{"url":"/task/fad","name":"FAD","slug":"fad","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"derived"},"counts":{"papers_tagged":62,"papers_with_code":24,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":0,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":24,"of":24,"tagged_in_all":62,"items":[{"url":"/paper/adapting-frechet-audio-distance-for","title":"Adapting Frechet Audio Distance for Generative Music Evaluation","date":"2023-11-02","arxiv_id":"2311.01616","repositories_listed":5,"syntology":{"n":10,"n_ran":5,"n_unverified":5,"n_pointer_only":1}},{"url":"/paper/rethinking-emotion-bias-in-music-via-frechet","title":"Addressing Emotion Bias in Music Emotion Recognition and Generation with Frechet Audio Distance","date":"2024-09-23","arxiv_id":"2409.15545","repositories_listed":2,"syntology":null},{"url":"/paper/bemaganv2-a-tutorial-and-comparative-survey","title":"BemaGANv2: A Tutorial and Comparative Survey of GAN-based Vocoders for Long-Term Audio Generation","date":"2025-06-11","arxiv_id":"2506.09487","repositories_listed":1,"syntology":null},{"url":"/paper/dose-drum-one-shot-extraction-from-music","title":"DOSE : Drum One-Shot Extraction from Music Mixture","date":"2025-04-25","arxiv_id":"2504.18157","repositories_listed":1,"syntology":null},{"url":"/paper/enhance-generation-quality-of-flow-matching","title":"Enhance Generation Quality of Flow Matching V2A Model via Multi-Step CoT-Like Guidance and Combined Preference Optimization","date":"2025-03-28","arxiv_id":"2503.22200","repositories_listed":1,"syntology":null},{"url":"/paper/aligning-text-to-music-evaluation-with-human","title":"Aligning Text-to-Music Evaluation with Human Preferences","date":"2025-03-20","arxiv_id":"2503.16669","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/flowdec-a-flow-based-full-band-general-audio","title":"FlowDec: A flow-based full-band general audio codec with high perceptual quality","date":"2025-03-03","arxiv_id":"2503.01485","repositories_listed":1,"syntology":null},{"url":"/paper/kad-no-more-fad-an-effective-and-efficient","title":"KAD: No More FAD! An Effective and Efficient Evaluation Metric for Audio Generation","date":"2025-02-21","arxiv_id":"2502.15602","repositories_listed":1,"syntology":null},{"url":"/paper/frechet-music-distance-a-metric-for","title":"Frechet Music Distance: A Metric For Generative Symbolic Music Evaluation","date":"2024-12-10","arxiv_id":"2412.07948","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/multi-source-music-generation-with-latent","title":"Multi-Source Music Generation with Latent Diffusion","date":"2024-09-10","arxiv_id":"2409.06190","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/efficient-autoregressive-audio-modeling-via","title":"Efficient Autoregressive Audio Modeling via Next-Scale Prediction","date":"2024-08-16","arxiv_id":"2408.09027","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/l4dr-lidar-4dradar-fusion-for-weather-robust","title":"L4DR: LiDAR-4DRadar Fusion for Weather-Robust 3D Object Detection","date":"2024-08-07","arxiv_id":"2408.03677","repositories_listed":1,"syntology":{"n":8,"n_ran":3,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/taming-data-and-transformers-for-audio-1","title":"Taming Data and Transformers for Audio Generation","date":"2024-06-27","arxiv_id":"2406.19388","repositories_listed":1,"syntology":null},{"url":"/paper/melfusion-synthesizing-music-from-image-and","title":"MeLFusion: Synthesizing Music from Image and Language Cues using Diffusion Models","date":"2024-06-07","arxiv_id":"2406.04673","repositories_listed":1,"syntology":{"n":12,"n_ran":12,"n_unverified":0,"n_pointer_only":12}},{"url":"/paper/reverse-the-auditory-processing-pathway","title":"Reverse the auditory processing pathway: Coarse-to-fine audio reconstruction from fMRI","date":"2024-05-29","arxiv_id":"2405.18726","repositories_listed":1,"syntology":null},{"url":"/paper/latent-clap-loss-for-better-foley-sound","title":"Latent CLAP Loss for Better Foley Sound Synthesis","date":"2024-03-18","arxiv_id":"2403.12182","repositories_listed":1,"syntology":null},{"url":"/paper/amsp-uod-when-vortex-convolution-and","title":"AMSP-UOD: When Vortex Convolution and Stochastic Perturbation Meet Underwater Object Detection","date":"2023-08-23","arxiv_id":"2308.11918","repositories_listed":1,"syntology":{"n":6,"n_ran":2,"n_unverified":4,"n_pointer_only":6}},{"url":"/paper/adapting-offline-speech-translation-models","title":"Adapting Offline Speech Translation Models for Streaming with Future-Aware Distillation and Inference","date":"2023-03-14","arxiv_id":"2303.07914","repositories_listed":1,"syntology":null},{"url":"/paper/mm-diffusion-learning-multi-modal-diffusion","title":"MM-Diffusion: Learning Multi-Modal Diffusion Models for Joint Audio and Video Generation","date":"2022-12-19","arxiv_id":"2212.09478","repositories_listed":1,"syntology":{"n":18,"n_ran":9,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/refined-semantic-enhancement-towards","title":"Refined Semantic Enhancement towards Frequency Diffusion for Video Captioning","date":"2022-11-28","arxiv_id":"2211.15076","repositories_listed":1,"syntology":null},{"url":"/paper/generating-diverse-vocal-bursts-with","title":"Generating Diverse Vocal Bursts with StyleGAN2 and MEL-Spectrograms","date":"2022-06-25","arxiv_id":"2206.12563","repositories_listed":1,"syntology":null},{"url":"/paper/timbre-transfer-with-variational-auto","title":"Timbre Transfer with Variational Auto Encoding and Cycle-Consistent Adversarial Networks","date":"2021-09-05","arxiv_id":"2109.02096","repositories_listed":1,"syntology":null},{"url":"/paper/representation-sharing-for-fast-object","title":"Representation Sharing for Fast Object Detector Search and Beyond","date":"2020-07-23","arxiv_id":"2007.12075","repositories_listed":1,"syntology":null},{"url":"/paper/twitch-plays-pokemon-machine-learns-twitch","title":"Twitch Plays Pokemon, Machine Learns Twitch: Unsupervised Context-Aware Anomaly Detection for Identifying Trolls in Streaming Data","date":"2019-02-17","arxiv_id":"1902.06208","repositories_listed":1,"syntology":null}],"syntology_records":9,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}