{"total":105,"rows":[{"id":"2308.13418","title":"Nougat: Neural Optical Understanding for Academic Documents","created":"2023-08-25","cited_by_count":245,"area":null},{"id":"2206.09391","title":"Towards Adversarial Attack on Vision-Language Pre-training Models","created":"2022-06-19","cited_by_count":144,"area":"mllm"},{"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":"2204.13631","title":"Reliable Visual Question Answering: Abstain Rather Than Answer Incorrectly","created":"2022-04-28","cited_by_count":89,"area":null},{"id":"2110.06465","title":"Breaking the Dilemma of Medical Image-to-image Translation","created":"2021-10-13","cited_by_count":82,"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":"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":"2104.03149","title":"Beyond Question-Based Biases: Assessing Multimodal Shortcut Learning in Visual Question Answering","created":"2021-04-07","cited_by_count":71,"area":null},{"id":"2108.10008","title":"BiaSwap: Removing dataset bias with bias-tailored swapping augmentation","created":"2021-08-23","cited_by_count":70,"area":null},{"id":"2205.01883","title":"All You May Need for VQA are Image Captions","created":"2022-05-04","cited_by_count":65,"area":null},{"id":"2107.00758","title":"The Spotlight: A General Method for Discovering Systematic Errors in Deep Learning Models","created":"2021-07-01","cited_by_count":63,"area":null},{"id":"2106.02280","title":"Human-Adversarial Visual Question Answering","created":"2021-06-04","cited_by_count":57,"area":null},{"id":"2305.03689","title":"COLA: A Benchmark for Compositional Text-to-image Retrieval","created":"2023-05-05","cited_by_count":53,"area":"mllm"},{"id":"2203.16586","title":"Counterfactual Cycle-Consistent Learning for Instruction Following and Generation in Vision-Language Navigation","created":"2022-03-30","cited_by_count":51,"area":null},{"id":"2303.16604","title":"Bi-directional Training for Composed Image Retrieval via Text Prompt Learning","created":"2023-03-29","cited_by_count":43,"area":null},{"id":"2101.12059","title":"VX2TEXT: End-to-End Learning of Video-Based Text Generation From Multimodal Inputs","created":"2021-01-28","cited_by_count":42,"area":null},{"id":"2312.02896","title":"BenchLMM: Benchmarking Cross-style Visual Capability of Large Multimodal Models","created":"2023-12-05","cited_by_count":41,"area":"lr"},{"id":"2406.05491","title":"One Perturbation is Enough: On Generating Universal Adversarial Perturbations against Vision-Language Pre-training Models","created":"2024-06-08","cited_by_count":40,"area":"mllm"},{"id":"2208.14882","title":"Hierarchical Local-Global Transformer for Temporal Sentence Grounding","created":"2022-08-31","cited_by_count":38,"area":null},{"id":"2104.08161","title":"Back to Square One: Artifact Detection, Training and Commonsense Disentanglement in the Winograd Schema","created":"2021-04-16","cited_by_count":32,"area":null},{"id":"2201.05729","title":"CLIP-TD: CLIP Targeted Distillation for Vision-Language Tasks","created":"2022-01-15","cited_by_count":32,"area":null},{"id":"2404.10193","title":"Consistency and Uncertainty: Identifying Unreliable Responses From Black-Box Vision-Language Models for Selective Visual Question Answering","created":"2024-04-16","cited_by_count":32,"area":"mllm"},{"id":"2205.05019","title":"Learning to Answer Visual Questions from Web Videos","created":"2022-05-10","cited_by_count":30,"area":null},{"id":"2408.04223","title":"VideoQA in the Era of LLMs: An Empirical Study","created":"2024-08-08","cited_by_count":29,"area":null},{"id":"2508.17298","title":"Explain Before You Answer: A Survey on Compositional Visual Reasoning","created":"2025-08-24","cited_by_count":28,"area":"lr"},{"id":"2410.15334","title":"Modality-Fair Preference Optimization for Trustworthy MLLM Alignment","created":"2024-10-20","cited_by_count":26,"area":"mllm"},{"id":"2107.09106","title":"Separating Skills and Concepts for Novel Visual Question Answering","created":"2021-07-19","cited_by_count":24,"area":null},{"id":"2204.10496","title":"Multimodal Adaptive Distillation for Leveraging Unimodal Encoders for Vision-Language Tasks","created":"2022-04-22","cited_by_count":23,"area":null},{"id":"2307.11471","title":"Robust Visual Question Answering: Datasets, Methods, and Future Challenges","created":"2023-07-21","cited_by_count":23,"area":null},{"id":"2110.01013","title":"Counterfactual Samples Synthesizing and Training for Robust Visual Question Answering","created":"2021-10-03","cited_by_count":22,"area":null},{"id":"2410.08695","title":"Dynamic Multimodal Evaluation with Flexible Complexity by Vision-Language Bootstrapping","created":"2024-10-11","cited_by_count":22,"area":"mllm"},{"id":"2506.02095","title":"Cycle Consistency as Reward: Learning Image-Text Alignment without Human Preferences","created":"2025-06-02","cited_by_count":22,"area":"alignment"},{"id":"2405.14974","title":"LOVA3: Learning to Visual Question Answering, Asking and Assessment","created":"2024-05-23","cited_by_count":21,"area":null},{"id":"2109.13139","title":"Multimodal Integration of Human-Like Attention in Visual Question Answering","created":"2021-09-27","cited_by_count":20,"area":null},{"id":"2210.13626","title":"VLC-BERT: Visual Question Answering with Contextualized Commonsense Knowledge","created":"2022-10-24","cited_by_count":20,"area":null},{"id":"2306.03932","title":"Q: How to Specialize Large Vision-Language Models to Data-Scarce VQA Tasks? A: Self-Train on Unlabeled Images!","created":"2023-06-06","cited_by_count":19,"area":"mllm"},{"id":"2105.14300","title":"LPF: A Language-Prior Feedback Objective Function for De-biased Visual Question Answering","created":"2021-05-29","cited_by_count":17,"area":null},{"id":"2209.11000","title":"Selecting Better Samples from Pre-trained LLMs: A Case Study on Question Generation","created":"2022-09-22","cited_by_count":17,"area":null},{"id":"2109.13116","title":"VQA-MHUG: A Gaze Dataset to Study Multimodal Neural Attention in Visual Question Answering","created":"2021-09-27","cited_by_count":16,"area":null},{"id":"2106.04484","title":"Are VQA Systems RAD? Measuring Robustness to Augmented Data with Focused Interventions","created":"2021-06-08","cited_by_count":15,"area":null},{"id":"2204.07190","title":"Measuring Compositional Consistency for Video Question Answering","created":"2022-04-14","cited_by_count":15,"area":null},{"id":"2410.20883","title":"Improving Generalization in Visual Reasoning via Self-Ensemble","created":"2024-10-28","cited_by_count":15,"area":"lr"},{"id":"2109.06122","title":"Discovering the Unknown Knowns: Turning Implicit Knowledge in the Dataset into Explicit Training Examples for Visual Question Answering","created":"2021-09-13","cited_by_count":14,"area":null},{"id":"2208.02080","title":"A Feature-space Multimodal Data Augmentation Technique for Text-video Retrieval","created":"2022-08-03","cited_by_count":13,"area":null},{"id":"2211.07516","title":"Why Did the Chicken Cross the Road? Rephrasing and Analyzing Ambiguous Questions in VQA","created":"2022-11-14","cited_by_count":13,"area":null},{"id":"2105.12932","title":"Contrastive Fine-tuning Improves Robustness for Neural Rankers","created":"2021-05-27","cited_by_count":12,"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":"2310.17050","title":"Exploring Question Decomposition for Zero-Shot VQA","created":"2023-10-25","cited_by_count":12,"area":null},{"id":"2412.13989","title":"What makes a good metric? Evaluating automatic metrics for text-to-image consistency","created":"2024-12-18","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":"2203.07613","title":"CARETS: A Consistency And Robustness Evaluative Test Suite for VQA","created":"2022-03-15","cited_by_count":11,"area":null},{"id":"2206.01909","title":"Toward Learning Robust and Invariant Representations with Alignment Regularization and Data Augmentation","created":"2022-06-04","cited_by_count":11,"area":null},{"id":"2502.15895","title":"Directional Gradient Projection for Robust Fine-Tuning of Foundation Models","created":"2025-02-21","cited_by_count":11,"area":null},{"id":"2105.05391","title":"News Headline Grouping as a Challenging NLU Task","created":"2021-05-12","cited_by_count":10,"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":"2209.08860","title":"A Survey of Deep Causal Models and Their Industrial Applications","created":"2022-09-19","cited_by_count":10,"area":null},{"id":"2411.01713","title":"Rethinking Weight Decay for Robust Fine-Tuning of Foundation Models","created":"2024-11-03","cited_by_count":9,"area":null},{"id":"2110.11205","title":"Robustness through Data Augmentation Loss Consistency","created":"2021-10-21","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":"2105.04780","title":"Cross-Modal Generative Augmentation for Visual Question Answering","created":"2021-05-11","cited_by_count":7,"area":null},{"id":"2209.06954","title":"Correlation Information Bottleneck: Towards Adapting Pretrained Multimodal Models for Robust Visual Question Answering","created":"2022-09-14","cited_by_count":7,"area":"mllm"},{"id":"2304.10727","title":"RoCOCO: Robustness Benchmark of MS-COCO to Stress-test Image-Text Matching Models","created":"2023-04-21","cited_by_count":7,"area":"mllm"},{"id":"2306.02204","title":"Cycle Consistency Driven Object Discovery","created":"2023-06-03","cited_by_count":7,"area":null},{"id":"2308.07575","title":"Story Visualization by Online Text Augmentation with Context Memory","created":"2023-08-15","cited_by_count":7,"area":null},{"id":"2108.12510","title":"Pulling Up by the Causal Bootstraps: Causal Data Augmentation for Pre-training Debiasing","created":"2021-08-27","cited_by_count":6,"area":null},{"id":"2112.04453","title":"MLP Architectures for Vision-and-Language Modeling: An Empirical Study","created":"2021-12-08","cited_by_count":6,"area":null},{"id":"2303.09427","title":"Logical Implications for Visual Question Answering Consistency","created":"2023-03-16","cited_by_count":6,"area":"lr"},{"id":"2312.15162","title":"Cycle-Consistency Learning for Captioning and Grounding","created":"2023-12-23","cited_by_count":6,"area":null},{"id":"2103.14785","title":"A Comprehensive Review of the Video-to-Text Problem","created":"2021-03-27","cited_by_count":5,"area":null},{"id":"2210.10020","title":"ULN: Towards Underspecified Vision-and-Language Navigation","created":"2022-10-18","cited_by_count":5,"area":null},{"id":"2408.05334","title":"Revisiting Multi-Modal LLM Evaluation","created":"2024-08-09","cited_by_count":5,"area":"mllm"},{"id":"2503.03651","title":"DoraCycle: Domain-Oriented Adaptation of Unified Generative Model in Multimodal Cycles","created":"2025-03-05","cited_by_count":5,"area":null},{"id":"2505.21755","title":"FRAMES-VQA: Benchmarking Fine-Tuning Robustness across Multi-Modal Shifts in Visual Question Answering","created":"2025-05-27","cited_by_count":5,"area":null},{"id":"2602.18057","title":"Temporal Consistency-Aware Text-to-Motion Generation","created":"2026-02-20","cited_by_count":5,"area":null},{"id":"2403.19080","title":"MMCert: Provable Defense against Adversarial Attacks to Multi-modal Models","created":"2024-03-28","cited_by_count":4,"area":null},{"id":"2407.12842","title":"MS2SL: Multimodal Spoken Data-Driven Continuous Sign Language Production","created":"2024-07-04","cited_by_count":4,"area":null},{"id":"2410.11639","title":"Efficient and Effective Universal Adversarial Attack against Vision-Language Pre-training Models","created":"2024-10-15","cited_by_count":4,"area":"mllm"},{"id":"2602.21428","title":"PSF-Med: Measuring and Explaining Paraphrase Sensitivity in Medical Vision Language Models","created":"2026-02-24","cited_by_count":4,"area":"mllm"},{"id":"2305.10143","title":"An Empirical Study on the Language Modal in Visual Question Answering","created":"2023-05-17","cited_by_count":3,"area":null},{"id":"2305.11769","title":"Enhancing Vision-Language Pre-Training with Jointly Learned Questioner and Dense Captioner","created":"2023-05-19","cited_by_count":3,"area":"mllm"},{"id":"2510.22171","title":"HARMONY: Hidden Activation Representations and Model Output-Aware Uncertainty Estimation for Vision-Language Models","created":"2025-10-25","cited_by_count":3,"area":"mllm"},{"id":"2601.16400","title":"Clarify or Answer: Reinforcement Learning for Agentic VQA with Context Under-specification","created":"2026-01-23","cited_by_count":3,"area":"agents"},{"id":"2303.16133","title":"Exposing and Addressing Cross-Task Inconsistency in Unified Vision-Language Models","created":"2023-03-28","cited_by_count":2,"area":"mllm"},{"id":"2305.03971","title":"Adaptive loose optimization for robust question answering","created":"2023-05-06","cited_by_count":2,"area":null},{"id":"2305.13208","title":"Iterative Adversarial Attack on Image-guided Story Ending Generation","created":"2023-05-16","cited_by_count":2,"area":null},{"id":"2510.21182","title":"KBE-DME: Dynamic Multimodal Evaluation via Knowledge Enhanced Benchmark Evolution","created":"2025-10-24","cited_by_count":2,"area":"mllm"},{"id":"2603.00148","title":"Mechanistically Guided LoRA Improves Paraphrase Consistency in Medical Vision-Language Models","created":"2026-02-24","cited_by_count":2,"area":"mllm"},{"id":"2105.03943","title":"gComm: An environment for investigating generalization in Grounded Language Acquisition","created":"2021-05-09","cited_by_count":1,"area":null},{"id":"2307.10405","title":"Generative Visual Question Answering","created":"2023-07-18","cited_by_count":1,"area":null},{"id":"2309.12224","title":"Towards Answering Health-related Questions from Medical Videos: Datasets and Approaches","created":"2023-09-21","cited_by_count":1,"area":null},{"id":"2407.05100","title":"Ask Questions with Double Hints: Visual Question Generation with Answer-awareness and Region-reference","created":"2024-07-06","cited_by_count":1,"area":null},{"id":"2411.00898","title":"Replace-then-Perturb: Targeted Adversarial Attacks With Visual Reasoning for Vision-Language Models","created":"2024-11-01","cited_by_count":1,"area":"lr"},{"id":"2412.13636","title":"Consistency of Compositional Generalization across Multiple Levels","created":"2024-12-18","cited_by_count":1,"area":null},{"id":"2508.12430","title":"Adversarial Attacks on VQA-NLE: Exposing and Alleviating Inconsistencies in Visual Question Answering Explanations","created":"2025-08-17","cited_by_count":1,"area":null},{"id":"2607.01503","title":"Disentangling Pictorial Cue Understanding from Language Bias in VLMs via Depth Ordering Task","created":"2026-07-01","cited_by_count":1,"area":"mllm"},{"id":"2407.10373","title":"Mutual Learning for Acoustic Matching and Dereverberation via Visual Scene-driven Diffusion","created":"2024-07-15","cited_by_count":0,"area":"diffusion"},{"id":"2506.12394","title":"LARGO: Low-Rank Regulated Gradient Projection for Robust Parameter Efficient Fine-Tuning","created":"2025-06-14","cited_by_count":0,"area":null},{"id":"2601.21220","title":"LAMP: Learning Universal Adversarial Perturbations for Multi-Image Tasks via Pre-trained Models","created":"2026-01-29","cited_by_count":0,"area":"mllm"},{"id":"2605.07919","title":"MedVIGIL: Evaluating Trustworthy Medical VLMs Under Broken Visual Evidence","created":"2026-05-08","cited_by_count":0,"area":null}],"next_cursor":"100"}