{"list":"other","total":53,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2106.07447","title":"HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units","created":"2021-06-14","cited_by_count":2342},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"id":"1804.08771","title":"A Call for Clarity in Reporting BLEU Scores","created":"2018-04-23","cited_by_count":1799},{"id":"1904.01038","title":"fairseq: A Fast, Extensible Toolkit for Sequence Modeling","created":"2019-04-01","cited_by_count":1488},{"id":"2010.05646","title":"HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis","created":"2020-10-12","cited_by_count":1154},{"id":"2301.02111","title":"Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers","created":"2023-01-05","cited_by_count":752},{"id":"2209.03143","title":"AudioLM: a Language Modeling Approach to Audio Generation","created":"2022-09-07","cited_by_count":616},{"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":"2305.11000","title":"SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities","created":"2023-05-18","cited_by_count":529},{"id":"2402.12226","title":"AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling","created":"2024-02-19","cited_by_count":217},{"id":"2408.16725","title":"Mini-Omni: Language Models Can Hear, Talk While Thinking in Streaming","created":"2024-08-29","cited_by_count":210},{"id":"2312.05187","title":"Seamless: Multilingual Expressive and Streaming Speech Translation","created":"2023-12-08","cited_by_count":192},{"id":"2107.05604","title":"Direct speech-to-speech translation with discrete units","created":"2021-07-12","cited_by_count":149},{"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":"2307.11795","title":"Prompting Large Language Models with Speech Recognition Abilities","created":"2023-07-21","cited_by_count":140},{"id":"2305.04160","title":"X-LLM: Bootstrapping Advanced Large Language Models by Treating Multi-Modalities as Foreign Languages","created":"2023-05-07","cited_by_count":128},{"id":"1904.06037","title":"Direct speech-to-speech translation with a sequence-to-sequence model","created":"2019-04-12","cited_by_count":118},{"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":"1610.00388","title":"Learning to Translate in Real-time with Neural Machine Translation","created":"2016-10-03","cited_by_count":97},{"id":"2004.07437","title":"Non-Autoregressive Machine Translation with Latent Alignments","created":"2020-04-16","cited_by_count":96},{"id":"2007.16193","title":"SimulEval: An Evaluation Toolkit for Simultaneous Translation","created":"2020-07-31","cited_by_count":94},{"id":"1909.12406","title":"Monotonic Multihead Attention","created":"2019-09-26","cited_by_count":93},{"id":"2410.03751","title":"Recent Advances in Speech Language Models: A Survey","created":"2024-10-01","cited_by_count":87},{"id":"2004.10234","title":"ESPnet-ST: All-in-One Speech Translation Toolkit","created":"2020-04-21","cited_by_count":82},{"id":"2011.02048","title":"SimulMT to SimulST: Adapting Simultaneous Text Translation to End-to-End Simultaneous Speech Translation","created":"2020-11-03","cited_by_count":81},{"id":"1905.11235","title":"CIF: Continuous Integrate-and-Fire for End-to-End Speech Recognition","created":"2019-05-27","cited_by_count":77},{"id":"2107.08661","title":"Translatotron 2: High-quality direct speech-to-speech translation with voice preservation","created":"2021-07-19","cited_by_count":71},{"id":"2408.02622","title":"Language Model Can Listen While Speaking","created":"2024-08-05","cited_by_count":63},{"id":"2212.08055","title":"UnitY: Two-pass Direct Speech-to-speech Translation with Discrete Units","created":"2022-12-15","cited_by_count":60},{"id":"2206.05807","title":"Over-Generation Cannot Be Rewarded: Length-Adaptive Average Lagging for Simultaneous Speech Translation","created":"2022-06-12","cited_by_count":57},{"id":"2005.11185","title":"Low-Latency Sequence-to-Sequence Speech Recognition and Translation by Partial Hypothesis Selection","created":"2020-05-22","cited_by_count":49},{"id":"2106.04833","title":"RealTranS: End-to-End Simultaneous Speech Translation with Convolutional Weighted-Shrinking Transformer","created":"2021-06-09","cited_by_count":40},{"id":"2305.11408","title":"AlignAtt: Using Attention-based Audio-Translation Alignments as a Guide for Simultaneous Speech Translation","created":"2023-05-19","cited_by_count":35},{"id":"2402.04636","title":"TransLLaMa: LLM-based Simultaneous Translation System","created":"2024-02-07","cited_by_count":34},{"id":"2212.07850","title":"Attention as a Guide for Simultaneous Speech Translation","created":"2022-12-15","cited_by_count":32},{"id":"2204.05352","title":"Large-Scale Streaming End-to-End Speech Translation with Neural Transducers","created":"2022-04-11","cited_by_count":31},{"id":"2109.07368","title":"Learning When to Translate for Streaming Speech","created":"2021-09-15","cited_by_count":30},{"id":"2305.03101","title":"Hybrid Transducer and Attention based Encoder-Decoder Modeling for Speech-to-Text Tasks","created":"2023-05-04","cited_by_count":20},{"id":"2406.19954","title":"BESTOW: Efficient and Streamable Speech Language Model with the Best of Two Worlds in GPT and T5","created":"2024-06-28","cited_by_count":19},{"id":"2211.13173","title":"Average Token Delay: A Latency Metric for Simultaneous Translation","created":"2022-11-22","cited_by_count":15},{"id":"2406.09569","title":"Speech ReaLLM -- Real-time Streaming Speech Recognition with Multimodal LLMs by Teaching the Flow of Time","created":"2024-06-13","cited_by_count":15},{"id":"2204.09595","title":"Exploring Continuous Integrate-and-Fire for Adaptive Simultaneous Speech Translation","created":"2022-03-22","cited_by_count":14},{"id":"2405.17809","title":"TransVIP: Speech to Speech Translation System with Voice and Isochrony Preservation","created":"2024-05-28","cited_by_count":10},{"id":"2406.13476","title":"LLMs Are Zero-Shot Context-Aware Simultaneous Translators","created":"2024-06-19","cited_by_count":10},{"id":"2311.11353","title":"Label-Synchronous Neural Transducer for Adaptable Online E2E Speech Recognition","created":"2023-11-19","cited_by_count":5},{"id":"2406.04541","title":"Label-Synchronous Neural Transducer for E2E Simultaneous Speech Translation","created":"2024-06-06","cited_by_count":5},{"id":"2410.03298","title":"Textless Streaming Speech-to-Speech Translation using Semantic Speech Tokens","created":"2024-10-04","cited_by_count":5},{"id":"2411.17170","title":"Overcoming Non-monotonicity in Transducer-based Streaming Generation","created":"2024-11-26","cited_by_count":4}],"next_cursor":null}