{"list":"other","total":59,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2302.04761","title":"Toolformer: Language Models Can Teach Themselves to Use Tools","created":"2023-02-09","cited_by_count":4182},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"2305.10601","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","created":"2023-05-17","cited_by_count":3211},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"2305.04388","title":"Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting","created":"2023-05-07","cited_by_count":1122},{"id":"2412.06769","title":"Training Large Language Models to Reason in a Continuous Latent Space","created":"2024-12-09","cited_by_count":797},{"id":"1904.02882","title":"LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech","created":"2019-04-05","cited_by_count":649},{"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":"2108.08877","title":"Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Models","created":"2021-08-19","cited_by_count":463},{"id":"1510.08484","title":"MUSAN: A Music, Speech, and Noise Corpus","created":"2015-10-28","cited_by_count":425},{"id":"2204.02152","title":"UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022","created":"2022-04-05","cited_by_count":390},{"id":"2412.10117","title":"CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models","created":"2024-12-13","cited_by_count":288},{"id":"2502.17416","title":"Reasoning with Latent Thoughts: On the Power of Looped Transformers","created":"2025-02-24","cited_by_count":240},{"id":"1711.05597","title":"Advances in Variational Inference","created":"2017-11-15","cited_by_count":236},{"id":"1909.09577","title":"NeMo: a toolkit for building AI applications using Neural Modules","created":"2019-09-14","cited_by_count":235},{"id":"1811.06621","title":"Streaming End-to-end Speech Recognition For Mobile Devices","created":"2018-11-15","cited_by_count":234},{"id":"2502.21074","title":"CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillation","created":"2025-02-28","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":"2212.10001","title":"Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matters","created":"2022-12-20","cited_by_count":222},{"id":"2410.17196","title":"VoiceBench: Benchmarking LLM-Based Voice Assistants","created":"2024-10-22","cited_by_count":200},{"id":"1803.09047","title":"Towards End-to-End Prosody Transfer for Expressive Speech Synthesis with Tacotron","created":"2018-03-24","cited_by_count":173},{"id":"2510.25741","title":"Scaling Latent Reasoning via Looped Language Models","created":"2025-10-29","cited_by_count":165},{"id":"2412.02595","title":"Nemotron-CC: Transforming Common Crawl into a Refined Long-Horizon Pretraining Dataset","created":"2024-12-03","cited_by_count":160},{"id":"2411.00774","title":"Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLM","created":"2024-11-01","cited_by_count":141},{"id":"2203.16502","title":"Generative Spoken Dialogue Language Modeling","created":"2022-03-30","cited_by_count":126},{"id":"2305.05084","title":"Fast Conformer with Linearly Scalable Attention for Efficient Speech Recognition","created":"2023-05-08","cited_by_count":124},{"id":"2505.15778","title":"Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space","created":"2025-05-21","cited_by_count":117},{"id":"2502.12134","title":"SoftCoT: Soft Chain-of-Thought for Efficient Reasoning with LLMs","created":"2025-02-17","cited_by_count":116},{"id":"2506.04779","title":"MMSU: A Massive Multi-task Spoken Language Understanding and Reasoning Benchmark","created":"2025-06-05","cited_by_count":103},{"id":"2503.04721","title":"Full-Duplex-Bench: A Benchmark to Evaluate Full-duplex Spoken Dialogue Models on Turn-taking Capabilities","created":"2025-03-06","cited_by_count":100},{"id":"2305.15255","title":"Spoken Question Answering and Speech Continuation Using Spectrogram-Powered LLM","created":"2023-05-24","cited_by_count":94},{"id":"2410.03751","title":"Recent Advances in Speech Language Models: A Survey","created":"2024-10-01","cited_by_count":87},{"id":"2505.12514","title":"Reasoning by Superposition: A Theoretical Perspective on Chain of Continuous Thought","created":"2025-05-18","cited_by_count":77},{"id":"2001.02674","title":"Streaming automatic speech recognition with the transformer model","created":"2020-01-08","cited_by_count":73},{"id":"2409.15594","title":"Beyond Turn-Based Interfaces: Synchronous LLMs as Full-Duplex Dialogue Agents","created":"2024-09-23","cited_by_count":72},{"id":"2502.17239","title":"Baichuan-Audio: A Unified Framework for End-to-End Speech Interaction","created":"2025-02-24","cited_by_count":68},{"id":"2104.01497","title":"Hi-Fi Multi-Speaker English TTS Dataset","created":"2021-04-03","cited_by_count":60},{"id":"2406.00899","title":"YODAS: Youtube-Oriented Dataset for Audio and Speech","created":"2024-06-02","cited_by_count":60},{"id":"2505.20674","title":"PonderLM: Pretraining Language Models to Ponder in Continuous Space","created":"2025-05-27","cited_by_count":44},{"id":"2505.11484","title":"SoftCoT++: Test-Time Scaling with Soft Chain-of-Thought Reasoning","created":"2025-05-16","cited_by_count":41},{"id":"2405.19487","title":"A Full-duplex Speech Dialogue Scheme Based On Large Language Models","created":"2024-05-29","cited_by_count":40},{"id":"2109.12072","title":"SD-QA: Spoken Dialectal Question Answering for the Real World","created":"2021-09-24","cited_by_count":38},{"id":"2505.15670","title":"SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model","created":"2025-05-21","cited_by_count":34},{"id":"2505.17060","title":"SALMONN-omni: A Standalone Speech LLM without Codec Injection for Full-duplex Conversation","created":"2025-05-17","cited_by_count":27},{"id":"2507.15375","title":"STITCH: Simultaneous Thinking and Talking with Chunked Reasoning for Spoken Language Models","created":"2025-07-21","cited_by_count":26},{"id":"2312.17279","title":"Stateful Conformer with Cache-based Inference for Streaming Automatic Speech Recognition","created":"2023-12-27","cited_by_count":25},{"id":"2505.13404","title":"Granary: Speech Recognition and Translation Dataset in 25 European Languages","created":"2025-05-19","cited_by_count":22},{"id":"2406.13858","title":"Distributional reasoning in LLMs: Parallel reasoning processes in multi-hop reasoning","created":"2024-06-19","cited_by_count":21},{"id":"2510.06917","title":"SHANKS: Simultaneous Hearing and Thinking for Spoken Language Models","created":"2025-10-08","cited_by_count":19},{"id":"2509.23365","title":"Emergence of Superposition: Unveiling the Training Dynamics of Chain of Continuous Thought","created":"2025-09-27","cited_by_count":16},{"id":"2510.07497","title":"Can Speech LLMs Think while Listening?","created":"2025-10-08","cited_by_count":16},{"id":"2510.05150","title":"Chronological Thinking in Full-Duplex Spoken Dialogue Language Models","created":"2025-10-02","cited_by_count":14},{"id":"2406.12946","title":"Instruction Data Generation and Unsupervised Adaptation for Speech Language Models","created":"2024-06-18","cited_by_count":9},{"id":"2502.14145","title":"LLM-Enhanced Dialogue Management for Full-Duplex Spoken Dialogue Systems","created":"2025-02-19","cited_by_count":9},{"id":"2510.02066","title":"Chain-of-Thought Reasoning in Streaming Full-Duplex End-to-End Spoken Dialogue Systems","created":"2025-10-02","cited_by_count":5}],"next_cursor":null}