{"total":82,"rows":[{"id":"2405.06211","title":"A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models","created":"2024-05-10","cited_by_count":452,"area":"rag"},{"id":"2402.19473","title":"Retrieval-Augmented Generation for AI-Generated Content: A Survey","created":"2024-02-29","cited_by_count":354,"area":"rag"},{"id":"2211.12561","title":"Retrieval-Augmented Multimodal Language Modeling","created":"2022-11-22","cited_by_count":125,"area":"mllm"},{"id":"2410.03727","title":"FaithEval: Can Your Language Model Stay Faithful to Context, Even If \"The Moon is Made of Marshmallows\"","created":"2024-09-30","cited_by_count":86,"area":"rag"},{"id":"2404.15406","title":"Wiki-LLaVA: Hierarchical Retrieval-Augmented Generation for Multimodal LLMs","created":"2024-04-23","cited_by_count":80,"area":"mllm"},{"id":"2305.14800","title":"Exploring Diverse In-Context Configurations for Image Captioning","created":"2023-05-24","cited_by_count":63,"area":null},{"id":"2504.09795","title":"VDocRAG: Retrieval-Augmented Generation over Visually-Rich Documents","created":"2025-04-14","cited_by_count":59,"area":"rag"},{"id":"2401.00789","title":"Retrieval-Augmented Egocentric Video Captioning","created":"2024-01-01","cited_by_count":42,"area":null},{"id":"2312.07353","title":"CLIP in Medical Imaging: A Survey","created":"2023-12-12","cited_by_count":40,"area":null},{"id":"2411.15720","title":"Chain of Attack: On the Robustness of Vision-Language Models Against Transfer-Based Adversarial Attacks","created":"2024-11-24","cited_by_count":39,"area":"mllm"},{"id":"2503.10677","title":"A Survey on Knowledge-Oriented Retrieval-Augmented Generation","created":"2025-03-11","cited_by_count":36,"area":"rag"},{"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":"2311.15879","title":"EVCap: Retrieval-Augmented Image Captioning with External Visual-Name Memory for Open-World Comprehension","created":"2023-11-27","cited_by_count":32,"area":"rag"},{"id":"2302.08268","title":"Retrieval-augmented Image Captioning","created":"2023-02-16","cited_by_count":29,"area":"rag"},{"id":"2408.00555","title":"Alleviating Hallucination in Large Vision-Language Models with Active Retrieval Augmentation","created":"2024-08-01","cited_by_count":29,"area":"mllm"},{"id":"2411.15421","title":"OphCLIP: Hierarchical Retrieval-Augmented Learning for Ophthalmic Surgical Video-Language Pretraining","created":"2024-11-23","cited_by_count":29,"area":"mllm"},{"id":"2501.01346","title":"Large Vision-Language Model Alignment and Misalignment: A Survey Through the Lens of Explainability","created":"2025-01-02","cited_by_count":28,"area":"mllm"},{"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":"2309.09836","title":"RECAP: Retrieval-Augmented Audio Captioning","created":"2023-09-18","cited_by_count":27,"area":"rag"},{"id":"2402.14835","title":"MIKE: A New Benchmark for Fine-grained Multimodal Entity Knowledge Editing","created":"2024-02-18","cited_by_count":25,"area":"mllm"},{"id":"2410.07071","title":"Retrieval-Augmented Decision Transformer: External Memory for In-context RL","created":"2024-10-09","cited_by_count":21,"area":"rag"},{"id":"2308.12383","title":"With a Little Help from your own Past: Prototypical Memory Networks for Image Captioning","created":"2023-08-23","cited_by_count":18,"area":null},{"id":"2305.19821","title":"LMCap: Few-shot Multilingual Image Captioning by Retrieval Augmented Language Model Prompting","created":"2023-05-31","cited_by_count":17,"area":"rag"},{"id":"2410.17251","title":"Altogether: Image Captioning via Re-aligning Alt-text","created":"2024-10-22","cited_by_count":17,"area":null},{"id":"2404.14808","title":"Visual-Augmented Dynamic Semantic Prototype for Generative Zero-Shot Learning","created":"2024-04-23","cited_by_count":16,"area":null},{"id":"2410.07336","title":"Positive-Augmented Contrastive Learning for Vision-and-Language Evaluation and Training","created":"2024-10-09","cited_by_count":16,"area":null},{"id":"2506.05872","title":"Domain-RAG: Retrieval-Guided Compositional Image Generation for Cross-Domain Few-Shot Object Detection","created":"2025-06-06","cited_by_count":15,"area":null},{"id":"2407.20341","title":"BRIDGE: Bridging Gaps in Image Captioning Evaluation with Stronger Visual Cues","created":"2024-07-29","cited_by_count":13,"area":null},{"id":"2403.12693","title":"As Firm As Their Foundations: Can open-sourced foundation models be used to create adversarial examples for downstream tasks?","created":"2024-03-19","cited_by_count":11,"area":null},{"id":"2409.14083","title":"SURf: Teaching Large Vision-Language Models to Selectively Utilize Retrieved Information","created":"2024-09-21","cited_by_count":11,"area":"mllm"},{"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":"2302.11352","title":"X-TRA: Improving Chest X-ray Tasks with Cross-Modal Retrieval Augmentation","created":"2023-02-22","cited_by_count":10,"area":null},{"id":"2406.19150","title":"RAVEN: Multitask Retrieval Augmented Vision-Language Learning","created":"2024-06-27","cited_by_count":10,"area":"rag"},{"id":"2504.09480","title":"Vision-Language Model for Object Detection and Segmentation: A Review and Evaluation","created":"2025-04-13","cited_by_count":10,"area":"mllm"},{"id":"2406.02265","title":"Understanding Retrieval Robustness for Retrieval-Augmented Image Captioning","created":"2024-06-04","cited_by_count":9,"area":"rag"},{"id":"2407.06304","title":"VIMI: Grounding Video Generation through Multi-modal Instruction","created":"2024-07-08","cited_by_count":8,"area":"diffusion"},{"id":"2309.04965","title":"Prefix-diffusion: A Lightweight Diffusion Model for Diverse Image Captioning","created":"2023-09-10","cited_by_count":7,"area":"diffusion"},{"id":"2309.15729","title":"MindGPT: Interpreting What You See with Non-invasive Brain Recordings","created":"2023-09-27","cited_by_count":6,"area":null},{"id":"2506.04565","title":"From Standalone LLMs to Integrated Intelligence: A Survey of Compound Al Systems","created":"2025-06-05","cited_by_count":6,"area":null},{"id":"2312.04793","title":"User-Aware Prefix-Tuning is a Good Learner for Personalized Image Captioning","created":"2023-12-08","cited_by_count":5,"area":null},{"id":"2408.14547","title":"Revisiting Image Captioning Training Paradigm via Direct CLIP-based Optimization","created":"2024-08-26","cited_by_count":5,"area":null},{"id":"2502.06600","title":"Evaluation of Multilingual Image Captioning: How far can we get with CLIP models?","created":"2025-02-10","cited_by_count":5,"area":null},{"id":"2504.01472","title":"ANNEXE: Unified Analyzing, Answering, and Pixel Grounding for Egocentric Interaction","created":"2025-04-02","cited_by_count":5,"area":null},{"id":"2508.13739","title":"Enhancing Targeted Adversarial Attacks on Large Vision-Language Models via Intermediate Projector","created":"2025-08-19","cited_by_count":5,"area":"mllm"},{"id":"2306.07490","title":"Top-Down Framework for Weakly-supervised Grounded Image Captioning","created":"2023-06-13","cited_by_count":4,"area":null},{"id":"2403.18969","title":"A Survey on Large Language Models from Concept to Implementation","created":"2024-03-27","cited_by_count":4,"area":null},{"id":"2504.07415","title":"RA-RRG: Multimodal Retrieval-Augmented Radiology Report Generation with Key Phrase Extraction","created":"2025-04-10","cited_by_count":4,"area":"rag"},{"id":"2506.03100","title":"Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds","created":"2025-06-03","cited_by_count":4,"area":"rag"},{"id":"2408.01349","title":"PC$^2$: Pseudo-Classification Based Pseudo-Captioning for Noisy Correspondence Learning in Cross-Modal Retrieval","created":"2024-08-02","cited_by_count":3,"area":null},{"id":"2411.08715","title":"Retrieval Augmented Recipe Generation","created":"2024-11-13","cited_by_count":3,"area":"mllm"},{"id":"2303.02411","title":"The Contribution of Knowledge in Visiolinguistic Learning: A Survey on Tasks and Challenges","created":"2023-03-04","cited_by_count":2,"area":null},{"id":"2406.07133","title":"Translating speech with just images","created":"2024-06-11","cited_by_count":2,"area":null},{"id":"2406.10839","title":"Reminding Multimodal Large Language Models of Object-aware Knowledge with Retrieved Tags","created":"2024-06-16","cited_by_count":2,"area":"mllm"},{"id":"2407.11393","title":"CIC-BART-SSA: Controllable Image Captioning with Structured Semantic Augmentation","created":"2024-07-16","cited_by_count":2,"area":null},{"id":"2501.02584","title":"Efficient Architectures for High Resolution Vision-Language Models","created":"2025-01-05","cited_by_count":2,"area":"mllm"},{"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":"2412.01115","title":"DIR: Retrieval-Augmented Image Captioning with Comprehensive Understanding","created":"2024-12-02","cited_by_count":1,"area":"rag"},{"id":"2412.02262","title":"Composing Open-domain Vision with RAG for Ocean Monitoring and Conservation","created":"2024-12-03","cited_by_count":1,"area":null},{"id":"2504.14011","title":"Fashion-RAG: Multimodal Fashion Image Editing via Retrieval-Augmented Generation","created":"2025-04-18","cited_by_count":1,"area":"rag"},{"id":"2508.09170","title":"Multimodal RAG Enhanced Visual Description","created":"2025-08-06","cited_by_count":1,"area":null},{"id":"2508.21451","title":"MM-SeR: Multimodal Self-Refinement for Lightweight Image Captioning","created":"2025-08-29","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":"2602.21819","title":"SemVideo: Reconstructs What You Watch from Brain Activity via Hierarchical Semantic Guidance","created":"2026-02-25","cited_by_count":1,"area":null},{"id":"2307.05591","title":"Linear Alignment of Vision-language Models for Image Captioning","created":"2023-07-10","cited_by_count":0,"area":"mllm"},{"id":"2307.14750","title":"Exploring Annotation-free Image Captioning with Retrieval-augmented Pseudo Sentence Generation","created":"2023-07-27","cited_by_count":0,"area":"rag"},{"id":"2401.02961","title":"A Surrogate-Assisted Extended Generative Adversarial Network for Parameter Optimization in Free-Form Metasurface Design","created":"2023-10-18","cited_by_count":0,"area":null},{"id":"2503.01453","title":"AC-Lite : A Lightweight Image Captioning Model for Low-Resource Assamese Language","created":"2025-03-03","cited_by_count":0,"area":null},{"id":"2507.20411","title":"CONCAP: Seeing Beyond English with Concepts Retrieval-Augmented Captioning","created":"2025-07-27","cited_by_count":0,"area":"mllm"},{"id":"2508.07318","title":"RORPCap: Retrieval-based Objects and Relations Prompt for Image Captioning","created":"2025-08-10","cited_by_count":0,"area":null},{"id":"2509.15883","title":"RACap: Relation-Aware Prompting for Lightweight Retrieval-Augmented Image Captioning","created":"2025-09-19","cited_by_count":0,"area":"rag"},{"id":"2510.24813","title":"DualCap: Enhancing Lightweight Image Captioning via Dual Retrieval with Similar Scenes Visual Prompts","created":"2025-10-28","cited_by_count":0,"area":null},{"id":"2510.27164","title":"Generating Accurate and Detailed Captions for High-Resolution Images","created":"2025-10-31","cited_by_count":0,"area":"mllm"},{"id":"2511.01059","title":"Efficient Test-Time Retrieval Augmented Generation","created":"2025-11-02","cited_by_count":0,"area":"rag"},{"id":"2512.00887","title":"Multilingual Training-Free Remote Sensing Image Captioning","created":"2025-11-30","cited_by_count":0,"area":null},{"id":"2512.15531","title":"An Efficient and Effective Encoder Model for Vision and Language Tasks in the Remote Sensing Domain","created":"2025-12-17","cited_by_count":0,"area":null},{"id":"2603.01696","title":"Cross-modal Identity Mapping: Minimizing Information Loss in Modality Conversion via Reinforcement Learning","created":"2026-03-02","cited_by_count":0,"area":"mllm"},{"id":"2606.12633","title":"ECA: Efficient Continual Alignment for Open-Ended Image-to-Text Generation","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2608.00994","title":"Entity-Faithful Repair of Synthetic Supervision for Zero-Shot Image Captioning","created":"2026-08-02","cited_by_count":0,"area":null},{"id":"2608.04052","title":"When Modalities Fail to Tango: Conformal Backdoor Detection in Multimodal Contrastive Learning","created":"2026-08-04","cited_by_count":0,"area":"safety"},{"id":"2608.21305","title":"Re$^3$Cap: Retrieval-Guided Refinement for Image Captioning Enhancement via Reinforcement Learning","created":"2026-08-21","cited_by_count":0,"area":"lr"},{"id":"2609.14100","title":"RA-CoA: Training-free Fashion Image Captioning via Retrieval-Augmented Chain-of-Attributes","created":"2026-09-12","cited_by_count":0,"area":"rag"}],"next_cursor":null}