{"list":"other","total":54,"rows":[{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"2306.02858","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","created":"2023-06-05","cited_by_count":1471},{"id":"2503.20215","title":"Qwen2.5-Omni Technical Report","created":"2025-03-26","cited_by_count":736},{"id":"2211.06687","title":"Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation","created":"2022-11-12","cited_by_count":719},{"id":"2311.16922","title":"Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding","created":"2023-11-28","cited_by_count":688},{"id":"2004.14368","title":"VGGSound: A Large-scale Audio-Visual Dataset","created":"2020-04-29","cited_by_count":648},{"id":"2210.15097","title":"Contrastive Decoding: Open-ended Text Generation as Optimization","created":"2022-10-27","cited_by_count":609},{"id":"1912.10211","title":"PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition","created":"2019-12-21","cited_by_count":574},{"id":"2307.16449","title":"MovieChat: From Dense Token to Sparse Memory for Long Video Understanding","created":"2023-07-31","cited_by_count":542},{"id":"2401.17270","title":"YOLO-World: Real-Time Open-Vocabulary Object Detection","created":"2024-01-30","cited_by_count":503},{"id":"2305.16355","title":"PandaGPT: One Model To Instruction-Follow Them All","created":"2023-05-25","cited_by_count":334},{"id":"2305.14739","title":"Trusting Your Evidence: Hallucinate Less with Context-aware Decoding","created":"2023-05-24","cited_by_count":327},{"id":"2406.11816","title":"VideoLLM-online: Online Video Large Language Model for Streaming Video","created":"2024-06-17","cited_by_count":225},{"id":"2408.05211","title":"VITA: Towards Open-Source Interactive Omni Multimodal LLM","created":"2024-08-09","cited_by_count":173},{"id":"2501.03230","title":"Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition","created":"2024-05-07","cited_by_count":153},{"id":"2411.03628","title":"StreamingBench: Assessing the Gap for MLLMs to Achieve Streaming Video Understanding","created":"2024-11-06","cited_by_count":144},{"id":"1708.05237","title":"S$^3$FD: Single Shot Scale-invariant Face Detector","created":"2017-08-17","cited_by_count":142},{"id":"2501.03218","title":"Dispider: Enabling Video LLMs with Active Real-Time Interaction via Disentangled Perception, Decision, and Reaction","created":"2025-01-06","cited_by_count":127},{"id":"2505.21374","title":"Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?","created":"2025-05-27","cited_by_count":118},{"id":"2107.06592","title":"Is Someone Speaking? Exploring Long-term Temporal Features for Audio-visual Active Speaker Detection","created":"2021-07-14","cited_by_count":113},{"id":"2310.13025","title":"Powerset multi-class cross entropy loss for neural speaker diarization","created":"2023-10-19","cited_by_count":111},{"id":"2505.17862","title":"Daily-Omni: Towards Audio-Visual Reasoning with Temporal Alignment across Modalities","created":"2025-05-23","cited_by_count":110},{"id":"2406.15704","title":"video-SALMONN: Speech-Enhanced Audio-Visual Large Language Models","created":"2024-06-22","cited_by_count":102},{"id":"2504.17343","title":"TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos","created":"2025-04-24","cited_by_count":97},{"id":"2306.17806","title":"Stay on topic with Classifier-Free Guidance","created":"2023-06-30","cited_by_count":91},{"id":"2502.19680","title":"M-LLM Based Video Frame Selection for Efficient Video Understanding","created":"2025-02-27","cited_by_count":88},{"id":"2505.21523","title":"More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models","created":"2025-05-23","cited_by_count":86},{"id":"2506.23825","title":"Flash-VStream: Efficient Real-Time Understanding for Long Video Streams","created":"2025-06-30","cited_by_count":81},{"id":"2503.21483","title":"BOLT: Boost Large Vision-Language Model Without Training for Long-form Video Understanding","created":"2025-03-27","cited_by_count":75},{"id":"2501.13468","title":"Streaming Video Understanding and Multi-round Interaction with Memory-enhanced Knowledge","created":"2025-01-23","cited_by_count":73},{"id":"2505.05467","title":"StreamBridge: Turning Your Offline Video Large Language Model into a Proactive Streaming Assistant","created":"2025-05-08","cited_by_count":63},{"id":"2510.10689","title":"OmniVideoBench: Towards Audio-Visual Understanding Evaluation for Omni MLLMs","created":"2025-10-12","cited_by_count":59},{"id":"2403.04640","title":"CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios","created":"2024-03-07","cited_by_count":53},{"id":"2510.18269","title":"StreamingTOM: Streaming Token Compression for Efficient Video Understanding","created":"2025-10-21","cited_by_count":43},{"id":"2601.14724","title":"HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding","created":"2026-01-21","cited_by_count":41},{"id":"2505.18657","title":"MLLMs are Deeply Affected by Modality Bias","created":"2025-05-24","cited_by_count":40},{"id":"2512.00891","title":"Accelerating Streaming Video Large Language Models via Hierarchical Token Compression","created":"2025-11-30","cited_by_count":37},{"id":"2603.12262","title":"Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously","created":"2026-03-12","cited_by_count":22},{"id":"2603.08620","title":"StreamReady: Learning What to Answer and When in Long Streaming Videos","created":"2026-03-09","cited_by_count":19},{"id":"2404.12020","title":"Look, Listen, and Answer: Overcoming Biases for Audio-Visual Question Answering","created":"2024-04-18","cited_by_count":18},{"id":"2412.18495","title":"How \"Real\" is Your Real-Time Simultaneous Speech-to-Text Translation System?","created":"2024-12-24","cited_by_count":17},{"id":"2605.18577","title":"OmniPro: A Comprehensive Benchmark for Omni-Proactive Streaming Video Understanding","created":"2026-05-18","cited_by_count":11},{"id":"2604.02605","title":"Do Audio-Visual Large Language Models Really See and Hear?","created":"2026-04-03","cited_by_count":9},{"id":"2511.10059","title":"When Eyes and Ears Disagree: Can MLLMs Discern Audio-Visual Confusion?","created":"2025-11-13","cited_by_count":8},{"id":"2601.13719","title":"Hierarchical Long Video Understanding with Audiovisual Entity Cohesion and Agentic Search","created":"2026-01-20","cited_by_count":8},{"id":"2603.11896","title":"Think While Watching: Online Streaming Segment-Level Memory for Multi-Turn Video Reasoning in Multimodal Large Language Models","created":"2026-03-12","cited_by_count":8},{"id":"2511.11106","title":"AccKV: Towards Efficient Audio-Video LLMs Inference via Adaptive-Focusing and Cross-Calibration KV Cache Optimization","created":"2025-11-14","cited_by_count":6},{"id":"2604.14129","title":"Don't Let the Video Speak: Audio-Contrastive Preference Optimization for Audio-Visual Language Models","created":"2026-04-15","cited_by_count":6},{"id":"2604.18459","title":"Progressive Online Video Understanding with Evidence-Aligned Timing and Transparent Decisions","created":"2026-04-20","cited_by_count":5},{"id":"2605.25621","title":"StreamOV: Streaming Omni-Video Understanding via Evidence-Guided Memory and Response Triggering","created":"2026-05-25","cited_by_count":5},{"id":"2510.15231","title":"Extending Audio Context for Long-Form Understanding in Large Audio-Language Models","created":"2025-10-17","cited_by_count":2},{"id":"2511.11005","title":"Draft and Refine with Visual Experts","created":"2025-11-14","cited_by_count":2},{"id":"2608.08794","title":"Deferred Audio Pruning with Local Audio-Visual Dynamics for Omni-LLMs","created":"2026-08-09","cited_by_count":2}],"next_cursor":null}