{"list":"other","total":54,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2209.03003","title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","created":"2022-09-07","cited_by_count":3700},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"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":"2412.03603","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","created":"2024-12-03","cited_by_count":1660},{"id":"2105.08276","title":"NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions","created":"2021-05-18","cited_by_count":744},{"id":"2410.13720","title":"Movie Gen: A Cast of Media Foundation Models","created":"2024-10-17","cited_by_count":644},{"id":"1910.01442","title":"CLEVRER: CoLlision Events for Video REpresentation and Reasoning","created":"2019-10-03","cited_by_count":484},{"id":"2503.21776","title":"Video-R1: Reinforcing Video Reasoning in MLLMs","created":"2025-03-27","cited_by_count":484},{"id":"2505.13211","title":"MAGI-1: Autoregressive Video Generation at Scale","created":"2025-05-19","cited_by_count":276},{"id":"2405.09711","title":"STAR: A Benchmark for Situated Reasoning in Real-World Videos","created":"2024-05-15","cited_by_count":213},{"id":"2304.09790","title":"AMT: All-Pairs Multi-Field Transforms for Efficient Frame Interpolation","created":"2023-04-19","cited_by_count":180},{"id":"2411.17440","title":"Identity-Preserving Text-to-Video Generation by Frequency Decomposition","created":"2024-11-26","cited_by_count":158},{"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":"2309.15091","title":"VideoDirectorGPT: Consistent Multi-scene Video Generation via LLM-Guided Planning","created":"2023-09-26","cited_by_count":141},{"id":"2312.00777","title":"VideoBooth: Diffusion-based Video Generation with Image Prompts","created":"2023-12-01","cited_by_count":126},{"id":"2503.10589","title":"Long Context Tuning for Video Generation","created":"2025-03-13","cited_by_count":113},{"id":"2503.07314","title":"Automated Movie Generation via Multi-Agent CoT Planning","created":"2025-03-10","cited_by_count":89},{"id":"2510.08377","title":"UniVideo: Unified Understanding, Generation, and Editing for Videos","created":"2025-10-09","cited_by_count":87},{"id":"2401.01256","title":"VideoStudio: Generating Consistent-Content and Multi-Scene Videos","created":"2024-01-02","cited_by_count":64},{"id":"2010.07999","title":"What is More Likely to Happen Next? Video-and-Language Future Event Prediction","created":"2020-10-15","cited_by_count":62},{"id":"2303.10437","title":"Grounding 3D Object Affordance from 2D Interactions in Images","created":"2023-03-18","cited_by_count":62},{"id":"2402.09368","title":"Magic-Me: Identity-Specific Video Customized Diffusion","created":"2024-02-14","cited_by_count":59},{"id":"2510.20822","title":"HoloCine: Holistic Generation of Cinematic Multi-Shot Long Video Narratives","created":"2025-10-23","cited_by_count":54},{"id":"2312.08963","title":"LEMON: Learning 3D Human-Object Interaction Relation from 2D Images","created":"2023-12-14","cited_by_count":49},{"id":"2512.19539","title":"StoryMem: Multi-shot Long Video Storytelling with Memory","created":"2025-12-22","cited_by_count":40},{"id":"2412.09349","title":"DisPose: Disentangling Pose Guidance for Controllable Human Image Animation","created":"2024-12-12","cited_by_count":35},{"id":"2510.05094","title":"VChain: Chain-of-Visual-Thought for Reasoning in Video Generation","created":"2025-10-06","cited_by_count":32},{"id":"2410.05227","title":"The Dawn of Video Generation: Preliminary Explorations with SORA-like Models","created":"2024-10-07","cited_by_count":31},{"id":"2411.19626","title":"GREAT: Geometry-Intention Collaborative Inference for Open-Vocabulary 3D Object Affordance Grounding","created":"2024-11-29","cited_by_count":28},{"id":"2603.25746","title":"ShotStream: Streaming Multi-Shot Video Generation for Interactive Storytelling","created":"2026-03-26","cited_by_count":28},{"id":"2405.13659","title":"EgoChoir: Capturing 3D Human-Object Interaction Regions from Egocentric Views","created":"2024-05-22","cited_by_count":26},{"id":"2512.12372","title":"STAGE: Storyboard-Anchored Generation for Cinematic Multi-shot Narrative","created":"2025-12-13","cited_by_count":23},{"id":"2509.24200","title":"UniVid: The Open-Source Unified Video Model","created":"2025-09-29","cited_by_count":19},{"id":"2501.06173","title":"VideoAuteur: Towards Long Narrative Video Generation","created":"2025-01-10","cited_by_count":18},{"id":"2505.22457","title":"Fostering Video Reasoning via Next-Event Prediction","created":"2025-05-28","cited_by_count":18},{"id":"2503.08270","title":"HERO: Human Reaction Generation from Videos","created":"2025-03-11","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":"2505.18078","title":"DanceTogether! Identity-Preserving Multi-Person Interactive Video Generation","created":"2025-05-23","cited_by_count":13},{"id":"2504.06982","title":"SIGMAN:Scaling 3D Human Gaussian Generation with Millions of Assets","created":"2025-04-09","cited_by_count":12},{"id":"2604.07823","title":"LPM 1.0: Video-based Character Performance Model","created":"2026-04-09","cited_by_count":11},{"id":"2511.16669","title":"Video-as-Answer: Predict and Generate Next Video Event with Joint-GRPO","created":"2025-11-20","cited_by_count":9},{"id":"2506.02448","title":"VidEvent: A Large Dataset for Understanding Dynamic Evolution of Events in Videos","created":"2025-06-03","cited_by_count":8},{"id":"2510.14874","title":"TOUCH: Text-guided Controllable Generation of Free-Form Hand-Object Interactions","created":"2025-10-16","cited_by_count":8},{"id":"2506.14404","title":"Causally Steered Diffusion for Automated Video Counterfactual Generation","created":"2025-06-17","cited_by_count":6},{"id":"2406.18227","title":"GUIDE: A Guideline-Guided Dataset for Instructional Video Comprehension","created":"2024-06-26","cited_by_count":4},{"id":"2511.17481","title":"Counterfactual World Models via Digital Twin-conditioned Video Diffusion","created":"2025-11-21","cited_by_count":4},{"id":"2603.29931","title":"Gloria: Consistent Character Video Generation via Content Anchors","created":"2026-03-31","cited_by_count":3},{"id":"2512.13015","title":"What Happens Next? Next Scene Prediction with a Unified Video Model","created":"2025-12-15","cited_by_count":2}],"next_cursor":null}