{"list":"other","total":57,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"2311.10122","title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","created":"2023-11-16","cited_by_count":1402},{"id":"2404.04475","title":"Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators","created":"2024-04-06","cited_by_count":897},{"id":"2304.00685","title":"Vision-Language Models for Vision Tasks: A Survey","created":"2023-04-03","cited_by_count":839},{"id":"2301.02111","title":"Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers","created":"2023-01-05","cited_by_count":752},{"id":"2503.20215","title":"Qwen2.5-Omni Technical Report","created":"2025-03-26","cited_by_count":736},{"id":"2401.10020","title":"Self-Rewarding Language Models","created":"2024-01-18","cited_by_count":681},{"id":"2310.12773","title":"Safe RLHF: Safe Reinforcement Learning from Human Feedback","created":"2023-10-19","cited_by_count":656},{"id":"1904.02882","title":"LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech","created":"2019-04-05","cited_by_count":649},{"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},{"id":"2410.00037","title":"Moshi: a speech-text foundation model for real-time dialogue","created":"2024-09-17","cited_by_count":568},{"id":"2407.10759","title":"Qwen2-Audio Technical Report","created":"2024-07-15","cited_by_count":560},{"id":"2401.01335","title":"Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models","created":"2024-01-02","cited_by_count":557},{"id":"1612.00563","title":"Self-critical Sequence Training for Image Captioning","created":"2016-12-02","cited_by_count":547},{"id":"2305.11000","title":"SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities","created":"2023-05-18","cited_by_count":529},{"id":"2310.13289","title":"SALMONN: Towards Generic Hearing Abilities for Large Language Models","created":"2023-10-20","cited_by_count":506},{"id":"2205.12446","title":"FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech","created":"2022-05-25","cited_by_count":469},{"id":"2406.08464","title":"Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing","created":"2024-06-12","cited_by_count":346},{"id":"2306.12925","title":"AudioPaLM: A Large Language Model That Can Speak and Listen","created":"2023-06-22","cited_by_count":343},{"id":"2102.01192","title":"Generative Spoken Language Modeling from Raw Audio","created":"2021-02-01","cited_by_count":340},{"id":"2407.05407","title":"CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens","created":"2024-07-07","cited_by_count":334},{"id":"2405.07863","title":"RLHF Workflow: From Reward Modeling to Online RLHF","created":"2024-05-13","cited_by_count":267},{"id":"2412.02612","title":"GLM-4-Voice: Towards Intelligent and Human-Like End-to-End Spoken Chatbot","created":"2024-12-03","cited_by_count":224},{"id":"2504.18425","title":"Kimi-Audio Technical Report","created":"2025-04-25","cited_by_count":222},{"id":"2507.08128","title":"Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models","created":"2025-07-10","cited_by_count":219},{"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},{"id":"2408.16532","title":"WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modeling","created":"2024-08-29","cited_by_count":129},{"id":"2310.00704","title":"UniAudio: An Audio Foundation Model Toward Universal Audio Generation","created":"2023-10-01","cited_by_count":127},{"id":"2308.11596","title":"SeamlessM4T: Massively Multilingual & Multimodal Machine Translation","created":"2023-08-22","cited_by_count":125},{"id":"2402.10571","title":"Direct Preference Optimization with an Offset","created":"2024-02-16","cited_by_count":122},{"id":"2505.13032","title":"MMAR: A Challenging Benchmark for Deep Reasoning in Speech, Audio, Music, and Their Mix","created":"2025-05-19","cited_by_count":117},{"id":"2404.00656","title":"WavLLM: Towards Robust and Adaptive Speech Large Language Model","created":"2024-03-31","cited_by_count":109},{"id":"2305.15255","title":"Spoken Question Answering and Speech Continuation Using Spectrogram-Powered LLM","created":"2023-05-24","cited_by_count":94},{"id":"2309.00916","title":"BLSP: Bootstrapping Language-Speech Pre-training via Behavior Alignment of Continuation Writing","created":"2023-09-02","cited_by_count":79},{"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},{"id":"1808.08866","title":"A Study of Reinforcement Learning for Neural Machine Translation","created":"2018-08-27","cited_by_count":74},{"id":"1712.01818","title":"Minimum Word Error Rate Training for Attention-based Sequence-to-Sequence Models","created":"2017-12-05","cited_by_count":68},{"id":"2405.08295","title":"SpeechVerse: A Large-scale Generalizable Audio Language Model","created":"2024-05-14","cited_by_count":63},{"id":"2311.06753","title":"AudioChatLlama: Towards General-Purpose Speech Abilities for LLMs","created":"2023-11-12","cited_by_count":59},{"id":"2308.15930","title":"LLaSM: Large Language and Speech Model","created":"2023-08-30","cited_by_count":58},{"id":"2411.17607","title":"Scaling Speech-Text Pre-training with Synthetic Interleaved Data","created":"2024-11-26","cited_by_count":47},{"id":"2504.15900","title":"SARI: Structured Audio Reasoning via Curriculum-Guided Reinforcement Learning","created":"2025-04-22","cited_by_count":34},{"id":"1306.6294","title":"Learning Trajectory Preferences for Manipulators via Iterative Improvement","created":"2013-06-26","cited_by_count":31},{"id":"2505.03739","title":"VITA-Audio: Fast Interleaved Cross-Modal Token Generation for Efficient Large Speech-Language Model","created":"2025-05-06","cited_by_count":31},{"id":"2312.15316","title":"Paralinguistics-Enhanced Large Language Modeling of Spoken Dialogue","created":"2023-12-23","cited_by_count":25},{"id":"2503.03746","title":"Process-based Self-Rewarding Language Models","created":"2025-03-05","cited_by_count":22},{"id":"2508.08039","title":"Audio-Thinker: Guiding Audio Language Model When and How to Think via Reinforcement Learning","created":"2025-08-11","cited_by_count":19},{"id":"2409.11538","title":"Chain-of-Thought Prompting for Speech Translation","created":"2024-09-17","cited_by_count":17},{"id":"2506.12935","title":"SoundMind: RL-Incentivized Logic Reasoning for Audio-Language Models","created":"2025-06-15","cited_by_count":15},{"id":"2402.05706","title":"Paralinguistics-Aware Speech-Empowered Large Language Models for Natural Conversation","created":"2024-02-08","cited_by_count":14},{"id":"2508.02018","title":"SpeechR: A Benchmark for Speech Reasoning in Large Audio-Language Models","created":"2025-08-04","cited_by_count":14}],"next_cursor":null}