{"total":213,"rows":[{"id":"2204.00598","title":"Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language","created":"2022-04-01","cited_by_count":513,"area":"lr"},{"id":"2301.11325","title":"MusicLM: Generating Music From Text","created":"2023-01-26","cited_by_count":448,"area":null},{"id":"2212.09058","title":"BEATs: Audio Pre-Training with Acoustic Tokenizers","created":"2022-12-18","cited_by_count":388,"area":null},{"id":"2302.07241","title":"ConceptFusion: Open-set Multimodal 3D Mapping","created":"2023-02-14","cited_by_count":304,"area":null},{"id":"2204.08583","title":"VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidance","created":"2022-04-18","cited_by_count":285,"area":null},{"id":"2303.17395","title":"WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research","created":"2023-03-30","cited_by_count":267,"area":null},{"id":"2306.15724","title":"REFLECT: Summarizing Robot Experiences for Failure Explanation and Correction","created":"2023-06-27","cited_by_count":175,"area":null},{"id":"2503.03983","title":"Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities","created":"2025-03-06","cited_by_count":133,"area":"lr"},{"id":"2305.11172","title":"ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities","created":"2023-05-18","cited_by_count":118,"area":null},{"id":"2402.17723","title":"Seeing and Hearing: Open-domain Visual-Audio Generation with Diffusion Latent Aligners","created":"2024-02-27","cited_by_count":111,"area":null},{"id":"2407.01494","title":"FoleyCrafter: Bring Silent Videos to Life with Lifelike and Synchronized Sounds","created":"2024-07-01","cited_by_count":110,"area":null},{"id":"2303.17480","title":"Seeing What You Said: Talking Face Generation Guided by a Lip Reading Expert","created":"2023-03-29","cited_by_count":98,"area":null},{"id":"2308.01546","title":"MusicLDM: Enhancing Novelty in Text-to-Music Generation Using Beat-Synchronous Mixup Strategies","created":"2023-08-03","cited_by_count":94,"area":"diffusion"},{"id":"2203.03022","title":"HEAR: Holistic Evaluation of Audio Representations","created":"2022-03-06","cited_by_count":78,"area":null},{"id":"2308.11276","title":"Music Understanding LLaMA: Advancing Text-to-Music Generation with Question Answering and Captioning","created":"2023-08-22","cited_by_count":77,"area":null},{"id":"2309.16429","title":"Diverse and Aligned Audio-to-Video Generation via Text-to-Video Model Adaptation","created":"2023-09-28","cited_by_count":69,"area":null},{"id":"2308.09300","title":"V2A-Mapper: A Lightweight Solution for Vision-to-Audio Generation by Connecting Foundation Models","created":"2023-08-18","cited_by_count":65,"area":null},{"id":"2401.03497","title":"EAT: Self-Supervised Pre-Training with Efficient Audio Transformer","created":"2024-01-07","cited_by_count":53,"area":null},{"id":"2206.02338","title":"OrdinalCLIP: Learning Rank Prompts for Language-Guided Ordinal Regression","created":"2022-06-06","cited_by_count":44,"area":null},{"id":"2310.08753","title":"CompA: Addressing the Gap in Compositional Reasoning in Audio-Language Models","created":"2023-10-12","cited_by_count":43,"area":"lr"},{"id":"2411.14517","title":"The Double-Ellipsoid Geometry of CLIP","created":"2024-11-21","cited_by_count":42,"area":null},{"id":"2303.17490","title":"Sound to Visual Scene Generation by Audio-to-Visual Latent Alignment","created":"2023-03-30","cited_by_count":41,"area":null},{"id":"2506.19774","title":"Kling-Foley: Multimodal Diffusion Transformer for High-Quality Video-to-Audio Generation","created":"2025-06-24","cited_by_count":40,"area":"diffusion"},{"id":"2407.11895","title":"OmniBind: Large-scale Omni Multimodal Representation via Binding Spaces","created":"2024-07-16","cited_by_count":39,"area":null},{"id":"2210.14395","title":"IMU2CLIP: Multimodal Contrastive Learning for IMU Motion Sensors from Egocentric Videos and Text","created":"2022-10-26","cited_by_count":37,"area":null},{"id":"2406.03344","title":"Audio Mamba: Bidirectional State Space Model for Audio Representation Learning","created":"2024-06-05","cited_by_count":37,"area":"ssm"},{"id":"2305.14381","title":"Connecting Multi-modal Contrastive Representations","created":"2023-05-22","cited_by_count":36,"area":null},{"id":"2112.00007","title":"Sound-Guided Semantic Image Manipulation","created":"2021-11-30","cited_by_count":35,"area":null},{"id":"2204.09273","title":"Sound-Guided Semantic Video Generation","created":"2022-04-20","cited_by_count":35,"area":null},{"id":"2209.14275","title":"Audio Retrieval with WavText5K and CLAP Training","created":"2022-09-28","cited_by_count":35,"area":null},{"id":"2308.05184","title":"PromptPaint: Steering Text-to-Image Generation Through Paint Medium-like Interactions","created":"2023-08-09","cited_by_count":34,"area":"diffusion"},{"id":"2208.12208","title":"Contrastive Audio-Language Learning for Music","created":"2022-08-25","cited_by_count":33,"area":null},{"id":"2212.06858","title":"LidarCLIP or: How I Learned to Talk to Point Clouds","created":"2022-12-13","cited_by_count":33,"area":null},{"id":"2309.11500","title":"Auto-ACD: A Large-scale Dataset for Audio-Language Representation Learning","created":"2023-09-20","cited_by_count":33,"area":null},{"id":"2309.10724","title":"Sound Source Localization is All about Cross-Modal Alignment","created":"2023-09-19","cited_by_count":31,"area":null},{"id":"2205.12630","title":"Multimodal Knowledge Alignment with Reinforcement Learning","created":"2022-05-25","cited_by_count":30,"area":null},{"id":"2303.07522","title":"Audio Visual Language Maps for Robot Navigation","created":"2023-03-13","cited_by_count":30,"area":null},{"id":"2210.00705","title":"SpeechCLIP: Integrating Speech with Pre-Trained Vision and Language Model","created":"2022-10-03","cited_by_count":29,"area":null},{"id":"2212.03814","title":"iQuery: Instruments as Queries for Audio-Visual Sound Separation","created":"2022-12-07","cited_by_count":29,"area":null},{"id":"2309.09501","title":"Discovering Sounding Objects by Audio Queries for Audio Visual Segmentation","created":"2023-09-18","cited_by_count":29,"area":null},{"id":"2310.07160","title":"LLark: A Multimodal Instruction-Following Language Model for Music","created":"2023-10-11","cited_by_count":29,"area":null},{"id":"2407.10387","title":"Masked Generative Video-to-Audio Transformers with Enhanced Synchronicity","created":"2024-07-15","cited_by_count":28,"area":null},{"id":"2404.00225","title":"Heterogeneous Contrastive Learning for Foundation Models and Beyond","created":"2024-03-30","cited_by_count":27,"area":null},{"id":"2503.05242","title":"MM-StoryAgent: Immersive Narrated Storybook Video Generation with a Multi-Agent Paradigm across Text, Image and Audio","created":"2025-03-07","cited_by_count":27,"area":"agents"},{"id":"2211.09778","title":"I Can't Believe There's No Images! Learning Visual Tasks Using only Language Supervision","created":"2022-11-17","cited_by_count":26,"area":null},{"id":"2407.01851","title":"Meerkat: Audio-Visual Large Language Model for Grounding in Space and Time","created":"2024-07-01","cited_by_count":26,"area":"mllm"},{"id":"2410.10676","title":"Both Ears Wide Open: Towards Language-Driven Spatial Audio Generation","created":"2024-10-14","cited_by_count":25,"area":"diffusion"},{"id":"2205.05949","title":"Automated Audio Captioning: An Overview of Recent Progress and New Challenges","created":"2022-05-12","cited_by_count":23,"area":null},{"id":"2212.07065","title":"CLIPSep: Learning Text-queried Sound Separation with Noisy Unlabeled Videos","created":"2022-12-14","cited_by_count":23,"area":null},{"id":"2308.02915","title":"DiffDance: Cascaded Human Motion Diffusion Model for Dance Generation","created":"2023-08-05","cited_by_count":23,"area":"diffusion"},{"id":"2205.05072","title":"Learning Visual Styles from Audio-Visual Associations","created":"2022-05-10","cited_by_count":22,"area":null},{"id":"2305.13050","title":"AudioToken: Adaptation of Text-Conditioned Diffusion Models for Audio-to-Image Generation","created":"2023-05-22","cited_by_count":22,"area":"diffusion"},{"id":"2310.06282","title":"MuseChat: A Conversational Music Recommendation System for Videos","created":"2023-10-10","cited_by_count":21,"area":null},{"id":"2310.08884","title":"Extending Multi-modal Contrastive Representations","created":"2023-10-13","cited_by_count":21,"area":null},{"id":"2303.16342","title":"Language-Guided Audio-Visual Source Separation via Trimodal Consistency","created":"2023-03-28","cited_by_count":20,"area":null},{"id":"2306.09635","title":"CLIPSonic: Text-to-Audio Synthesis with Unlabeled Videos and Pretrained Language-Vision Models","created":"2023-06-16","cited_by_count":20,"area":"diffusion"},{"id":"2405.16108","title":"OmniBind: Teach to Build Unequal-Scale Modality Interaction for Omni-Bind of All","created":"2024-05-25","cited_by_count":20,"area":null},{"id":"2503.14963","title":"Continual Multimodal Contrastive Learning","created":"2025-03-19","cited_by_count":20,"area":null},{"id":"2404.01751","title":"T-VSL: Text-Guided Visual Sound Source Localization in Mixtures","created":"2024-04-02","cited_by_count":19,"area":null},{"id":"2405.04883","title":"FreeBind: Free Lunch in Unified Multimodal Space via Knowledge Fusion","created":"2024-05-08","cited_by_count":19,"area":null},{"id":"2507.17343","title":"Principled Multimodal Representation Learning","created":"2025-07-23","cited_by_count":19,"area":null},{"id":"2604.10905","title":"Audio Flamingo Next: Next-Generation Open Audio-Language Models for Speech, Sound, and Music","created":"2026-04-13","cited_by_count":19,"area":null},{"id":"2303.06591","title":"Accommodating Audio Modality in CLIP for Multimodal Processing","created":"2023-03-12","cited_by_count":18,"area":"mllm"},{"id":"2306.09327","title":"Language-Guided Music Recommendation for Video via Prompt Analogies","created":"2023-06-15","cited_by_count":18,"area":null},{"id":"2404.17806","title":"T-CLAP: Temporal-Enhanced Contrastive Language-Audio Pretraining","created":"2024-04-27","cited_by_count":18,"area":null},{"id":"2112.08995","title":"Connecting the Dots between Audio and Text without Parallel Data through Visual Knowledge Transfer","created":"2021-12-16","cited_by_count":17,"area":null},{"id":"2412.10768","title":"VinTAGe: Joint Video and Text Conditioning for Holistic Audio Generation","created":"2024-12-14","cited_by_count":16,"area":null},{"id":"2411.14452","title":"Past, Present, and Future of Sensor-Based Human Activity Recognition Using Wearables: A Surveying Tutorial on a Still Challenging Task","created":"2024-11-11","cited_by_count":15,"area":null},{"id":"2304.06818","title":"Soundini: Sound-Guided Diffusion for Natural Video Editing","created":"2023-04-13","cited_by_count":14,"area":"diffusion"},{"id":"2309.10667","title":"Learning Tri-modal Embeddings for Zero-Shot Soundscape Mapping","created":"2023-09-19","cited_by_count":14,"area":null},{"id":"2311.04066","title":"Can CLIP Help Sound Source Localization?","created":"2023-11-07","cited_by_count":14,"area":null},{"id":"2405.09266","title":"Dance Any Beat: Blending Beats with Visuals in Dance Video Generation","created":"2024-05-15","cited_by_count":14,"area":null},{"id":"2407.21646","title":"Towards Achieving Human Parity on End-to-end Simultaneous Speech Translation via LLM Agent","created":"2024-07-31","cited_by_count":14,"area":"agents"},{"id":"2404.09313","title":"Text-to-Song: Towards Controllable Music Generation Incorporating Vocals and Accompaniment","created":"2024-04-14","cited_by_count":13,"area":null},{"id":"2412.08174","title":"Can Graph Neural Networks Learn Language with Extremely Weak Text Supervision?","created":"2024-12-11","cited_by_count":13,"area":null},{"id":"2203.06760","title":"CMKD: CNN/Transformer-Based Cross-Model Knowledge Distillation for Audio Classification","created":"2022-03-13","cited_by_count":12,"area":"distill"},{"id":"2307.09788","title":"Density-invariant Features for Distant Point Cloud Registration","created":"2023-07-19","cited_by_count":12,"area":null},{"id":"2309.14580","title":"CWCL: Cross-Modal Transfer with Continuously Weighted Contrastive Loss","created":"2023-09-26","cited_by_count":12,"area":null},{"id":"2409.09213","title":"ReCLAP: Improving Zero Shot Audio Classification by Describing Sounds","created":"2024-09-13","cited_by_count":12,"area":null},{"id":"2306.07744","title":"Contrastive Learning-Based Audio to Lyrics Alignment for Multiple Languages","created":"2023-06-13","cited_by_count":11,"area":null},{"id":"2406.06612","title":"SEE-2-SOUND: Zero-Shot Spatial Environment-to-Spatial Sound","created":"2024-06-06","cited_by_count":10,"area":null},{"id":"2408.12023","title":"Limitations in Employing Natural Language Supervision for Sensor-Based Human Activity Recognition -- And Ways to Overcome Them","created":"2024-08-21","cited_by_count":10,"area":null},{"id":"2411.15127","title":"PRIMUS: Pretraining IMU Encoders with Multimodal Self-Supervision","created":"2024-11-22","cited_by_count":10,"area":null},{"id":"2504.05684","title":"TARO: Timestep-Adaptive Representation Alignment with Onset-Aware Conditioning for Synchronized Video-to-Audio Synthesis","created":"2025-04-08","cited_by_count":10,"area":null},{"id":"2604.14816","title":"NTIRE 2026 Challenge on Video Saliency Prediction: Methods and Results","created":"2026-04-16","cited_by_count":10,"area":null},{"id":"2309.00424","title":"Learning Speech Representation From Contrastive Token-Acoustic Pretraining","created":"2023-09-01","cited_by_count":9,"area":null},{"id":"2401.04210","title":"FunnyNet-W: Multimodal Learning of Funny Moments in Videos in the Wild","created":"2024-01-08","cited_by_count":9,"area":null},{"id":"2410.03335","title":"Audio-Agent: Leveraging LLMs For Audio Generation, Editing and Composition","created":"2024-10-04","cited_by_count":9,"area":"agents"},{"id":"2207.10760","title":"A Proposal for Foley Sound Synthesis Challenge","created":"2022-07-21","cited_by_count":8,"area":null},{"id":"2407.13676","title":"Aligning Sight and Sound: Advanced Sound Source Localization Through Audio-Visual Alignment","created":"2024-07-18","cited_by_count":8,"area":null},{"id":"2208.14114","title":"Robust Sound-Guided Image Manipulation","created":"2022-08-30","cited_by_count":7,"area":null},{"id":"2211.11492","title":"ClipCrop: Conditioned Cropping Driven by Vision-Language Model","created":"2022-11-21","cited_by_count":7,"area":"mllm"},{"id":"2304.10309","title":"Improving Speech Translation by Cross-Modal Multi-Grained Contrastive Learning","created":"2023-04-20","cited_by_count":7,"area":null},{"id":"2312.09812","title":"Structural Information Guided Multimodal Pre-training for Vehicle-centric Perception","created":"2023-12-15","cited_by_count":7,"area":null},{"id":"2403.14203","title":"Unsupervised Audio-Visual Segmentation with Modality Alignment","created":"2024-03-21","cited_by_count":7,"area":null},{"id":"2408.05758","title":"VQ-CTAP: Cross-Modal Fine-Grained Sequence Representation Learning for Speech Processing","created":"2024-08-11","cited_by_count":7,"area":null},{"id":"2409.06135","title":"Draw an Audio: Leveraging Multi-Instruction for Video-to-Audio Synthesis","created":"2024-09-10","cited_by_count":7,"area":null},{"id":"2504.04495","title":"AVadCLIP: Audio-Visual Collaboration for Robust Video Anomaly Detection","created":"2025-04-06","cited_by_count":7,"area":null},{"id":"2506.24124","title":"Teaching Time Series to See and Speak: Forecasting with Aligned Visual and Textual Perspectives","created":"2025-06-30","cited_by_count":7,"area":null},{"id":"2209.12900","title":"The Efficacy of Self-Supervised Speech Models for Audio Representations","created":"2022-09-26","cited_by_count":6,"area":null}],"next_cursor":"100"}