{"total":82,"rows":[{"id":"2405.05941","title":"Evaluating Real-World Robot Manipulation Policies in Simulation","created":"2024-05-09","cited_by_count":495,"area":null},{"id":"2304.04321","title":"ARNOLD: A Benchmark for Language-Grounded Task Learning With Continuous States in Realistic 3D Scenes","created":"2023-04-09","cited_by_count":69,"area":null},{"id":"2303.17056","title":"Audio-Visual Grouping Network for Sound Localization from Mixtures","created":"2023-03-29","cited_by_count":52,"area":null},{"id":"2302.02088","title":"AV-NeRF: Learning Neural Fields for Real-World Audio-Visual Scene Synthesis","created":"2023-02-04","cited_by_count":49,"area":null},{"id":"2210.06849","title":"Retrospectives on the Embodied AI Workshop","created":"2022-10-13","cited_by_count":46,"area":null},{"id":"2306.09126","title":"STARSS23: An Audio-Visual Dataset of Spatial Recordings of Real Scenes with Spatiotemporal Annotations of Sound Events","created":"2023-06-15","cited_by_count":41,"area":null},{"id":"2401.08577","title":"MultiPLY: A Multisensory Object-Centric Embodied Large Language Model in 3D World","created":"2024-01-16","cited_by_count":39,"area":null},{"id":"2301.08730","title":"Novel-View Acoustic Synthesis","created":"2023-01-20","cited_by_count":33,"area":null},{"id":"2505.12079","title":"SepPrune: Structured Pruning for Efficient Deep Speech Separation","created":"2025-05-17","cited_by_count":31,"area":null},{"id":"2405.13659","title":"EgoChoir: Capturing 3D Human-Object Interaction Regions from Egocentric Views","created":"2024-05-22","cited_by_count":26,"area":null},{"id":"2312.01017","title":"Unveiling the Power of Audio-Visual Early Fusion Transformers with Dense Interactions through Masked Modeling","created":"2023-12-02","cited_by_count":24,"area":null},{"id":"2305.19458","title":"A Unified Audio-Visual Learning Framework for Localization, Separation, and Recognition","created":"2023-05-30","cited_by_count":21,"area":null},{"id":"2406.09272","title":"Action2Sound: Ambient-Aware Generation of Action Sounds from Egocentric Videos","created":"2024-06-13","cited_by_count":21,"area":null},{"id":"2312.00834","title":"AV-RIR: Audio-Visual Room Impulse Response Estimation","created":"2023-11-30","cited_by_count":20,"area":null},{"id":"2403.18821","title":"Real Acoustic Fields: An Audio-Visual Room Acoustics Dataset and Benchmark","created":"2024-03-27","cited_by_count":20,"area":null},{"id":"2308.10306","title":"Omnidirectional Information Gathering for Knowledge Transfer-based Audio-Visual Navigation","created":"2023-08-20","cited_by_count":19,"area":null},{"id":"2210.01353","title":"Pay Self-Attention to Audio-Visual Navigation","created":"2022-10-04","cited_by_count":18,"area":null},{"id":"2303.11329","title":"Sound Localization from Motion: Jointly Learning Sound Direction and Camera Rotation","created":"2023-03-20","cited_by_count":18,"area":null},{"id":"2407.18550","title":"ReALFRED: An Embodied Instruction Following Benchmark in Photo-Realistic Environments","created":"2024-07-26","cited_by_count":16,"area":null},{"id":"2308.12370","title":"AdVerb: Visually Guided Audio Dereverberation","created":"2023-08-23","cited_by_count":15,"area":null},{"id":"2509.16924","title":"Audio-Guided Dynamic Modality Fusion with Stereo-Aware Attention for Audio-Visual Navigation","created":"2025-09-21","cited_by_count":15,"area":null},{"id":"2307.15064","title":"Self-Supervised Visual Acoustic Matching","created":"2023-07-27","cited_by_count":14,"area":null},{"id":"2509.22698","title":"Advancing Audio-Visual Navigation Through Multi-Agent Collaboration in 3D Environments","created":"2025-09-21","cited_by_count":14,"area":null},{"id":"2509.25652","title":"Iterative Residual Cross-Attention Mechanism: An Integrated Approach for Audio-Visual Navigation Tasks","created":"2025-09-30","cited_by_count":14,"area":null},{"id":"2502.15336","title":"Exploring Embodied Multimodal Large Models: Development, Datasets, and Future Directions","created":"2025-02-21","cited_by_count":13,"area":null},{"id":"2509.21377","title":"Dynamic Multi-Target Fusion for Efficient Audio-Visual Navigation","created":"2025-09-23","cited_by_count":13,"area":null},{"id":"2406.07532","title":"Hearing Anything Anywhere","created":"2024-06-11","cited_by_count":12,"area":null},{"id":"2407.13083","title":"Modeling and Driving Human Body Soundfields through Acoustic Primitives","created":"2024-07-18","cited_by_count":12,"area":null},{"id":"2410.01469","title":"TIGER: Time-frequency Interleaved Gain Extraction and Reconstruction for Efficient Speech Separation","created":"2024-10-02","cited_by_count":11,"area":null},{"id":"2302.02809","title":"Listen2Scene: Interactive material-aware binaural sound propagation for reconstructed 3D scenes","created":"2023-02-02","cited_by_count":10,"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":"2211.04473","title":"Towards Improved Room Impulse Response Estimation for Speech Recognition","created":"2022-11-08","cited_by_count":9,"area":null},{"id":"2306.00923","title":"Sonicverse: A Multisensory Simulation Platform for Embodied Household Agents that See and Hear","created":"2023-06-01","cited_by_count":9,"area":null},{"id":"2405.18213","title":"NeRAF: 3D Scene Infused Neural Radiance and Acoustic Fields","created":"2024-05-28","cited_by_count":9,"area":null},{"id":"2307.04760","title":"Learning Spatial Features from Audio-Visual Correspondence in Egocentric Videos","created":"2023-07-10","cited_by_count":8,"area":null},{"id":"2504.10746","title":"Hearing Anywhere in Any Environment","created":"2025-04-14","cited_by_count":8,"area":null},{"id":"2605.07061","title":"Do Joint Audio-Video Generation Models Understand Physics?","created":"2026-05-08","cited_by_count":8,"area":null},{"id":"2405.02821","title":"Sim2Real Transfer for Audio-Visual Navigation with Frequency-Adaptive Acoustic Field Prediction","created":"2024-05-05","cited_by_count":7,"area":null},{"id":"2407.13095","title":"Audio-visual Generalized Zero-shot Learning the Easy Way","created":"2024-07-18","cited_by_count":7,"area":null},{"id":"2308.00219","title":"Multi-goal Audio-visual Navigation using Sound Direction Map","created":"2023-08-01","cited_by_count":6,"area":null},{"id":"2310.15130","title":"Novel-View Acoustic Synthesis from 3D Reconstructed Rooms","created":"2023-10-23","cited_by_count":6,"area":null},{"id":"2506.06862","title":"Multimodal Spatial Language Maps for Robot Navigation and Manipulation","created":"2025-06-07","cited_by_count":6,"area":null},{"id":"2507.02864","title":"The Sound of Simulation: Learning Multimodal Sim-to-Real Robot Policies with Generative Audio","created":"2025-07-03","cited_by_count":6,"area":null},{"id":"2411.11222","title":"The Sound of Water: Inferring Physical Properties from Pouring Liquids","created":"2024-11-18","cited_by_count":5,"area":null},{"id":"2504.21847","title":"Differentiable Room Acoustic Rendering with Multi-View Vision Priors","created":"2025-04-30","cited_by_count":5,"area":null},{"id":"2510.02110","title":"SoundReactor: Frame-level Online Video-to-Audio Generation","created":"2025-10-02","cited_by_count":5,"area":null},{"id":"2402.09245","title":"Overview of the L3DAS23 Challenge on Audio-Visual Extended Reality","created":"2024-02-14","cited_by_count":4,"area":null},{"id":"2410.01481","title":"SonicSim: A customizable simulation platform for speech processing in moving sound source scenarios","created":"2024-10-02","cited_by_count":4,"area":null},{"id":"2410.23230","title":"Aligning Audio-Visual Joint Representations with an Agentic Workflow","created":"2024-10-30","cited_by_count":4,"area":null},{"id":"2506.08524","title":"Teaching Physical Awareness to LLMs through Sounds","created":"2025-06-10","cited_by_count":4,"area":null},{"id":"2508.02905","title":"How Would It Sound? Material-Controlled Multimodal Acoustic Profile Generation for Indoor Scenes","created":"2025-08-04","cited_by_count":4,"area":null},{"id":"2407.02264","title":"SOAF: Scene Occlusion-aware Neural Acoustic Field","created":"2024-07-02","cited_by_count":3,"area":null},{"id":"2507.09750","title":"MB-RIRs: a Synthetic Room Impulse Response Dataset with Frequency-Dependent Absorption Coefficients","created":"2025-07-13","cited_by_count":3,"area":null},{"id":"2404.16216","title":"ActiveRIR: Active Audio-Visual Exploration for Acoustic Environment Modeling","created":"2024-04-24","cited_by_count":2,"area":null},{"id":"2411.02236","title":"3D Audio-Visual Segmentation","created":"2024-11-04","cited_by_count":2,"area":null},{"id":"2601.21667","title":"From Instruction to Event: Sound-Triggered Mobile Manipulation","created":"2026-01-29","cited_by_count":2,"area":null},{"id":"2603.19660","title":"Semantic Audio-Visual Navigation in Continuous Environments","created":"2026-03-20","cited_by_count":2,"area":null},{"id":"2606.14141","title":"Spatio-Temporal Audio Language Modeling for Dynamic Sound Sources","created":"2026-06-12","cited_by_count":2,"area":null},{"id":"2609.23407","title":"OmniEcho: Audio-Visual Spatial Understanding for Omni-Modal Embodied Agents","created":"2026-09-20","cited_by_count":2,"area":null},{"id":"2305.17749","title":"Bayesian inference and neural estimation of acoustic wave propagation","created":"2023-05-28","cited_by_count":1,"area":null},{"id":"2505.13617","title":"Direction-Aware Neural Acoustic Fields for Few-Shot Interpolation of Ambisonic Impulse Responses","created":"2025-05-19","cited_by_count":1,"area":null},{"id":"2510.20602","title":"Resounding Acoustic Fields with Reciprocity","created":"2025-10-23","cited_by_count":1,"area":null},{"id":"2511.20422","title":"VibraVerse: A Large-Scale Geometry-Acoustics Alignment Dataset for Physically-Consistent Multimodal Learning","created":"2025-11-25","cited_by_count":1,"area":null},{"id":"2404.01611","title":"Audio Simulation for Sound Source Localization in Virtual Evironment","created":"2024-04-02","cited_by_count":0,"area":null},{"id":"2405.13860","title":"MAGIC: Map-Guided Few-Shot Audio-Visual Acoustics Modeling","created":"2024-05-22","cited_by_count":0,"area":null},{"id":"2406.11006","title":"SPEAR: Receiver-to-Receiver Acoustic Neural Warping Field","created":"2024-06-16","cited_by_count":0,"area":null},{"id":"2410.18932","title":"ANAVI: Audio Noise Awareness using Visuals of Indoor environments for NAVIgation","created":"2024-10-24","cited_by_count":0,"area":null},{"id":"2412.16861","title":"SoundLoc3D: Invisible 3D Sound Source Localization and Classification Using a Multimodal RGB-D Acoustic Camera","created":"2024-12-22","cited_by_count":0,"area":null},{"id":"2506.00934","title":"GRAM: Spatial general-purpose audio representation models for real-world applications","created":"2025-06-01","cited_by_count":0,"area":null},{"id":"2512.07845","title":"AudioScene: Integrating Object-Event Audio into 3D Scenes","created":"2025-11-25","cited_by_count":0,"area":null},{"id":"2512.12165","title":"Audio-Visual Camera Pose Estimation with Passive Scene Sounds and In-the-Wild Video","created":"2025-12-13","cited_by_count":0,"area":null},{"id":"2604.21119","title":"Materialistic RIR: Material Conditioned Realistic RIR Generation","created":"2026-04-22","cited_by_count":0,"area":null},{"id":"2605.00431","title":"MMAudioReverbs: Video-Guided Acoustic Modeling for Dereverberation and Room Impulse Response Estimation","created":"2026-05-01","cited_by_count":0,"area":null},{"id":"2605.30469","title":"3DAE: Binaural Quality Assessment for Audio Novel View Synthesis with Spatial Maps and Benchmark","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.14820","title":"Spectro-Temporal Interference Confounds Phase Encoding in Spatial Audio Foundation Models","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2607.15265","title":"SceneBind: Binding What and Where Across Vision, Audio and Language","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2607.23293","title":"PathRIR: Physics-Guided Acoustic Path Selection and Late-Tail Compensation for Fast Room Impulse Response Simulation","created":"2026-07-25","cited_by_count":0,"area":null},{"id":"2609.32224","title":"RAO-Nav: Probing Omni-Language Models for Zero-shot Semantic Audio-Visual Navigation","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.36503","title":"AVIO: Learning to Add and Remove Sounding Objects in Audiovisual Scenes","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.38897","title":"FFASR: Benchmarking Far-Field Automatic Speech Recognition using High-Fidelity Simulated RIRs","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.01388","title":"Supervising Sound Localization by In-the-wild Egomotion","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.14077","title":"Two-Stage Multi-modal Learning for Dynamic Audio-Visual Navigation: From Physical Alignment to Scene Aggregation","created":"2026-10-08","cited_by_count":0,"area":null}],"next_cursor":null}