{"total":82,"rows":[{"id":"2206.06488","title":"Multimodal Learning with Transformers: A Survey","created":"2022-06-13","cited_by_count":400,"area":null},{"id":"2206.06994","title":"ProcTHOR: Large-Scale Embodied AI Using Procedural Generation","created":"2022-06-14","cited_by_count":380,"area":null},{"id":"2201.10029","title":"PONI: Potential Functions for ObjectGoal Navigation with Interaction-free Learning","created":"2022-01-25","cited_by_count":150,"area":null},{"id":"2206.08312","title":"SoundSpaces 2.0: A Simulation Platform for Visual-Acoustic Learning","created":"2022-06-16","cited_by_count":95,"area":null},{"id":"2202.02440","title":"Zero Experience Required: Plug & Play Modular Transfer Learning for Semantic Visual Navigation","created":"2022-02-05","cited_by_count":67,"area":null},{"id":"2106.15648","title":"Learning to Map for Active Semantic Goal Navigation","created":"2021-06-29","cited_by_count":50,"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":"2202.10910","title":"Sound Adversarial Audio-Visual Navigation","created":"2022-02-22","cited_by_count":48,"area":null},{"id":"2206.04006","title":"Few-Shot Audio-Visual Learning of Environment Acoustics","created":"2022-06-08","cited_by_count":48,"area":null},{"id":"2210.06849","title":"Retrospectives on the Embodied AI Workshop","created":"2022-10-13","cited_by_count":46,"area":null},{"id":"2202.06875","title":"Visual Acoustic Matching","created":"2022-02-14","cited_by_count":45,"area":null},{"id":"2208.09579","title":"Learning in Audio-visual Context: A Review, Analysis, and New Perspective","created":"2022-08-20","cited_by_count":44,"area":null},{"id":"2112.02306","title":"Toward Practical Monocular Indoor Depth Estimation","created":"2021-12-04","cited_by_count":42,"area":null},{"id":"2111.14843","title":"Catch Me If You Hear Me: Audio-Visual Navigation in Complex Unmapped Environments with Moving Sounds","created":"2021-11-29","cited_by_count":41,"area":null},{"id":"2212.14164","title":"On Transforming Reinforcement Learning by Transformer: The Development Trajectory","created":"2022-12-29","cited_by_count":36,"area":null},{"id":"2105.07142","title":"Move2Hear: Active Audio-Visual Source Separation","created":"2021-05-15","cited_by_count":35,"area":null},{"id":"2308.11073","title":"Audio-Visual Class-Incremental Learning","created":"2023-08-21","cited_by_count":33,"area":null},{"id":"2106.07732","title":"Learning Audio-Visual Dereverberation","created":"2021-06-14","cited_by_count":26,"area":null},{"id":"2210.07940","title":"AVLEN: Audio-Visual-Language Embodied Navigation in 3D Environments","created":"2022-10-14","cited_by_count":26,"area":"wm"},{"id":"2210.16822","title":"Towards Versatile Embodied Navigation","created":"2022-10-30","cited_by_count":26,"area":null},{"id":"2111.10882","title":"Geometry-Aware Multi-Task Learning for Binaural Audio Generation from Video","created":"2021-11-21","cited_by_count":22,"area":null},{"id":"2310.05368","title":"Measuring Acoustics with Collaborative Multiple Agents","created":"2023-10-09","cited_by_count":22,"area":null},{"id":"2210.07505","title":"Learning Active Camera for Multi-Object Navigation","created":"2022-10-14","cited_by_count":21,"area":null},{"id":"2502.12425","title":"Robust Disentangled Counterfactual Learning for Physical Audiovisual Commonsense Reasoning","created":"2025-02-18","cited_by_count":20,"area":"lr"},{"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":"2305.17343","title":"Modality-Independent Teachers Meet Weakly-Supervised Audio-Visual Event Parser","created":"2023-05-27","cited_by_count":18,"area":null},{"id":"2309.08138","title":"Find What You Want: Learning Demand-conditioned Object Attribute Space for Demand-driven Navigation","created":"2023-09-15","cited_by_count":18,"area":null},{"id":"2309.16772","title":"XVO: Generalized Visual Odometry via Cross-Modal Self-Training","created":"2023-09-28","cited_by_count":18,"area":null},{"id":"2111.05846","title":"Structure from Silence: Learning Scene Structure from Ambient Sound","created":"2021-11-10","cited_by_count":17,"area":null},{"id":"2202.00850","title":"Active Audio-Visual Separation of Dynamic Sound Sources","created":"2022-02-02","cited_by_count":16,"area":null},{"id":"2303.06357","title":"CASP-Net: Rethinking Video Saliency Prediction from an Audio-VisualConsistency Perceptual Perspective","created":"2023-03-11","cited_by_count":15,"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":"2207.03483","title":"Finding Fallen Objects Via Asynchronous Audio-Visual Integration","created":"2022-07-07","cited_by_count":14,"area":null},{"id":"2310.19559","title":"Disentangled Counterfactual Learning for Physical Audiovisual Commonsense Reasoning","created":"2023-10-30","cited_by_count":13,"area":"lr"},{"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":"2506.07016","title":"MAGNET: A Multi-agent Framework for Finding Audio-Visual Needles by Reasoning over Multi-Video Haystacks","created":"2025-06-08","cited_by_count":12,"area":"mllm"},{"id":"2403.03145","title":"Dual Mean-Teacher: An Unbiased Semi-Supervised Framework for Audio-Visual Source Localization","created":"2024-03-05","cited_by_count":10,"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":"2206.08500","title":"What do navigation agents learn about their environment?","created":"2022-06-17","cited_by_count":8,"area":null},{"id":"2301.02184","title":"Chat2Map: Efficient Scene Mapping from Multi-Ego Conversations","created":"2023-01-04","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":"2109.08867","title":"V-SlowFast Network for Efficient Visual Sound Separation","created":"2021-09-18","cited_by_count":6,"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":"2109.02763","title":"Binaural SoundNet: Predicting Semantics, Depth and Motion with Binaural Sounds","created":"2021-09-06","cited_by_count":4,"area":null},{"id":"2205.07444","title":"A Deep Reinforcement Learning Blind AI in DareFightingICE","created":"2022-05-16","cited_by_count":4,"area":null},{"id":"2207.01136","title":"Beyond Visual Field of View: Perceiving 3D Environment with Echoes and Vision","created":"2022-07-03","cited_by_count":4,"area":null},{"id":"2212.11345","title":"Knowledge-driven Scene Priors for Semantic Audio-Visual Embodied Navigation","created":"2022-12-21","cited_by_count":4,"area":null},{"id":"2307.16741","title":"Multi-Spectral Image Stitching via Spatial Graph Reasoning","created":"2023-07-31","cited_by_count":4,"area":null},{"id":"2506.21080","title":"EgoAdapt: Adaptive Multisensory Distillation and Policy Learning for Efficient Egocentric Perception","created":"2025-06-26","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":"2512.16250","title":"AMUSE: Audio-Visual Benchmark and Alignment Framework for Agentic Multi-Speaker Understanding","created":"2025-12-18","cited_by_count":4,"area":"mllm"},{"id":"2407.02264","title":"SOAF: Scene Occlusion-aware Neural Acoustic Field","created":"2024-07-02","cited_by_count":3,"area":null},{"id":"2510.21809","title":"Embodied Navigation with Auxiliary Task of Action Description Prediction","created":"2025-10-21","cited_by_count":3,"area":"deeprl"},{"id":"2603.09853","title":"SCENEBench: An Audio Understanding Benchmark Grounded in Assistive and Industrial Use Cases","created":"2026-03-10","cited_by_count":3,"area":null},{"id":"2403.14163","title":"Leveraging Large Language Model-based Room-Object Relationships Knowledge for Enhancing Multimodal-Input Object Goal Navigation","created":"2024-03-21","cited_by_count":2,"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":"2505.09615","title":"UWAV: Uncertainty-weighted Weakly-supervised Audio-Visual Video Parsing","created":"2025-05-14","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":"2609.23407","title":"OmniEcho: Audio-Visual Spatial Understanding for Omni-Modal Embodied Agents","created":"2026-09-20","cited_by_count":2,"area":null},{"id":"2510.11760","title":"Audio-Guided Visual Perception for Audio-Visual Navigation","created":"2025-10-13","cited_by_count":1,"area":null},{"id":"2601.08868","title":"Residual Cross-Modal Fusion Networks for Audio-Visual Navigation","created":"2026-01-11","cited_by_count":1,"area":null},{"id":"2602.02790","title":"Simulating Human Audiovisual Search Behavior","created":"2026-02-02","cited_by_count":1,"area":null},{"id":"2204.01925","title":"Online No-regret Model-Based Meta RL for Personalized Navigation","created":"2022-04-05","cited_by_count":0,"area":null},{"id":"2206.00393","title":"Towards Generalisable Audio Representations for Audio-Visual Navigation","created":"2022-06-01","cited_by_count":0,"area":null},{"id":"2504.01089","title":"HomeEmergency -- Using Audio to Find and Respond to Emergencies in the Home","created":"2025-04-01","cited_by_count":0,"area":null},{"id":"2604.02389","title":"Audio Spatially-Guided Fusion for Audio-Visual Navigation","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2604.02390","title":"Spatial-Aware Conditioned Fusion for Audio-Visual Navigation","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2604.05007","title":"Generalizable Audio-Visual Navigation via Binaural Difference Attention and Action Transition Prediction","created":"2026-04-06","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":"2605.06595","title":"Cross-Modal Navigation with Multi-Agent Reinforcement Learning","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2608.07923","title":"SCoPE: Training-Free Audio-Visual Event Perception via Sparse Cross-Modal Prior Exchange","created":"2026-08-08","cited_by_count":0,"area":null},{"id":"2609.17420","title":"CTAN: Cycle-Temporal Attention Network for Embodied Audio-Visual Navigation","created":"2026-07-25","cited_by_count":0,"area":null},{"id":"2609.17421","title":"Transformer-Based Token Fusion and Dynamic Graph Planning for Audio-Visual Navigation","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2609.21792","title":"AcousticDiffusion: Semantically Conditioned Audio-Guided Diffusion Policy for Search-and-Rescue Assistance","created":"2026-09-18","cited_by_count":0,"area":"diffusion"},{"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":"2610.13300","title":"Sonic-AMG: Streaming Human Motion Generation from Spatial Audio","created":"2026-10-09","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},{"id":"2610.15956","title":"ADAPT: Audio-Depth Action Planning with Transition-Aware Rewards for Lights-Out Industrial Navigation","created":"2026-10-11","cited_by_count":0,"area":"vla"}],"next_cursor":null}