{"total":139,"rows":[{"id":"2206.01718","title":"A-OKVQA: A Benchmark for Visual Question Answering using World Knowledge","created":"2022-06-03","cited_by_count":710,"area":null},{"id":"2405.02246","title":"What matters when building vision-language models?","created":"2024-05-03","cited_by_count":326,"area":"mllm"},{"id":"2408.12637","title":"Building and better understanding vision-language models: insights and future directions","created":"2024-08-22","cited_by_count":173,"area":"mllm"},{"id":"2412.05237","title":"MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale","created":"2024-12-06","cited_by_count":127,"area":"lr"},{"id":"2306.09224","title":"Encyclopedic VQA: Visual questions about detailed properties of fine-grained categories","created":"2023-06-15","cited_by_count":107,"area":"rag"},{"id":"2212.00259","title":"Super-CLEVR: A Virtual Benchmark to Diagnose Domain Robustness in Visual Reasoning","created":"2022-12-01","cited_by_count":92,"area":"lr"},{"id":"2103.15538","title":"SUTD-TrafficQA: A Question Answering Benchmark and an Efficient Network for Video Reasoning over Traffic Events","created":"2021-03-29","cited_by_count":84,"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":"2411.17558","title":"Natural Language Understanding and Inference with MLLM in Visual Question Answering: A Survey","created":"2024-11-26","cited_by_count":76,"area":"mllm"},{"id":"2205.01883","title":"All You May Need for VQA are Image Captions","created":"2022-05-04","cited_by_count":65,"area":null},{"id":"2107.02331","title":"Mind Your Outliers! Investigating the Negative Impact of Outliers on Active Learning for Visual Question Answering","created":"2021-07-06","cited_by_count":62,"area":null},{"id":"2308.14179","title":"Towards Vision-Language Mechanistic Interpretability: A Causal Tracing Tool for BLIP","created":"2023-08-27","cited_by_count":62,"area":"mechinterp"},{"id":"2308.12305","title":"FedDAT: An Approach for Foundation Model Finetuning in Multi-Modal Heterogeneous Federated Learning","created":"2023-08-21","cited_by_count":60,"area":null},{"id":"2207.12647","title":"Cross-Modal Causal Relational Reasoning for Event-Level Visual Question Answering","created":"2022-07-26","cited_by_count":57,"area":"lr"},{"id":"2306.17842","title":"SPAE: Semantic Pyramid AutoEncoder for Multimodal Generation with Frozen LLMs","created":"2023-06-30","cited_by_count":55,"area":null},{"id":"2510.17269","title":"FineVision: Open Data Is All You Need","created":"2025-10-20","cited_by_count":53,"area":"mllm"},{"id":"2403.16558","title":"Elysium: Exploring Object-level Perception in Videos via MLLM","created":"2024-03-25","cited_by_count":48,"area":"mllm"},{"id":"2112.08359","title":"3D Question Answering","created":"2021-12-15","cited_by_count":41,"area":null},{"id":"2201.12382","title":"Deep Learning Methods for Abstract Visual Reasoning: A Survey on Raven's Progressive Matrices","created":"2022-01-28","cited_by_count":37,"area":"lr"},{"id":"2407.06438","title":"SOLO: A Single Transformer for Scalable Vision-Language Modeling","created":"2024-07-08","cited_by_count":37,"area":"mllm"},{"id":"2110.08515","title":"Multimodal Dialogue Response Generation","created":"2021-10-16","cited_by_count":32,"area":null},{"id":"2109.03438","title":"ArchivalQA: A Large-scale Benchmark Dataset for Open Domain Question Answering over Historical News Collections","created":"2021-09-08","cited_by_count":30,"area":null},{"id":"2203.05126","title":"PACTran: PAC-Bayesian Metrics for Estimating the Transferability of Pretrained Models to Classification Tasks","created":"2022-03-10","cited_by_count":30,"area":null},{"id":"2205.05019","title":"Learning to Answer Visual Questions from Web Videos","created":"2022-05-10","cited_by_count":30,"area":null},{"id":"2202.09195","title":"A Review on Methods and Applications in Multimodal Deep Learning","created":"2022-02-18","cited_by_count":29,"area":null},{"id":"2203.01922","title":"Vision-Language Intelligence: Tasks, Representation Learning, and Large Models","created":"2022-03-03","cited_by_count":28,"area":null},{"id":"2605.27365","title":"LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding","created":"2026-05-26","cited_by_count":28,"area":"mllm"},{"id":"2105.11087","title":"Recent Advances and Trends in Multimodal Deep Learning: A Review","created":"2021-05-24","cited_by_count":26,"area":null},{"id":"2310.10942","title":"UNK-VQA: A Dataset and a Probe into the Abstention Ability of Multi-modal Large Models","created":"2023-10-17","cited_by_count":25,"area":null},{"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":"2403.07874","title":"Beyond Text: Frozen Large Language Models in Visual Signal Comprehension","created":"2024-03-12","cited_by_count":23,"area":null},{"id":"2308.08414","title":"Tem-adapter: Adapting Image-Text Pretraining for Video Question Answer","created":"2023-08-16","cited_by_count":22,"area":null},{"id":"2112.10728","title":"MuMuQA: Multimedia Multi-Hop News Question Answering via Cross-Media Knowledge Extraction and Grounding","created":"2021-12-20","cited_by_count":19,"area":null},{"id":"2502.18778","title":"M2-omni: Advancing Omni-MLLM for Comprehensive Modality Support with Competitive Performance","created":"2025-02-26","cited_by_count":19,"area":null},{"id":"2112.03572","title":"Question Answering Survey: Directions, Challenges, Datasets, Evaluation Matrices","created":"2021-12-07","cited_by_count":17,"area":null},{"id":"2308.06262","title":"Foundation Model is Efficient Multimodal Multitask Model Selector","created":"2023-08-11","cited_by_count":16,"area":null},{"id":"2310.17914","title":"3D-Aware Visual Question Answering about Parts, Poses and Occlusions","created":"2023-10-27","cited_by_count":16,"area":null},{"id":"2410.20263","title":"EfficientEQA: An Efficient Approach to Open-Vocabulary Embodied Question Answering","created":"2024-10-26","cited_by_count":15,"area":null},{"id":"2410.23828","title":"Show Me What and Where has Changed? Question Answering and Grounding for Remote Sensing Change Detection","created":"2024-10-31","cited_by_count":15,"area":null},{"id":"2104.05981","title":"CLEVR_HYP: A Challenge Dataset and Baselines for Visual Question Answering with Hypothetical Actions over Images","created":"2021-04-13","cited_by_count":14,"area":null},{"id":"2110.00711","title":"Asking questions on handwritten document collections","created":"2021-10-02","cited_by_count":14,"area":null},{"id":"2205.07548","title":"A Neuro-Symbolic ASP Pipeline for Visual Question Answering","created":"2022-05-16","cited_by_count":14,"area":null},{"id":"2212.13296","title":"VQA and Visual Reasoning: An Overview of Recent Datasets, Methods and Challenges","created":"2022-12-26","cited_by_count":14,"area":"lr"},{"id":"2407.15589","title":"Exploring the Effectiveness of Object-Centric Representations in Visual Question Answering: Comparative Insights with Foundation Models","created":"2024-07-22","cited_by_count":14,"area":null},{"id":"2502.15786","title":"MindLLM: A Subject-Agnostic and Versatile Model for fMRI-to-Text Decoding","created":"2025-02-18","cited_by_count":14,"area":null},{"id":"2109.08475","title":"GoG: Relation-aware Graph-over-Graph Network for Visual Dialog","created":"2021-09-17","cited_by_count":13,"area":null},{"id":"2410.10799","title":"Towards Foundation Models for 3D Vision: How Close Are We?","created":"2024-10-14","cited_by_count":13,"area":null},{"id":"2305.17690","title":"HaVQA: A Dataset for Visual Question Answering and Multimodal Research in Hausa Language","created":"2023-05-28","cited_by_count":12,"area":null},{"id":"2402.18695","title":"Grounding Language Models for Visual Entity Recognition","created":"2024-02-28","cited_by_count":12,"area":null},{"id":"2103.15974","title":"Domain-robust VQA with diverse datasets and methods but no target labels","created":"2021-03-29","cited_by_count":11,"area":null},{"id":"2104.07921","title":"VGNMN: Video-grounded Neural Module Network to Video-Grounded Language Tasks","created":"2021-04-16","cited_by_count":11,"area":null},{"id":"2109.08478","title":"Multimodal Incremental Transformer with Visual Grounding for Visual Dialogue Generation","created":"2021-09-17","cited_by_count":11,"area":null},{"id":"2211.12328","title":"A survey on knowledge-enhanced multimodal learning","created":"2022-11-19","cited_by_count":11,"area":null},{"id":"2303.14423","title":"Task-Attentive Transformer Architecture for Continual Learning of Vision-and-Language Tasks Using Knowledge Distillation","created":"2023-03-25","cited_by_count":11,"area":"distill"},{"id":"2407.04923","title":"OmChat: A Recipe to Train Multimodal Language Models with Strong Long Context and Video Understanding","created":"2024-07-06","cited_by_count":11,"area":"mllm"},{"id":"2109.06013","title":"Learning to Ground Visual Objects for Visual Dialog","created":"2021-09-13","cited_by_count":10,"area":null},{"id":"2306.16713","title":"Answer Mining from a Pool of Images: Towards Retrieval-Based Visual Question Answering","created":"2023-06-29","cited_by_count":10,"area":null},{"id":"2501.03995","title":"RAG-Check: Evaluating Multimodal Retrieval Augmented Generation Performance","created":"2025-01-07","cited_by_count":10,"area":"mllm"},{"id":"2503.14421","title":"ExDDV: A New Dataset for Explainable Deepfake Detection in Video","created":"2025-03-18","cited_by_count":10,"area":null},{"id":"2206.01017","title":"Structured Two-stream Attention Network for Video Question Answering","created":"2022-06-02","cited_by_count":9,"area":null},{"id":"2209.05401","title":"MaXM: Towards Multilingual Visual Question Answering","created":"2022-09-12","cited_by_count":9,"area":null},{"id":"2209.06650","title":"WildQA: In-the-Wild Video Question Answering","created":"2022-09-14","cited_by_count":9,"area":null},{"id":"2304.03147","title":"Improving Visual Question Answering Models through Robustness Analysis and In-Context Learning with a Chain of Basic Questions","created":"2023-04-06","cited_by_count":9,"area":null},{"id":"2503.20502","title":"MLLM-Selector: Necessity and Diversity-driven High-Value Data Selection for Enhanced Visual Instruction Tuning","created":"2025-03-26","cited_by_count":9,"area":"mllm"},{"id":"2203.17219","title":"SimVQA: Exploring Simulated Environments for Visual Question Answering","created":"2022-03-31","cited_by_count":8,"area":null},{"id":"2207.11401","title":"Chunk-aware Alignment and Lexical Constraint for Visual Entailment with Natural Language Explanations","created":"2022-07-23","cited_by_count":8,"area":"mllm"},{"id":"2401.15275","title":"Dynamic Transformer Architecture for Continual Learning of Multimodal Tasks","created":"2024-01-27","cited_by_count":8,"area":null},{"id":"2411.11150","title":"A Comprehensive Survey on Visual Question Answering Datasets and Algorithms","created":"2024-11-17","cited_by_count":8,"area":null},{"id":"2507.16403","title":"ReasonVQA: A Multi-hop Reasoning Benchmark with Structural Knowledge for Visual Question Answering","created":"2025-07-22","cited_by_count":8,"area":"lr"},{"id":"2511.20648","title":"LocateAnything3D: Vision-Language 3D Detection with Chain-of-Sight","created":"2025-11-25","cited_by_count":8,"area":null},{"id":"2206.01923","title":"From Pixels to Objects: Cubic Visual Attention for Visual Question Answering","created":"2022-06-04","cited_by_count":7,"area":null},{"id":"2209.01621","title":"Interactive Question Answering Systems: Literature Review","created":"2022-09-04","cited_by_count":7,"area":null},{"id":"2303.02635","title":"VTQA: Visual Text Question Answering via Entity Alignment and Cross-Media Reasoning","created":"2023-03-05","cited_by_count":7,"area":null},{"id":"2310.14670","title":"Dataset Bias Mitigation in Multiple-Choice Visual Question Answering and Beyond","created":"2023-10-23","cited_by_count":7,"area":null},{"id":"2502.15803","title":"Megrez-Omni Technical Report","created":"2025-02-19","cited_by_count":7,"area":null},{"id":"2510.12750","title":"VQArt-Bench: A semantically rich VQA Benchmark for Art and Cultural Heritage","created":"2025-10-14","cited_by_count":7,"area":"mllm"},{"id":"2510.20818","title":"VAMOS: A Hierarchical Vision-Language-Action Model for Capability-Modulated and Steerable Navigation","created":"2025-10-23","cited_by_count":7,"area":"vla"},{"id":"2302.11752","title":"EVJVQA Challenge: Multilingual Visual Question Answering","created":"2023-02-23","cited_by_count":6,"area":null},{"id":"2308.08628","title":"Learning the meanings of function words from grounded language using a visual question answering model","created":"2023-08-16","cited_by_count":6,"area":null},{"id":"2506.09638","title":"FedVLMBench: Benchmarking Federated Fine-Tuning of Vision-Language Models","created":"2025-06-11","cited_by_count":6,"area":"mllm"},{"id":"2509.17191","title":"VaseVQA: Multimodal Agent and Benchmark for Ancient Greek Pottery","created":"2025-09-21","cited_by_count":6,"area":"agents"},{"id":"2204.07302","title":"Improving Cross-Modal Understanding in Visual Dialog via Contrastive Learning","created":"2022-04-15","cited_by_count":5,"area":null},{"id":"2310.18046","title":"ViCLEVR: A Visual Reasoning Dataset and Hybrid Multimodal Fusion Model for Visual Question Answering in Vietnamese","created":"2023-10-27","cited_by_count":5,"area":"lr"},{"id":"2311.00807","title":"VQA-GEN: A Visual Question Answering Benchmark for Domain Generalization","created":"2023-11-01","cited_by_count":5,"area":"lr"},{"id":"2408.05334","title":"Revisiting Multi-Modal LLM Evaluation","created":"2024-08-09","cited_by_count":5,"area":"mllm"},{"id":"2410.14991","title":"ChitroJera: A Regionally Relevant Visual Question Answering Dataset for Bangla","created":"2024-10-19","cited_by_count":5,"area":null},{"id":"2306.15706","title":"Approximated Prompt Tuning for Vision-Language Pre-trained Models","created":"2023-06-27","cited_by_count":4,"area":"mllm"},{"id":"2402.12846","title":"ConVQG: Contrastive Visual Question Generation with Multimodal Guidance","created":"2024-02-20","cited_by_count":4,"area":null},{"id":"2406.02601","title":"Multimodal Deep Learning for Low-Resource Settings: A Vector Embedding Alignment Approach for Healthcare Applications","created":"2024-06-02","cited_by_count":4,"area":null},{"id":"2503.01261","title":"Towards Improved Text-Aligned Codebook Learning: Multi-Hierarchical Codebook-Text Alignment with Long Text","created":"2025-03-03","cited_by_count":4,"area":null},{"id":"2508.00260","title":"Instruction-Grounded Visual Projectors for Continual Learning of Generative Vision-Language Models","created":"2025-08-01","cited_by_count":4,"area":"mllm"},{"id":"2605.30794","title":"MechVQA: Benchmarking and Enhancing Multimodal LLMs on Comprehensive Mechanical Drawing Understanding","created":"2026-05-29","cited_by_count":4,"area":"mllm"},{"id":"2307.14142","title":"LOIS: Looking Out of Instance Semantics for Visual Question Answering","created":"2023-07-26","cited_by_count":3,"area":null},{"id":"2310.15597","title":"Emergent Communication in Interactive Sketch Question Answering","created":"2023-10-24","cited_by_count":3,"area":null},{"id":"2401.08968","title":"COCO is \"ALL'' You Need for Visual Instruction Fine-tuning","created":"2024-01-17","cited_by_count":3,"area":"mllm"},{"id":"2405.15684","title":"Prompt-Aware Adapter: Towards Learning Adaptive Visual Tokens for Multimodal Large Language Models","created":"2024-05-24","cited_by_count":3,"area":"mllm"},{"id":"2503.07631","title":"OWLViz: An Open-World Benchmark for Visual Question Answering","created":"2025-03-04","cited_by_count":3,"area":null},{"id":"2509.16628","title":"Enhancing Scientific Visual Question Answering via Vision-Caption aware Supervised Fine-Tuning","created":"2025-09-20","cited_by_count":3,"area":"mllm"},{"id":"2104.10139","title":"Towards Solving Multimodal Comprehension","created":"2021-04-20","cited_by_count":2,"area":null},{"id":"2104.14383","title":"Privacy-Preserving Federated Learning on Partitioned Attributes","created":"2021-04-29","cited_by_count":2,"area":null}],"next_cursor":"100"}