{"total":643,"rows":[{"id":"2311.07919","title":"Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models","created":"2023-11-14","cited_by_count":608,"area":null},{"id":"2407.10759","title":"Qwen2-Audio Technical Report","created":"2024-07-15","cited_by_count":560,"area":null},{"id":"2106.13219","title":"Towards Understanding and Mitigating Social Biases in Language Models","created":"2021-06-24","cited_by_count":296,"area":null},{"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":"2107.07567","title":"Beyond Goldfish Memory: Long-Term Open-Domain Conversation","created":"2021-07-15","cited_by_count":267,"area":null},{"id":"2504.18425","title":"Kimi-Audio Technical Report","created":"2025-04-25","cited_by_count":222,"area":null},{"id":"2402.07729","title":"AIR-Bench: Benchmarking Large Audio-Language Models via Generative Comprehension","created":"2024-02-12","cited_by_count":220,"area":null},{"id":"2312.15185","title":"emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representation","created":"2023-12-23","cited_by_count":205,"area":null},{"id":"2402.01831","title":"Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities","created":"2024-02-02","cited_by_count":186,"area":null},{"id":"2107.07502","title":"MultiBench: Multiscale Benchmarks for Multimodal Representation Learning","created":"2021-07-15","cited_by_count":146,"area":null},{"id":"2503.03983","title":"Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities","created":"2025-03-06","cited_by_count":133,"area":"lr"},{"id":"2105.04387","title":"Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Survey","created":"2021-05-10","cited_by_count":130,"area":null},{"id":"2406.16020","title":"AudioBench: A Universal Benchmark for Audio Large Language Models","created":"2024-06-23","cited_by_count":128,"area":null},{"id":"2407.04051","title":"FunAudioLLM: Voice Understanding and Generation Foundation Models for Natural Interaction Between Humans and LLMs","created":"2024-07-04","cited_by_count":122,"area":null},{"id":"2303.03369","title":"Multimodal Prompting with Missing Modalities for Visual Recognition","created":"2023-03-06","cited_by_count":121,"area":null},{"id":"2503.01710","title":"Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens","created":"2025-03-03","cited_by_count":113,"area":null},{"id":"2505.17862","title":"Daily-Omni: Towards Audio-Visual Reasoning with Temporal Alignment across Modalities","created":"2025-05-23","cited_by_count":110,"area":"lr"},{"id":"2405.11273","title":"Uni-MoE: Scaling Unified Multimodal LLMs with Mixture of Experts","created":"2024-05-18","cited_by_count":108,"area":"mllm"},{"id":"2506.04779","title":"MMSU: A Massive Multi-task Spoken Language Understanding and Reasoning Benchmark","created":"2025-06-05","cited_by_count":103,"area":"lr"},{"id":"2107.06779","title":"MMGCN: Multimodal Fusion via Deep Graph Convolution Network for Emotion Recognition in Conversation","created":"2021-07-14","cited_by_count":99,"area":null},{"id":"2306.08990","title":"Emotional Speech-Driven Animation with Content-Emotion Disentanglement","created":"2023-06-15","cited_by_count":98,"area":null},{"id":"2105.12907","title":"Directed Acyclic Graph Network for Conversational Emotion Recognition","created":"2021-05-27","cited_by_count":97,"area":null},{"id":"2503.02318","title":"Audio-Reasoner: Improving Reasoning Capability in Large Audio Language Models","created":"2025-03-04","cited_by_count":95,"area":"lr"},{"id":"2409.07825","title":"Deep Multimodal Learning with Missing Modality: A Survey","created":"2024-09-12","cited_by_count":92,"area":null},{"id":"2411.13577","title":"WavChat: A Survey of Spoken Dialogue Models","created":"2024-11-15","cited_by_count":90,"area":null},{"id":"2310.04673","title":"LauraGPT: Listen, Attend, Understand, and Regenerate Audio with GPT","created":"2023-10-07","cited_by_count":78,"area":null},{"id":"2604.27393","title":"MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction","created":"2026-04-30","cited_by_count":78,"area":"mllm"},{"id":"2103.06413","title":"FairFil: Contrastive Neural Debiasing Method for Pretrained Text Encoders","created":"2021-03-11","cited_by_count":75,"area":null},{"id":"2302.03269","title":"PLACES: Prompting Language Models for Social Conversation Synthesis","created":"2023-02-07","cited_by_count":72,"area":null},{"id":"2106.01978","title":"DialogueCRN: Contextual Reasoning Networks for Emotion Recognition in Conversations","created":"2021-06-03","cited_by_count":71,"area":null},{"id":"2207.01063","title":"DailyTalk: Spoken Dialogue Dataset for Conversational Text-to-Speech","created":"2022-07-03","cited_by_count":69,"area":null},{"id":"2406.13340","title":"SD-Eval: A Benchmark Dataset for Spoken Dialogue Understanding Beyond Words","created":"2024-06-19","cited_by_count":68,"area":null},{"id":"2211.11256","title":"UniMSE: Towards Unified Multimodal Sentiment Analysis and Emotion Recognition","created":"2022-11-21","cited_by_count":61,"area":null},{"id":"2108.12009","title":"EmoBERTa: Speaker-Aware Emotion Recognition in Conversation with RoBERTa","created":"2021-08-26","cited_by_count":60,"area":null},{"id":"2510.15870","title":"OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM","created":"2025-10-17","cited_by_count":59,"area":null},{"id":"2106.01071","title":"Topic-Driven and Knowledge-Aware Transformer for Dialogue Emotion Detection","created":"2021-06-02","cited_by_count":56,"area":null},{"id":"2304.09582","title":"Is ChatGPT Equipped with Emotional Dialogue Capabilities?","created":"2023-04-19","cited_by_count":54,"area":null},{"id":"2304.03347","title":"Towards Interpretable Mental Health Analysis with Large Language Models","created":"2023-04-06","cited_by_count":53,"area":null},{"id":"2402.12071","title":"EmoBench: Evaluating the Emotional Intelligence of Large Language Models","created":"2024-02-19","cited_by_count":53,"area":null},{"id":"2203.02385","title":"MM-DFN: Multimodal Dynamic Fusion Network for Emotion Recognition in Conversations","created":"2022-03-04","cited_by_count":52,"area":null},{"id":"2306.09486","title":"FedMultimodal: A Benchmark For Multimodal Federated Learning","created":"2023-06-15","cited_by_count":51,"area":null},{"id":"2205.10237","title":"M3ED: Multi-modal Multi-scene Multi-label Emotional Dialogue Database","created":"2022-05-09","cited_by_count":50,"area":null},{"id":"2507.02768","title":"DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal Alignment","created":"2025-07-03","cited_by_count":50,"area":"synth"},{"id":"2203.13504","title":"EmoCaps: Emotion Capsule based Model for Conversational Emotion Recognition","created":"2022-03-25","cited_by_count":48,"area":null},{"id":"2206.02187","title":"M2FNet: Multi-modal Fusion Network for Emotion Recognition in Conversation","created":"2022-06-05","cited_by_count":47,"area":null},{"id":"2312.06337","title":"Deep Imbalanced Learning for Multimodal Emotion Recognition in Conversations","created":"2023-12-11","cited_by_count":47,"area":null},{"id":"2206.05238","title":"Dimensional Modeling of Emotions in Text with Appraisal Theories: Corpus Creation, Annotation Reliability, and Prediction","created":"2022-06-10","cited_by_count":46,"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":"2209.02604","title":"Make Acoustic and Visual Cues Matter: CH-SIMS v2.0 Dataset and AV-Mixup Consistent Module","created":"2022-08-22","cited_by_count":44,"area":null},{"id":"2501.16566","title":"AffectGPT: A New Dataset, Model, and Benchmark for Emotion Understanding with Multimodal Large Language Models","created":"2025-01-27","cited_by_count":44,"area":"mllm"},{"id":"2505.13237","title":"SAKURA: On the Multi-hop Reasoning of Large Audio-Language Models Based on Speech and Audio Information","created":"2025-05-19","cited_by_count":42,"area":"lr"},{"id":"2209.04355","title":"MIntRec: A New Dataset for Multimodal Intent Recognition","created":"2022-09-09","cited_by_count":41,"area":null},{"id":"2406.07867","title":"Let's Go Real Talk: Spoken Dialogue Model for Face-to-Face Conversation","created":"2024-06-12","cited_by_count":41,"area":null},{"id":"2406.07162","title":"EmoBox: Multilingual Multi-corpus Speech Emotion Recognition Toolkit and Benchmark","created":"2024-06-11","cited_by_count":40,"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":"2505.19797","title":"The Avengers: A Simple Recipe for Uniting Smaller Language Models to Challenge Proprietary Giants","created":"2025-05-26","cited_by_count":38,"area":null},{"id":"2601.07206","title":"LLMRouterBench: A Massive Benchmark and Unified Framework for LLM Routing","created":"2026-01-12","cited_by_count":38,"area":null},{"id":"2310.20494","title":"A Transformer-Based Model With Self-Distillation for Multimodal Emotion Recognition in Conversations","created":"2023-10-31","cited_by_count":37,"area":"distill"},{"id":"2406.03872","title":"BLSP-Emo: Towards Empathetic Large Speech-Language Models","created":"2024-06-06","cited_by_count":36,"area":null},{"id":"2108.11626","title":"CoMPM: Context Modeling with Speaker's Pre-trained Memory Tracking for Emotion Recognition in Conversation","created":"2021-08-26","cited_by_count":35,"area":null},{"id":"2112.11202","title":"Contrast and Generation Make BART a Good Dialogue Emotion Recognizer","created":"2021-12-21","cited_by_count":35,"area":null},{"id":"2112.06346","title":"ValueNet: A New Dataset for Human Value Driven Dialogue System","created":"2021-12-12","cited_by_count":34,"area":null},{"id":"2504.15900","title":"SARI: Structured Audio Reasoning via Curriculum-Guided Reinforcement Learning","created":"2025-04-22","cited_by_count":34,"area":"lr"},{"id":"2304.08981","title":"MER 2023: Multi-label Learning, Modality Robustness, and Semi-Supervised Learning","created":"2023-04-18","cited_by_count":33,"area":null},{"id":"2404.17858","title":"Revisiting Multi-modal Emotion Learning with Broad State Space Models and Probability-guidance Fusion","created":"2024-04-27","cited_by_count":33,"area":"ssm"},{"id":"2404.17862","title":"Revisiting Multimodal Emotion Recognition in Conversation from the Perspective of Graph Spectrum","created":"2024-04-27","cited_by_count":33,"area":null},{"id":"2312.05735","title":"A Comprehensive Survey on Multi-modal Conversational Emotion Recognition with Deep Learning","created":"2023-12-10","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":"2110.08020","title":"Multimodal Emotion-Cause Pair Extraction in Conversations","created":"2021-10-15","cited_by_count":31,"area":null},{"id":"2210.08713","title":"Supervised Prototypical Contrastive Learning for Emotion Recognition in Conversation","created":"2022-10-17","cited_by_count":31,"area":null},{"id":"2305.13500","title":"Learning Emotion Representations from Verbal and Nonverbal Communication","created":"2023-05-22","cited_by_count":31,"area":null},{"id":"2203.09978","title":"WOODS: Benchmarks for Out-of-Distribution Generalization in Time Series","created":"2022-03-18","cited_by_count":30,"area":null},{"id":"2310.11374","title":"DialogueLLM: Context and Emotion Knowledge-Tuned Large Language Models for Emotion Recognition in Conversations","created":"2023-10-17","cited_by_count":30,"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":"2306.17799","title":"A Low-rank Matching Attention based Cross-modal Feature Fusion Method for Conversational Emotion Recognition","created":"2023-06-16","cited_by_count":29,"area":null},{"id":"2510.13747","title":"InteractiveOmni: A Unified Omni-modal Model for Audio-Visual Multi-turn Dialogue","created":"2025-10-15","cited_by_count":29,"area":null},{"id":"2408.11424","title":"EMO-LLaMA: Enhancing Facial Emotion Understanding with Instruction Tuning","created":"2024-08-21","cited_by_count":28,"area":null},{"id":"2403.01222","title":"Emotion Analysis in NLP: Trends, Gaps and Roadmap for Future Directions","created":"2024-03-02","cited_by_count":27,"area":null},{"id":"2407.21315","title":"Beyond Silent Letters: Amplifying LLMs in Emotion Recognition with Vocal Nuances","created":"2024-07-31","cited_by_count":27,"area":null},{"id":"2109.04008","title":"Graph Based Network with Contextualized Representations of Turns in Dialogue","created":"2021-09-09","cited_by_count":26,"area":null},{"id":"2205.14727","title":"CPED: A Large-Scale Chinese Personalized and Emotional Dialogue Dataset for Conversational AI","created":"2022-05-29","cited_by_count":26,"area":null},{"id":"2403.10943","title":"MIntRec2.0: A Large-scale Benchmark Dataset for Multimodal Intent Recognition and Out-of-scope Detection in Conversations","created":"2024-03-16","cited_by_count":26,"area":null},{"id":"2509.25373","title":"From Perception to Cognition: A Survey of Vision-Language Interactive Reasoning in Multimodal Large Language Models","created":"2025-09-29","cited_by_count":26,"area":"lr"},{"id":"2511.00279","title":"LongCat-Flash-Omni Technical Report","created":"2025-10-31","cited_by_count":26,"area":"moe"},{"id":"2112.11718","title":"Hybrid Curriculum Learning for Emotion Recognition in Conversation","created":"2021-12-22","cited_by_count":25,"area":null},{"id":"2408.04638","title":"Affective Computing in the Era of Large Language Models: A Survey from the NLP Perspective","created":"2024-07-30","cited_by_count":25,"area":null},{"id":"2306.02210","title":"GPT-FL: Generative Pre-trained Model-Assisted Federated Learning","created":"2023-06-03","cited_by_count":24,"area":null},{"id":"2312.10579","title":"DER-GCN: Dialogue and Event Relation-Aware Graph Convolutional Neural Network for Multimodal Dialogue Emotion Recognition","created":"2023-12-17","cited_by_count":23,"area":null},{"id":"2402.12025","title":"Speech Translation with Speech Foundation Models and Large Language Models: What is There and What is Missing?","created":"2024-02-19","cited_by_count":23,"area":null},{"id":"2404.17113","title":"MER 2024: Semi-Supervised Learning, Noise Robustness, and Open-Vocabulary Multimodal Emotion Recognition","created":"2024-04-26","cited_by_count":23,"area":null},{"id":"2407.00119","title":"Efficient Long-distance Latent Relation-aware Graph Neural Network for Multi-modal Emotion Recognition in Conversations","created":"2024-06-27","cited_by_count":23,"area":null},{"id":"2501.18592","title":"Advances in Multimodal Adaptation and Generalization: From Traditional Approaches to Foundation Models","created":"2025-01-30","cited_by_count":23,"area":null},{"id":"2212.09171","title":"Rainproof: An Umbrella To Shield Text Generators From Out-Of-Distribution Data","created":"2022-12-18","cited_by_count":21,"area":null},{"id":"2307.01595","title":"Prompt Tuning Pushes Farther, Contrastive Learning Pulls Closer: A Two-Stage Approach to Mitigate Social Biases","created":"2023-07-04","cited_by_count":21,"area":null},{"id":"2401.13898","title":"Cross-Modal Prototype based Multimodal Federated Learning under Severely Missing Modality","created":"2024-01-25","cited_by_count":21,"area":null},{"id":"2511.12609","title":"Uni-MoE-2.0-Omni: Scaling Language-Centric Omnimodal Large Model with Advanced MoE, Training and Data","created":"2025-11-16","cited_by_count":21,"area":"moe"},{"id":"2109.04919","title":"EmoWOZ: A Large-Scale Corpus and Labelling Scheme for Emotion Recognition in Task-Oriented Dialogue Systems","created":"2021-09-10","cited_by_count":20,"area":null},{"id":"2207.12261","title":"GraphCFC: A Directed Graph Based Cross-Modal Feature Complementation Approach for Multimodal Conversational Emotion Recognition","created":"2022-07-06","cited_by_count":20,"area":null},{"id":"2306.01505","title":"Supervised Adversarial Contrastive Learning for Emotion Recognition in Conversations","created":"2023-06-02","cited_by_count":19,"area":null},{"id":"2407.16714","title":"Masked Graph Learning with Recurrent Alignment for Multimodal Emotion Recognition in Conversation","created":"2024-07-23","cited_by_count":19,"area":null}],"next_cursor":"100"}