{"total":45,"rows":[{"id":"2209.03143","title":"AudioLM: a Language Modeling Approach to Audio Generation","created":"2022-09-07","cited_by_count":616,"area":null},{"id":"2212.14052","title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","created":"2022-12-28","cited_by_count":499,"area":null},{"id":"2301.11325","title":"MusicLM: Generating Music From Text","created":"2023-01-26","cited_by_count":448,"area":null},{"id":"2206.13947","title":"Long Range Language Modeling via Gated State Spaces","created":"2022-06-27","cited_by_count":265,"area":null},{"id":"2305.07185","title":"MEGABYTE: Predicting Million-byte Sequences with Multiscale Transformers","created":"2023-05-12","cited_by_count":170,"area":null},{"id":"2503.19325","title":"Long-Context Autoregressive Video Modeling with Next-Frame Prediction","created":"2025-03-25","cited_by_count":123,"area":null},{"id":"2305.09636","title":"SoundStorm: Efficient Parallel Audio Generation","created":"2023-05-16","cited_by_count":114,"area":null},{"id":"2203.07852","title":"Block-Recurrent Transformers","created":"2022-03-11","cited_by_count":110,"area":null},{"id":"2305.15255","title":"Spoken Question Answering and Speech Continuation Using Spectrogram-Powered LLM","created":"2023-05-24","cited_by_count":94,"area":null},{"id":"2211.05030","title":"Creative Writing with an AI-Powered Writing Assistant: Perspectives from Professional Writers","created":"2022-11-09","cited_by_count":69,"area":null},{"id":"2301.12662","title":"SingSong: Generating musical accompaniments from singing","created":"2023-01-30","cited_by_count":55,"area":null},{"id":"2303.09489","title":"Effectively Modeling Time Series with Simple Discrete State Spaces","created":"2023-03-16","cited_by_count":54,"area":null},{"id":"2404.08801","title":"Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length","created":"2024-04-12","cited_by_count":46,"area":null},{"id":"2502.17437","title":"Fractal Generative Models","created":"2025-02-24","cited_by_count":46,"area":null},{"id":"2210.02396","title":"Temporally Consistent Transformers for Video Generation","created":"2022-10-05","cited_by_count":44,"area":null},{"id":"2208.04347","title":"Investigating Efficiently Extending Transformers for Long Input Summarization","created":"2022-08-08","cited_by_count":43,"area":null},{"id":"2306.08620","title":"Anticipatory Music Transformer","created":"2023-06-14","cited_by_count":36,"area":null},{"id":"2309.16354","title":"Transformer-VQ: Linear-Time Transformers via Vector Quantization","created":"2023-09-28","cited_by_count":26,"area":null},{"id":"2204.10878","title":"ChapterBreak: A Challenge Dataset for Long-Range Language Models","created":"2022-04-22","cited_by_count":18,"area":null},{"id":"2305.12689","title":"FIT: Far-reaching Interleaved Transformers","created":"2023-05-22","cited_by_count":16,"area":null},{"id":"2212.08379","title":"GeneFormer: Learned Gene Compression using Transformer-based Context Modeling","created":"2022-12-16","cited_by_count":10,"area":null},{"id":"2307.11078","title":"Brain2Music: Reconstructing Music from Human Brain Activity","created":"2023-07-20","cited_by_count":10,"area":null},{"id":"2501.02393","title":"Graph-Aware Isomorphic Attention for Adaptive Dynamics in Transformers","created":"2025-01-04","cited_by_count":7,"area":null},{"id":"2210.08031","title":"Neural Attentive Circuits","created":"2022-10-14","cited_by_count":6,"area":null},{"id":"2210.11807","title":"Is Encoder-Decoder Redundant for Neural Machine Translation?","created":"2022-10-21","cited_by_count":5,"area":null},{"id":"2406.00146","title":"A Survey of Deep Learning Audio Generation Methods","created":"2024-05-31","cited_by_count":5,"area":null},{"id":"2510.18080","title":"MEG-GPT: A transformer-based foundation model for magnetoencephalography data","created":"2025-10-20","cited_by_count":5,"area":null},{"id":"2602.10095","title":"Causality in Video Diffusers is Separable from Denoising","created":"2026-02-10","cited_by_count":4,"area":null},{"id":"2603.24576","title":"Chameleon: Control-Indexed Prospective Memory for Visuomotor Manipulation","created":"2026-03-25","cited_by_count":4,"area":null},{"id":"2210.13944","title":"A Survey on Artificial Intelligence for Music Generation: Agents, Domains and Perspectives","created":"2022-10-25","cited_by_count":3,"area":null},{"id":"2306.01070","title":"Hierarchical Attention Encoder Decoder","created":"2023-06-01","cited_by_count":3,"area":null},{"id":"2602.04289","title":"Proxy Compression for Language Modeling","created":"2026-02-04","cited_by_count":3,"area":null},{"id":"2208.03196","title":"COPER: Continuous Patient State Perceiver","created":"2022-08-05","cited_by_count":2,"area":null},{"id":"2210.16264","title":"Efficient Speech Translation with Dynamic Latent Perceivers","created":"2022-10-28","cited_by_count":2,"area":null},{"id":"2602.11852","title":"Prototype Transformer: Towards Language Model Architectures Interpretable by Design","created":"2026-02-12","cited_by_count":2,"area":null},{"id":"2305.12121","title":"ACA-Net: Towards Lightweight Speaker Verification using Asymmetric Cross Attention","created":"2023-05-20","cited_by_count":1,"area":null},{"id":"2409.10870","title":"Adaptive Large Language Models By Layerwise Attention Shortcuts","created":"2024-09-17","cited_by_count":1,"area":null},{"id":"2412.06106","title":"Efficient Context Propagating Perceiver Architectures for Auto-Regressive Language Modeling","created":"2024-12-08","cited_by_count":1,"area":null},{"id":"2511.18105","title":"AdaPerceiver: Transformers with Adaptive Width, Depth, and Tokens","created":"2025-11-22","cited_by_count":1,"area":null},{"id":"2607.13522","title":"Kepler-Encoder-v0.1: Towards a Multimodal Embedding Model for Robots","created":"2026-07-15","cited_by_count":1,"area":null},{"id":"2209.13129","title":"Deep Generative Multimedia Children's Literature","created":"2022-09-27","cited_by_count":0,"area":null},{"id":"2411.08307","title":"PerceiverS: A Multi-Scale Perceiver with Effective Segmentation for Long-Term Expressive Symbolic Music Generation","created":"2024-11-13","cited_by_count":0,"area":null},{"id":"2504.13981","title":"CacheFormer: High Attention-Based Segment Caching","created":"2025-04-18","cited_by_count":0,"area":null},{"id":"2602.19816","title":"Whole-Piece Training for Symbolic Music Language Models via Full-Horizon Compressed Recurrence","created":"2026-02-23","cited_by_count":0,"area":null},{"id":"2604.00039","title":"Transformers for Program Termination","created":"2026-03-25","cited_by_count":0,"area":null}],"next_cursor":null}