{"total":95,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744,"area":"wm"},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386,"area":"mllm"},{"id":"2308.02490","title":"MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities","created":"2023-08-04","cited_by_count":1239,"area":"mllm"},{"id":"2209.06794","title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","created":"2022-09-14","cited_by_count":766,"area":null},{"id":"2205.14100","title":"GIT: A Generative Image-to-text Transformer for Vision and Language","created":"2022-05-27","cited_by_count":537,"area":null},{"id":"2104.12756","title":"InfographicVQA","created":"2021-04-26","cited_by_count":437,"area":null},{"id":"2210.03347","title":"Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding","created":"2022-10-07","cited_by_count":366,"area":null},{"id":"2408.04840","title":"mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models","created":"2024-08-09","cited_by_count":291,"area":"mllm"},{"id":"2104.08541","title":"TransVG: End-to-End Visual Grounding with Transformers","created":"2021-04-17","cited_by_count":271,"area":null},{"id":"2407.04973","title":"LogicVista: Multimodal LLM Logical Reasoning Benchmark in Visual Contexts","created":"2024-07-06","cited_by_count":245,"area":"lr"},{"id":"2403.12895","title":"mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understanding","created":"2024-03-19","cited_by_count":220,"area":null},{"id":"2111.12233","title":"Scaling Up Vision-Language Pre-training for Image Captioning","created":"2021-11-24","cited_by_count":196,"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":"2311.10774","title":"MMC: Advancing Multimodal Chart Understanding with Large-scale Instruction Tuning","created":"2023-11-15","cited_by_count":150,"area":"mllm"},{"id":"2310.05126","title":"UReader: Universal OCR-free Visually-situated Language Understanding with Multimodal Large Language Model","created":"2023-10-08","cited_by_count":143,"area":"mllm"},{"id":"2107.06912","title":"From Show to Tell: A Survey on Deep Learning-based Image Captioning","created":"2021-07-14","cited_by_count":138,"area":null},{"id":"2104.00563","title":"Latent Variable Sequential Set Transformers For Joint Multi-Agent Motion Prediction","created":"2021-02-19","cited_by_count":131,"area":null},{"id":"2105.11450","title":"SAT: 2D Semantics Assisted Training for 3D Visual Grounding","created":"2021-05-24","cited_by_count":124,"area":null},{"id":"2111.12085","title":"UniTAB: Unifying Text and Box Outputs for Grounded Vision-Language Modeling","created":"2021-11-23","cited_by_count":122,"area":"mllm"},{"id":"2201.05273","title":"Pretrained Language Models for Text Generation: A Survey","created":"2022-01-14","cited_by_count":122,"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":"2206.07643","title":"Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone","created":"2022-06-15","cited_by_count":109,"area":"mllm"},{"id":"2306.08640","title":"AssistGPT: A General Multi-modal Assistant that can Plan, Execute, Inspect, and Learn","created":"2023-06-14","cited_by_count":97,"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":"2112.12494","title":"LaTr: Layout-Aware Transformer for Scene-Text VQA","created":"2021-12-23","cited_by_count":72,"area":null},{"id":"2401.08392","title":"DoraemonGPT: Toward Understanding Dynamic Scenes with Large Language Models (Exemplified as A Video Agent)","created":"2024-01-16","cited_by_count":58,"area":"agents"},{"id":"2204.07356","title":"Vision-and-Language Pretrained Models: A Survey","created":"2022-04-15","cited_by_count":50,"area":null},{"id":"2306.01733","title":"DocFormerv2: Local Features for Document Understanding","created":"2023-06-02","cited_by_count":46,"area":null},{"id":"2104.11832","title":"Playing Lottery Tickets with Vision and Language","created":"2021-04-23","cited_by_count":45,"area":null},{"id":"2207.00193","title":"Reading and Writing: Discriminative and Generative Modeling for Self-Supervised Text Recognition","created":"2022-07-01","cited_by_count":45,"area":null},{"id":"2206.06619","title":"TransVG++: End-to-End Visual Grounding with Language Conditioned Vision Transformer","created":"2022-06-14","cited_by_count":42,"area":null},{"id":"2211.14241","title":"Look Around and Refer: 2D Synthetic Semantics Knowledge Distillation for 3D Visual Grounding","created":"2022-11-25","cited_by_count":41,"area":"distill"},{"id":"2301.11843","title":"Reading and Reasoning over Chart Images for Evidence-based Automated Fact-Checking","created":"2023-01-27","cited_by_count":35,"area":null},{"id":"2206.00311","title":"MaskOCR: Text Recognition with Masked Encoder-Decoder Pretraining","created":"2022-06-01","cited_by_count":34,"area":null},{"id":"2207.10026","title":"Locality Guidance for Improving Vision Transformers on Tiny Datasets","created":"2022-07-20","cited_by_count":33,"area":null},{"id":"2404.16375","title":"List Items One by One: A New Data Source and Learning Paradigm for Multimodal LLMs","created":"2024-04-25","cited_by_count":32,"area":"mllm"},{"id":"2203.16778","title":"ViSTA: Vision and Scene Text Aggregation for Cross-Modal Retrieval","created":"2022-03-31","cited_by_count":29,"area":null},{"id":"2209.05534","title":"PreSTU: Pre-Training for Scene-Text Understanding","created":"2022-09-12","cited_by_count":27,"area":null},{"id":"2211.00288","title":"Self-supervised Character-to-Character Distillation for Text Recognition","created":"2022-11-01","cited_by_count":27,"area":null},{"id":"2209.10326","title":"Toward 3D Spatial Reasoning for Human-like Text-based Visual Question Answering","created":"2022-09-21","cited_by_count":25,"area":"lr"},{"id":"2311.00308","title":"From Image to Language: A Critical Analysis of Visual Question Answering (VQA) Approaches, Challenges, and Opportunities","created":"2023-11-01","cited_by_count":25,"area":null},{"id":"2307.03948","title":"Reading Between the Lanes: Text VideoQA on the Road","created":"2023-07-08","cited_by_count":23,"area":null},{"id":"2303.01903","title":"Prophet: Prompting Large Language Models with Complementary Answer Heuristics for Knowledge-based Visual Question Answering","created":"2023-03-03","cited_by_count":21,"area":null},{"id":"2305.11033","title":"Visual Question Answering: A Survey on Techniques and Common Trends in Recent Literature","created":"2023-05-18","cited_by_count":21,"area":null},{"id":"2211.05588","title":"Watching the News: Towards VideoQA Models that can Read","created":"2022-11-10","cited_by_count":20,"area":"lr"},{"id":"2502.09927","title":"Granite Vision: a lightweight, open-source multimodal model for enterprise Intelligence","created":"2025-02-14","cited_by_count":20,"area":null},{"id":"2503.14140","title":"Marten: Visual Question Answering with Mask Generation for Multi-modal Document Understanding","created":"2025-03-18","cited_by_count":20,"area":"mllm"},{"id":"2305.05095","title":"Less is More: Removing Text-regions Improves CLIP Training Efficiency and Robustness","created":"2023-05-08","cited_by_count":19,"area":null},{"id":"2106.04630","title":"PAM: Understanding Product Images in Cross Product Category Attribute Extraction","created":"2021-06-08","cited_by_count":18,"area":null},{"id":"2204.13867","title":"Vision-Language Pre-Training for Boosting Scene Text Detectors","created":"2022-04-29","cited_by_count":18,"area":"mllm"},{"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":"2212.01803","title":"Controllable Image Captioning via Prompting","created":"2022-12-04","cited_by_count":15,"area":null},{"id":"2301.07389","title":"Towards Models that Can See and Read","created":"2023-01-18","cited_by_count":15,"area":null},{"id":"2305.18641","title":"Enhanced Chart Understanding in Vision and Language Task via Cross-modal Pre-training on Plot Table Pairs","created":"2023-05-29","cited_by_count":15,"area":null},{"id":"2108.08965","title":"Localize, Group, and Select: Boosting Text-VQA by Scene Text Modeling","created":"2021-08-20","cited_by_count":14,"area":null},{"id":"2208.01813","title":"TAG: Boosting Text-VQA via Text-aware Visual Question-answer Generation","created":"2022-08-03","cited_by_count":12,"area":null},{"id":"2204.12974","title":"CapOnImage: Context-driven Dense-Captioning on Image","created":"2022-04-27","cited_by_count":11,"area":null},{"id":"2108.02059","title":"Question-controlled Text-aware Image Captioning","created":"2021-08-04","cited_by_count":9,"area":null},{"id":"2308.16383","title":"Separate and Locate: Rethink the Text in Text-based Visual Question Answering","created":"2023-08-31","cited_by_count":7,"area":null},{"id":"2412.15523","title":"InstructOCR: Instruction Boosting Scene Text Spotting","created":"2024-12-20","cited_by_count":7,"area":null},{"id":"2310.09147","title":"Exploring Sparse Spatial Relation in Graph Inference for Text-Based VQA","created":"2023-10-13","cited_by_count":6,"area":null},{"id":"2106.15332","title":"Winner Team Mia at TextVQA Challenge 2021: Vision-and-Language Representation Learning with Pre-trained Sequence-to-Sequence Model","created":"2021-06-24","cited_by_count":5,"area":null},{"id":"2203.01322","title":"Recent, rapid advancement in visual question answering architecture: a review","created":"2022-03-02","cited_by_count":5,"area":null},{"id":"2603.14367","title":"HomeGuard: VLM-based Embodied Safeguard for Identifying Contextual Risk in Household Task","created":"2026-03-15","cited_by_count":5,"area":"mllm"},{"id":"2201.06734","title":"Cross-modal Contrastive Distillation for Instructional Activity Anticipation","created":"2022-01-18","cited_by_count":4,"area":"distill"},{"id":"2208.08104","title":"Understanding Attention for Vision-and-Language Tasks","created":"2022-08-17","cited_by_count":4,"area":null},{"id":"2209.06730","title":"MUST-VQA: MUltilingual Scene-text VQA","created":"2022-09-14","cited_by_count":4,"area":null},{"id":"2304.01603","title":"Locate Then Generate: Bridging Vision and Language with Bounding Box for Scene-Text VQA","created":"2023-04-04","cited_by_count":4,"area":null},{"id":"2309.15857","title":"A Survey on Image-text Multimodal Models","created":"2023-09-23","cited_by_count":4,"area":null},{"id":"2311.08622","title":"Multiple-Question Multiple-Answer Text-VQA","created":"2023-11-15","cited_by_count":4,"area":null},{"id":"2302.01540","title":"DEVICE: Depth and Visual Concepts Aware Transformer for OCR-based Image Captioning","created":"2023-02-03","cited_by_count":3,"area":null},{"id":"2308.10447","title":"Explore and Tell: Embodied Visual Captioning in 3D Environments","created":"2023-08-21","cited_by_count":3,"area":null},{"id":"2309.12382","title":"SCOB: Universal Text Understanding via Character-wise Supervised Contrastive Learning with Online Text Rendering for Bridging Domain Gap","created":"2023-09-21","cited_by_count":3,"area":null},{"id":"2310.09285","title":"SAIR: Learning Semantic-aware Implicit Representation","created":"2023-10-13","cited_by_count":3,"area":null},{"id":"2407.19889","title":"Self-Supervised Learning for Text Recognition: A Critical Survey","created":"2024-07-29","cited_by_count":3,"area":null},{"id":"2410.12564","title":"FTII-Bench: A Comprehensive Multimodal Benchmark for Flow Text with Image Insertion","created":"2024-10-16","cited_by_count":3,"area":"mllm"},{"id":"2203.12929","title":"Towards Escaping from Language Bias and OCR Error: Semantics-Centered Text Visual Question Answering","created":"2022-03-24","cited_by_count":2,"area":null},{"id":"2207.01772","title":"Vision-and-Language Pretraining","created":"2022-07-05","cited_by_count":2,"area":null},{"id":"2309.10206","title":"Image-Text Pre-Training for Logo Recognition","created":"2023-09-18","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":"2111.03994","title":"NarrationBot and InfoBot: A Hybrid System for Automated Video Description","created":"2021-11-07","cited_by_count":1,"area":null},{"id":"2307.09604","title":"DenseMP: Unsupervised Dense Pre-training for Few-shot Medical Image Segmentation","created":"2023-07-13","cited_by_count":1,"area":null},{"id":"2308.00295","title":"Making the V in Text-VQA Matter","created":"2023-08-01","cited_by_count":1,"area":null},{"id":"2310.00917","title":"Harnessing the Power of Multi-Lingual Datasets for Pre-training: Towards Enhancing Text Spotting Performance","created":"2023-10-02","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":"2411.04642","title":"TAP-VL: Text Layout-Aware Pre-training for Enriched Vision-Language Models","created":"2024-11-07","cited_by_count":1,"area":"mllm"},{"id":"2605.06058","title":"Towards Self-Explainable Document Visual Question Answering with Chain-of-Explanation Predictions","created":"2026-05-07","cited_by_count":1,"area":"mllm"},{"id":"2108.09717","title":"EKTVQA: Generalized use of External Knowledge to empower Scene Text in Text-VQA","created":"2021-08-22","cited_by_count":0,"area":null},{"id":"2207.04174","title":"Towards Multimodal Vision-Language Models Generating Non-Generic Text","created":"2022-07-09","cited_by_count":0,"area":"mllm"},{"id":"2403.09288","title":"Adversarial Training with OCR Modality Perturbation for Scene-Text Visual Question Answering","created":"2024-03-14","cited_by_count":0,"area":null},{"id":"2405.00479","title":"Enhanced Textual Feature Extraction for Visual Question Answering: A Simple Convolutional Approach","created":"2024-05-01","cited_by_count":0,"area":null},{"id":"2506.03665","title":"ROSA: Addressing text understanding challenges in photographs via ROtated SAmpling","created":"2025-06-04","cited_by_count":0,"area":null},{"id":"2511.02046","title":"Text-VQA Aug: Pipelined Harnessing of Large Multimodal Models for Automated Synthesis","created":"2025-11-03","cited_by_count":0,"area":"mllm"},{"id":"2512.18755","title":"MEEA: Mere Exposure Effect-Driven Confrontational Optimization for LLM Jailbreaking","created":"2025-12-21","cited_by_count":0,"area":"alignment"},{"id":"2609.16919","title":"NeuroSymbEAD: A Large Scale Neuro-Symbolic Caption Dataset for Omni-Directional Embodied Autonomous Driving","created":"2026-09-15","cited_by_count":0,"area":"driving"}],"next_cursor":null}