{"total":20,"rows":[{"id":"2410.18325","title":"AVHBench: A Cross-Modal Hallucination Benchmark for Audio-Visual Large Language Models","created":"2024-10-23","cited_by_count":56,"area":null},{"id":"2503.19851","title":"Towards Online Multi-Modal Social Interaction Understanding","created":"2025-03-25","cited_by_count":12,"area":null},{"id":"2511.17952","title":"Multi-speaker Attention Alignment for Multimodal Social Interaction","created":"2025-11-22","cited_by_count":9,"area":null},{"id":"2502.18331","title":"BottleHumor: Self-Informed Humor Explanation using the Information Bottleneck Principle","created":"2025-02-22","cited_by_count":6,"area":null},{"id":"2408.07694","title":"End-to-end Semantic-centric Video-based Multimodal Affective Computing","created":"2024-08-14","cited_by_count":4,"area":null},{"id":"2506.11162","title":"VIBE: Can a VLM Read the Room?","created":"2025-06-11","cited_by_count":4,"area":null},{"id":"2604.00267","title":"Omni-MMSI: Toward Identity-attributed Social Interaction Understanding","created":"2026-03-31","cited_by_count":4,"area":null},{"id":"2605.10079","title":"SocialDirector: Training-Free Social Interaction Control for Multi-Person Video Generation","created":"2026-05-11","cited_by_count":4,"area":null},{"id":"2410.13206","title":"BQA: Body Language Question Answering Dataset for Video Large Language Models","created":"2024-10-17","cited_by_count":3,"area":null},{"id":"2512.00582","title":"SatireDecoder: Visual Cascaded Decoupling for Enhancing Satirical Image Comprehension","created":"2025-11-29","cited_by_count":3,"area":null},{"id":"2605.25409","title":"MTLLFM: Multimodal-Temporal Laughter Localization: UR-FUNNY-Temporal and SMILE-Temporal Benchmarks with an Adaptive Multimodal Fusion Model","created":"2026-05-25","cited_by_count":2,"area":null},{"id":"2606.02642","title":"SVHalluc: Benchmarking Speech-Vision Hallucination in Audio-Visual Large Language Models","created":"2026-05-31","cited_by_count":2,"area":null},{"id":"2509.25773","title":"v-HUB: A Benchmark for Video Humor Understanding from Vision and Sound","created":"2025-09-30","cited_by_count":1,"area":null},{"id":"2603.18678","title":"Words at Play: Benchmarking Audio Pun Understanding in Large Audio-Language Models","created":"2026-03-19","cited_by_count":1,"area":null},{"id":"2607.27895","title":"MMHBench: A Multi-Perspective Benchmark for Mental Health Understanding in Long-Form Videos","created":"2026-07-30","cited_by_count":1,"area":null},{"id":"2411.02430","title":"Generative Emotion Cause Explanation in Multimodal Conversations","created":"2024-11-01","cited_by_count":0,"area":null},{"id":"2510.18014","title":"ManzaiSet: A Multimodal Dataset of Viewer Responses to Japanese Manzai Comedy","created":"2025-10-20","cited_by_count":0,"area":null},{"id":"2608.04939","title":"Reading Between the Frames of Multimodal Drivelology","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2609.06646","title":"When Does a Laugh Begin? Structured Annotator Disagreement in Temporal Laughter Localization","created":"2026-09-06","cited_by_count":0,"area":null},{"id":"2609.19793","title":"AI Smart Glasses for Wearable Intelligence: From Egocentric Sensing to Agentic Personalization","created":"2026-09-17","cited_by_count":0,"area":null}],"next_cursor":null}