{"list":"other","total":83,"rows":[{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822},{"id":"2110.13900","title":"WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing","created":"2021-10-26","cited_by_count":1657},{"id":"1812.01717","title":"Towards Accurate Generative Models of Video: A New Metric & Challenges","created":"2018-12-03","cited_by_count":1234},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"id":"2205.15868","title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","created":"2022-05-29","cited_by_count":985},{"id":"2004.14368","title":"VGGSound: A Large-scale Audio-Visual Dataset","created":"2020-04-29","cited_by_count":648},{"id":"2301.12503","title":"AudioLDM: Text-to-Audio Generation with Latent Diffusion Models","created":"2023-01-29","cited_by_count":599},{"id":"2312.03641","title":"MotionCtrl: A Unified and Flexible Motion Controller for Video Generation","created":"2023-12-06","cited_by_count":580},{"id":"2307.06942","title":"InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation","created":"2023-07-13","cited_by_count":497},{"id":"2509.17765","title":"Qwen3-Omni Technical Report","created":"2025-09-22","cited_by_count":497},{"id":"2503.07598","title":"VACE: All-in-One Video Creation and Editing","created":"2025-03-10","cited_by_count":479},{"id":"2410.06885","title":"F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching","created":"2024-10-09","cited_by_count":361},{"id":"2407.05407","title":"CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens","created":"2024-07-07","cited_by_count":334},{"id":"2506.09113","title":"Seedance 1.0: Exploring the Boundaries of Video Generation Models","created":"2025-06-10","cited_by_count":259},{"id":"2403.14773","title":"StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text","created":"2024-03-21","cited_by_count":251},{"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":"2212.09478","title":"MM-Diffusion: Learning Multi-Modal Diffusion Models for Joint Audio and Video Generation","created":"2022-12-19","cited_by_count":227},{"id":"2403.03100","title":"NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models","created":"2024-03-05","cited_by_count":226},{"id":"1812.08466","title":"Fr\\'echet Audio Distance: A Metric for Evaluating Music Enhancement Algorithms","created":"2018-12-20","cited_by_count":225},{"id":"2412.02700","title":"Motion Prompting: Controlling Video Generation with Motion Trajectories","created":"2024-12-03","cited_by_count":178},{"id":"2008.04838","title":"TransNet V2: An effective deep network architecture for fast shot transition detection","created":"2020-08-11","cited_by_count":171},{"id":"2511.18870","title":"HunyuanVideo 1.5 Technical Report","created":"2025-11-24","cited_by_count":160},{"id":"2410.23775","title":"In-Context LoRA for Diffusion Transformers","created":"2024-10-31","cited_by_count":158},{"id":"2309.15091","title":"VideoDirectorGPT: Consistent Multi-scene Video Generation via LLM-Guided Planning","created":"2023-09-26","cited_by_count":141},{"id":"2502.05139","title":"Meta Audiobox Aesthetics: Unified Automatic Quality Assessment for Speech, Music, and Sound","created":"2025-02-07","cited_by_count":137},{"id":"2306.17203","title":"Diff-Foley: Synchronized Video-to-Audio Synthesis with Latent Diffusion Models","created":"2023-06-29","cited_by_count":134},{"id":"2412.15322","title":"MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis","created":"2024-12-19","cited_by_count":134},{"id":"2502.11079","title":"Phantom: Subject-consistent video generation via cross-modal alignment","created":"2025-02-16","cited_by_count":129},{"id":"2601.15621","title":"Qwen3-TTS Technical Report","created":"2026-01-22","cited_by_count":118},{"id":"2402.17723","title":"Seeing and Hearing: Open-domain Visual-Audio Generation with Diffusion Latent Aligners","created":"2024-02-27","cited_by_count":111},{"id":"1712.01393","title":"Visual to Sound: Generating Natural Sound for Videos in the Wild","created":"2017-12-04","cited_by_count":98},{"id":"2005.04208","title":"Condensed Movies: Story Based Retrieval with Contextual Embeddings","created":"2020-05-08","cited_by_count":95},{"id":"2406.17758","title":"MotionBooth: Motion-Aware Customized Text-to-Video Generation","created":"2024-06-25","cited_by_count":93},{"id":"2407.16655","title":"MovieDreamer: Hierarchical Generation for Coherent Long Visual Sequence","created":"2024-07-23","cited_by_count":89},{"id":"2503.07314","title":"Automated Movie Generation via Multi-Agent CoT Planning","created":"2025-03-10","cited_by_count":89},{"id":"2503.23377","title":"JavisDiT: Joint Audio-Video Diffusion Transformer with Hierarchical Spatio-Temporal Prior Synchronization","created":"2025-03-30","cited_by_count":88},{"id":"2510.01284","title":"Ovi: Twin Backbone Cross-Modal Fusion for Audio-Video Generation","created":"2025-09-30","cited_by_count":83},{"id":"2412.00115","title":"OpenHumanVid: A Large-Scale High-Quality Dataset for Enhancing Human-Centric Video Generation","created":"2024-11-28","cited_by_count":77},{"id":"2309.16429","title":"Diverse and Aligned Audio-to-Video Generation via Text-to-Video Model Adaptation","created":"2023-09-28","cited_by_count":69},{"id":"2501.06187","title":"Multi-subject Open-set Personalization in Video Generation","created":"2025-01-10","cited_by_count":66},{"id":"2401.01256","title":"VideoStudio: Generating Consistent-Content and Multi-Scene Videos","created":"2024-01-02","cited_by_count":64},{"id":"2503.16421","title":"MagicMotion: Controllable Video Generation with Dense-to-Sparse Trajectory Guidance","created":"2025-03-20","cited_by_count":61},{"id":"2509.06155","title":"UniVerse-1: Unified Audio-Video Generation via Stitching of Experts","created":"2025-09-07","cited_by_count":61},{"id":"2503.23368","title":"VLIPP: Towards Physically Plausible Video Generation with Vision and Language Informed Physical Prior","created":"2025-03-30","cited_by_count":52},{"id":"2405.13557","title":"MotionCraft: Physics-based Zero-Shot Video Generation","created":"2024-05-22","cited_by_count":48},{"id":"2508.16930","title":"HunyuanVideo-Foley: Multimodal Diffusion with Representation Alignment for High-Fidelity Foley Audio Generation","created":"2025-08-23","cited_by_count":46},{"id":"2602.08794","title":"MOVA: Towards Scalable and Synchronized Video-Audio Generation","created":"2026-02-09","cited_by_count":43},{"id":"2412.05263","title":"Mind the Time: Temporally-Controlled Multi-Event Video Generation","created":"2024-12-06","cited_by_count":40},{"id":"2512.19539","title":"StoryMem: Multi-shot Long Video Storytelling with Memory","created":"2025-12-22","cited_by_count":40},{"id":"2505.07652","title":"ShotAdapter: Text-to-Multi-Shot Video Generation with Diffusion Models","created":"2025-05-12","cited_by_count":38},{"id":"2411.15262","title":"MovieBench: A Hierarchical Movie Level Dataset for Long Video Generation","created":"2024-11-22","cited_by_count":36},{"id":"2503.15138","title":"VideoGen-of-Thought: Step-by-step generating multi-shot video with minimal manual intervention","created":"2025-03-19","cited_by_count":36},{"id":"2411.10836","title":"AnimateAnything: Consistent and Controllable Animation for Video Generation","created":"2024-11-16","cited_by_count":35},{"id":"2312.01409","title":"Generative Rendering: Controllable 4D-Guided Video Generation with 2D Diffusion Models","created":"2023-12-03","cited_by_count":30},{"id":"2406.16260","title":"Video-Infinity: Distributed Long Video Generation","created":"2024-06-24","cited_by_count":30},{"id":"2512.18099","title":"SAM Audio: Segment Anything in Audio","created":"2025-12-19","cited_by_count":30},{"id":"2506.15838","title":"EchoShot: Multi-Shot Portrait Video Generation","created":"2025-06-16","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":"2007.12130","title":"Sound2Sight: Generating Visual Dynamics from Sound and Context","created":"2020-07-23","cited_by_count":28},{"id":"2602.19163","title":"JavisDiT++: Unified Modeling and Optimization for Joint Audio-Video Generation","created":"2026-02-22","cited_by_count":25},{"id":"2512.12372","title":"STAGE: Storyboard-Anchored Generation for Cinematic Multi-shot Narrative","created":"2025-12-13","cited_by_count":23},{"id":"2305.17098","title":"ControlVideo: Conditional Control for One-shot Text-driven Video Editing and Beyond","created":"2023-05-26","cited_by_count":22},{"id":"2412.15191","title":"AV-Link: Temporally-Aligned Diffusion Features for Cross-Modal Audio-Video Generation","created":"2024-12-19","cited_by_count":22},{"id":"2410.01594","title":"MM-LDM: Multi-Modal Latent Diffusion Model for Sounding Video Generation","created":"2024-10-02","cited_by_count":17},{"id":"2412.10768","title":"VinTAGe: Joint Video and Text Conditioning for Holistic Audio Generation","created":"2024-12-14","cited_by_count":16},{"id":"2506.08003","title":"Audio-Sync Video Generation with Multi-Stream Temporal Control","created":"2025-06-09","cited_by_count":15},{"id":"2508.08244","title":"Cut2Next: Generating Next Shot via In-Context Tuning","created":"2025-08-11","cited_by_count":15},{"id":"2503.18150","title":"LongDiff: Training-Free Long Video Generation in One Go","created":"2025-03-23","cited_by_count":13},{"id":"2406.10221","title":"Long Story Short: Story-level Video Understanding from 20K Short Films","created":"2024-06-14","cited_by_count":12},{"id":"2602.23969","title":"MSVBench: Towards Human-Level Evaluation of Multi-Shot Video Generation","created":"2026-02-27","cited_by_count":12},{"id":"2601.04151","title":"Apollo: Unified Multi-Task Audio-Video Joint Generation","created":"2026-01-07","cited_by_count":10},{"id":"2205.05487","title":"Scene Consistency Representation Learning for Video Scene Segmentation","created":"2022-05-11","cited_by_count":9},{"id":"2512.10571","title":"AVI-Edit: Audio-sync Video Instance Editing with Granularity-Aware Mask Refiner","created":"2025-12-11","cited_by_count":9},{"id":"2601.01568","title":"MM-Sonate: Multimodal Controllable Audio-Video Generation with Zero-Shot Voice Cloning","created":"2026-01-04","cited_by_count":7},{"id":"2605.18467","title":"InstructAV2AV: Instruction-Guided Audio-Video Joint Editing","created":"2026-05-18","cited_by_count":5}],"next_cursor":null}