{"total":38,"rows":[{"id":"2111.03017","title":"MT3: Multi-Task Multitrack Music Transcription","created":"2021-11-04","cited_by_count":71,"area":null},{"id":"2302.13372","title":"Localizing Moments in Long Video Via Multimodal Guidance","created":"2023-02-26","cited_by_count":23,"area":null},{"id":"2106.16036","title":"A Generative Model for Raw Audio Using Transformer Architectures","created":"2021-06-30","cited_by_count":18,"area":null},{"id":"2206.07148","title":"It's Time for Artistic Correspondence in Music and Video","created":"2022-06-14","cited_by_count":18,"area":null},{"id":"2506.00343","title":"The iNaturalist Sounds Dataset","created":"2025-05-31","cited_by_count":17,"area":null},{"id":"2307.03493","title":"ITA: An Energy-Efficient Attention and Softmax Accelerator for Quantized Transformers","created":"2023-07-07","cited_by_count":12,"area":null},{"id":"2309.02320","title":"SeisCLIP: A seismology foundation model pre-trained by multi-modal data for multi-purpose seismic feature extraction","created":"2023-09-05","cited_by_count":8,"area":null},{"id":"2406.10254","title":"Towards Signal Processing In Large Language Models","created":"2024-06-10","cited_by_count":7,"area":null},{"id":"2107.00623","title":"Improving Sound Event Classification by Increasing Shift Invariance in Convolutional Neural Networks","created":"2021-07-01","cited_by_count":5,"area":null},{"id":"2311.01526","title":"ATGNN: Audio Tagging Graph Neural Network","created":"2023-11-02","cited_by_count":4,"area":null},{"id":"2401.04023","title":"Efficient Multiscale Multimodal Bottleneck Transformer for Audio-Video Classification","created":"2024-01-08","cited_by_count":4,"area":null},{"id":"2305.12712","title":"LEAN: Light and Efficient Audio Classification Network","created":"2023-05-22","cited_by_count":3,"area":null},{"id":"2209.00291","title":"Generating Coherent Drum Accompaniment With Fills And Improvisations","created":"2022-09-01","cited_by_count":2,"area":null},{"id":"2310.15177","title":"A Neuro-mimetic Realization of the Common Model of Cognition via Hebbian Learning and Free Energy Minimization","created":"2023-10-14","cited_by_count":2,"area":null},{"id":"2412.10599","title":"Advances in Transformers for Robotic Applications: A Review","created":"2024-12-13","cited_by_count":2,"area":null},{"id":"2412.11449","title":"Whisper-GPT -- Continuous Discrete Hybrid Representation Language Models For Speech And Music","created":"2024-12-16","cited_by_count":2,"area":null},{"id":"2110.03183","title":"Attention is All You Need? Good Embeddings with Statistics are enough:Large Scale Audio Understanding without Transformers/ Convolutions/ BERTs/ Mixers/ Attention/ RNNs or ....","created":"2021-10-07","cited_by_count":1,"area":null},{"id":"2110.06999","title":"Study of positional encoding approaches for Audio Spectrogram Transformers","created":"2021-10-13","cited_by_count":1,"area":null},{"id":"2304.10505","title":"Video Pre-trained Transformer: A Multimodal Mixture of Pre-trained Experts","created":"2023-03-24","cited_by_count":1,"area":null},{"id":"2307.00461","title":"Conformer LLMs -- Convolution Augmented Large Language Models","created":"2023-07-02","cited_by_count":1,"area":null},{"id":"2407.08934","title":"Compositional Structures in Neural Embedding and Interaction Decompositions","created":"2024-07-12","cited_by_count":1,"area":null},{"id":"2409.12924","title":"Wavelet GPT: Wavelet Inspired Large Language Models","created":"2024-09-04","cited_by_count":1,"area":null},{"id":"2505.17091","title":"Large Language Models Implicitly Learn to See and Hear Just By Reading","created":"2025-05-20","cited_by_count":1,"area":null},{"id":"2509.15448","title":"Hierarchical Self-Attention: Generalizing Neural Attention Mechanics to Multi-Scale Problems","created":"2025-09-18","cited_by_count":1,"area":null},{"id":"2509.21341","title":"From Embeddings to Equations: Genetic-Programming Surrogates for Interpretable Transformer Classification","created":"2025-09-16","cited_by_count":1,"area":null},{"id":"2208.07994","title":"Enhancing Audio Perception of Music By AI Picked Room Acoustics","created":"2022-08-16","cited_by_count":0,"area":null},{"id":"2210.11549","title":"H4VDM: H.264 Video Device Matching","created":"2022-10-20","cited_by_count":0,"area":null},{"id":"2210.15750","title":"One-Shot Acoustic Matching Of Audio Signals -- Learning to Hear Music In Any Room/ Concert Hall","created":"2022-10-27","cited_by_count":0,"area":null},{"id":"2308.10388","title":"Neural Architectures Learning Fourier Transforms, Signal Processing and Much More....","created":"2023-08-20","cited_by_count":0,"area":null},{"id":"2309.08751","title":"Diverse Audio Embeddings -- Bringing Features Back Outperforms CLAP!","created":"2023-09-15","cited_by_count":0,"area":null},{"id":"2309.11087","title":"Embed-Search-Align: DNA Sequence Alignment using Transformer Models","created":"2023-09-20","cited_by_count":0,"area":null},{"id":"2409.08083","title":"SimMAT: Exploring Transferability from Vision Foundation Models to Any Image Modality","created":"2024-09-12","cited_by_count":0,"area":null},{"id":"2412.00503","title":"Homeostasis and Sparsity in Transformer","created":"2024-11-30","cited_by_count":0,"area":null},{"id":"2511.01956","title":"Vibe Learning: Education in the age of AI","created":"2025-11-03","cited_by_count":0,"area":null},{"id":"2511.03423","title":"Seeing What You Say: Expressive Image Generation from Speech","created":"2025-11-05","cited_by_count":0,"area":null},{"id":"2511.11754","title":"Batch Transformer Architecture: Case of Synthetic Image Generation for Emotion Expression Facial Recognition","created":"2025-11-13","cited_by_count":0,"area":null},{"id":"2511.16848","title":"Sex and age determination in European lobsters using AI-Enhanced bioacoustics","created":"2025-11-20","cited_by_count":0,"area":null},{"id":"2603.14917","title":"Spectrogram features for audio and speech analysis","created":"2026-03-16","cited_by_count":0,"area":null}],"next_cursor":null}