{"list":"other","total":102,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"2503.19786","title":"Gemma 3 Technical Report","created":"2025-03-25","cited_by_count":1824},{"id":"1912.06670","title":"Common Voice: A Massively-Multilingual Speech Corpus","created":"2019-12-13","cited_by_count":1384},{"id":"1804.03209","title":"Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition","created":"2018-04-09","cited_by_count":752},{"id":"1706.08612","title":"VoxCeleb: a large-scale speaker identification dataset","created":"2017-06-26","cited_by_count":732},{"id":"1312.6211","title":"An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks","created":"2013-12-21","cited_by_count":722},{"id":"2211.06687","title":"Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation","created":"2022-11-12","cited_by_count":719},{"id":"2312.07533","title":"VILA: On Pre-training for Visual Language Models","created":"2023-12-12","cited_by_count":692},{"id":"2105.01051","title":"SUPERB: Speech processing Universal PERformance Benchmark","created":"2021-05-03","cited_by_count":666},{"id":"1810.02508","title":"MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations","created":"2018-10-05","cited_by_count":643},{"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":"2304.15010","title":"LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model","created":"2023-04-28","cited_by_count":602},{"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":"2305.03726","title":"Otter: A Multi-Modal Model with In-Context Instruction Tuning","created":"2023-05-05","cited_by_count":550},{"id":"2503.01743","title":"Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs","created":"2025-03-03","cited_by_count":521},{"id":"2310.13289","title":"SALMONN: Towards Generic Hearing Abilities for Large Language Models","created":"2023-10-20","cited_by_count":506},{"id":"1510.08484","title":"MUSAN: A Music, Speech, and Noise Corpus","created":"2015-10-28","cited_by_count":425},{"id":"2212.09689","title":"Unnatural Instructions: Tuning Language Models with (Almost) No Human Labor","created":"2022-12-19","cited_by_count":397},{"id":"1910.09387","title":"Clotho: An Audio Captioning Dataset","created":"2019-10-21","cited_by_count":358},{"id":"2010.00475","title":"FSD50K: An Open Dataset of Human-Labeled Sound Events","created":"2020-10-01","cited_by_count":342},{"id":"2308.12032","title":"From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning","created":"2023-08-23","cited_by_count":307},{"id":"2410.19168","title":"MMAU: A Massive Multi-Task Audio Understanding and Reasoning Benchmark","created":"2024-10-24","cited_by_count":288},{"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},{"id":"1704.01279","title":"Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders","created":"2017-04-05","cited_by_count":225},{"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":"2305.10790","title":"Listen, Think, and Understand","created":"2023-05-18","cited_by_count":209},{"id":"1612.01840","title":"FMA: A Dataset For Music Analysis","created":"2016-12-06","cited_by_count":207},{"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},{"id":"2410.17196","title":"VoiceBench: Benchmarking LLM-Based Voice Assistants","created":"2024-10-22","cited_by_count":200},{"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},{"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},{"id":"2406.11768","title":"GAMA: A Large Audio-Language Model with Advanced Audio Understanding and Complex Reasoning Abilities","created":"2024-06-17","cited_by_count":156},{"id":"2308.06259","title":"Self-Alignment with Instruction Backtranslation","created":"2023-08-11","cited_by_count":151},{"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},{"id":"2406.16020","title":"AudioBench: A Universal Benchmark for Audio Large Language Models","created":"2024-06-23","cited_by_count":128},{"id":"2407.12580","title":"E5-V: Universal Embeddings with Multimodal Large Language Models","created":"2024-07-17","cited_by_count":126},{"id":"2010.14794","title":"Seen and Unseen emotional style transfer for voice conversion with a new emotional speech dataset","created":"2020-10-28","cited_by_count":121},{"id":"2504.08528","title":"On The Landscape of Spoken Language Models: A Comprehensive Survey","created":"2025-04-11","cited_by_count":118},{"id":"2211.12171","title":"PromptTTS: Controllable Text-to-Speech with Text Descriptions","created":"2022-11-22","cited_by_count":110},{"id":"2404.00656","title":"WavLLM: Towards Robust and Adaptive Speech Large Language Model","created":"2024-03-31","cited_by_count":109},{"id":"2408.11791","title":"Critique-out-Loud Reward Models","created":"2024-08-21","cited_by_count":106},{"id":"2305.18802","title":"LibriTTS-R: A Restored Multi-Speaker Text-to-Speech Corpus","created":"2023-05-30","cited_by_count":101},{"id":"2309.09510","title":"Dynamic-SUPERB: Towards A Dynamic, Collaborative, and Comprehensive Instruction-Tuning Benchmark for Speech","created":"2023-09-18","cited_by_count":101},{"id":"2309.14405","title":"Joint Audio and Speech Understanding","created":"2023-09-25","cited_by_count":100},{"id":"2308.05725","title":"EXPRESSO: A Benchmark and Analysis of Discrete Expressive Speech Resynthesis","created":"2023-08-10","cited_by_count":98},{"id":"2402.13669","title":"Self-Distillation Bridges Distribution Gap in Language Model Fine-Tuning","created":"2024-02-21","cited_by_count":96},{"id":"2411.13577","title":"WavChat: A Survey of Spoken Dialogue Models","created":"2024-11-15","cited_by_count":90},{"id":"2410.03751","title":"Recent Advances in Speech Language Models: A Survey","created":"2024-10-01","cited_by_count":87},{"id":"2307.16645","title":"Scaling Sentence Embeddings with Large Language Models","created":"2023-07-31","cited_by_count":85},{"id":"2203.03022","title":"HEAR: Holistic Evaluation of Audio Representations","created":"2022-03-06","cited_by_count":78},{"id":"2110.07393","title":"M2MeT: The ICASSP 2022 Multi-Channel Multi-Party Meeting Transcription Challenge","created":"2021-10-14","cited_by_count":71},{"id":"2410.18908","title":"A Survey on Speech Large Language Models for Understanding","created":"2024-10-24","cited_by_count":71},{"id":"2411.05361","title":"Dynamic-SUPERB Phase-2: A Collaboratively Expanding Benchmark for Measuring the Capabilities of Spoken Language Models with 180 Tasks","created":"2024-11-08","cited_by_count":71},{"id":"2207.01063","title":"DailyTalk: Spoken Dialogue Dataset for Conversational Text-to-Speech","created":"2022-07-03","cited_by_count":69},{"id":"2205.03433","title":"Vocalsound: A Dataset for Improving Human Vocal Sounds Recognition","created":"2022-05-06","cited_by_count":62},{"id":"2501.07246","title":"Audio-CoT: Exploring Chain-of-Thought Reasoning in Large Audio Language Model","created":"2025-01-13","cited_by_count":62},{"id":"1806.09514","title":"The Emotional Voices Database: Towards Controlling the Emotion Dimension in Voice Generation Systems","created":"2018-06-25","cited_by_count":61},{"id":"2112.10358","title":"Multi-Singer: Fast Multi-Singer Singing Voice Vocoder With A Large-Scale Corpus","created":"2021-12-20","cited_by_count":60},{"id":"2311.06753","title":"AudioChatLlama: Towards General-Purpose Speech Abilities for LLMs","created":"2023-11-12","cited_by_count":59},{"id":"2102.05889","title":"ASVspoof 2019: spoofing countermeasures for the detection of synthesized, converted and replayed speech","created":"2021-02-11","cited_by_count":58},{"id":"2310.06434","title":"Whispering LLaMA: A Cross-Modal Generative Error Correction Framework for Speech Recognition","created":"2023-10-10","cited_by_count":56},{"id":"2409.20007","title":"DeSTA2: Developing Instruction-Following Speech Language Model Without Speech Instruction-Tuning Data","created":"2024-09-30","cited_by_count":45},{"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},{"id":"2404.09385","title":"A Large-Scale Evaluation of Speech Foundation Models","created":"2024-04-15","cited_by_count":40},{"id":"2410.02678","title":"Distilling an End-to-End Voice Assistant Without Instruction Training Data","created":"2024-10-03","cited_by_count":39},{"id":"2505.15957","title":"Towards Holistic Evaluation of Large Audio-Language Models: A Comprehensive Survey","created":"2025-05-21","cited_by_count":39},{"id":"2406.18871","title":"DeSTA: Enhancing Speech Language Models through Descriptive Speech-Text Alignment","created":"2024-06-27","cited_by_count":33},{"id":"2311.09193","title":"The Role of Chain-of-Thought in Complex Vision-Language Reasoning Task","created":"2023-11-15","cited_by_count":32},{"id":"2406.14875","title":"GLOBE: A High-quality English Corpus with Global Accents for Zero-shot Speaker Adaptive Text-to-Speech","created":"2024-06-21","cited_by_count":30},{"id":"2407.09886","title":"Speech-Copilot: Leveraging Large Language Models for Speech Processing via Task Decomposition, Modularization, and Program Generation","created":"2024-07-13","cited_by_count":27},{"id":"2505.19037","title":"Speech-IFEval: Evaluating Instruction-Following and Quantifying Catastrophic Forgetting in Speech-Aware Language Models","created":"2025-05-25","cited_by_count":27},{"id":"2408.12734","title":"Towards measuring fairness in speech recognition: Fair-Speech dataset","created":"2024-08-22","cited_by_count":26},{"id":"2501.17202","title":"Audio Large Language Models Can Be Descriptive Speech Quality Evaluators","created":"2025-01-27","cited_by_count":25},{"id":"2411.07111","title":"Building a Taiwanese Mandarin Spoken Language Model: A First Attempt","created":"2024-11-11","cited_by_count":23},{"id":"2005.07973","title":"AccentDB: A Database of Non-Native English Accents to Assist Neural Speech Recognition","created":"2020-05-16","cited_by_count":19},{"id":"2503.04381","title":"TRACT: Regression-Aware Fine-tuning Meets Chain-of-Thought Reasoning for LLM-as-a-Judge","created":"2025-03-06","cited_by_count":17},{"id":"2406.07237","title":"CodecFake: Enhancing Anti-Spoofing Models Against Deepfake Audios from Codec-Based Speech Synthesis Systems","created":"2024-06-11","cited_by_count":16},{"id":"2402.11192","title":"I Learn Better If You Speak My Language: Understanding the Superior Performance of Fine-Tuning Large Language Models with LLM-Generated Responses","created":"2024-02-17","cited_by_count":15},{"id":"2504.09081","title":"SIFT-50M: A Large-Scale Multilingual Dataset for Speech Instruction Fine-Tuning","created":"2025-04-12","cited_by_count":14},{"id":"2401.00273","title":"Investigating Zero-Shot Generalizability on Mandarin-English Code-Switched ASR and Speech-to-text Translation of Recent Foundation Models with Self-Supervision and Weak Supervision","created":"2023-12-30","cited_by_count":13},{"id":"2310.03018","title":"Zero Resource Code-switched Speech Benchmark Using Speech Utterance Pairs For Multiple Spoken Languages","created":"2023-10-04","cited_by_count":12},{"id":"2406.11064","title":"Continual Test-time Adaptation for End-to-end Speech Recognition on Noisy Speech","created":"2024-06-16","cited_by_count":12},{"id":"2309.12766","title":"A Study on Incorporating Whisper for Robust Speech Assessment","created":"2023-09-22","cited_by_count":11},{"id":"2505.17496","title":"Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models","created":"2025-05-23","cited_by_count":11},{"id":"2305.13137","title":"EMNS /Imz/ Corpus: An emotive single-speaker dataset for narrative storytelling in games, television and graphic novels","created":"2023-05-22","cited_by_count":7},{"id":"2408.13891","title":"SpeechCaps: Advancing Instruction-Based Universal Speech Models with Multi-Talker Speaking Style Captioning","created":"2024-08-25","cited_by_count":6},{"id":"2501.08238","title":"CodecFake+: Codec-Based Resynthesized Data as a Proxy for Detecting CodecFake Speech","created":"2025-01-14","cited_by_count":6},{"id":"2212.12266","title":"Large Raw Emotional Dataset with Aggregation Mechanism","created":"2022-12-23","cited_by_count":5}],"next_cursor":"100"}