{"total":388,"rows":[{"id":"2406.07476","title":"VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs","created":"2024-06-11","cited_by_count":771,"area":null},{"id":"2501.09747","title":"FAST: Efficient Action Tokenization for Vision-Language-Action Models","created":"2025-01-16","cited_by_count":665,"area":"vla"},{"id":"2310.13289","title":"SALMONN: Towards Generic Hearing Abilities for Large Language Models","created":"2023-10-20","cited_by_count":506,"area":null},{"id":"2403.15377","title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","created":"2024-03-22","cited_by_count":317,"area":null},{"id":"2401.13601","title":"MM-LLMs: Recent Advances in MultiModal Large Language Models","created":"2024-01-24","cited_by_count":278,"area":"mllm"},{"id":"2303.17395","title":"WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research","created":"2023-03-30","cited_by_count":267,"area":null},{"id":"2408.16725","title":"Mini-Omni: Language Models Can Hear, Talk While Thinking in Streaming","created":"2024-08-29","cited_by_count":210,"area":"lr"},{"id":"2305.18500","title":"VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset","created":"2023-05-29","cited_by_count":169,"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":"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":"2507.16632","title":"Step-Audio 2 Technical Report","created":"2025-07-22","cited_by_count":105,"area":null},{"id":"2406.15704","title":"video-SALMONN: Speech-Enhanced Audio-Visual Large Language Models","created":"2024-06-22","cited_by_count":102,"area":null},{"id":"2409.15272","title":"OmniBench: Towards The Future of Universal Omni-Language Models","created":"2024-09-23","cited_by_count":102,"area":"mllm"},{"id":"2411.13577","title":"WavChat: A Survey of Spoken Dialogue Models","created":"2024-11-15","cited_by_count":90,"area":null},{"id":"2402.08846","title":"An Embarrassingly Simple Approach for LLM with Strong ASR Capacity","created":"2024-02-13","cited_by_count":88,"area":null},{"id":"2410.03751","title":"Recent Advances in Speech Language Models: A Survey","created":"2024-10-01","cited_by_count":87,"area":null},{"id":"2502.04328","title":"Ola: Pushing the Frontiers of Omni-Modal Language Model","created":"2025-02-06","cited_by_count":83,"area":null},{"id":"2311.18799","title":"X-InstructBLIP: A Framework for aligning X-Modal instruction-aware representations to LLMs and Emergent Cross-modal Reasoning","created":"2023-11-30","cited_by_count":80,"area":"lr"},{"id":"2408.17175","title":"Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Model","created":"2024-08-30","cited_by_count":72,"area":null},{"id":"2309.16429","title":"Diverse and Aligned Audio-to-Video Generation via Text-to-Video Model Adaptation","created":"2023-09-28","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":"2305.16103","title":"ChatBridge: Bridging Modalities with Large Language Model as a Language Catalyst","created":"2023-05-25","cited_by_count":66,"area":null},{"id":"2408.01319","title":"A Comprehensive Review of Multimodal Large Language Models: Performance and Challenges Across Different Tasks","created":"2024-08-02","cited_by_count":57,"area":"mllm"},{"id":"2410.18325","title":"AVHBench: A Cross-Modal Hallucination Benchmark for Audio-Visual Large Language Models","created":"2024-10-23","cited_by_count":56,"area":null},{"id":"2412.11959","title":"Gramian Multimodal Representation Learning and Alignment","created":"2024-12-16","cited_by_count":54,"area":null},{"id":"2401.03497","title":"EAT: Self-Supervised Pre-Training with Efficient Audio Transformer","created":"2024-01-07","cited_by_count":53,"area":null},{"id":"2411.19772","title":"LongVALE: Vision-Audio-Language-Event Benchmark Towards Time-Aware Omni-Modal Perception of Long Videos","created":"2024-11-29","cited_by_count":51,"area":null},{"id":"2405.00233","title":"SemantiCodec: An Ultra Low Bitrate Semantic Audio Codec for General Sound","created":"2024-04-30","cited_by_count":45,"area":null},{"id":"2408.01337","title":"MuChoMusic: Evaluating Music Understanding in Multimodal Audio-Language Models","created":"2024-08-02","cited_by_count":44,"area":null},{"id":"2408.14340","title":"Foundation Models for Music: A Survey","created":"2024-08-26","cited_by_count":37,"area":"diffusion"},{"id":"2402.01591","title":"BAT: Learning to Reason about Spatial Sounds with Large Language Models","created":"2024-02-02","cited_by_count":36,"area":"lr"},{"id":"2403.10380","title":"BirdSet: A Large-Scale Dataset for Audio Classification in Avian Bioacoustics","created":"2024-03-15","cited_by_count":36,"area":null},{"id":"2404.06393","title":"MuPT: A Generative Symbolic Music Pretrained Transformer","created":"2024-04-09","cited_by_count":33,"area":null},{"id":"2307.16620","title":"Audio-Visual Segmentation by Exploring Cross-Modal Mutual Semantics","created":"2023-07-31","cited_by_count":32,"area":null},{"id":"2308.10175","title":"BAVS: Bootstrapping Audio-Visual Segmentation by Integrating Foundation Knowledge","created":"2023-08-20","cited_by_count":32,"area":null},{"id":"2403.05659","title":"Audio-Synchronized Visual Animation","created":"2024-03-08","cited_by_count":32,"area":null},{"id":"2406.14294","title":"DASB - Discrete Audio and Speech Benchmark","created":"2024-06-20","cited_by_count":32,"area":"mllm"},{"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":"2308.11957","title":"CED: Consistent ensemble distillation for audio tagging","created":"2023-08-23","cited_by_count":29,"area":"distill"},{"id":"2407.10387","title":"Masked Generative Video-to-Audio Transformers with Enhanced Synchronicity","created":"2024-07-15","cited_by_count":28,"area":null},{"id":"2412.18619","title":"Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey","created":"2024-12-16","cited_by_count":27,"area":null},{"id":"2504.12880","title":"Can Masked Autoencoders Also Listen to Birds?","created":"2025-04-17","cited_by_count":26,"area":null},{"id":"2306.04186","title":"Self-supervised Audio Teacher-Student Transformer for Both Clip-level and Frame-level Tasks","created":"2023-06-07","cited_by_count":25,"area":"distill"},{"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":"2412.11694","title":"From Specific-MLLMs to Omni-MLLMs: A Survey on MLLMs Aligned with Multi-modalities","created":"2024-12-16","cited_by_count":22,"area":null},{"id":"2412.15191","title":"AV-Link: Temporally-Aligned Diffusion Features for Cross-Modal Audio-Video Generation","created":"2024-12-19","cited_by_count":22,"area":"diffusion"},{"id":"2310.18709","title":"Audio-Visual Instance Segmentation","created":"2023-10-28","cited_by_count":21,"area":null},{"id":"2407.06957","title":"Listen and Speak Fairly: A Study on Semantic Gender Bias in Speech Integrated Large Language Models","created":"2024-07-09","cited_by_count":21,"area":null},{"id":"2508.10922","title":"A Survey on Video Temporal Grounding with Multimodal Large Language Model","created":"2025-08-07","cited_by_count":20,"area":"mllm"},{"id":"2406.02178","title":"Audio Mamba: Selective State Spaces for Self-Supervised Audio Representations","created":"2024-06-04","cited_by_count":19,"area":"ssm"},{"id":"2408.15876","title":"Unleashing the Temporal-Spatial Reasoning Capacity of GPT for Training-Free Audio and Language Referenced Video Object Segmentation","created":"2024-08-28","cited_by_count":19,"area":"lr"},{"id":"2507.17343","title":"Principled Multimodal Representation Learning","created":"2025-07-23","cited_by_count":19,"area":null},{"id":"2503.13068","title":"Crab: A Unified Audio-Visual Scene Understanding Model with Explicit Cooperation","created":"2025-03-17","cited_by_count":18,"area":"lr"},{"id":"2509.24734","title":"A TRIANGLE Enables Multimodal Alignment Beyond Cosine Similarity","created":"2025-09-29","cited_by_count":18,"area":null},{"id":"2402.05889","title":"CREMA: Generalizable and Efficient Video-Language Reasoning via Multimodal Modular Fusion","created":"2024-02-08","cited_by_count":17,"area":"lr"},{"id":"2506.14291","title":"Equivariance Everywhere All At Once: A Recipe for Graph Foundation Models","created":"2025-06-17","cited_by_count":17,"area":null},{"id":"2405.03272","title":"WorldQA: Multimodal World Knowledge in Videos through Long-Chain Reasoning","created":"2024-05-06","cited_by_count":16,"area":"wm"},{"id":"2501.04962","title":"VoxEval: Benchmarking the Knowledge Understanding Capabilities of End-to-End Spoken Language Models","created":"2025-01-09","cited_by_count":16,"area":null},{"id":"2506.12222","title":"SSLAM: Enhancing Self-Supervised Models with Audio Mixtures for Polyphonic Soundscapes","created":"2025-06-13","cited_by_count":16,"area":"mllm"},{"id":"2506.16895","title":"With Limited Data for Multimodal Alignment, Let the STRUCTURE Guide You","created":"2025-06-20","cited_by_count":16,"area":null},{"id":"2411.07076","title":"StoryTeller: Improving Long Video Description through Global Audio-Visual Character Identification","created":"2024-11-11","cited_by_count":15,"area":"mllm"},{"id":"2502.07461","title":"JamendoMaxCaps: A Large Scale Music-caption Dataset with Imputed Metadata","created":"2025-02-11","cited_by_count":15,"area":null},{"id":"2506.08003","title":"Audio-Sync Video Generation with Multi-Stream Temporal Control","created":"2025-06-09","cited_by_count":15,"area":null},{"id":"2508.04195","title":"NVSpeech: An Integrated and Scalable Pipeline for Human-Like Speech Modeling with Paralinguistic Vocalizations","created":"2025-08-06","cited_by_count":15,"area":null},{"id":"2512.22905","title":"JavisGPT: A Unified Multi-modal LLM for Sounding-Video Comprehension and Generation","created":"2025-12-28","cited_by_count":15,"area":"mllm"},{"id":"2311.04066","title":"Can CLIP Help Sound Source Localization?","created":"2023-11-07","cited_by_count":14,"area":null},{"id":"2406.13275","title":"Enhancing Automated Audio Captioning via Large Language Models with Optimized Audio Encoding","created":"2024-06-19","cited_by_count":14,"area":null},{"id":"2412.13845","title":"Do Language Models Understand Time?","created":"2024-12-18","cited_by_count":14,"area":null},{"id":"2504.09081","title":"SIFT-50M: A Large-Scale Multilingual Dataset for Speech Instruction Fine-Tuning","created":"2025-04-12","cited_by_count":14,"area":null},{"id":"2405.02132","title":"Unveiling the Potential of LLM-Based ASR on Chinese Open-Source Datasets","created":"2024-05-03","cited_by_count":13,"area":null},{"id":"2407.10947","title":"Can Textual Semantics Mitigate Sounding Object Segmentation Preference?","created":"2024-07-15","cited_by_count":13,"area":null},{"id":"2409.16644","title":"Enabling Auditory Large Language Models for Automatic Speech Quality Evaluation","created":"2024-09-25","cited_by_count":13,"area":null},{"id":"2410.24019","title":"Speech is More Than Words: Do Speech-to-Text Translation Systems Leverage Prosody?","created":"2024-10-31","cited_by_count":13,"area":null},{"id":"2512.19687","title":"Pushing the Frontier of Audiovisual Perception with Large-Scale Multimodal Correspondence Learning","created":"2025-12-22","cited_by_count":13,"area":null},{"id":"2402.12750","title":"Model Composition for Multimodal Large Language Models","created":"2024-02-20","cited_by_count":12,"area":"mllm"},{"id":"2410.20178","title":"LLMs Can Evolve Continually on Modality for X-Modal Reasoning","created":"2024-10-26","cited_by_count":12,"area":"lr"},{"id":"2306.00561","title":"Masked Autoencoders with Multi-Window Local-Global Attention Are Better Audio Learners","created":"2023-06-01","cited_by_count":11,"area":null},{"id":"2407.16638","title":"Unveiling and Mitigating Bias in Audio Visual Segmentation","created":"2024-07-23","cited_by_count":11,"area":null},{"id":"2503.01715","title":"KeyFace: Expressive Audio-Driven Facial Animation for Long Sequences via KeyFrame Interpolation","created":"2025-03-03","cited_by_count":11,"area":null},{"id":"2505.19203","title":"EnvSDD: Benchmarking Environmental Sound Deepfake Detection","created":"2025-05-25","cited_by_count":11,"area":null},{"id":"2508.01277","title":"Foundation Models for Bioacoustics -- a Comparative Review","created":"2025-08-02","cited_by_count":11,"area":null},{"id":"2606.01802","title":"MOSS-Audio Technical Report","created":"2026-06-01","cited_by_count":11,"area":null},{"id":"2312.14378","title":"Multimodal Attention Merging for Improved Speech Recognition and Audio Event Classification","created":"2023-12-22","cited_by_count":10,"area":null},{"id":"2409.10999","title":"Enhancing Low-Resource Language and Instruction Following Capabilities of Audio Language Models","created":"2024-09-17","cited_by_count":10,"area":null},{"id":"2504.05684","title":"TARO: Timestep-Adaptive Representation Alignment with Onset-Aware Conditioning for Synchronized Video-to-Audio Synthesis","created":"2025-04-08","cited_by_count":10,"area":null},{"id":"2506.11350","title":"GLAP: General contrastive audio-text pretraining across domains and languages","created":"2025-06-12","cited_by_count":10,"area":null},{"id":"2307.08029","title":"Noise-aware Speech Enhancement using Diffusion Probabilistic Model","created":"2023-07-16","cited_by_count":9,"area":"diffusion"},{"id":"2309.07391","title":"EnCodecMAE: Leveraging neural codecs for universal audio representation learning","created":"2023-09-14","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":"2411.17666","title":"How do Multimodal Foundation Models Encode Text and Speech? An Analysis of Cross-Lingual and Cross-Modal Representations","created":"2024-11-26","cited_by_count":9,"area":null},{"id":"2501.01384","title":"OmniChat: Enhancing Spoken Dialogue Systems with Scalable Synthetic Data for Diverse Scenarios","created":"2025-01-02","cited_by_count":9,"area":"synth"},{"id":"2507.06256","title":"Attacker's Noise Can Manipulate Your Audio-based LLM in the Real World","created":"2025-07-07","cited_by_count":9,"area":null},{"id":"2507.16343","title":"Detect Any Sound: Open-Vocabulary Sound Event Detection with Multi-Modal Queries","created":"2025-07-22","cited_by_count":9,"area":null},{"id":"2311.17951","title":"C3Net: Compound Conditioned ControlNet for Multimodal Content Generation","created":"2023-11-29","cited_by_count":8,"area":null},{"id":"2405.00574","title":"EALD-MLLM: Emotion Analysis in Long-sequential and De-identity videos with Multi-modal Large Language Model","created":"2024-05-01","cited_by_count":8,"area":null},{"id":"2405.02179","title":"Training-Free Deepfake Voice Recognition by Leveraging Large-Scale Pre-Trained Models","created":"2024-05-03","cited_by_count":8,"area":null},{"id":"2412.09818","title":"MERaLiON-AudioLLM: Bridging Audio and Language with Large Language Models","created":"2024-12-13","cited_by_count":8,"area":"lr"},{"id":"2502.00718","title":"\"I am bad\": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models","created":"2025-02-02","cited_by_count":8,"area":"safety"},{"id":"2504.09656","title":"KeyVID: Keyframe-Aware Video Diffusion for Audio-Synchronized Visual Animation","created":"2025-04-13","cited_by_count":8,"area":"diffusion"}],"next_cursor":"100"}