{"total":529,"rows":[{"id":"2306.02858","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","created":"2023-06-05","cited_by_count":1471,"area":"mllm"},{"id":"2306.13549","title":"A Survey on Multimodal Large Language Models","created":"2023-06-23","cited_by_count":909,"area":"mllm"},{"id":"2309.05519","title":"NExT-GPT: Any-to-Any Multimodal LLM","created":"2023-09-11","cited_by_count":615,"area":"mllm"},{"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":"2310.13289","title":"SALMONN: Towards Generic Hearing Abilities for Large Language Models","created":"2023-10-20","cited_by_count":506,"area":null},{"id":"2308.05734","title":"AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining","created":"2023-08-10","cited_by_count":344,"area":"diffusion"},{"id":"2305.16355","title":"PandaGPT: One Model To Instruction-Follow Them All","created":"2023-05-25","cited_by_count":334,"area":null},{"id":"2412.10117","title":"CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models","created":"2024-12-13","cited_by_count":288,"area":"diffusion"},{"id":"2401.13601","title":"MM-LLMs: Recent Advances in MultiModal Large Language Models","created":"2024-01-24","cited_by_count":278,"area":"mllm"},{"id":"2306.17107","title":"LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding","created":"2023-06-29","cited_by_count":274,"area":null},{"id":"2309.10020","title":"Multimodal Foundation Models: From Specialists to General-Purpose Assistants","created":"2023-09-18","cited_by_count":247,"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":"2402.12226","title":"AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling","created":"2024-02-19","cited_by_count":217,"area":"mllm"},{"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":"2410.17196","title":"VoiceBench: Benchmarking LLM-Based Voice Assistants","created":"2024-10-22","cited_by_count":200,"area":null},{"id":"2501.01957","title":"VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction","created":"2025-01-03","cited_by_count":197,"area":"mllm"},{"id":"2312.03700","title":"OneLLM: One Framework to Align All Modalities with Language","created":"2023-12-06","cited_by_count":187,"area":"mllm"},{"id":"2503.12605","title":"Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey","created":"2025-03-16","cited_by_count":182,"area":"lr"},{"id":"2409.06666","title":"LLaMA-Omni: Seamless Speech Interaction with Large Language Models","created":"2024-09-10","cited_by_count":173,"area":null},{"id":"2307.04087","title":"SVIT: Scaling up Visual Instruction Tuning","created":"2023-07-09","cited_by_count":162,"area":null},{"id":"2307.03917","title":"On decoder-only architecture for speech-to-text and large language model integration","created":"2023-07-08","cited_by_count":145,"area":null},{"id":"2411.00774","title":"Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLM","created":"2024-11-01","cited_by_count":141,"area":"mllm"},{"id":"2408.16532","title":"WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modeling","created":"2024-08-29","cited_by_count":129,"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":"2402.05755","title":"Spirit LM: Interleaved Spoken and Written Language Model","created":"2024-02-08","cited_by_count":126,"area":"mllm"},{"id":"2504.01990","title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","created":"2025-03-31","cited_by_count":126,"area":"agents"},{"id":"2504.08528","title":"On The Landscape of Spoken Language Models: A Comprehensive Survey","created":"2025-04-11","cited_by_count":118,"area":null},{"id":"2402.01801","title":"Large Language Models for Time Series: A Survey","created":"2024-02-02","cited_by_count":114,"area":null},{"id":"2311.07361","title":"The Impact of Large Language Models on Scientific Discovery: a Preliminary Study using GPT-4","created":"2023-11-13","cited_by_count":112,"area":null},{"id":"2404.00656","title":"WavLLM: Towards Robust and Adaptive Speech Large Language Model","created":"2024-03-31","cited_by_count":109,"area":null},{"id":"2507.16632","title":"Step-Audio 2 Technical Report","created":"2025-07-22","cited_by_count":105,"area":null},{"id":"2312.08782","title":"Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis","created":"2023-12-14","cited_by_count":103,"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":"2401.06071","title":"GroundingGPT:Language Enhanced Multi-modal Grounding Model","created":"2024-01-11","cited_by_count":101,"area":"mllm"},{"id":"2309.14405","title":"Joint Audio and Speech Understanding","created":"2023-09-25","cited_by_count":100,"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":"2305.15255","title":"Spoken Question Answering and Speech Continuation Using Spectrogram-Powered LLM","created":"2023-05-24","cited_by_count":94,"area":null},{"id":"2411.13577","title":"WavChat: A Survey of Spoken Dialogue Models","created":"2024-11-15","cited_by_count":90,"area":null},{"id":"2505.04921","title":"Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models","created":"2025-05-08","cited_by_count":90,"area":"lr"},{"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":"2305.16107","title":"VioLA: Unified Codec Language Models for Speech Recognition, Synthesis, and Translation","created":"2023-05-25","cited_by_count":87,"area":null},{"id":"2308.16692","title":"SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models","created":"2023-08-31","cited_by_count":87,"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":"2402.15319","title":"GPTVQ: The Blessing of Dimensionality for LLM Quantization","created":"2024-02-23","cited_by_count":82,"area":null},{"id":"2309.13963","title":"Connecting Speech Encoder and Large Language Model for ASR","created":"2023-09-25","cited_by_count":80,"area":null},{"id":"2401.12242","title":"BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models","created":"2024-01-20","cited_by_count":80,"area":"lr"},{"id":"2411.02038","title":"Addressing Representation Collapse in Vector Quantized Models with One Linear Layer","created":"2024-11-04","cited_by_count":80,"area":null},{"id":"2309.00916","title":"BLSP: Bootstrapping Language-Speech Pre-training via Behavior Alignment of Continuation Writing","created":"2023-09-02","cited_by_count":79,"area":"synth"},{"id":"2310.04673","title":"LauraGPT: Listen, Attend, Understand, and Regenerate Audio with GPT","created":"2023-10-07","cited_by_count":78,"area":null},{"id":"2310.09424","title":"SALM: Speech-augmented Language Model with In-context Learning for Speech Recognition and Translation","created":"2023-10-13","cited_by_count":76,"area":null},{"id":"2505.02625","title":"LLaMA-Omni2: LLM-based Real-time Spoken Chatbot with Autoregressive Streaming Speech Synthesis","created":"2025-05-05","cited_by_count":76,"area":null},{"id":"2309.07937","title":"Voxtlm: unified decoder-only models for consolidating speech recognition/synthesis and speech/text continuation tasks","created":"2023-09-14","cited_by_count":72,"area":null},{"id":"2311.18836","title":"ChatPose: Chatting about 3D Human Pose","created":"2023-11-30","cited_by_count":72,"area":"mllm"},{"id":"2409.15594","title":"Beyond Turn-Based Interfaces: Synchronous LLMs as Full-Duplex Dialogue Agents","created":"2024-09-23","cited_by_count":72,"area":"agents"},{"id":"2402.11941","title":"CoCo-Agent: A Comprehensive Cognitive MLLM Agent for Smartphone GUI Automation","created":"2024-02-19","cited_by_count":70,"area":"mllm"},{"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":"2310.00230","title":"SLM: Bridge the thin gap between speech and text foundation models","created":"2023-09-30","cited_by_count":67,"area":null},{"id":"2512.23808","title":"MiMo-Audio: Audio Language Models are Few-Shot Learners","created":"2025-12-29","cited_by_count":65,"area":null},{"id":"2405.08295","title":"SpeechVerse: A Large-scale Generalizable Audio Language Model","created":"2024-05-14","cited_by_count":63,"area":null},{"id":"2408.02622","title":"Language Model Can Listen While Speaking","created":"2024-08-05","cited_by_count":63,"area":null},{"id":"2410.17799","title":"OmniFlatten: An End-to-end GPT Model for Seamless Voice Conversation","created":"2024-10-23","cited_by_count":60,"area":null},{"id":"2509.14128","title":"Canary-1B-v2 & Parakeet-TDT-0.6B-v3: Efficient and High-Performance Models for Multilingual ASR and AST","created":"2025-09-17","cited_by_count":60,"area":null},{"id":"2308.15930","title":"LLaSM: Large Language and Speech Model","created":"2023-08-30","cited_by_count":58,"area":"mllm"},{"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":"2310.08903","title":"SeqXGPT: Sentence-Level AI-Generated Text Detection","created":"2023-10-13","cited_by_count":56,"area":null},{"id":"2406.10729","title":"A Comprehensive Survey of Foundation Models in Medicine","created":"2024-06-15","cited_by_count":56,"area":null},{"id":"2411.19842","title":"Scaling Transformers for Low-Bitrate High-Quality Speech Coding","created":"2024-11-29","cited_by_count":49,"area":null},{"id":"2404.15676","title":"Beyond Chain-of-Thought: A Survey of Chain-of-X Paradigms for LLMs","created":"2024-04-24","cited_by_count":48,"area":"lr"},{"id":"2412.09596","title":"InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions","created":"2024-12-12","cited_by_count":48,"area":"mllm"},{"id":"2404.05600","title":"SpeechAlign: Aligning Speech Generation to Human Preferences","created":"2024-04-08","cited_by_count":47,"area":"alignment"},{"id":"2412.10523","title":"The Language of Motion: Unifying Verbal and Non-verbal Language of 3D Human Motion","created":"2024-12-13","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":"2409.18042","title":"EMOVA: Empowering Language Models to See, Hear and Speak with Vivid Emotions","created":"2024-09-26","cited_by_count":45,"area":null},{"id":"2406.02030","title":"Multimodal Reasoning with Multimodal Knowledge Graph","created":"2024-06-04","cited_by_count":44,"area":"lr"},{"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":"2308.12219","title":"Diffusion Language Models Can Perform Many Tasks with Scaling and Instruction-Finetuning","created":"2023-08-23","cited_by_count":39,"area":"diffusion"},{"id":"2312.04293","title":"GPT-4V with Emotion: A Zero-shot Benchmark for Generalized Emotion Recognition","created":"2023-12-07","cited_by_count":38,"area":null},{"id":"2405.16273","title":"M$^3$GPT: An Advanced Multimodal, Multitask Framework for Motion Comprehension and Generation","created":"2024-05-25","cited_by_count":38,"area":null},{"id":"2412.08608","title":"AdvWave: Stealthy Adversarial Jailbreak Attack against Large Audio-Language Models","created":"2024-12-11","cited_by_count":38,"area":"safety"},{"id":"2401.13527","title":"SpeechGPT-Gen: Scaling Chain-of-Information Speech Generation","created":"2024-01-24","cited_by_count":37,"area":"diffusion"},{"id":"2408.14340","title":"Foundation Models for Music: A Survey","created":"2024-08-26","cited_by_count":37,"area":"diffusion"},{"id":"2406.03872","title":"BLSP-Emo: Towards Empathetic Large Speech-Language Models","created":"2024-06-06","cited_by_count":36,"area":null},{"id":"2405.19334","title":"LLMs Meet Multimodal Generation and Editing: A Survey","created":"2024-05-29","cited_by_count":35,"area":null},{"id":"2504.12867","title":"EmoVoice: LLM-based Emotional Text-To-Speech Model with Freestyle Text Prompting","created":"2025-04-17","cited_by_count":34,"area":null},{"id":"2505.15670","title":"SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model","created":"2025-05-21","cited_by_count":34,"area":null},{"id":"2411.18138","title":"SALMONN-omni: A Codec-free LLM for Full-duplex Speech Understanding and Generation","created":"2024-11-27","cited_by_count":33,"area":"mllm"},{"id":"2404.00685","title":"Scaling Properties of Speech Language Models","created":"2024-03-31","cited_by_count":32,"area":null},{"id":"2311.02248","title":"COSMIC: Data Efficient Instruction-tuning For Speech In-Context Learning","created":"2023-11-03","cited_by_count":31,"area":"mllm"},{"id":"2504.01094","title":"Multilingual and Multi-Accent Jailbreaking of Audio LLMs","created":"2025-04-01","cited_by_count":31,"area":"safety"},{"id":"2402.14418","title":"Uncertainty-Aware Evaluation for Vision-Language Models","created":"2024-02-22","cited_by_count":29,"area":"mllm"},{"id":"2412.05167","title":"Benchmarking Open-ended Audio Dialogue Understanding for Large Audio-Language Models","created":"2024-12-06","cited_by_count":29,"area":null},{"id":"2312.13585","title":"Speech Translation with Large Language Models: An Industrial Practice","created":"2023-12-21","cited_by_count":28,"area":null},{"id":"2406.05948","title":"Chain-of-Scrutiny: Detecting Backdoor Attacks for Large Language Models","created":"2024-06-10","cited_by_count":28,"area":"safety"},{"id":"2309.00169","title":"RepCodec: A Speech Representation Codec for Speech Tokenization","created":"2023-08-31","cited_by_count":27,"area":null},{"id":"2410.03878","title":"SPARTUN3D: Situated Spatial Understanding of 3D World in Large Language Models","created":"2024-10-04","cited_by_count":27,"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":"2505.17060","title":"SALMONN-omni: A Standalone Speech LLM without Codec Injection for Full-duplex Conversation","created":"2025-05-17","cited_by_count":27,"area":null},{"id":"2312.15316","title":"Paralinguistics-Enhanced Large Language Modeling of Spoken Dialogue","created":"2023-12-23","cited_by_count":25,"area":null}],"next_cursor":"100"}