{"list":"other","total":51,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"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":"2503.06749","title":"Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models","created":"2025-03-09","cited_by_count":665},{"id":"2004.14368","title":"VGGSound: A Large-scale Audio-Visual Dataset","created":"2020-04-29","cited_by_count":648},{"id":"1811.02508","title":"SDR - half-baked or well done?","created":"2018-11-06","cited_by_count":423},{"id":"1809.07454","title":"Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation","created":"2018-09-20","cited_by_count":406},{"id":"2503.12937","title":"R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization","created":"2025-03-17","cited_by_count":301},{"id":"1804.03160","title":"The Sound of Pixels","created":"2018-04-09","cited_by_count":259},{"id":"1607.00325","title":"Permutation Invariant Training of Deep Models for Speaker-Independent Multi-talker Speech Separation","created":"2016-07-01","cited_by_count":191},{"id":"2010.13154","title":"Attention is All You Need in Speech Separation","created":"2020-10-25","cited_by_count":185},{"id":"2211.08553","title":"Hybrid Transformers for Music Source Separation","created":"2022-11-15","cited_by_count":134},{"id":"1711.00541","title":"TasNet: time-domain audio separation network for real-time, single-channel speech separation","created":"2017-11-01","cited_by_count":115},{"id":"2101.03149","title":"VisualVoice: Audio-Visual Speech Separation with Cross-Modal Consistency","created":"2021-01-08","cited_by_count":114},{"id":"2008.09586","title":"An Overview of Deep-Learning-Based Audio-Visual Speech Enhancement and Separation","created":"2020-08-21","cited_by_count":81},{"id":"2002.08933","title":"Wavesplit: End-to-End Speech Separation by Speaker Clustering","created":"2020-02-20","cited_by_count":75},{"id":"2209.15174","title":"Music Source Separation with Band-split RNN","created":"2022-09-30","cited_by_count":70},{"id":"2505.02835","title":"R1-Reward: Training Multimodal Reward Model Through Stable Reinforcement Learning","created":"2025-05-05","cited_by_count":65},{"id":"2203.15147","title":"Separate What You Describe: Language-Queried Audio Source Separation","created":"2022-03-28","cited_by_count":45},{"id":"2308.05037","title":"Separate Anything You Describe","created":"2023-08-09","cited_by_count":43},{"id":"1804.06267","title":"The 2018 Signal Separation Evaluation Campaign","created":"2018-04-17","cited_by_count":41},{"id":"1905.03330","title":"Universal Sound Separation","created":"2019-05-08","cited_by_count":41},{"id":"2105.07142","title":"Move2Hear: Active Audio-Visual Source Separation","created":"2021-05-15","cited_by_count":35},{"id":"2212.03814","title":"iQuery: Instruments as Queries for Audio-Visual Sound Separation","created":"2022-12-07","cited_by_count":29},{"id":"2112.07891","title":"Zero-shot Audio Source Separation through Query-based Learning from Weakly-labeled Data","created":"2021-12-15","cited_by_count":27},{"id":"2212.07065","title":"CLIPSep: Learning Text-queried Sound Separation with Noisy Unlabeled Videos","created":"2022-12-14","cited_by_count":23},{"id":"2409.07614","title":"FlowSep: Language-Queried Sound Separation with Rectified Flow Matching","created":"2024-09-11","cited_by_count":21},{"id":"2303.16342","title":"Language-Guided Audio-Visual Source Separation via Trimodal Consistency","created":"2023-03-28","cited_by_count":20},{"id":"1908.06593","title":"Audio query-based music source separation","created":"2019-08-19","cited_by_count":17},{"id":"2308.00122","title":"High-Quality Visually-Guided Sound Separation from Diverse Categories","created":"2023-07-31","cited_by_count":11},{"id":"1611.06265","title":"Deep Clustering and Conventional Networks for Music Separation: Stronger Together","created":"2016-11-18","cited_by_count":10},{"id":"2402.17455","title":"CLAPSep: Leveraging Contrastive Pre-trained Model for Multi-Modal Query-Conditioned Target Sound Extraction","created":"2024-02-27","cited_by_count":9},{"id":"2501.01384","title":"OmniChat: Enhancing Spoken Dialogue Systems with Scalable Synthetic Data for Diverse Scenarios","created":"2025-01-02","cited_by_count":9},{"id":"2210.12108","title":"Adversarial Permutation Invariant Training for Universal Sound Separation","created":"2022-10-21","cited_by_count":8},{"id":"2306.06410","title":"OpenSR: Open-Modality Speech Recognition via Maintaining Multi-Modality Alignment","created":"2023-06-10","cited_by_count":8},{"id":"2310.20446","title":"LAVSS: Location-Guided Audio-Visual Spatial Audio Separation","created":"2023-10-31","cited_by_count":8},{"id":"2403.02288","title":"PixIT: Joint Training of Speaker Diarization and Speech Separation from Real-world Multi-speaker Recordings","created":"2024-03-04","cited_by_count":8},{"id":"2410.21269","title":"OmniSep: Unified Omni-Modality Sound Separation with Query-Mixup","created":"2024-10-28","cited_by_count":8},{"id":"2411.02860","title":"Continual Audio-Visual Sound Separation","created":"2024-11-05","cited_by_count":7},{"id":"2407.04936","title":"A Reference-free Metric for Language-Queried Audio Source Separation using Contrastive Language-Audio Pretraining","created":"2024-07-06","cited_by_count":5},{"id":"2409.13292","title":"Exploring Text-Queried Sound Event Detection with Audio Source Separation","created":"2024-09-20","cited_by_count":5},{"id":"2310.11713","title":"Separating Invisible Sounds Toward Universal Audiovisual Scene-Aware Sound Separation","created":"2023-10-18","cited_by_count":4},{"id":"2505.23625","title":"ZeroSep: Separate Anything in Audio with Zero Training","created":"2025-05-29","cited_by_count":4},{"id":"2106.08703","title":"Source Separation-based Data Augmentation for Improved Joint Beat and Downbeat Tracking","created":"2021-06-16","cited_by_count":2},{"id":"2203.15092","title":"Improved singing voice separation with chromagram-based pitch-aware remixing","created":"2022-03-28","cited_by_count":2},{"id":"2409.19270","title":"OpenSep: Leveraging Large Language Models with Textual Inversion for Open World Audio Separation","created":"2024-09-28","cited_by_count":2},{"id":"2509.22063","title":"High-Quality Sound Separation Across Diverse Categories via Visually-Guided Generative Modeling","created":"2025-09-26","cited_by_count":2},{"id":"2504.17782","title":"Unleashing the Power of Natural Audio Featuring Multiple Sound Sources","created":"2025-04-24","cited_by_count":1}],"next_cursor":null}