{"total":78,"rows":[{"id":"2102.08981","title":"Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts","created":"2021-02-17","cited_by_count":1216,"area":null},{"id":"2104.12756","title":"InfographicVQA","created":"2021-04-26","cited_by_count":437,"area":null},{"id":"2312.06709","title":"AM-RADIO: Agglomerative Vision Foundation Model -- Reduce All Domains Into One","created":"2023-12-10","cited_by_count":169,"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":"2412.07755","title":"SAT: Dynamic Spatial Aptitude Training for Multimodal Language Models","created":"2024-12-10","cited_by_count":114,"area":"mllm"},{"id":"2103.03493","title":"Causal Attention for Vision-Language Tasks","created":"2021-03-05","cited_by_count":111,"area":"mllm"},{"id":"2305.13035","title":"Getting ViT in Shape: Scaling Laws for Compute-Optimal Model Design","created":"2023-05-22","cited_by_count":89,"area":null},{"id":"2306.07915","title":"Image Captioners Are Scalable Vision Learners Too","created":"2023-06-13","cited_by_count":89,"area":"mllm"},{"id":"2112.05253","title":"MAGMA -- Multimodal Augmentation of Generative Models through Adapter-based Finetuning","created":"2021-12-09","cited_by_count":85,"area":null},{"id":"2103.12248","title":"Multi-Modal Answer Validation for Knowledge-Based VQA","created":"2021-03-23","cited_by_count":79,"area":null},{"id":"2106.00245","title":"Adversarial VQA: A New Benchmark for Evaluating the Robustness of VQA Models","created":"2021-06-01","cited_by_count":75,"area":null},{"id":"2209.13232","title":"A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspective","created":"2022-09-27","cited_by_count":56,"area":null},{"id":"2412.08442","title":"From Multimodal LLMs to Generalist Embodied Agents: Methods and Lessons","created":"2024-12-11","cited_by_count":42,"area":"mllm"},{"id":"2403.10378","title":"EXAMS-V: A Multi-Discipline Multilingual Multimodal Exam Benchmark for Evaluating Vision Language Models","created":"2024-03-15","cited_by_count":41,"area":"mllm"},{"id":"2205.01850","title":"Visual Commonsense in Pretrained Unimodal and Multimodal Models","created":"2022-05-04","cited_by_count":39,"area":null},{"id":"2403.19596","title":"LocCa: Visual Pretraining with Location-aware Captioners","created":"2024-03-28","cited_by_count":35,"area":null},{"id":"2306.14060","title":"DesCo: Learning Object Recognition with Rich Language Descriptions","created":"2023-06-24","cited_by_count":25,"area":null},{"id":"2203.00758","title":"There is a Time and Place for Reasoning Beyond the Image","created":"2022-03-01","cited_by_count":22,"area":null},{"id":"2111.05547","title":"ICDAR 2021 Competition on Document VisualQuestion Answering","created":"2021-11-10","cited_by_count":19,"area":null},{"id":"2510.17205","title":"$\\mathcal{V}isi\\mathcal{P}runer$: Decoding Discontinuous Cross-Modal Dynamics for Efficient Multimodal LLMs","created":"2025-10-20","cited_by_count":17,"area":"mllm"},{"id":"2404.13874","title":"VALOR-EVAL: Holistic Coverage and Faithfulness Evaluation of Large Vision-Language Models","created":"2024-04-22","cited_by_count":16,"area":"mllm"},{"id":"2203.13883","title":"Multi-modal Misinformation Detection: Approaches, Challenges and Opportunities","created":"2022-03-25","cited_by_count":15,"area":null},{"id":"2105.02626","title":"A First Look: Towards Explainable TextVQA Models via Visual and Textual Explanations","created":"2021-04-29","cited_by_count":14,"area":null},{"id":"2203.17273","title":"FindIt: Generalized Localization with Natural Language Queries","created":"2022-03-31","cited_by_count":13,"area":null},{"id":"2211.03779","title":"CRIPP-VQA: Counterfactual Reasoning about Implicit Physical Properties via Video Question Answering","created":"2022-11-07","cited_by_count":13,"area":null},{"id":"2510.08559","title":"SciVideoBench: Benchmarking Scientific Video Reasoning in Large Multimodal Models","created":"2025-10-09","cited_by_count":13,"area":"mllm"},{"id":"2205.00949","title":"Answer-Me: Multi-Task Open-Vocabulary Visual Question Answering","created":"2022-05-02","cited_by_count":12,"area":"lr"},{"id":"2409.04095","title":"UNIT: Unifying Image and Text Recognition in One Vision Encoder","created":"2024-09-06","cited_by_count":12,"area":null},{"id":"2412.13702","title":"Typhoon 2: A Family of Open Text and Multimodal Thai Large Language Models","created":"2024-12-18","cited_by_count":12,"area":"mllm"},{"id":"2502.13061","title":"Robust Adaptation of Large Multimodal Models for Retrieval Augmented Hateful Meme Detection","created":"2025-02-18","cited_by_count":12,"area":"mllm"},{"id":"2209.04372","title":"Pre-training image-language transformers for open-vocabulary tasks","created":"2022-09-09","cited_by_count":11,"area":null},{"id":"2206.13296","title":"Consistency-preserving Visual Question Answering in Medical Imaging","created":"2022-06-27","cited_by_count":10,"area":null},{"id":"2301.07236","title":"Effective End-to-End Vision Language Pretraining with Semantic Visual Loss","created":"2023-01-18","cited_by_count":10,"area":"mllm"},{"id":"2303.17376","title":"A Study of Autoregressive Decoders for Multi-Tasking in Computer Vision","created":"2023-03-30","cited_by_count":10,"area":null},{"id":"2511.23031","title":"From Illusion to Intention: Visual Rationale Learning for Vision-Language Reasoning","created":"2025-11-28","cited_by_count":9,"area":"lr"},{"id":"2203.02985","title":"Dynamic Key-value Memory Enhanced Multi-step Graph Reasoning for Knowledge-based Visual Question Answering","created":"2022-03-06","cited_by_count":7,"area":null},{"id":"2210.10176","title":"Entity-Focused Dense Passage Retrieval for Outside-Knowledge Visual Question Answering","created":"2022-10-18","cited_by_count":7,"area":null},{"id":"2211.04861","title":"ERNIE-UniX2: A Unified Cross-lingual Cross-modal Framework for Understanding and Generation","created":"2022-11-09","cited_by_count":7,"area":"mllm"},{"id":"2403.12026","title":"FlexCap: Describe Anything in Images in Controllable Detail","created":"2024-03-18","cited_by_count":7,"area":"mllm"},{"id":"2412.14515","title":"Relational Programming with Foundation Models","created":"2024-12-19","cited_by_count":7,"area":null},{"id":"2503.13947","title":"Conformal Prediction and MLLM aided Uncertainty Quantification in Scene Graph Generation","created":"2025-03-18","cited_by_count":7,"area":null},{"id":"2201.02010","title":"Self-Training Vision Language BERTs with a Unified Conditional Model","created":"2022-01-06","cited_by_count":6,"area":null},{"id":"2506.02803","title":"SemVink: Advancing VLMs' Semantic Understanding of Optical Illusions via Visual Global Thinking","created":"2025-06-03","cited_by_count":6,"area":"lr"},{"id":"2605.20177","title":"From Seeing to Thinking: Decoupling Perception and Reasoning Improves Post-Training of Vision-Language Models","created":"2026-05-19","cited_by_count":6,"area":"lr"},{"id":"2106.14587","title":"Topos and Stacks of Deep Neural Networks","created":"2021-06-28","cited_by_count":5,"area":null},{"id":"2307.01067","title":"Localized Questions in Medical Visual Question Answering","created":"2023-07-03","cited_by_count":5,"area":null},{"id":"2405.19854","title":"RTGen: Generating Region-Text Pairs for Open-Vocabulary Object Detection","created":"2024-05-30","cited_by_count":4,"area":null},{"id":"2505.12884","title":"TinyAlign: Boosting Lightweight Vision-Language Models by Mitigating Modal Alignment Bottlenecks","created":"2025-05-19","cited_by_count":4,"area":"mllm"},{"id":"2505.21538","title":"Caption This, Reason That: VLMs Caught in the Middle","created":"2025-05-24","cited_by_count":4,"area":"lr"},{"id":"2508.04280","title":"Enhancing Vision-Language Model Training with Reinforcement Learning in Synthetic Worlds for Real-World Success","created":"2025-08-06","cited_by_count":4,"area":"mllm"},{"id":"2512.00736","title":"REM: Evaluating LLM Embodied Spatial Reasoning through Multi-Frame Trajectories","created":"2025-11-30","cited_by_count":4,"area":"lr"},{"id":"2208.03030","title":"ChiQA: A Large Scale Image-based Real-World Question Answering Dataset for Multi-Modal Understanding","created":"2022-08-05","cited_by_count":3,"area":null},{"id":"2601.03500","title":"SDCD: Structure-Disrupted Contrastive Decoding for Mitigating Hallucinations in Large Vision-Language Models","created":"2026-01-07","cited_by_count":3,"area":"mllm"},{"id":"2409.14785","title":"Towards Efficient and Robust VQA-NLE Data Generation with Large Vision-Language Models","created":"2024-09-23","cited_by_count":2,"area":"mllm"},{"id":"2412.09907","title":"IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs","created":"2024-12-13","cited_by_count":2,"area":null},{"id":"2509.23673","title":"RCI: A Score for Evaluating Global and Local Reasoning in Multimodal Benchmarks","created":"2025-09-28","cited_by_count":2,"area":"lr"},{"id":"2512.19070","title":"Watch Closely: Mitigating Object Hallucinations in Large Vision-Language Models with Disentangled Decoding","created":"2025-12-22","cited_by_count":2,"area":"mllm"},{"id":"2606.16783","title":"Gen-VCoT: Generative Visual Chain-of-Thought Reasoning via Diffusion-Based RGB Intermediate Representations","created":"2026-06-15","cited_by_count":2,"area":"lr"},{"id":"2607.12815","title":"Visual Access Boundaries in Vision-Language Model Reasoning","created":"2026-07-14","cited_by_count":2,"area":"lr"},{"id":"2202.08138","title":"When Did It Happen? Duration-informed Temporal Localization of Narrated Actions in Vlogs","created":"2022-02-16","cited_by_count":1,"area":null},{"id":"2207.00590","title":"ViRel: Unsupervised Visual Relations Discovery with Graph-level Analogy","created":"2022-07-04","cited_by_count":1,"area":null},{"id":"2408.03043","title":"Targeted Visual Prompting for Medical Visual Question Answering","created":"2024-08-06","cited_by_count":1,"area":"mllm"},{"id":"2512.20595","title":"Cube Bench: A Benchmark for Spatial Visual Reasoning in MLLMs","created":"2025-12-23","cited_by_count":1,"area":"lr"},{"id":"2601.16527","title":"Beyond Superficial Unlearning: Sharpness-Aware Robust Erasure of Hallucinations in Multimodal LLMs","created":"2026-01-23","cited_by_count":1,"area":"mllm"},{"id":"2604.16930","title":"CoGR-MoE: Concept-Guided Expert Routing with Consistent Selection and Flexible Reasoning for Visual Question Answering","created":"2026-04-18","cited_by_count":1,"area":"moe"},{"id":"2608.14721","title":"AeroGround: A Comprehensive Benchmark for Aerial-Ground Collaborative Reasoning","created":"2026-08-12","cited_by_count":1,"area":"lr"},{"id":"2112.09253","title":"Logically at Factify 2022: Multimodal Fact Verification","created":"2021-12-16","cited_by_count":0,"area":null},{"id":"2303.05983","title":"Accountable Textual-Visual Chat Learns to Reject Human Instructions in Image Re-creation","created":"2023-03-10","cited_by_count":0,"area":null},{"id":"2305.19924","title":"Joint Adaptive Representations for Image-Language Learning","created":"2023-05-31","cited_by_count":0,"area":null},{"id":"2406.15359","title":"Constructing Multilingual Visual-Text Datasets Revealing Visual Multilingual Ability of Vision Language Models","created":"2024-03-29","cited_by_count":0,"area":"mllm"},{"id":"2412.13847","title":"A Concept-Centric Approach to Multi-Modality Learning","created":"2024-12-18","cited_by_count":0,"area":null},{"id":"2511.01213","title":"Thought-For-Food: Reasoning Chain Induced Food Visual Question Answering","created":"2025-11-03","cited_by_count":0,"area":"lr"},{"id":"2512.00936","title":"SceneProp: Combining Neural Network and Markov Random Field for Scene-Graph Grounding","created":"2025-11-30","cited_by_count":0,"area":"mllm"},{"id":"2601.08010","title":"CASHEW: Stabilizing Multimodal Reasoning via Iterative Trajectory Aggregation","created":"2026-01-12","cited_by_count":0,"area":"lr"},{"id":"2601.22666","title":"ExpAlign: Expectation-Guided Vision-Language Alignment for Open-Vocabulary Grounding","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2605.23883","title":"PGT: Procedurally Generated Tasks for improving visual grounding in MLLMs","created":"2026-05-22","cited_by_count":0,"area":"mllm"},{"id":"2609.09184","title":"Evidence-Order Calibration for Selective Visual Reasoning under Progressive Loss of Question-Critical Evidence","created":"2026-08-29","cited_by_count":0,"area":"lr"},{"id":"2610.07984","title":"Decide Before You Look: Learning Which Retrieved Memories Deserve Pixels","created":"2026-10-06","cited_by_count":0,"area":null}],"next_cursor":null}