{"list":"other","total":62,"rows":[{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"id":"2206.00364","title":"Elucidating the Design Space of Diffusion-Based Generative Models","created":"2022-06-01","cited_by_count":3045},{"id":"2211.09800","title":"InstructPix2Pix: Learning to Follow Image Editing Instructions","created":"2022-11-17","cited_by_count":2611},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"2307.06281","title":"MMBench: Is Your Multi-modal Model an All-around Player?","created":"2023-07-12","cited_by_count":2141},{"id":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822},{"id":"2307.04725","title":"AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning","created":"2023-07-10","cited_by_count":1433},{"id":"1812.07035","title":"On the Continuity of Rotation Representations in Neural Networks","created":"2018-12-17","cited_by_count":1214},{"id":"2311.17005","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","created":"2023-11-28","cited_by_count":1109},{"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":"2312.03641","title":"MotionCtrl: A Unified and Flexible Motion Controller for Video Generation","created":"2023-12-06","cited_by_count":580},{"id":"2503.07598","title":"VACE: All-in-One Video Creation and Editing","created":"2025-03-10","cited_by_count":479},{"id":"2404.02101","title":"CameraCtrl: Enabling Camera Control for Text-to-Video Generation","created":"2024-04-02","cited_by_count":460},{"id":"2402.05672","title":"Multilingual E5 Text Embeddings: A Technical Report","created":"2024-02-08","cited_by_count":372},{"id":"2503.03751","title":"GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control","created":"2025-03-05","cited_by_count":341},{"id":"2310.11440","title":"EvalCrafter: Benchmarking and Evaluating Large Video Generation Models","created":"2023-10-17","cited_by_count":340},{"id":"2501.13918","title":"Improving Video Generation with Human Feedback","created":"2025-01-23","cited_by_count":284},{"id":"2501.13826","title":"Video-MMMU: Evaluating Knowledge Acquisition from Multi-Discipline Professional Videos","created":"2025-01-23","cited_by_count":236},{"id":"2402.03162","title":"Direct-a-Video: Customized Video Generation with User-Directed Camera Movement and Object Motion","created":"2024-02-05","cited_by_count":167},{"id":"2404.01258","title":"Direct Preference Optimization of Video Large Multimodal Models from Language Model Reward","created":"2024-04-01","cited_by_count":147},{"id":"2312.10240","title":"Rich Human Feedback for Text-to-Image Generation","created":"2023-12-15","cited_by_count":141},{"id":"2405.17414","title":"Collaborative Video Diffusion: Consistent Multi-video Generation with Camera Control","created":"2024-05-27","cited_by_count":117},{"id":"2412.14167","title":"VideoDPO: Omni-Preference Alignment for Video Diffusion Generation","created":"2024-12-18","cited_by_count":108},{"id":"2407.08737","title":"Video Diffusion Alignment via Reward Gradients","created":"2024-07-11","cited_by_count":107},{"id":"2508.19652","title":"Self-Rewarding Vision-Language Model via Reasoning Decomposition","created":"2025-08-27","cited_by_count":97},{"id":"2502.08639","title":"CineMaster: A 3D-Aware and Controllable Framework for Cinematic Text-to-Video Generation","created":"2025-02-12","cited_by_count":74},{"id":"2410.05677","title":"T2V-Turbo-v2: Enhancing Video Generation Model Post-Training through Data, Reward, and Conditional Guidance Design","created":"2024-10-08","cited_by_count":54},{"id":"2404.15789","title":"MotionMaster: Training-free Camera Motion Transfer For Video Generation","created":"2024-04-24","cited_by_count":51},{"id":"2502.04299","title":"MotionCanvas: Cinematic Shot Design with Controllable Image-to-Video Generation","created":"2025-02-06","cited_by_count":50},{"id":"2305.13840","title":"Control-A-Video: Controllable Text-to-Video Diffusion Models with Motion Prior and Reward Feedback Learning","created":"2023-05-23","cited_by_count":48},{"id":"2412.02617","title":"Improving Dynamic Object Interactions in Text-to-Video Generation with AI Feedback","created":"2024-12-03","cited_by_count":47},{"id":"2509.21309","title":"NewtonGen: Physics-Consistent and Controllable Text-to-Video Generation via Neural Newtonian Dynamics","created":"2025-09-25","cited_by_count":41},{"id":"2402.03746","title":"Tuning Large Multimodal Models for Videos using Reinforcement Learning from AI Feedback","created":"2024-02-06","cited_by_count":36},{"id":"2505.17017","title":"Delving into RL for Image Generation with CoT: A Study on DPO vs. GRPO","created":"2025-05-22","cited_by_count":31},{"id":"2311.15657","title":"Enhancing Diffusion Models with Text-Encoder Reinforcement Learning","created":"2023-11-27","cited_by_count":30},{"id":"2407.01516","title":"E.T. the Exceptional Trajectories: Text-to-camera-trajectory generation with character awareness","created":"2024-07-01","cited_by_count":25},{"id":"2506.02095","title":"Cycle Consistency as Reward: Learning Image-Text Alignment without Human Preferences","created":"2025-06-02","cited_by_count":22},{"id":"2506.21356","title":"ShotBench: Expert-Level Cinematic Understanding in Vision-Language Models","created":"2025-06-26","cited_by_count":22},{"id":"2301.12688","title":"Dynamic Storyboard Generation in an Engine-based Virtual Environment for Video Production","created":"2023-01-30","cited_by_count":21},{"id":"2402.16143","title":"Cinematographic Camera Diffusion Model","created":"2024-02-25","cited_by_count":18},{"id":"2412.03177","title":"PatchDPO: Patch-level DPO for Finetuning-free Personalized Image Generation","created":"2024-12-04","cited_by_count":18},{"id":"2412.14158","title":"AKiRa: Augmentation Kit on Rays for optical video generation","created":"2024-12-18","cited_by_count":18},{"id":"2504.07083","title":"GenDoP: Auto-regressive Camera Trajectory Generation as a Director of Photography","created":"2025-04-09","cited_by_count":18},{"id":"1910.06988","title":"Autonomous Aerial Cinematography In Unstructured Environments With Learned Artistic Decision-Making","created":"2019-10-15","cited_by_count":16},{"id":"2403.04182","title":"Regression-aware Inference with LLMs","created":"2024-03-07","cited_by_count":14},{"id":"2505.02686","title":"Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards","created":"2025-05-05","cited_by_count":14},{"id":"2303.15427","title":"JAWS: Just A Wild Shot for Cinematic Transfer in Neural Radiance Fields","created":"2023-03-27","cited_by_count":13},{"id":"2311.17754","title":"Cinematic Behavior Transfer via NeRF-based Differentiable Filming","created":"2023-11-29","cited_by_count":12},{"id":"1904.02579","title":"Can a Robot Become a Movie Director? Learning Artistic Principles for Aerial Cinematography","created":"2019-04-04","cited_by_count":10},{"id":"2505.21491","title":"Frame In-N-Out: Unbounded Controllable Image-to-Video Generation","created":"2025-05-27","cited_by_count":10},{"id":"2403.13667","title":"DanceCamera3D: 3D Camera Movement Synthesis with Music and Dance","created":"2024-03-20","cited_by_count":8},{"id":"2510.05097","title":"Pulp Motion: Framing-aware multimodal camera and human motion generation","created":"2025-10-06","cited_by_count":8},{"id":"2408.17424","title":"CinePreGen: Camera Controllable Video Previsualization via Engine-powered Diffusion","created":"2024-08-30","cited_by_count":7},{"id":"2504.17828","title":"VEU-Bench: Towards Comprehensive Understanding of Video Editing","created":"2025-04-24","cited_by_count":7},{"id":"2507.20355","title":"CineVision: An Interactive Pre-visualization Storyboard System for Director-Cinematographer Collaboration","created":"2025-07-27","cited_by_count":7},{"id":"2509.22925","title":"Soft-Di[M]O: Improving One-Step Discrete Image Generation with Soft Embeddings","created":"2025-09-26","cited_by_count":6},{"id":"2208.05701","title":"Cine-AI: Generating Video Game Cutscenes in the Style of Human Directors","created":"2022-08-11","cited_by_count":5},{"id":"2401.05272","title":"CineMPC: A Fully Autonomous Drone Cinematography System Incorporating Zoom, Focus, Pose, and Scene Composition","created":"2024-01-10","cited_by_count":5},{"id":"2504.08772","title":"Reward Generation via Large Vision-Language Model in Offline Reinforcement Learning","created":"2025-04-03","cited_by_count":2},{"id":"2506.22832","title":"Listener-Rewarded Thinking in VLMs for Image Preferences","created":"2025-06-28","cited_by_count":2}],"next_cursor":null}