{"total":616,"rows":[{"id":"2301.02111","title":"Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers","created":"2023-01-05","cited_by_count":752,"area":null},{"id":"2308.06571","title":"ModelScope Text-to-Video Technical Report","created":"2023-08-12","cited_by_count":658,"area":"diffusion"},{"id":"2506.01844","title":"SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics","created":"2025-06-02","cited_by_count":530,"area":"mllm"},{"id":"2305.11000","title":"SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities","created":"2023-05-18","cited_by_count":529,"area":"mllm"},{"id":"2310.06114","title":"Learning Interactive Real-World Simulators","created":"2023-10-09","cited_by_count":458,"area":"wm"},{"id":"2301.11325","title":"MusicLM: Generating Music From Text","created":"2023-01-26","cited_by_count":448,"area":null},{"id":"2306.06546","title":"High-Fidelity Audio Compression with Improved RVQGAN","created":"2023-06-11","cited_by_count":431,"area":null},{"id":"2312.00063","title":"MoMask: Generative Masked Modeling of 3D Human Motions","created":"2023-11-29","cited_by_count":400,"area":null},{"id":"2305.02463","title":"Shap-E: Generating Conditional 3D Implicit Functions","created":"2023-05-03","cited_by_count":385,"area":null},{"id":"2306.15687","title":"Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale","created":"2023-06-23","cited_by_count":379,"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":"2306.12925","title":"AudioPaLM: A Large Language Model That Can Speak and Listen","created":"2023-06-22","cited_by_count":343,"area":null},{"id":"2301.12661","title":"Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion Models","created":"2023-01-30","cited_by_count":324,"area":"diffusion"},{"id":"2312.17172","title":"Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Action","created":"2023-12-28","cited_by_count":302,"area":null},{"id":"2209.15352","title":"AudioGen: Textually Guided Audio Generation","created":"2022-09-30","cited_by_count":295,"area":null},{"id":"2307.14334","title":"Towards Generalist Biomedical AI","created":"2023-07-26","cited_by_count":289,"area":null},{"id":"2403.08319","title":"Knowledge Conflicts for LLMs: A Survey","created":"2024-03-13","cited_by_count":283,"area":null},{"id":"2304.12995","title":"AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head","created":"2023-04-25","cited_by_count":265,"area":null},{"id":"2307.01850","title":"Self-Consuming Generative Models Go MAD","created":"2023-07-04","cited_by_count":250,"area":null},{"id":"2304.09116","title":"NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers","created":"2023-04-18","cited_by_count":235,"area":"diffusion"},{"id":"2403.03100","title":"NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models","created":"2024-03-05","cited_by_count":226,"area":"diffusion"},{"id":"2504.18425","title":"Kimi-Audio Technical Report","created":"2025-04-25","cited_by_count":222,"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":"2211.15089","title":"Continuous diffusion for categorical data","created":"2022-11-28","cited_by_count":214,"area":"diffusion"},{"id":"2407.05361","title":"Emilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generation","created":"2024-07-07","cited_by_count":204,"area":null},{"id":"2306.00107","title":"MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training","created":"2023-05-31","cited_by_count":181,"area":null},{"id":"2402.04825","title":"Fast Timing-Conditioned Latent Audio Diffusion","created":"2024-02-07","cited_by_count":181,"area":null},{"id":"2302.03917","title":"Noise2Music: Text-conditioned Music Generation with Diffusion Models","created":"2023-02-08","cited_by_count":173,"area":"diffusion"},{"id":"2409.06666","title":"LLaMA-Omni: Seamless Speech Interaction with Large Language Models","created":"2024-09-10","cited_by_count":173,"area":null},{"id":"2406.16964","title":"Are Language Models Actually Useful for Time Series Forecasting?","created":"2024-06-22","cited_by_count":168,"area":null},{"id":"2303.03926","title":"Speak Foreign Languages with Your Own Voice: Cross-Lingual Neural Codec Language Modeling","created":"2023-03-07","cited_by_count":167,"area":null},{"id":"2409.00750","title":"MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformer","created":"2024-09-01","cited_by_count":161,"area":null},{"id":"2309.16534","title":"MotionLM: Multi-Agent Motion Forecasting as Language Modeling","created":"2023-09-28","cited_by_count":156,"area":"agents"},{"id":"2306.00814","title":"Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis","created":"2023-06-01","cited_by_count":153,"area":null},{"id":"2405.15223","title":"iVideoGPT: Interactive VideoGPTs are Scalable World Models","created":"2024-05-24","cited_by_count":146,"area":"wm"},{"id":"2305.18703","title":"Domain Specialization as the Key to Make Large Language Models Disruptive: A Comprehensive Survey","created":"2023-05-30","cited_by_count":135,"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":"2406.05370","title":"VALL-E 2: Neural Codec Language Models are Human Parity Zero-Shot Text to Speech Synthesizers","created":"2024-06-08","cited_by_count":122,"area":null},{"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":"2305.09636","title":"SoundStorm: Efficient Parallel Audio Generation","created":"2023-05-16","cited_by_count":114,"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":"2402.13217","title":"VideoPrism: A Foundational Visual Encoder for Video Understanding","created":"2024-02-20","cited_by_count":105,"area":null},{"id":"2507.16632","title":"Step-Audio 2 Technical Report","created":"2025-07-22","cited_by_count":105,"area":null},{"id":"2305.13009","title":"Textually Pretrained Speech Language Models","created":"2023-05-22","cited_by_count":101,"area":null},{"id":"2311.08355","title":"Mustango: Toward Controllable Text-to-Music Generation","created":"2023-11-14","cited_by_count":100,"area":"diffusion"},{"id":"2308.05725","title":"EXPRESSO: A Benchmark and Analysis of Discrete Expressive Speech Resynthesis","created":"2023-08-10","cited_by_count":98,"area":null},{"id":"2404.09956","title":"Tango 2: Aligning Diffusion-based Text-to-Audio Generations through Direct Preference Optimization","created":"2024-04-15","cited_by_count":97,"area":"diffusion"},{"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":"2301.12867","title":"Red teaming ChatGPT via Jailbreaking: Bias, Robustness, Reliability and Toxicity","created":"2023-01-30","cited_by_count":89,"area":"safety"},{"id":"2404.10301","title":"Long-form music generation with latent diffusion","created":"2024-04-16","cited_by_count":89,"area":"diffusion"},{"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":"2301.04655","title":"ChatGPT is not all you need. A State of the Art Review of large Generative AI models","created":"2023-01-11","cited_by_count":86,"area":"diffusion"},{"id":"2504.08685","title":"Seaweed-7B: Cost-Effective Training of Video Generation Foundation Model","created":"2025-04-11","cited_by_count":82,"area":null},{"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":"2301.11757","title":"Mo\\^usai: Text-to-Music Generation with Long-Context Latent Diffusion","created":"2023-01-27","cited_by_count":78,"area":"diffusion"},{"id":"2310.04673","title":"LauraGPT: Listen, Attend, Understand, and Regenerate Audio with GPT","created":"2023-10-07","cited_by_count":78,"area":null},{"id":"2401.17264","title":"Proactive Detection of Voice Cloning with Localized Watermarking","created":"2024-01-30","cited_by_count":78,"area":null},{"id":"2402.08093","title":"BASE TTS: Lessons from building a billion-parameter Text-to-Speech model on 100K hours of data","created":"2024-02-12","cited_by_count":75,"area":null},{"id":"2401.12179","title":"DITTO: Diffusion Inference-Time T-Optimization for Music Generation","created":"2024-01-22","cited_by_count":73,"area":"diffusion"},{"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":"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":"2406.08619","title":"Self-Supervised Speech Representations are More Phonetic than Semantic","created":"2024-06-12","cited_by_count":71,"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":"2305.11473","title":"Graphologue: Exploring Large Language Model Responses with Interactive Diagrams","created":"2023-05-19","cited_by_count":66,"area":null},{"id":"2407.08551","title":"Autoregressive Speech Synthesis without Vector Quantization","created":"2024-07-11","cited_by_count":65,"area":null},{"id":"2308.06873","title":"SpeechX: Neural Codec Language Model as a Versatile Speech Transformer","created":"2023-08-14","cited_by_count":64,"area":null},{"id":"2302.02257","title":"Multi-Source Diffusion Models for Simultaneous Music Generation and Separation","created":"2023-02-04","cited_by_count":63,"area":"diffusion"},{"id":"2408.02622","title":"Language Model Can Listen While Speaking","created":"2024-08-05","cited_by_count":63,"area":null},{"id":"2303.11568","title":"Large AI Models in Health Informatics: Applications, Challenges, and the Future","created":"2023-03-21","cited_by_count":61,"area":null},{"id":"2307.04686","title":"VampNet: Music Generation via Masked Acoustic Token Modeling","created":"2023-07-10","cited_by_count":57,"area":null},{"id":"2212.08045","title":"CLIPPO: Image-and-Language Understanding from Pixels Only","created":"2022-12-15","cited_by_count":55,"area":null},{"id":"2301.12662","title":"SingSong: Generating musical accompaniments from singing","created":"2023-01-30","cited_by_count":55,"area":null},{"id":"2306.17842","title":"SPAE: Semantic Pyramid AutoEncoder for Multimodal Generation with Frozen LLMs","created":"2023-06-30","cited_by_count":55,"area":null},{"id":"2310.16338","title":"Generative Pre-training for Speech with Flow Matching","created":"2023-10-25","cited_by_count":55,"area":"diffusion"},{"id":"2306.03509","title":"Mega-TTS: Zero-Shot Text-to-Speech at Scale with Intrinsic Inductive Bias","created":"2023-06-06","cited_by_count":51,"area":null},{"id":"2305.15719","title":"Efficient Neural Music Generation","created":"2023-05-25","cited_by_count":50,"area":null},{"id":"2401.04577","title":"Masked Audio Generation using a Single Non-Autoregressive Transformer","created":"2024-01-09","cited_by_count":50,"area":null},{"id":"2401.07333","title":"ELLA-V: Stable Neural Codec Language Modeling with Alignment-guided Sequence Reordering","created":"2024-01-14","cited_by_count":50,"area":null},{"id":"2506.03719","title":"On the Closed-Form of Flow Matching: Generalization Does Not Arise from Target Stochasticity","created":"2025-06-04","cited_by_count":50,"area":"diffusion"},{"id":"2411.19842","title":"Scaling Transformers for Low-Bitrate High-Quality Speech Coding","created":"2024-11-29","cited_by_count":49,"area":null},{"id":"2301.00591","title":"Analysing Discrete Self Supervised Speech Representation for Spoken Language Modeling","created":"2023-01-02","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":"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":"2412.02692","title":"Scalable Image Tokenization with Index Backpropagation Quantization","created":"2024-12-03","cited_by_count":44,"area":null},{"id":"2410.14411","title":"SNAC: Multi-Scale Neural Audio Codec","created":"2024-10-18","cited_by_count":43,"area":null},{"id":"2502.06490","title":"Recent Advances in Discrete Speech Tokens: A Review","created":"2025-02-10","cited_by_count":43,"area":null},{"id":"2309.15800","title":"Exploring Speech Recognition, Translation, and Understanding with Discrete Speech Units: A Comparative Study","created":"2023-09-27","cited_by_count":42,"area":null},{"id":"2308.04729","title":"JEN-1: Text-Guided Universal Music Generation with Omnidirectional Diffusion Models","created":"2023-08-09","cited_by_count":41,"area":"diffusion"},{"id":"2404.02677","title":"The VoicePrivacy 2024 Challenge Evaluation Plan","created":"2024-04-03","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":"2305.18378","title":"Disentanglement via Latent Quantization","created":"2023-05-28","cited_by_count":40,"area":null},{"id":"2506.19774","title":"Kling-Foley: Multimodal Diffusion Transformer for High-Quality Video-to-Audio Generation","created":"2025-06-24","cited_by_count":40,"area":"diffusion"},{"id":"2407.09499","title":"Self-Consuming Generative Models with Curated Data Provably Optimize Human Preferences","created":"2024-06-12","cited_by_count":39,"area":"alignment"},{"id":"2311.16093","title":"Visual cognition in multimodal large language models","created":"2023-11-27","cited_by_count":38,"area":"mllm"},{"id":"2406.07855","title":"VALL-E R: Robust and Efficient Zero-Shot Text-to-Speech Synthesis via Monotonic Alignment","created":"2024-06-12","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":"2312.11529","title":"Efficient and Scalable Graph Generation through Iterative Local Expansion","created":"2023-12-14","cited_by_count":36,"area":null},{"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":"2406.05551","title":"Autoregressive Diffusion Transformer for Text-to-Speech Synthesis","created":"2024-06-08","cited_by_count":34,"area":"diffusion"}],"next_cursor":"100"}