{"list":"other","total":69,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"2004.04906","title":"Dense Passage Retrieval for Open-Domain Question Answering","created":"2020-04-10","cited_by_count":3824},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"1702.08734","title":"Billion-scale similarity search with GPUs","created":"2017-02-28","cited_by_count":2497},{"id":"2002.08909","title":"REALM: Retrieval-Augmented Language Model Pre-Training","created":"2020-02-10","cited_by_count":2141},{"id":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071},{"id":"2112.04426","title":"Improving language models by retrieving from trillions of tokens","created":"2021-12-08","cited_by_count":1293},{"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":"2210.13438","title":"High Fidelity Neural Audio Compression","created":"2022-10-24","cited_by_count":687},{"id":"2106.13884","title":"Multimodal Few-Shot Learning with Frozen Language Models","created":"2021-06-25","cited_by_count":661},{"id":"1810.02508","title":"MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations","created":"2018-10-05","cited_by_count":643},{"id":"2104.01778","title":"AST: Audio Spectrogram Transformer","created":"2021-04-05","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":"2004.09813","title":"Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation","created":"2020-04-21","cited_by_count":593},{"id":"1912.10211","title":"PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition","created":"2019-12-21","cited_by_count":574},{"id":"2309.05463","title":"Textbooks Are All You Need II: phi-1.5 technical report","created":"2023-09-11","cited_by_count":565},{"id":"2310.13289","title":"SALMONN: Towards Generic Hearing Abilities for Large Language Models","created":"2023-10-20","cited_by_count":506},{"id":"2301.11325","title":"MusicLM: Generating Music From Text","created":"2023-01-26","cited_by_count":448},{"id":"1910.09387","title":"Clotho: An Audio Captioning Dataset","created":"2019-10-21","cited_by_count":358},{"id":"2306.12925","title":"AudioPaLM: A Large Language Model That Can Speak and Listen","created":"2023-06-22","cited_by_count":343},{"id":"2010.00475","title":"FSD50K: An Open Dataset of Human-Labeled Sound Events","created":"2020-10-01","cited_by_count":342},{"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":"2304.12995","title":"AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head","created":"2023-04-25","cited_by_count":265},{"id":"2212.12017","title":"OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalization","created":"2022-12-22","cited_by_count":236},{"id":"1704.01279","title":"Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders","created":"2017-04-05","cited_by_count":225},{"id":"2305.11834","title":"Pengi: An Audio Language Model for Audio Tasks","created":"2023-05-19","cited_by_count":220},{"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":"2203.14072","title":"Learning to Answer Questions in Dynamic Audio-Visual Scenarios","created":"2022-03-26","cited_by_count":191},{"id":"2306.00107","title":"MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training","created":"2023-05-31","cited_by_count":181},{"id":"2202.00874","title":"HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection","created":"2022-02-02","cited_by_count":176},{"id":"2306.09093","title":"Macaw-LLM: Multi-Modal Language Modeling with Image, Audio, Video, and Text Integration","created":"2023-06-15","cited_by_count":172},{"id":"2309.03905","title":"ImageBind-LLM: Multi-modality Instruction Tuning","created":"2023-09-07","cited_by_count":142},{"id":"2309.14405","title":"Joint Audio and Speech Understanding","created":"2023-09-25","cited_by_count":100},{"id":"2309.16058","title":"AnyMAL: An Efficient and Scalable Any-Modality Augmented Language Model","created":"2023-09-27","cited_by_count":93},{"id":"2208.12415","title":"MuLan: A Joint Embedding of Music Audio and Natural Language","created":"2022-08-26","cited_by_count":87},{"id":"2204.09634","title":"Clotho-AQA: A Crowdsourced Dataset for Audio Question Answering","created":"2022-04-20","cited_by_count":85},{"id":"2105.07031","title":"The Benefit Of Temporally-Strong Labels In Audio Event Classification","created":"2021-05-14","cited_by_count":83},{"id":"2307.16372","title":"LP-MusicCaps: LLM-Based Pseudo Music Captioning","created":"2023-07-31","cited_by_count":83},{"id":"2308.11276","title":"Music Understanding LLaMA: Advancing Text-to-Music Generation with Question Answering and Captioning","created":"2023-08-22","cited_by_count":77},{"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},{"id":"2307.03183","title":"Whisper-AT: Noise-Robust Automatic Speech Recognizers are Also Strong General Audio Event Taggers","created":"2023-07-06","cited_by_count":72},{"id":"2305.16103","title":"ChatBridge: Bridging Modalities with Large Language Model as a Language Catalyst","created":"2023-05-25","cited_by_count":66},{"id":"2311.18775","title":"CoDi-2: In-Context, Interleaved, and Interactive Any-to-Any Generation","created":"2023-11-30","cited_by_count":63},{"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":"2309.05767","title":"Natural Language Supervision for General-Purpose Audio Representations","created":"2023-09-11","cited_by_count":61},{"id":"2105.02192","title":"Audio Retrieval with Natural Language Queries","created":"2021-05-05","cited_by_count":49},{"id":"2311.03318","title":"A Foundation Model for Music Informatics","created":"2023-11-06","cited_by_count":46},{"id":"2302.04858","title":"Re-ViLM: Retrieval-Augmented Visual Language Model for Zero and Few-Shot Image Captioning","created":"2023-02-09","cited_by_count":41},{"id":"2209.14275","title":"Audio Retrieval with WavText5K and CLAP Training","created":"2022-09-28","cited_by_count":35},{"id":"2309.07081","title":"Can Whisper perform speech-based in-context learning?","created":"2023-09-13","cited_by_count":35},{"id":"2310.13650","title":"BotChat: Evaluating LLMs' Capabilities of Having Multi-Turn Dialogues","created":"2023-10-20","cited_by_count":34},{"id":"2211.02289","title":"CochlScene: Acquisition of acoustic scene data using crowdsourcing","created":"2022-11-04","cited_by_count":33},{"id":"2309.09836","title":"RECAP: Retrieval-Augmented Audio Captioning","created":"2023-09-18","cited_by_count":27},{"id":"2203.15863","title":"WAVPROMPT: Towards Few-Shot Spoken Language Understanding with Frozen Language Models","created":"2022-03-29","cited_by_count":26},{"id":"1803.05434","title":"The OMG-Emotion Behavior Dataset","created":"2018-03-14","cited_by_count":25},{"id":"2311.08396","title":"Zero-shot audio captioning with audio-language model guidance and audio context keywords","created":"2023-11-14","cited_by_count":11},{"id":"2310.12477","title":"Exploring In-Context Learning of Textless Speech Language Model for Speech Classification Tasks","created":"2023-10-19","cited_by_count":5},{"id":"1708.05604","title":"Accelerating recurrent neural network training using sequence bucketing and multi-GPU data parallelization","created":"2017-08-18","cited_by_count":4},{"id":"2210.05917","title":"Enemy Spotted: in-game gun sound dataset for gunshot classification and localization","created":"2022-10-12","cited_by_count":3}],"next_cursor":null}