{"list":"other","total":62,"rows":[{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"2306.05424","title":"Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models","created":"2023-06-08","cited_by_count":1062},{"id":"2305.06355","title":"VideoChat: Chat-Centric Video Understanding","created":"2023-05-10","cited_by_count":857},{"id":"2509.17765","title":"Qwen3-Omni Technical Report","created":"2025-09-22","cited_by_count":497},{"id":"2204.02152","title":"UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022","created":"2022-04-05","cited_by_count":390},{"id":"2405.01434","title":"StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation","created":"2024-05-02","cited_by_count":247},{"id":"2601.03233","title":"LTX-2: Efficient Joint Audio-Visual Foundation Model","created":"2026-01-06","cited_by_count":236},{"id":"2312.04433","title":"DreamVideo: Composing Your Dream Videos with Customized Subject and Motion","created":"2023-12-07","cited_by_count":188},{"id":"2411.17440","title":"Identity-Preserving Text-to-Video Generation by Frequency Decomposition","created":"2024-11-26","cited_by_count":158},{"id":"2502.11079","title":"Phantom: Subject-consistent video generation via cross-modal alignment","created":"2025-02-16","cited_by_count":129},{"id":"2503.10589","title":"Long Context Tuning for Video Generation","created":"2025-03-13","cited_by_count":113},{"id":"2501.15368","title":"Baichuan-Omni-1.5 Technical Report","created":"2025-01-26","cited_by_count":111},{"id":"2406.15704","title":"video-SALMONN: Speech-Enhanced Audio-Visual Large Language Models","created":"2024-06-22","cited_by_count":102},{"id":"2503.05379","title":"R1-Omni: Explainable Omni-Multimodal Emotion Recognition with Reinforcement Learning","created":"2025-03-07","cited_by_count":100},{"id":"2508.21058","title":"Mixture of Contexts for Long Video Generation","created":"2025-08-28","cited_by_count":95},{"id":"2505.04512","title":"HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation","created":"2025-05-07","cited_by_count":87},{"id":"2502.04328","title":"Ola: Pushing the Frontiers of Omni-Modal Language Model","created":"2025-02-06","cited_by_count":83},{"id":"2510.01284","title":"Ovi: Twin Backbone Cross-Modal Fusion for Audio-Video Generation","created":"2025-09-30","cited_by_count":83},{"id":"2401.09962","title":"CustomVideo: Customizing Text-to-Video Generation with Multiple Subjects","created":"2024-01-18","cited_by_count":77},{"id":"2504.02436","title":"SkyReels-A2: Compose Anything in Video Diffusion Transformers","created":"2025-04-03","cited_by_count":73},{"id":"2501.04698","title":"ConceptMaster: Multi-Concept Video Customization on Diffusion Transformer Models Without Test-Time Tuning","created":"2025-01-08","cited_by_count":68},{"id":"2501.06187","title":"Multi-subject Open-set Personalization in Video Generation","created":"2025-01-10","cited_by_count":66},{"id":"2509.06155","title":"UniVerse-1: Unified Audio-Video Generation via Stitching of Experts","created":"2025-09-07","cited_by_count":61},{"id":"2506.21277","title":"HumanOmniV2: From Understanding to Omni-Modal Reasoning with Context","created":"2025-06-26","cited_by_count":55},{"id":"2510.20822","title":"HoloCine: Holistic Generation of Cinematic Multi-Shot Long Video Narratives","created":"2025-10-23","cited_by_count":54},{"id":"2507.18634","title":"Captain Cinema: Towards Short Movie Generation","created":"2025-07-24","cited_by_count":48},{"id":"2506.15220","title":"video-SALMONN 2: Caption-Enhanced Audio-Visual Large Language Models","created":"2025-06-18","cited_by_count":47},{"id":"2501.01427","title":"VideoAnydoor: High-fidelity Video Object Insertion with Precise Motion Control","created":"2025-01-02","cited_by_count":42},{"id":"2406.07686","title":"AV-DiT: Efficient Audio-Visual Diffusion Transformer for Joint Audio and Video Generation","created":"2024-06-11","cited_by_count":41},{"id":"2505.20256","title":"Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System Collaboration","created":"2025-05-26","cited_by_count":41},{"id":"2505.07652","title":"ShotAdapter: Text-to-Multi-Shot Video Generation with Diffusion Models","created":"2025-05-12","cited_by_count":38},{"id":"2512.03041","title":"MultiShotMaster: A Controllable Multi-Shot Video Generation Framework","created":"2025-12-02","cited_by_count":36},{"id":"2503.23307","title":"MoCha: Towards Movie-Grade Talking Character Synthesis","created":"2025-03-30","cited_by_count":31},{"id":"2510.12720","title":"Omni-Captioner: Data Pipeline, Models, and Benchmark for Omni Detailed Perception","created":"2025-10-14","cited_by_count":30},{"id":"2502.07802","title":"Movie Weaver: Tuning-Free Multi-Concept Video Personalization with Anchored Prompts","created":"2025-02-04","cited_by_count":29},{"id":"2505.04623","title":"EchoInk-R1: Exploring Audio-Visual Reasoning in Multimodal LLMs via Reinforcement Learning","created":"2025-05-07","cited_by_count":29},{"id":"2508.11484","title":"CineTrans: Learning to Generate Videos with Cinematic Transitions via Masked Diffusion Models","created":"2025-08-15","cited_by_count":29},{"id":"2510.10395","title":"AVoCaDO: An Audiovisual Video Captioner Driven by Temporal Orchestration","created":"2025-10-12","cited_by_count":27},{"id":"2503.19881","title":"Mask$^2$DiT: Dual Mask-based Diffusion Transformer for Multi-Scene Long Video Generation","created":"2025-03-25","cited_by_count":25},{"id":"2603.21986","title":"Speed by Simplicity: A Single-Stream Architecture for Fast Audio-Video Generative Foundation Model","created":"2026-03-23","cited_by_count":25},{"id":"2511.12609","title":"Uni-MoE-2.0-Omni: Scaling Language-Centric Omnimodal Large Model with Advanced MoE, Training and Data","created":"2025-11-16","cited_by_count":21},{"id":"2405.12796","title":"DisenStudio: Customized Multi-subject Text-to-Video Generation with Disentangled Spatial Control","created":"2024-05-21","cited_by_count":20},{"id":"2405.14040","title":"Synchronized Video Storytelling: Generating Video Narrations with Structured Storyline","created":"2024-05-22","cited_by_count":19},{"id":"2504.12395","title":"InstantCharacter: Personalize Any Characters with a Scalable Diffusion Transformer Framework","created":"2025-04-16","cited_by_count":19},{"id":"2507.11336","title":"UGC-VideoCaptioner: An Omni UGC Video Detail Caption Model and New Benchmarks","created":"2025-07-15","cited_by_count":19},{"id":"2503.21781","title":"VideoMage: Multi-Subject and Motion Customization of Text-to-Video Diffusion Models","created":"2025-03-27","cited_by_count":17},{"id":"2512.12772","title":"JointAVBench: A Benchmark for Joint Audio-Visual Reasoning Evaluation","created":"2025-12-14","cited_by_count":17},{"id":"2506.07848","title":"PolyVivid: Vivid Multi-Subject Video Generation with Cross-Modal Interaction and Enhancement","created":"2025-06-09","cited_by_count":16},{"id":"2508.08244","title":"Cut2Next: Generating Next Shot via In-Context Tuning","created":"2025-08-11","cited_by_count":15},{"id":"2501.01790","title":"Ingredients: Blending Custom Photos with Video Diffusion Transformers","created":"2025-01-03","cited_by_count":13},{"id":"2510.03117","title":"Taming Text-to-Sounding Video Generation via Advanced Modality Condition and Interaction","created":"2025-10-03","cited_by_count":11},{"id":"2602.05847","title":"OmniVideo-R1: Reinforcing Audio-visual Reasoning with Query Intention and Modality Attention","created":"2026-02-05","cited_by_count":11},{"id":"2602.08711","title":"TimeChat-Captioner: Scripting Multi-Scene Videos with Time-Aware and Structural Audio-Visual Captions","created":"2026-02-09","cited_by_count":11},{"id":"2601.04151","title":"Apollo: Unified Multi-Task Audio-Video Joint Generation","created":"2026-01-07","cited_by_count":10},{"id":"2602.13013","title":"Towards Universal Video MLLMs with Attribute-Structured and Quality-Verified Instructions","created":"2026-02-13","cited_by_count":9},{"id":"2510.24134","title":"VC4VG: Optimizing Video Captions for Text-to-Video Generation","created":"2025-10-28","cited_by_count":8},{"id":"2508.07597","title":"ShoulderShot: Generating Over-the-Shoulder Dialogue Videos","created":"2025-08-11","cited_by_count":7},{"id":"2511.21780","title":"3MDiT: Unified Tri-Modal Diffusion Transformer for Text-Driven Synchronized Audio-Video Generation","created":"2025-11-26","cited_by_count":5},{"id":"2604.05079","title":"SVAgent: Storyline-Guided Long Video Understanding via Cross-Modal Multi-Agent Collaboration","created":"2026-04-06","cited_by_count":4},{"id":"2604.03738","title":"Rethinking Position Embedding as a Context Controller for Multi-Reference and Multi-Shot Video Generation","created":"2026-04-04","cited_by_count":3},{"id":"2509.11360","title":"GLaVE-Cap: Global-Local Aligned Video Captioning with Vision Expert Integration","created":"2025-09-14","cited_by_count":2}],"next_cursor":null}