{"total":119,"rows":[{"id":"2311.16922","title":"Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding","created":"2023-11-28","cited_by_count":688,"area":"mllm"},{"id":"2102.09542","title":"SLAKE: A Semantically-Labeled Knowledge-Enhanced Dataset for Medical Visual Question Answering","created":"2021-02-18","cited_by_count":449,"area":null},{"id":"2109.13238","title":"Visually Grounded Reasoning across Languages and Cultures","created":"2021-09-28","cited_by_count":189,"area":null},{"id":"2107.07502","title":"MultiBench: Multiscale Benchmarks for Multimodal Representation Learning","created":"2021-07-15","cited_by_count":146,"area":null},{"id":"2107.01372","title":"Learning Debiased Representation via Disentangled Feature Augmentation","created":"2021-07-03","cited_by_count":116,"area":null},{"id":"2209.03430","title":"Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questions","created":"2022-09-07","cited_by_count":116,"area":null},{"id":"2202.05306","title":"Characterizing and overcoming the greedy nature of learning in multi-modal deep neural networks","created":"2022-02-10","cited_by_count":95,"area":null},{"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":"2108.00316","title":"Chest ImaGenome Dataset for Clinical Reasoning","created":"2021-07-31","cited_by_count":90,"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":"2406.12718","title":"Mitigating Object Hallucinations in Large Vision-Language Models with Assembly of Global and Local Attention","created":"2024-06-18","cited_by_count":74,"area":"mllm"},{"id":"2410.15778","title":"Reducing Hallucinations in Vision-Language Models via Latent Space Steering","created":"2024-10-21","cited_by_count":59,"area":"mllm"},{"id":"2409.16597","title":"EventHallusion: Diagnosing Event Hallucinations in Video LLMs","created":"2024-09-25","cited_by_count":57,"area":"mllm"},{"id":"2501.00569","title":"Probing Visual Language Priors in VLMs","created":"2024-12-31","cited_by_count":45,"area":"lr"},{"id":"2112.08359","title":"3D Question Answering","created":"2021-12-15","cited_by_count":41,"area":null},{"id":"2503.13107","title":"ClearSight: Visual Signal Enhancement for Object Hallucination Mitigation in Multimodal Large language Models","created":"2025-03-17","cited_by_count":40,"area":"mllm"},{"id":"2204.09484","title":"Generalizing to the Future: Mitigating Entity Bias in Fake News Detection","created":"2022-04-20","cited_by_count":39,"area":null},{"id":"2204.02285","title":"SwapMix: Diagnosing and Regularizing the Over-Reliance on Visual Context in Visual Question Answering","created":"2022-04-05","cited_by_count":38,"area":null},{"id":"2506.09047","title":"Same Task, Different Circuits: Disentangling Modality-Specific Mechanisms in VLMs","created":"2025-06-10","cited_by_count":35,"area":"mllm"},{"id":"2203.02013","title":"DIME: Fine-grained Interpretations of Multimodal Models via Disentangled Local Explanations","created":"2022-03-03","cited_by_count":34,"area":null},{"id":"2106.01127","title":"Towards Robust Classification Model by Counterfactual and Invariant Data Generation","created":"2021-06-02","cited_by_count":30,"area":null},{"id":"2210.04692","title":"Language Prior Is Not the Only Shortcut: A Benchmark for Shortcut Learning in VQA","created":"2022-10-10","cited_by_count":30,"area":null},{"id":"2505.20862","title":"AVCD: Mitigating Hallucinations in Audio-Visual Large Language Models through Contrastive Decoding","created":"2025-05-27","cited_by_count":30,"area":"mllm"},{"id":"2408.04223","title":"VideoQA in the Era of LLMs: An Empirical Study","created":"2024-08-08","cited_by_count":29,"area":null},{"id":"2109.13986","title":"Symbolic Brittleness in Sequence Models: on Systematic Generalization in Symbolic Mathematics","created":"2021-09-28","cited_by_count":27,"area":null},{"id":"2107.14178","title":"ReFormer: The Relational Transformer for Image Captioning","created":"2021-07-29","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":"2109.08256","title":"Ethics Sheet for Automatic Emotion Recognition and Sentiment Analysis","created":"2021-09-17","cited_by_count":22,"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":"2301.08912","title":"Rationalization for Explainable NLP: A Survey","created":"2023-01-21","cited_by_count":22,"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":"2104.00926","title":"VisQA: X-raying Vision and Language Reasoning in Transformers","created":"2021-04-02","cited_by_count":19,"area":null},{"id":"2202.07280","title":"Saving Dense Retriever from Shortcut Dependency in Conversational Search","created":"2022-02-15","cited_by_count":19,"area":null},{"id":"2205.14594","title":"Revisiting the Importance of Amplifying Bias for Debiasing","created":"2022-05-29","cited_by_count":19,"area":null},{"id":"2312.00935","title":"Understanding Unimodal Bias in Multimodal Deep Linear Networks","created":"2023-12-01","cited_by_count":19,"area":null},{"id":"2106.04605","title":"Check It Again: Progressive Visual Question Answering via Visual Entailment","created":"2021-06-08","cited_by_count":18,"area":null},{"id":"2107.01183","title":"Ethics Sheets for AI Tasks","created":"2021-07-02","cited_by_count":18,"area":null},{"id":"2108.05863","title":"Towers of Babel: Combining Images, Language, and 3D Geometry for Learning Multimodal Vision","created":"2021-08-12","cited_by_count":18,"area":null},{"id":"2203.11130","title":"PACS: A Dataset for Physical Audiovisual CommonSense Reasoning","created":"2022-03-21","cited_by_count":18,"area":"lr"},{"id":"2205.05739","title":"Learning to Retrieve Videos by Asking Questions","created":"2022-05-11","cited_by_count":18,"area":null},{"id":"2207.08739","title":"Rethinking Data Augmentation for Robust Visual Question Answering","created":"2022-07-18","cited_by_count":18,"area":"distill"},{"id":"2104.10283","title":"GraghVQA: Language-Guided Graph Neural Networks for Graph-based Visual Question Answering","created":"2021-04-20","cited_by_count":16,"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":"2111.04104","title":"Uncertainty Calibration for Ensemble-Based Debiasing Methods","created":"2021-11-07","cited_by_count":16,"area":null},{"id":"2204.02380","title":"CLEVR-X: A Visual Reasoning Dataset for Natural Language Explanations","created":"2022-04-05","cited_by_count":16,"area":"lr"},{"id":"2209.08529","title":"Overcoming Language Priors in Visual Question Answering via Distinguishing Superficially Similar Instances","created":"2022-09-18","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":"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":"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":"2110.00519","title":"Calibrating Concepts and Operations: Towards Symbolic Reasoning on Real Images","created":"2021-10-01","cited_by_count":14,"area":null},{"id":"2210.04643","title":"Critical Learning Periods for Multisensory Integration in Deep Networks","created":"2022-10-06","cited_by_count":14,"area":null},{"id":"2101.00151","title":"DVD: A Diagnostic Dataset for Multi-step Reasoning in Video Grounded Dialogue","created":"2021-01-01","cited_by_count":13,"area":null},{"id":"2109.04653","title":"Towards Developing a Multilingual and Code-Mixed Visual Question Answering System by Knowledge Distillation","created":"2021-09-10","cited_by_count":13,"area":"distill"},{"id":"2208.00690","title":"Generative Bias for Robust Visual Question Answering","created":"2022-08-01","cited_by_count":12,"area":null},{"id":"2304.06354","title":"ODAM: Gradient-based instance-specific visual explanations for object detection","created":"2023-04-13","cited_by_count":12,"area":null},{"id":"2408.08074","title":"A Survey on Integrated Sensing, Communication, and Computation","created":"2024-08-15","cited_by_count":12,"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":"2107.11576","title":"X-GGM: Graph Generative Modeling for Out-of-Distribution Generalization in Visual Question Answering","created":"2021-07-24","cited_by_count":10,"area":null},{"id":"2212.05421","title":"Feature-Level Debiased Natural Language Understanding","created":"2022-12-11","cited_by_count":10,"area":null},{"id":"2210.04563","title":"Towards Robust Visual Question Answering: Making the Most of Biased Samples via Contrastive Learning","created":"2022-10-10","cited_by_count":9,"area":null},{"id":"2305.06407","title":"Combo of Thinking and Observing for Outside-Knowledge VQA","created":"2023-05-10","cited_by_count":9,"area":null},{"id":"2401.07803","title":"Uncovering the Full Potential of Visual Grounding Methods in VQA","created":"2024-01-15","cited_by_count":9,"area":null},{"id":"2202.07630","title":"Delving Deeper into Cross-lingual Visual Question Answering","created":"2022-02-15","cited_by_count":8,"area":null},{"id":"2305.15015","title":"Measuring Faithful and Plausible Visual Grounding in VQA","created":"2023-05-24","cited_by_count":8,"area":null},{"id":"2306.08889","title":"Dissecting Multimodality in VideoQA Transformer Models by Impairing Modality Fusion","created":"2023-06-15","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":"2105.07698","title":"Automatic Fake News Detection: Are Models Learning to Reason?","created":"2021-05-17","cited_by_count":7,"area":null},{"id":"2111.14730","title":"Understanding Out-of-distribution: A Perspective of Data Dynamics","created":"2021-11-29","cited_by_count":7,"area":null},{"id":"2405.11685","title":"ColorFoil: Investigating Color Blindness in Large Vision and Language Models","created":"2024-05-19","cited_by_count":7,"area":null},{"id":"2607.03647","title":"Do Medical Vision Language Models Actually See? A Counterfactual Grounding Framework and Hard-Negative Contrastive Training for Visually-Reliant Medical VLMs","created":"2026-07-04","cited_by_count":7,"area":"mllm"},{"id":"2109.08048","title":"Raising context awareness in motion forecasting","created":"2021-09-16","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":"2201.11014","title":"Language-biased image classification: evaluation based on semantic representations","created":"2022-01-26","cited_by_count":5,"area":null},{"id":"2305.07216","title":"Versatile audio-visual learning for emotion recognition","created":"2023-05-12","cited_by_count":5,"area":null},{"id":"2404.00973","title":"VideoDistill: Language-aware Vision Distillation for Video Question Answering","created":"2024-04-01","cited_by_count":5,"area":null},{"id":"2406.18253","title":"On the Role of Visual Grounding in VQA","created":"2024-06-26","cited_by_count":5,"area":null},{"id":"2110.13110","title":"Diagnosing Errors in Video Relation Detectors","created":"2021-10-25","cited_by_count":4,"area":null},{"id":"2311.16941","title":"Debiasing Multimodal Models via Causal Information Minimization","created":"2023-11-28","cited_by_count":4,"area":null},{"id":"2404.18413","title":"3AM: An Ambiguity-Aware Multi-Modal Machine Translation Dataset","created":"2024-04-29","cited_by_count":4,"area":null},{"id":"2506.17587","title":"HalluRNN: Mitigating Hallucinations via Recurrent Cross-Layer Reasoning in Large Vision-Language Models","created":"2025-06-21","cited_by_count":4,"area":"lr"},{"id":"2509.25339","title":"VisualOverload: Probing Visual Understanding of VLMs in Really Dense Scenes","created":"2025-09-29","cited_by_count":4,"area":null},{"id":"2510.04141","title":"The Artificial Intelligence Cognitive Examination: A Survey on the Evolution of Multimodal Evaluation from Recognition to Reasoning","created":"2025-10-05","cited_by_count":4,"area":"lr"},{"id":"2106.06147","title":"NAAQA: A Neural Architecture for Acoustic Question Answering","created":"2021-06-11","cited_by_count":3,"area":null},{"id":"2106.13445","title":"A Picture May Be Worth a Hundred Words for Visual Question Answering","created":"2021-06-25","cited_by_count":3,"area":null},{"id":"2201.05017","title":"Towards Automated Error Analysis: Learning to Characterize Errors","created":"2022-01-13","cited_by_count":3,"area":null},{"id":"2306.11386","title":"Did the Models Understand Documents? Benchmarking Models for Language Understanding in Document-Level Relation Extraction","created":"2023-06-20","cited_by_count":3,"area":null},{"id":"2602.00621","title":"Towards Interpretable Hallucination Analysis and Mitigation in LVLMs via Contrastive Neuron Steering","created":"2026-01-31","cited_by_count":3,"area":"mechinterp"},{"id":"2109.00077","title":"Interactive Machine Comprehension with Dynamic Knowledge Graphs","created":"2021-08-31","cited_by_count":2,"area":null},{"id":"2110.05159","title":"Beyond Accuracy: A Consolidated Tool for Visual Question Answering Benchmarking","created":"2021-10-11","cited_by_count":2,"area":null},{"id":"2211.13331","title":"Using Focal Loss to Fight Shallow Heuristics: An Empirical Analysis of Modulated Cross-Entropy in Natural Language Inference","created":"2022-11-23","cited_by_count":2,"area":null},{"id":"2305.19769","title":"Attention-Based Methods For Audio Question Answering","created":"2023-05-31","cited_by_count":2,"area":null},{"id":"2309.02691","title":"A Joint Study of Phrase Grounding and Task Performance in Vision and Language Models","created":"2023-09-06","cited_by_count":2,"area":null},{"id":"2309.04162","title":"GLS-CSC: A Simple but Effective Strategy to Mitigate Chinese STM Models' Over-Reliance on Superficial Clue","created":"2023-09-08","cited_by_count":2,"area":null},{"id":"2605.16403","title":"When Vision Speaks for Sound","created":"2026-05-13","cited_by_count":2,"area":null},{"id":"2201.03965","title":"On the Efficacy of Co-Attention Transformer Layers in Visual Question Answering","created":"2022-01-11","cited_by_count":1,"area":null},{"id":"2206.03680","title":"Improving Evaluation of Debiasing in Image Classification","created":"2022-06-08","cited_by_count":1,"area":null},{"id":"2210.02095","title":"ChemAlgebra: Algebraic Reasoning on Chemical Reactions","created":"2022-10-05","cited_by_count":1,"area":null},{"id":"2301.12032","title":"BinaryVQA: A Versatile Test Set to Evaluate the Out-of-Distribution Generalization of VQA Models","created":"2023-01-28","cited_by_count":1,"area":null},{"id":"2305.15087","title":"Pento-DIARef: A Diagnostic Dataset for Learning the Incremental Algorithm for Referring Expression Generation from Examples","created":"2023-05-24","cited_by_count":1,"area":null},{"id":"2312.01575","title":"A Challenging Multimodal Video Summary: Simultaneously Extracting and Generating Keyframe-Caption Pairs from Video","created":"2023-12-04","cited_by_count":1,"area":null}],"next_cursor":"100"}