258","title":"Text-only Synthesis for Image Captioning","created":"2024-05-28","cited_by_count":4,"area":null},{"id":"2410.23698","title":"Aggregate-and-Adapt Natural Language Prompts for Downstream Generalization of CLIP","created":"2024-10-31","cited_by_count":4,"area":"mllm"},{"id":"2212.04267","title":"Vision and Structured-Language Pretraining for Cross-Modal Food Retrieval","created":"2022-12-08","cited_by_count":3,"area":"mllm"},{"id":"2308.08881","title":"Text-Only Training for Visual Storytelling","created":"2023-08-17","cited_by_count":3,"area":null},{"id":"2309.03884","title":"Zero-Shot Audio Captioning via Audibility Guidance","created":"2023-09-07","cited_by_count":3,"area":null},{"id":"2311.05043","title":"Zero-shot Translation of Attention Patterns in VQA Models to Natural Language","created":"2023-11-08","cited_by_count":3,"area":null},{"id":"2407.11449","title":"Controllable Contextualized Image Captioning: Directing the Visual Narrative through User-Defined Highlights","created":"2024-07-16","cited_by_count":3,"area":null},{"id":"2304.13742","title":"TR0N: Translator Networks for 0-Shot Plug-and-Play Conditional Generation","created":"2023-04-26","cited_by_count":2,"area":null},{"id":"2403.01954","title":"DECIDER: A Dual-System Rule-Controllable Decoding Framework for Language Generation","created":"2024-03-04","cited_by_count":2,"area":null},{"id":"2405.18304","title":"Multi-modal Generation via Cross-Modal In-Context Learning","created":"2024-05-28","cited_by_count":2,"area":null},{"id":"2510.02898","title":"One Patch to Caption Them All: A Unified Zero-Shot Captioning Framework","created":"2025-10-03","cited_by_count":2,"area":null},{"id":"2207.01823","title":"Scene-Aware Prompt for Multi-modal Dialogue Understanding and Generation","created":"2022-07-05","cited_by_count":1,"area":null},{"id":"2210.12112","title":"Describing Sets of Images with Textual-PCA","created":"2022-10-21","cited_by_count":1,"area":null},{"id":"2210.12905","title":"Visualizing the Obvious: A Concreteness-based Ensemble Model for Noun Property Prediction","created":"2022-10-24","cited_by_count":1,"area":null},{"id":"2310.09767","title":"VLIS: Unimodal Language Models Guide Multimodal Language Generation","created":"2023-10-15","cited_by_count":1,"area":"mllm"},{"id":"2311.12268","title":"Boosting Audio-visual Zero-shot Learning with Large Language Models","created":"2023-11-21","cited_by_count":1,"area":null},{"id":"2403.19193","title":"Text Data-Centric Image Captioning with Interactive Prompts","created":"2024-03-28","cited_by_count":1,"area":null},{"id":"2509.12591","title":"MAGIC-Enhanced Keyword Prompting for Zero-Shot Audio Captioning with CLIP Models","created":"2025-09-16","cited_by_count":1,"area":null},{"id":"2512.04309","title":"Text-Only Training for Image Captioning with Retrieval Augmentation and Modality Gap Correction","created":"2025-12-03","cited_by_count":1,"area":null},{"id":"2302.00952","title":"QR-CLIP: Introducing Explicit Open-World Knowledge for Location and Time Reasoning","created":"2023-02-02","cited_by_count":0,"area":null},{"id":"2306.01753","title":"Preconditioned Visual Language Inference with Weak Supervision","created":"2023-05-22","cited_by_count":0,"area":null},{"id":"2310.18369","title":"Apollo: Zero-shot MultiModal Reasoning with Multiple Experts","created":"2023-10-25","cited_by_count":0,"area":"lr"},{"id":"2409.19960","title":"TROPE: TRaining-Free Object-Part Enhancement for Seamlessly Improving Fine-Grained Zero-Shot Image Captioning","created":"2024-09-30","cited_by_count":0,"area":null},{"id":"2412.08158","title":"How Vision-Language Tasks Benefit from Large Pre-trained Models: A Survey","created":"2024-12-11","cited_by_count":0,"area":"lr"},{"id":"2502.11751","title":"Language Models Can See Better: Visual Contrastive Decoding For LLM Multimodal Reasoning","created":"2025-02-17","cited_by_count":0,"area":"lr"},{"id":"2503.23679","title":"The Devil is in the Distributions: Explicit Modeling of Scene Content is Key in Zero-Shot Video Captioning","created":"2025-03-31","cited_by_count":0,"area":null},{"id":"2508.01270","title":"SGCap: Decoding Semantic Group for Zero-shot Video Captioning","created":"2025-08-02","cited_by_count":0,"area":null},{"id":"2510.08590","title":"Evolutionary Computation as Natural Generative AI","created":"2025-10-04","cited_by_count":0,"area":null},{"id":"2602.01257","title":"Boosting Point-supervised Temporal Action Localization via Text Refinement and Alignment","created":"2026-02-01","cited_by_count":0,"area":null},{"id":"2602.23588","title":"Hyperdimensional Cross-Modal Alignment of Frozen Language and Image Models for Efficient Image Captioning","created":"2026-02-27","cited_by_count":0,"area":null},{"id":"2607.28986","title":"Adjudicated Captioning: Multi-Agent Alignment Scoring and Consensus-Distilled Beam Arbitration for Strict Zero-Shot Image Captioning","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2608.11013","title":"Watching Synthetic Videos: Aligning Cross-modal Representations with Visual Synthesis for Zero-shot Video Captioning","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2610.16666","title":"Revisiting Natural Language Prompts from Large Language Models for Open-Vocabulary Video Recognition","created":"2026-10-12","cited_by_count":0,"area":"mllm"}],"next_cursor":null}