{"list":"other","total":98,"rows":[{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"2503.19786","title":"Gemma 3 Technical Report","created":"2025-03-25","cited_by_count":1824},{"id":"2506.09985","title":"V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning","created":"2025-06-11","cited_by_count":809},{"id":"2107.03312","title":"SoundStream: An End-to-End Neural Audio Codec","created":"2021-07-07","cited_by_count":771},{"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":"1609.09430","title":"CNN Architectures for Large-Scale Audio Classification","created":"2016-09-29","cited_by_count":704},{"id":"2210.13438","title":"High Fidelity Neural Audio Compression","created":"2022-10-24","cited_by_count":687},{"id":"2410.13720","title":"Movie Gen: A Cast of Media Foundation Models","created":"2024-10-17","cited_by_count":644},{"id":"2209.03143","title":"AudioLM: a Language Modeling Approach to Audio Generation","created":"2022-09-07","cited_by_count":616},{"id":"2301.12503","title":"AudioLDM: Text-to-Audio Generation with Latent Diffusion Models","created":"2023-01-29","cited_by_count":599},{"id":"2307.07635","title":"CoTracker: It is Better to Track Together","created":"2023-07-14","cited_by_count":522},{"id":"2306.05284","title":"Simple and Controllable Music Generation","created":"2023-06-08","cited_by_count":488},{"id":"2101.08779","title":"AI Choreographer: Music Conditioned 3D Dance Generation with AIST++","created":"2021-01-21","cited_by_count":485},{"id":"2301.11325","title":"MusicLM: Generating Music From Text","created":"2023-01-26","cited_by_count":448},{"id":"2306.06546","title":"High-Fidelity Audio Compression with Improved RVQGAN","created":"2023-06-11","cited_by_count":431},{"id":"2308.05734","title":"AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining","created":"2023-08-10","cited_by_count":344},{"id":"2301.12661","title":"Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion Models","created":"2023-01-30","cited_by_count":324},{"id":"2209.15352","title":"AudioGen: Textually Guided Audio Generation","created":"2022-09-30","cited_by_count":295},{"id":"2207.09983","title":"Diffsound: Discrete Diffusion Model for Text-to-sound Generation","created":"2022-07-20","cited_by_count":257},{"id":"1812.08466","title":"Fr\\'echet Audio Distance: A Metric for Evaluating Music Enhancement Algorithms","created":"2018-12-20","cited_by_count":225},{"id":"2305.11846","title":"Any-to-Any Generation via Composable Diffusion","created":"2023-05-19","cited_by_count":204},{"id":"2407.14358","title":"Stable Audio Open","created":"2024-07-19","cited_by_count":197},{"id":"2402.04825","title":"Fast Timing-Conditioned Latent Audio Diffusion","created":"2024-02-07","cited_by_count":181},{"id":"2306.17203","title":"Diff-Foley: Synchronized Video-to-Audio Synthesis with Latent Diffusion Models","created":"2023-06-29","cited_by_count":134},{"id":"2412.15322","title":"MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis","created":"2024-12-19","cited_by_count":134},{"id":"1512.08512","title":"Visually Indicated Sounds","created":"2015-12-28","cited_by_count":128},{"id":"2312.15821","title":"Audiobox: Unified Audio Generation with Natural Language Prompts","created":"2023-12-25","cited_by_count":120},{"id":"2311.08355","title":"Mustango: Toward Controllable Text-to-Music Generation","created":"2023-11-14","cited_by_count":100},{"id":"1712.01393","title":"Visual to Sound: Generating Natural Sound for Videos in the Wild","created":"2017-12-04","cited_by_count":98},{"id":"2401.12179","title":"DITTO: Diffusion Inference-Time T-Optimization for Music Generation","created":"2024-01-22","cited_by_count":73},{"id":"2503.08638","title":"YuE: Scaling Open Foundation Models for Long-Form Music Generation","created":"2025-03-11","cited_by_count":71},{"id":"2311.10057","title":"The Song Describer Dataset: a Corpus of Audio Captions for Music-and-Language Evaluation","created":"2023-11-16","cited_by_count":68},{"id":"2008.00820","title":"Generating Visually Aligned Sound from Videos","created":"2020-07-14","cited_by_count":67},{"id":"2311.18775","title":"CoDi-2: In-Context, Interleaved, and Interactive Any-to-Any Generation","created":"2023-11-30","cited_by_count":63},{"id":"2111.08380","title":"Video Background Music Generation with Controllable Music Transformer","created":"2021-11-16","cited_by_count":56},{"id":"2506.00045","title":"ACE-Step: A Step Towards Music Generation Foundation Model","created":"2025-05-28","cited_by_count":56},{"id":"2304.08490","title":"Conditional Generation of Audio from Video via Foley Analogies","created":"2023-04-17","cited_by_count":52},{"id":"2305.15719","title":"Efficient Neural Music Generation","created":"2023-05-25","cited_by_count":50},{"id":"2401.04577","title":"Masked Audio Generation using a Single Non-Autoregressive Transformer","created":"2024-01-09","cited_by_count":50},{"id":"2411.17698","title":"Video-Guided Foley Sound Generation with Multimodal Controls","created":"2024-11-26","cited_by_count":49},{"id":"1712.09382","title":"Audio to Body Dynamics","created":"2017-12-19","cited_by_count":48},{"id":"2311.03318","title":"A Foundation Model for Music Informatics","created":"2023-11-06","cited_by_count":46},{"id":"2508.16930","title":"HunyuanVideo-Foley: Multimodal Diffusion with Representation Alignment for High-Fidelity Foley Audio Generation","created":"2025-08-23","cited_by_count":46},{"id":"2206.07771","title":"Discrete Contrastive Diffusion for Cross-Modal Music and Image Generation","created":"2022-06-15","cited_by_count":44},{"id":"2309.10537","title":"FoleyGen: Visually-Guided Audio Generation","created":"2023-09-19","cited_by_count":40},{"id":"2406.04321","title":"VidMuse: A Simple Video-to-Music Generation Framework with Long-Short-Term Modeling","created":"2024-06-06","cited_by_count":40},{"id":"2506.19774","title":"Kling-Foley: Multimodal Diffusion Transformer for High-Quality Video-to-Audio Generation","created":"2025-06-24","cited_by_count":40},{"id":"2204.00604","title":"Quantized GAN for Complex Music Generation from Dance Videos","created":"2022-04-01","cited_by_count":37},{"id":"2311.00968","title":"Video2Music: Suitable Music Generation from Videos using an Affective Multimodal Transformer model","created":"2023-11-02","cited_by_count":37},{"id":"2408.14340","title":"Foundation Models for Music: A Survey","created":"2024-08-26","cited_by_count":37},{"id":"2411.05679","title":"Tell What You Hear From What You See -- Video to Audio Generation Through Text","created":"2024-11-08","cited_by_count":34},{"id":"2506.21448","title":"ThinkSound: Chain-of-Thought Reasoning in Multimodal Large Language Models for Audio Generation and Editing","created":"2025-06-26","cited_by_count":34},{"id":"2102.07092","title":"Learning Self-Similarity in Space and Time as Generalized Motion for Video Action Recognition","created":"2021-02-14","cited_by_count":31},{"id":"2211.11248","title":"Video Background Music Generation: Dataset, Method and Evaluation","created":"2022-11-21","cited_by_count":29},{"id":"2502.13128","title":"SongGen: A Single Stage Auto-regressive Transformer for Text-to-Song Generation","created":"2025-02-18","cited_by_count":29},{"id":"2311.11255","title":"M$^{2}$UGen: Multi-modal Music Understanding and Generation with the Power of Large Language Models","created":"2023-11-19","cited_by_count":24},{"id":"2405.11913","title":"Diff-BGM: A Diffusion Model for Video Background Music Generation","created":"2024-05-20","cited_by_count":23},{"id":"2409.19132","title":"From Vision to Audio and Beyond: A Unified Model for Audio-Visual Representation and Generation","created":"2024-09-27","cited_by_count":23},{"id":"2406.04673","title":"MeLFusion: Synthesizing Music from Image and Language Cues using Diffusion Models","created":"2024-06-07","cited_by_count":19},{"id":"2409.00587","title":"FLUX that Plays Music","created":"2024-09-01","cited_by_count":18},{"id":"2305.01319","title":"Long-Term Rhythmic Video Soundtracker","created":"2023-05-02","cited_by_count":17},{"id":"2405.12221","title":"Images that Sound: Composing Images and Sounds on a Single Canvas","created":"2024-05-20","cited_by_count":17},{"id":"2410.05167","title":"Presto! Distilling Steps and Layers for Accelerating Music Generation","created":"2024-10-07","cited_by_count":16},{"id":"2412.10768","title":"VinTAGe: Joint Video and Text Conditioning for Holistic Audio Generation","created":"2024-12-14","cited_by_count":16},{"id":"2409.07450","title":"VMAS: Video-to-Music Generation via Semantic Alignment in Web Music Videos","created":"2024-09-11","cited_by_count":15},{"id":"2501.08809","title":"XMusic: Towards a Generalized and Controllable Symbolic Music Generation Framework","created":"2025-01-15","cited_by_count":15},{"id":"2403.19638","title":"Siamese Vision Transformers are Scalable Audio-visual Learners","created":"2024-03-28","cited_by_count":14},{"id":"2404.16969","title":"COCOLA: Coherence-Oriented Contrastive Learning of Musical Audio Representations","created":"2024-04-25","cited_by_count":14},{"id":"2410.12957","title":"MuVi: Video-to-Music Generation with Semantic Alignment and Rhythmic Synchronization","created":"2024-10-16","cited_by_count":14},{"id":"2503.01725","title":"HarmonySet: A Comprehensive Dataset for Understanding Video-Music Semantic Alignment and Temporal Synchronization","created":"2025-03-03","cited_by_count":14},{"id":"2505.08175","title":"Fast Text-to-Audio Generation with Adversarial Post-Training","created":"2025-05-13","cited_by_count":14},{"id":"2401.17800","title":"Dance-to-Music Generation with Encoder-based Textual Inversion","created":"2024-01-31","cited_by_count":12},{"id":"2412.06296","title":"VidMusician: Video-to-Music Generation with Semantic-Rhythmic Alignment via Hierarchical Visual Features","created":"2024-12-09","cited_by_count":9},{"id":"2501.09972","title":"GVMGen: A General Video-to-Music Generation Model with Hierarchical Attentions","created":"2025-01-17","cited_by_count":9},{"id":"2410.03879","title":"SONIQUE: Video Background Music Generation Using Unpaired Audio-Visual Data","created":"2024-10-04","cited_by_count":8},{"id":"2405.02801","title":"Mozart's Touch: A Lightweight Multi-modal Music Generation Framework Based on Pre-Trained Large Models","created":"2024-05-05","cited_by_count":7},{"id":"2412.09428","title":"Multimodal Music Generation with Explicit Bridges and Retrieval Augmentation","created":"2024-12-12","cited_by_count":6},{"id":"2506.12573","title":"Video-Guided Text-to-Music Generation Using Public Domain Movie Collections","created":"2025-06-14","cited_by_count":6},{"id":"2503.08147","title":"FilmComposer: LLM-Driven Music Production for Silent Film Clips","created":"2025-03-11","cited_by_count":5},{"id":"2503.22138","title":"Enhancing Dance-to-Music Generation via Negative Conditioning Latent Diffusion Model","created":"2025-03-28","cited_by_count":5},{"id":"2506.00681","title":"Learning to Upsample and Upmix Audio in the Latent Domain","created":"2025-05-31","cited_by_count":5},{"id":"2504.07594","title":"Extending Visual Dynamics for Video-to-Music Generation","created":"2025-04-10","cited_by_count":4},{"id":"2504.15217","title":"DRAGON: Distributional Rewards Optimize Diffusion Generative Models","created":"2025-04-21","cited_by_count":4},{"id":"2507.07867","title":"Re-Bottleneck: Latent Re-Structuring for Neural Audio Autoencoders","created":"2025-07-10","cited_by_count":4},{"id":"2510.21581","title":"Foley Control: Aligning a Frozen Latent Text-to-Audio Model to Video","created":"2025-10-24","cited_by_count":4},{"id":"2309.02243","title":"Self-Similarity-Based and Novelty-based loss for music structure analysis","created":"2023-09-05","cited_by_count":3},{"id":"2507.20627","title":"Controllable Video-to-Music Generation with Multiple Time-Varying Conditions","created":"2025-07-28","cited_by_count":3},{"id":"2511.09090","title":"Diff-V2M: A Hierarchical Conditional Diffusion Model with Explicit Rhythmic Modeling for Video-to-Music Generation","created":"2025-11-12","cited_by_count":3},{"id":"2511.09585","title":"Video Echoed in Music: Semantic, Temporal, and Rhythmic Alignment for Video-to-Music Generation","created":"2025-11-12","cited_by_count":3},{"id":"2410.09928","title":"M2M-Gen: A Multimodal Framework for Automated Background Music Generation in Japanese Manga Using Large Language Models","created":"2024-10-13","cited_by_count":2},{"id":"2506.08570","title":"Auto-Regressive vs Flow-Matching: a Comparative Study of Modeling Paradigms for Text-to-Music Generation","created":"2025-06-10","cited_by_count":2},{"id":"2602.15749","title":"A Generative-First Neural Audio Autoencoder","created":"2026-02-17","cited_by_count":2},{"id":"2507.05894","title":"MusiScene: Leveraging MU-LLaMA for Scene Imagination and Enhanced Video Background Music Generation","created":"2025-07-08","cited_by_count":1}],"next_cursor":null}