{"total":70,"rows":[{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137,"area":"synth"},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386,"area":"mllm"},{"id":"2302.04023","title":"A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity","created":"2023-02-08","cited_by_count":894,"area":"lr"},{"id":"2302.14045","title":"Language Is Not All You Need: Aligning Perception with Language Models","created":"2023-02-27","cited_by_count":543,"area":"wm"},{"id":"2303.07280","title":"Vision-Language Models as Success Detectors","created":"2023-03-13","cited_by_count":142,"area":"mllm"},{"id":"2212.10846","title":"From Images to Textual Prompts: Zero-shot VQA with Frozen Large Language Models","created":"2022-12-21","cited_by_count":115,"area":null},{"id":"2206.06336","title":"Language Models are General-Purpose Interfaces","created":"2022-06-13","cited_by_count":97,"area":null},{"id":"2309.12314","title":"TinyCLIP: CLIP Distillation via Affinity Mimicking and Weight Inheritance","created":"2023-09-21","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":"2310.05338","title":"Negative Object Presence Evaluation (NOPE) to Measure Object Hallucination in Vision-Language Models","created":"2023-10-09","cited_by_count":80,"area":"mllm"},{"id":"2210.07688","title":"Plausible May Not Be Faithful: Probing Object Hallucination in Vision-Language Pre-training","created":"2022-10-14","cited_by_count":72,"area":"mllm"},{"id":"2309.17133","title":"Fine-grained Late-interaction Multi-modal Retrieval for Retrieval Augmented Visual Question Answering","created":"2023-09-29","cited_by_count":51,"area":"rag"},{"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":"2212.09648","title":"NusaCrowd: Open Source Initiative for Indonesian NLP Resources","created":"2022-12-19","cited_by_count":38,"area":null},{"id":"2402.03241","title":"FROSTER: Frozen CLIP Is A Strong Teacher for Open-Vocabulary Action Recognition","created":"2024-02-05","cited_by_count":36,"area":"distill"},{"id":"2307.03135","title":"Distilling Large Vision-Language Model with Out-of-Distribution Generalizability","created":"2023-07-06","cited_by_count":33,"area":"mllm"},{"id":"2403.07839","title":"MoPE-CLIP: Structured Pruning for Efficient Vision-Language Models with Module-wise Pruning Error Metric","created":"2024-03-12","cited_by_count":30,"area":"mllm"},{"id":"2303.02506","title":"Prismer: A Vision-Language Model with Multi-Task Experts","created":"2023-03-04","cited_by_count":28,"area":"mllm"},{"id":"2307.07063","title":"Bootstrapping Vision-Language Learning with Decoupled Language Pre-training","created":"2023-07-13","cited_by_count":28,"area":"synth"},{"id":"2309.14381","title":"Survey of Social Bias in Vision-Language Models","created":"2023-09-24","cited_by_count":26,"area":"mllm"},{"id":"2311.10986","title":"EdgeFM: Leveraging Foundation Model for Open-set Learning on the Edge","created":"2023-11-18","cited_by_count":21,"area":null},{"id":"2210.14562","title":"FairCLIP: Social Bias Elimination based on Attribute Prototype Learning and Representation Neutralization","created":"2022-10-26","cited_by_count":20,"area":null},{"id":"2311.03354","title":"CoVLM: Composing Visual Entities and Relationships in Large Language Models Via Communicative Decoding","created":"2023-11-06","cited_by_count":20,"area":null},{"id":"2503.18491","title":"MAGIC-VQA: Multimodal And Grounded Inference with Commonsense Knowledge for Visual Question Answering","created":"2025-03-24","cited_by_count":19,"area":"mllm"},{"id":"2401.15914","title":"Overcoming the Pitfalls of Vision-Language Model Finetuning for OOD Generalization","created":"2024-01-29","cited_by_count":17,"area":"mllm"},{"id":"2404.09011","title":"PracticalDG: Perturbation Distillation on Vision-Language Models for Hybrid Domain Generalization","created":"2024-04-13","cited_by_count":15,"area":"mllm"},{"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":"2407.13851","title":"X-Former: Unifying Contrastive and Reconstruction Learning for MLLMs","created":"2024-07-18","cited_by_count":14,"area":"mllm"},{"id":"2303.13455","title":"CoBIT: A Contrastive Bi-directional Image-Text Generation Model","created":"2023-03-23","cited_by_count":11,"area":null},{"id":"2305.17006","title":"Zero-shot Visual Question Answering with Language Model Feedback","created":"2023-05-26","cited_by_count":11,"area":null},{"id":"2503.22201","title":"Multi-modal Knowledge Distillation-based Human Trajectory Forecasting","created":"2025-03-28","cited_by_count":10,"area":"distill"},{"id":"2307.14611","title":"TextManiA: Enriching Visual Feature by Text-driven Manifold Augmentation","created":"2023-07-27","cited_by_count":9,"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":"2411.12174","title":"Just KIDDIN: Knowledge Infusion and Distillation for Detection of INdecent Memes","created":"2024-11-19","cited_by_count":8,"area":null},{"id":"2211.16504","title":"Improving Commonsense in Vision-Language Models via Knowledge Graph Riddles","created":"2022-11-29","cited_by_count":7,"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":"2407.07360","title":"Towards a text-based quantitative and explainable histopathology image analysis","created":"2024-07-10","cited_by_count":7,"area":null},{"id":"2502.20158","title":"Learning to Generalize without Bias for Open-Vocabulary Action Recognition","created":"2025-02-27","cited_by_count":7,"area":null},{"id":"2308.16689","title":"ViLTA: Enhancing Vision-Language Pre-training through Textual Augmentation","created":"2023-08-31","cited_by_count":6,"area":"mllm"},{"id":"2309.15494","title":"VideoAdviser: Video Knowledge Distillation for Multimodal Transfer Learning","created":"2023-09-27","cited_by_count":6,"area":"distill"},{"id":"2406.17960","title":"MAGIC: Meta-Ability Guided Interactive Chain-of-Distillation for Effective-and-Efficient Vision-and-Language Navigation","created":"2024-06-25","cited_by_count":6,"area":"distill"},{"id":"2211.01071","title":"Gradient Knowledge Distillation for Pre-trained Language Models","created":"2022-11-02","cited_by_count":5,"area":"distill"},{"id":"2212.07937","title":"Visually-augmented pretrained language models for NLP tasks without images","created":"2022-12-15","cited_by_count":5,"area":null},{"id":"2504.00691","title":"ToVE: Efficient Vision-Language Learning via Knowledge Transfer from Vision Experts","created":"2025-04-01","cited_by_count":5,"area":null},{"id":"2302.06072","title":"Actional Atomic-Concept Learning for Demystifying Vision-Language Navigation","created":"2023-02-13","cited_by_count":4,"area":null},{"id":"2305.11540","title":"Efficient Cross-Lingual Transfer for Chinese Stable Diffusion with Images as Pivots","created":"2023-05-19","cited_by_count":4,"area":"diffusion"},{"id":"2310.05109","title":"Lightweight In-Context Tuning for Multimodal Unified Models","created":"2023-10-08","cited_by_count":4,"area":null},{"id":"2405.10121","title":"Distilling Implicit Multimodal Knowledge into Large Language Models for Zero-Resource Dialogue Generation","created":"2024-05-16","cited_by_count":4,"area":"distill"},{"id":"2410.20035","title":"Training the Untrainable: Introducing Inductive Bias via Representational Alignment","created":"2024-10-26","cited_by_count":4,"area":null},{"id":"2502.00322","title":"MODS: Moderating a Mixture of Document Speakers to Summarize Debatable Queries in Document Collections","created":"2025-02-01","cited_by_count":4,"area":null},{"id":"2209.02427","title":"Multi-Modal Experience Inspired AI Creation","created":"2022-09-02","cited_by_count":3,"area":null},{"id":"2305.17369","title":"Modularized Zero-shot VQA with Pre-trained Models","created":"2023-05-27","cited_by_count":3,"area":null},{"id":"2310.09755","title":"Beyond Segmentation: Road Network Generation with Multi-Modal LLMs","created":"2023-10-15","cited_by_count":3,"area":"mllm"},{"id":"2406.00334","title":"Image Captioning via Dynamic Path Customization","created":"2024-06-01","cited_by_count":3,"area":null},{"id":"2404.19542","title":"One-Stage Open-Vocabulary Temporal Action Detection Leveraging Temporal Multi-scale and Action Label Features","created":"2024-04-30","cited_by_count":2,"area":null},{"id":"2406.13898","title":"The Use of Multimodal Large Language Models to Detect Objects from Thermal Images: Transportation Applications","created":"2024-06-20","cited_by_count":2,"area":"mllm"},{"id":"2502.01158","title":"MIND: Modality-Informed Knowledge Distillation Framework for Multimodal Clinical Prediction Tasks","created":"2025-02-03","cited_by_count":2,"area":"distill"},{"id":"2507.08710","title":"L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training","created":"2025-07-11","cited_by_count":2,"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":"2509.20871","title":"SCRA-VQA: Summarized Caption-Rerank for Augmented Large Language Models in Visual Question Answering","created":"2025-09-25","cited_by_count":1,"area":null},{"id":"2602.09509","title":"Beyond Student: An Asymmetric Network for Neural Network Inheritance","created":"2026-02-10","cited_by_count":1,"area":"distill"},{"id":"2207.02663","title":"Kaggle Competition: Cantonese Audio-Visual Speech Recognition for In-car Commands","created":"2022-07-06","cited_by_count":0,"area":null},{"id":"2309.15487","title":"Tackling VQA with Pretrained Foundation Models without Further Training","created":"2023-09-27","cited_by_count":0,"area":null},{"id":"2505.19354","title":"GC-KBVQA: A New Four-Stage Framework for Enhancing Knowledge Based Visual Question Answering Performance","created":"2025-05-25","cited_by_count":0,"area":null},{"id":"2509.16141","title":"AcT2I: Evaluating and Improving Action Depiction in Text-to-Image Models","created":"2025-09-19","cited_by_count":0,"area":null},{"id":"2509.22053","title":"Enriching Knowledge Distillation with Intra-Class Contrastive Learning","created":"2025-09-26","cited_by_count":0,"area":"distill"},{"id":"2511.12131","title":"OAD-Promoter: Enhancing Zero-shot VQA using Large Language Models with Object Attribute Description","created":"2025-11-15","cited_by_count":0,"area":null},{"id":"2603.25383","title":"CLIP-RD: Relational Distillation for Efficient CLIP Knowledge Distillation","created":"2026-03-26","cited_by_count":0,"area":"distill"},{"id":"2606.25478","title":"TACO: Towards Task-Consistent Open-Vocabulary Adaptation in Video Recognition","created":"2026-06-24","cited_by_count":0,"area":null}],"next_cursor":null}