{"total":174,"rows":[{"id":"2410.19168","title":"MMAU: A Massive Multi-Task Audio Understanding and Reasoning Benchmark","created":"2024-10-24","cited_by_count":288,"area":"lr"},{"id":"2107.07502","title":"MultiBench: Multiscale Benchmarks for Multimodal Representation Learning","created":"2021-07-15","cited_by_count":146,"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":"2209.06293","title":"Do Androids Laugh at Electric Sheep? Humor \"Understanding\" Benchmarks from The New Yorker Caption Contest","created":"2022-09-13","cited_by_count":98,"area":null},{"id":"2302.12247","title":"Quantifying & Modeling Multimodal Interactions: An Information Decomposition Framework","created":"2023-02-23","cited_by_count":83,"area":null},{"id":"2104.00783","title":"Action-Based Conversations Dataset: A Corpus for Building More In-Depth Task-Oriented Dialogue Systems","created":"2021-04-01","cited_by_count":75,"area":null},{"id":"2306.05268","title":"Factorized Contrastive Learning: Going Beyond Multi-view Redundancy","created":"2023-06-08","cited_by_count":75,"area":null},{"id":"2409.07402","title":"What to align in multimodal contrastive learning?","created":"2024-09-11","cited_by_count":47,"area":null},{"id":"2402.12786","title":"Advancing Large Language Models to Capture Varied Speaking Styles and Respond Properly in Spoken Conversations","created":"2024-02-20","cited_by_count":45,"area":null},{"id":"2210.07185","title":"On the Utility of Self-supervised Models for Prosody-related Tasks","created":"2022-10-13","cited_by_count":42,"area":null},{"id":"2209.04355","title":"MIntRec: A New Dataset for Multimodal Intent Recognition","created":"2022-09-09","cited_by_count":41,"area":null},{"id":"2410.02678","title":"Distilling an End-to-End Voice Assistant Without Instruction Training Data","created":"2024-10-03","cited_by_count":39,"area":null},{"id":"2110.10949","title":"Multimodal Learning using Optimal Transport for Sarcasm and Humor Detection","created":"2021-10-21","cited_by_count":37,"area":null},{"id":"2203.08055","title":"Modular and Parameter-Efficient Multimodal Fusion with Prompting","created":"2022-03-15","cited_by_count":35,"area":null},{"id":"2306.14899","title":"FunQA: Towards Surprising Video Comprehension","created":"2023-06-26","cited_by_count":35,"area":null},{"id":"2105.09984","title":"Multi-modal Sarcasm Detection and Humor Classification in Code-mixed Conversations","created":"2021-05-20","cited_by_count":33,"area":null},{"id":"2203.06419","title":"When did you become so smart, oh wise one?! Sarcasm Explanation in Multi-modal Multi-party Dialogues","created":"2022-03-12","cited_by_count":33,"area":null},{"id":"2303.00733","title":"SpeechPrompt v2: Prompt Tuning for Speech Classification Tasks","created":"2023-03-01","cited_by_count":32,"area":null},{"id":"2502.04424","title":"EmoBench-M: Benchmarking Emotional Intelligence for Multimodal Large Language Models","created":"2025-02-06","cited_by_count":32,"area":"mllm"},{"id":"2502.16282","title":"Understanding the Emergence of Multimodal Representation Alignment","created":"2025-02-22","cited_by_count":31,"area":null},{"id":"2206.02119","title":"A Multimodal Corpus for Emotion Recognition in Sarcasm","created":"2022-06-05","cited_by_count":29,"area":null},{"id":"2312.09818","title":"SMILE: Multimodal Dataset for Understanding Laughter in Video with Language Models","created":"2023-12-15","cited_by_count":28,"area":null},{"id":"2112.04873","title":"Nice perfume. How long did you marinate in it? Multimodal Sarcasm Explanation","created":"2021-12-09","cited_by_count":25,"area":null},{"id":"2312.15316","title":"Paralinguistics-Enhanced Large Language Modeling of Spoken Dialogue","created":"2023-12-23","cited_by_count":25,"area":null},{"id":"2306.04539","title":"Multimodal Learning Without Labeled Multimodal Data: Guarantees and Applications","created":"2023-06-07","cited_by_count":21,"area":null},{"id":"2311.09580","title":"MMoE: Enhancing Multimodal Models with Mixtures of Multimodal Interaction Experts","created":"2023-11-16","cited_by_count":21,"area":null},{"id":"2410.18882","title":"A Survey of Multimodal Sarcasm Detection","created":"2024-10-24","cited_by_count":19,"area":null},{"id":"2105.09601","title":"See, Hear, Read: Leveraging Multimodality with Guided Attention for Abstractive Text Summarization","created":"2021-05-20","cited_by_count":18,"area":null},{"id":"2404.09403","title":"Neuro-Inspired Information-Theoretic Hierarchical Perception for Multimodal Learning","created":"2024-04-15","cited_by_count":18,"area":null},{"id":"2402.11281","title":"Can Large Multimodal Models Uncover Deep Semantics Behind Images?","created":"2024-02-17","cited_by_count":17,"area":"mllm"},{"id":"2406.08068","title":"Large Language Models Meet Text-Centric Multimodal Sentiment Analysis: A Survey","created":"2024-06-12","cited_by_count":16,"area":null},{"id":"2407.21491","title":"Generative Expressive Conversational Speech Synthesis","created":"2024-07-31","cited_by_count":16,"area":null},{"id":"2407.17152","title":"XMeCap: Meme Caption Generation with Sub-Image Adaptability","created":"2024-07-24","cited_by_count":14,"area":null},{"id":"2511.12121","title":"To Align or Not to Align: Strategic Multimodal Representation Alignment for Optimal Performance","created":"2025-11-15","cited_by_count":14,"area":null},{"id":"2310.14159","title":"Can Language Models Laugh at YouTube Short-form Videos?","created":"2023-10-22","cited_by_count":11,"area":null},{"id":"2306.04125","title":"Multimodal Fusion Interactions: A Study of Human and Automatic Quantification","created":"2023-06-07","cited_by_count":9,"area":null},{"id":"2310.02973","title":"UniverSLU: Universal Spoken Language Understanding for Diverse Tasks with Natural Language Instructions","created":"2023-10-04","cited_by_count":9,"area":null},{"id":"2401.04210","title":"FunnyNet-W: Multimodal Learning of Funny Moments in Videos in the Wild","created":"2024-01-08","cited_by_count":9,"area":null},{"id":"2405.19041","title":"BLSP-KD: Bootstrapping Language-Speech Pre-training via Knowledge Distillation","created":"2024-05-29","cited_by_count":9,"area":"synth"},{"id":"2409.13592","title":"YesBut: A High-Quality Annotated Multimodal Dataset for evaluating Satire Comprehension capability of Vision-Language Models","created":"2024-09-20","cited_by_count":9,"area":"mllm"},{"id":"2504.16427","title":"Can Large Language Models Help Multimodal Language Analysis? MMLA: A Comprehensive Benchmark","created":"2025-04-23","cited_by_count":9,"area":null},{"id":"2508.07959","title":"Large Language Models for Subjective Language Understanding: A Survey","created":"2025-08-11","cited_by_count":9,"area":null},{"id":"2105.05542","title":"!Qu\\'e maravilla! Multimodal Sarcasm Detection in Spanish: a Dataset and a Baseline","created":"2021-05-12","cited_by_count":8,"area":null},{"id":"2107.08248","title":"Learning De-identified Representations of Prosody from Raw Audio","created":"2021-07-17","cited_by_count":8,"area":null},{"id":"2109.05522","title":"TEASEL: A Transformer-Based Speech-Prefixed Language Model","created":"2021-09-12","cited_by_count":8,"area":null},{"id":"2312.04642","title":"On Sarcasm Detection with OpenAI GPT-based Models","created":"2023-12-07","cited_by_count":8,"area":null},{"id":"2502.15919","title":"Mind the Gap! Static and Interactive Evaluations of Large Audio Models","created":"2025-02-21","cited_by_count":8,"area":null},{"id":"2602.00971","title":"Unveiling the Cognitive Compass: Theory-of-Mind-Guided Multimodal Emotion Reasoning","created":"2026-02-01","cited_by_count":8,"area":"lr"},{"id":"2310.01430","title":"Sarcasm in Sight and Sound: Benchmarking and Expansion to Improve Multimodal Sarcasm Detection","created":"2023-09-29","cited_by_count":7,"area":null},{"id":"2312.16023","title":"DocMSU: A Comprehensive Benchmark for Document-level Multimodal Sarcasm Understanding","created":"2023-12-26","cited_by_count":7,"area":null},{"id":"2403.11311","title":"Mixture-of-Prompt-Experts for Multi-modal Semantic Understanding","created":"2024-03-17","cited_by_count":7,"area":null},{"id":"2509.25270","title":"InfMasking: Unleashing Synergistic Information by Contrastive Multimodal Interactions","created":"2025-09-28","cited_by_count":7,"area":null},{"id":"2511.21331","title":"The More, the Merrier: Contrastive Fusion for Higher-Order Multimodal Alignment","created":"2025-11-26","cited_by_count":7,"area":null},{"id":"2109.15153","title":"Multi-Modal Sarcasm Detection Based on Contrastive Attention Mechanism","created":"2021-09-30","cited_by_count":6,"area":null},{"id":"2205.03313","title":"Combining Humor and Sarcasm for Improving Political Parody Detection","created":"2022-05-06","cited_by_count":6,"area":null},{"id":"2209.04712","title":"A Survey in Automatic Irony Processing: Linguistic, Cognitive, and Multi-X Perspectives","created":"2022-09-10","cited_by_count":6,"area":null},{"id":"2211.11049","title":"Explaining (Sarcastic) Utterances to Enhance Affect Understanding in Multimodal Dialogues","created":"2022-11-20","cited_by_count":6,"area":null},{"id":"2212.10522","title":"Transformers Go for the LOLs: Generating (Humourous) Titles from Scientific Abstracts End-to-End","created":"2022-12-20","cited_by_count":6,"area":null},{"id":"2303.15430","title":"TextMI: Textualize Multimodal Information for Integrating Non-verbal Cues in Pre-trained Language Models","created":"2023-03-27","cited_by_count":6,"area":null},{"id":"2402.01759","title":"Systematic Literature Review: Computational Approaches for Humour Style Classification","created":"2024-01-30","cited_by_count":6,"area":null},{"id":"2402.03658","title":"Sentiment-enhanced Graph-based Sarcasm Explanation in Dialogue","created":"2024-02-06","cited_by_count":6,"area":null},{"id":"2502.18331","title":"BottleHumor: Self-Informed Humor Explanation using the Information Bottleneck Principle","created":"2025-02-22","cited_by_count":6,"area":null},{"id":"2510.04899","title":"Human Behavior Atlas: Benchmarking Unified Psychological and Social Behavior Understanding","created":"2025-10-06","cited_by_count":6,"area":null},{"id":"2211.01889","title":"When to Laugh and How Hard? A Multimodal Approach to Detecting Humor and its Intensity","created":"2022-11-03","cited_by_count":5,"area":null},{"id":"2310.12477","title":"Exploring In-Context Learning of Textless Speech Language Model for Speech Classification Tasks","created":"2023-10-19","cited_by_count":5,"area":null},{"id":"2403.10568","title":"MoPE: Mixture of Prompt Experts for Parameter-Efficient and Scalable Multimodal Fusion","created":"2024-03-14","cited_by_count":5,"area":null},{"id":"2404.06357","title":"Generalizable Sarcasm Detection Is Just Around The Corner, Of Course!","created":"2024-04-09","cited_by_count":5,"area":null},{"id":"2410.02086","title":"Anchors Aweigh! Sail for Optimal Unified Multi-Modal Representations","created":"2024-10-02","cited_by_count":5,"area":null},{"id":"2412.11906","title":"PunchBench: Benchmarking MLLMs in Multimodal Punchline Comprehension","created":"2024-12-16","cited_by_count":5,"area":null},{"id":"2412.18733","title":"Intra- and Inter-modal Context Interaction Modeling for Conversational Speech Synthesis","created":"2024-12-25","cited_by_count":5,"area":null},{"id":"2509.12248","title":"Humor in Pixels: Benchmarking Large Multimodal Models Understanding of Online Comics","created":"2025-09-12","cited_by_count":5,"area":"mllm"},{"id":"2509.15361","title":"Beyond Spurious Signals: Debiasing Multimodal Large Language Models via Counterfactual Inference and Adaptive Expert Routing","created":"2025-09-18","cited_by_count":5,"area":"lr"},{"id":"2510.04417","title":"Partial Information Decomposition via Normalizing Flows in Latent Gaussian Distributions","created":"2025-10-06","cited_by_count":5,"area":null},{"id":"2510.23727","title":"MUStReason: A Benchmark for Diagnosing Pragmatic Reasoning in Video-LMs for Multimodal Sarcasm Detection","created":"2025-10-27","cited_by_count":5,"area":null},{"id":"2602.17598","title":"The Cascade Equivalence Hypothesis: When Do Speech LLMs Behave Like ASR$\\rightarrow$LLM Pipelines?","created":"2026-02-19","cited_by_count":5,"area":null},{"id":"2106.04853","title":"DravidianMultiModality: A Dataset for Multi-modal Sentiment Analysis in Tamil and Malayalam","created":"2021-06-09","cited_by_count":4,"area":null},{"id":"2205.00001","title":"Brainish: Formalizing A Multimodal Language for Intelligence and Consciousness","created":"2022-04-14","cited_by_count":4,"area":null},{"id":"2306.16413","title":"MultiZoo & MultiBench: A Standardized Toolkit for Multimodal Deep Learning","created":"2023-06-28","cited_by_count":4,"area":null},{"id":"2408.07694","title":"End-to-end Semantic-centric Video-based Multimodal Affective Computing","created":"2024-08-14","cited_by_count":4,"area":null},{"id":"2412.13008","title":"RCLMuFN: Relational Context Learning and Multiplex Fusion Network for Multimodal Sarcasm Detection","created":"2024-12-17","cited_by_count":4,"area":null},{"id":"2503.12149","title":"Seeing Sarcasm Through Different Eyes: Analyzing Multimodal Sarcasm Perception in Large Vision-Language Models","created":"2025-03-15","cited_by_count":4,"area":"mllm"},{"id":"2506.00955","title":"Leveraging Large Language Models for Sarcastic Speech Annotation in Sarcasm Detection","created":"2025-06-01","cited_by_count":4,"area":null},{"id":"2506.08430","title":"CAF-I: A Collaborative Multi-Agent Framework for Enhanced Irony Detection with Large Language Models","created":"2025-06-10","cited_by_count":4,"area":"agents"},{"id":"2509.04605","title":"Spoken in Jest, Detected in Earnest: A Systematic Review of Sarcasm Recognition -- Multimodal Fusion, Challenges, and Future Prospects","created":"2025-09-04","cited_by_count":4,"area":null},{"id":"2104.11560","title":"Weakly-supervised Multi-task Learning for Multimodal Affect Recognition","created":"2021-04-23","cited_by_count":3,"area":null},{"id":"2206.13969","title":"MACSA: A Multimodal Aspect-Category Sentiment Analysis Dataset with Multimodal Fine-grained Aligned Annotations","created":"2022-06-28","cited_by_count":3,"area":null},{"id":"2209.07678","title":"ConFiguRe: Exploring Discourse-level Chinese Figures of Speech","created":"2022-09-16","cited_by_count":3,"area":null},{"id":"2211.16509","title":"Multimodal Learning for Multi-Omics: A Survey","created":"2022-11-29","cited_by_count":3,"area":null},{"id":"2301.01134","title":"Ring That Bell: A Corpus and Method for Multimodal Metaphor Detection in Videos","created":"2022-12-15","cited_by_count":3,"area":null},{"id":"2406.12754","title":"Chumor 1.0: A Truly Funny and Challenging Chinese Humor Understanding Dataset from Ruo Zhi Ba","created":"2024-06-18","cited_by_count":3,"area":null},{"id":"2408.10246","title":"VyAnG-Net: A Novel Multi-Modal Sarcasm Recognition Model by Uncovering Visual, Acoustic and Glossary Features","created":"2024-08-05","cited_by_count":3,"area":null},{"id":"2502.07391","title":"Target-Augmented Shared Fusion-based Multimodal Sarcasm Explanation Generation","created":"2025-02-11","cited_by_count":3,"area":null},{"id":"2505.16258","title":"IRONIC: Coherence-Aware Reasoning Chains for Multi-Modal Sarcasm Detection","created":"2025-05-22","cited_by_count":3,"area":"lr"},{"id":"2508.20765","title":"Looking Beyond the Obvious: A Survey on Abstract Concept Recognition for Video Understanding","created":"2025-08-28","cited_by_count":3,"area":null},{"id":"2512.00582","title":"SatireDecoder: Visual Cascaded Decoupling for Enhancing Satirical Image Comprehension","created":"2025-11-29","cited_by_count":3,"area":null},{"id":"2512.16832","title":"What Do Prosody and Text Convey? Characterizing How Meaningful Information is Distributed Across Multiple Channels","created":"2025-12-18","cited_by_count":3,"area":null},{"id":"2211.13014","title":"Sarcasm Detection Framework Using Context, Emotion and Sentiment Features","created":"2022-11-23","cited_by_count":2,"area":null},{"id":"2408.02595","title":"Modelling Visual Semantics via Image Captioning to extract Enhanced Multi-Level Cross-Modal Semantic Incongruity Representation with Attention for Multimodal Sarcasm Detection","created":"2024-08-05","cited_by_count":2,"area":null},{"id":"2505.23272","title":"Are MLMs Trapped in the Visual Room?","created":"2025-05-29","cited_by_count":2,"area":null},{"id":"2508.13028","title":"Integrating Feedback Loss from Bi-modal Sarcasm Detector for Sarcastic Speech Synthesis","created":"2025-08-18","cited_by_count":2,"area":null}],"next_cursor":"100"}