{"total":18,"rows":[{"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,"area":null},{"id":"2502.06020","title":"Temporal Working Memory: Query-Guided Segment Refinement for Enhanced Multimodal Understanding","created":"2025-02-09","cited_by_count":28,"area":null},{"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,"area":null},{"id":"2404.12020","title":"Look, Listen, and Answer: Overcoming Biases for Audio-Visual Question Answering","created":"2024-04-18","cited_by_count":18,"area":null},{"id":"2502.06710","title":"Learning Musical Representations for Music Performance Question Answering","created":"2025-02-10","cited_by_count":17,"area":null},{"id":"2408.03320","title":"Hedge Fund Portfolio Construction Using PolyModel Theory and iTransformer","created":"2024-08-06","cited_by_count":7,"area":null},{"id":"2501.02414","title":"Journey into Automation: Image-Derived Pavement Texture Extraction and Evaluation","created":"2025-01-05","cited_by_count":7,"area":null},{"id":"2506.01319","title":"Learning Sparsity for Effective and Efficient Music Performance Question Answering","created":"2025-06-02","cited_by_count":4,"area":null},{"id":"2510.18346","title":"AV-Master: Dual-Path Comprehensive Perception Makes Better Audio-Visual Question Answering","created":"2025-10-21","cited_by_count":3,"area":null},{"id":"2411.04933","title":"SaSR-Net: Source-Aware Semantic Representation Network for Enhancing Audio-Visual Question Answering","created":"2024-11-07","cited_by_count":2,"area":null},{"id":"2509.17901","title":"Do Modern Video-LLMs Need to Listen? A Benchmark Audit and Scalable Remedy","created":"2025-09-22","cited_by_count":2,"area":null},{"id":"2602.04924","title":"Knowing When to Answer: Adaptive Confidence Refinement for Reliable Audio-Visual Question Answering","created":"2026-02-04","cited_by_count":2,"area":null},{"id":"2503.20978","title":"ScreenLLM: Stateful Screen Schema for Efficient Action Understanding and Prediction","created":"2025-03-26","cited_by_count":1,"area":null},{"id":"2511.05883","title":"Unveiling Modality Bias: Automated Sample-Specific Analysis for Multimodal Misinformation Benchmarks","created":"2025-11-08","cited_by_count":1,"area":null},{"id":"2503.17632","title":"FairFlow: Mitigating Dataset Biases through Undecided Learning","created":"2025-03-22","cited_by_count":0,"area":null},{"id":"2511.18696","title":"Empathetic Cascading Networks: A Multi-Stage Prompting Technique for Reducing Social Biases in Large Language Models","created":"2025-11-24","cited_by_count":0,"area":null},{"id":"2606.20970","title":"CogniRoute: Learning to Route Social Evidence in Omni-Modal Models","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2607.03825","title":"Q-TriM: Question-Guided Tri-Modal Attention for Audio-Visual Question Answering","created":"2026-07-04","cited_by_count":0,"area":null}],"next_cursor":null}