{"list":"other","total":115,"rows":[{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"1312.6114","title":"Auto-Encoding Variational Bayes","created":"2013-12-20","cited_by_count":4053},{"id":"2112.10741","title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","created":"2021-12-20","cited_by_count":3614},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2208.01618","title":"An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion","created":"2022-08-02","cited_by_count":2245},{"id":"2308.12966","title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","created":"2023-08-24","cited_by_count":2224},{"id":"2010.11934","title":"mT5: A massively multilingual pre-trained text-to-text transformer","created":"2020-10-22","cited_by_count":1818},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"id":"2212.08051","title":"Objaverse: A Universe of Annotated 3D Objects","created":"2022-12-15","cited_by_count":1540},{"id":"2406.09414","title":"Depth Anything V2","created":"2024-06-13","cited_by_count":1422},{"id":"2206.10789","title":"Scaling Autoregressive Models for Content-Rich Text-to-Image Generation","created":"2022-06-22","cited_by_count":1295},{"id":"2103.10360","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","created":"2021-03-18","cited_by_count":1031},{"id":"2303.08797","title":"Stochastic Interpolants: A Unifying Framework for Flows and Diffusions","created":"2023-03-15","cited_by_count":939},{"id":"2307.05663","title":"Objaverse-XL: A Universe of 10M+ 3D Objects","created":"2023-07-11","cited_by_count":774},{"id":"2401.08740","title":"SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers","created":"2024-01-16","cited_by_count":737},{"id":"2309.10305","title":"Baichuan 2: Open Large-scale Language Models","created":"2023-09-19","cited_by_count":670},{"id":"2104.10157","title":"VideoGPT: Video Generation using VQ-VAE and Transformers","created":"2021-04-20","cited_by_count":658},{"id":"2312.14125","title":"VideoPoet: A Large Language Model for Zero-Shot Video Generation","created":"2023-12-21","cited_by_count":492},{"id":"2402.17177","title":"Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models","created":"2024-02-27","cited_by_count":477},{"id":"2306.02018","title":"VideoComposer: Compositional Video Synthesis with Motion Controllability","created":"2023-06-03","cited_by_count":464},{"id":"2307.10373","title":"TokenFlow: Consistent Diffusion Features for Consistent Video Editing","created":"2023-07-19","cited_by_count":442},{"id":"2410.03825","title":"MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion","created":"2024-10-04","cited_by_count":442},{"id":"2306.15687","title":"Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale","created":"2023-06-23","cited_by_count":379},{"id":"2403.12008","title":"SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image using Latent Video Diffusion","created":"2024-03-18","cited_by_count":364},{"id":"2103.02406","title":"Multi-attentional Deepfake Detection","created":"2021-03-03","cited_by_count":341},{"id":"2407.02371","title":"OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation","created":"2024-07-02","cited_by_count":341},{"id":"2404.16994","title":"PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning","created":"2024-04-25","cited_by_count":322},{"id":"2405.08748","title":"Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding","created":"2024-05-14","cited_by_count":298},{"id":"2203.16194","title":"FlowFormer: A Transformer Architecture for Optical Flow","created":"2022-03-30","cited_by_count":275},{"id":"2308.08089","title":"DragNUWA: Fine-grained Control in Video Generation by Integrating Text, Image, and Trajectory","created":"2023-08-16","cited_by_count":264},{"id":"2402.17245","title":"Playground v2.5: Three Insights towards Enhancing Aesthetic Quality in Text-to-Image Generation","created":"2024-02-27","cited_by_count":256},{"id":"2402.17485","title":"EMO: Emote Portrait Alive -- Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions","created":"2024-02-27","cited_by_count":235},{"id":"2406.03520","title":"VideoPhy: Evaluating Physical Commonsense for Video Generation","created":"2024-06-05","cited_by_count":228},{"id":"2303.17604","title":"Token Merging for Fast Stable Diffusion","created":"2023-03-30","cited_by_count":224},{"id":"2408.16500","title":"CogVLM2: Visual Language Models for Image and Video Understanding","created":"2024-08-29","cited_by_count":217},{"id":"2402.17525","title":"Diffusion Model-Based Image Editing: A Survey","created":"2024-02-27","cited_by_count":212},{"id":"2411.02385","title":"How Far is Video Generation from World Model: A Physical Law Perspective","created":"2024-11-04","cited_by_count":212},{"id":"1805.09817","title":"Stereo Magnification: Learning View Synthesis using Multiplane Images","created":"2018-05-24","cited_by_count":211},{"id":"2206.02262","title":"Diffusion-GAN: Training GANs with Diffusion","created":"2022-06-05","cited_by_count":205},{"id":"2301.11280","title":"Text-To-4D Dynamic Scene Generation","created":"2023-01-26","cited_by_count":205},{"id":"2301.10972","title":"On the Importance of Noise Scheduling for Diffusion Models","created":"2023-01-26","cited_by_count":194},{"id":"2403.17694","title":"AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation","created":"2024-03-26","cited_by_count":194},{"id":"2206.13559","title":"ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning","created":"2022-06-27","cited_by_count":193},{"id":"2404.10667","title":"VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time","created":"2024-04-16","cited_by_count":187},{"id":"2412.02700","title":"Motion Prompting: Controlling Video Generation with Motion Trajectories","created":"2024-12-03","cited_by_count":178},{"id":"2411.18613","title":"CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models","created":"2024-11-27","cited_by_count":161},{"id":"2411.17440","title":"Identity-Preserving Text-to-Video Generation by Frequency Decomposition","created":"2024-11-26","cited_by_count":158},{"id":"2406.08070","title":"CFG++: Manifold-constrained Classifier Free Guidance for Diffusion Models","created":"2024-06-12","cited_by_count":149},{"id":"2502.01061","title":"OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Models","created":"2025-02-03","cited_by_count":129},{"id":"2312.01026","title":"Token Fusion: Bridging the Gap between Token Pruning and Token Merging","created":"2023-12-02","cited_by_count":125},{"id":"2303.01237","title":"FlowFormer++: Masked Cost Volume Autoencoding for Pretraining Optical Flow Estimation","created":"2023-03-02","cited_by_count":114},{"id":"2402.01566","title":"Boximator: Generating Rich and Controllable Motions for Video Synthesis","created":"2024-02-02","cited_by_count":107},{"id":"2006.10704","title":"Latent Video Transformer","created":"2020-06-18","cited_by_count":106},{"id":"2406.05338","title":"MotionClone: Training-Free Motion Cloning for Controllable Video Generation","created":"2024-06-08","cited_by_count":105},{"id":"2201.00308","title":"DiffuseVAE: Efficient, Controllable and High-Fidelity Generation from Low-Dimensional Latents","created":"2022-01-02","cited_by_count":104},{"id":"2412.12091","title":"Wonderland: Navigating 3D Scenes from a Single Image","created":"2024-12-16","cited_by_count":99},{"id":"2402.12712","title":"MVDiffusion++: A Dense High-resolution Multi-view Diffusion Model for Single or Sparse-view 3D Object Reconstruction","created":"2024-02-20","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":"2402.12376","title":"FiT: Flexible Vision Transformer for Diffusion Model","created":"2024-02-19","cited_by_count":85},{"id":"2303.08340","title":"VideoFlow: Exploiting Temporal Cues for Multi-frame Optical Flow Estimation","created":"2023-03-15","cited_by_count":82},{"id":"2311.00213","title":"Consistent Video-to-Video Transfer Using Synthetic Dataset","created":"2023-11-01","cited_by_count":81},{"id":"2308.14749","title":"MagicEdit: High-Fidelity and Temporally Coherent Video Editing","created":"2023-08-28","cited_by_count":76},{"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":"2312.06725","title":"EpiDiff: Enhancing Multi-View Synthesis via Localized Epipolar-Constrained Diffusion","created":"2023-12-11","cited_by_count":72},{"id":"2412.07759","title":"3DTrajMaster: Mastering 3D Trajectory for Multi-Entity Motion in Video Generation","created":"2024-12-10","cited_by_count":71},{"id":"2401.09414","title":"Vlogger: Make Your Dream A Vlog","created":"2024-01-17","cited_by_count":70},{"id":"2405.20279","title":"CV-VAE: A Compatible Video VAE for Latent Generative Video Models","created":"2024-05-30","cited_by_count":70},{"id":"2405.17933","title":"ToonCrafter: Generative Cartoon Interpolation","created":"2024-05-28","cited_by_count":68},{"id":"2411.04989","title":"SG-I2V: Self-Guided Trajectory Control in Image-to-Video Generation","created":"2024-11-07","cited_by_count":68},{"id":"2405.03121","title":"AniTalker: Animate Vivid and Diverse Talking Faces through Identity-Decoupled Facial Motion Encoding","created":"2024-05-06","cited_by_count":67},{"id":"2407.05965","title":"T2VSafetyBench: Evaluating the Safety of Text-to-Video Generative Models","created":"2024-07-08","cited_by_count":66},{"id":"2501.06187","title":"Multi-subject Open-set Personalization in Video Generation","created":"2025-01-10","cited_by_count":66},{"id":"2402.09368","title":"Magic-Me: Identity-Specific Video Customized Diffusion","created":"2024-02-14","cited_by_count":59},{"id":"2403.12034","title":"VFusion3D: Learning Scalable 3D Generative Models from Video Diffusion Models","created":"2024-03-18","cited_by_count":56},{"id":"2403.12035","title":"CoCoCo: Improving Text-Guided Video Inpainting for Better Consistency, Controllability and Compatibility","created":"2024-03-18","cited_by_count":50},{"id":"2402.13185","title":"UniEdit: A Unified Tuning-Free Framework for Video Motion and Appearance Editing","created":"2024-02-20","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":"2403.13248","title":"Mora: Enabling Generalist Video Generation via A Multi-Agent Framework","created":"2024-03-20","cited_by_count":45},{"id":"2410.13830","title":"DreamVideo-2: Zero-Shot Subject-Driven Video Customization with Precise Motion Control","created":"2024-10-17","cited_by_count":43},{"id":"2312.02216","title":"DragVideo: Interactive Drag-style Video Editing","created":"2023-12-03","cited_by_count":40},{"id":"2412.05263","title":"Mind the Time: Temporally-Controlled Multi-Event Video Generation","created":"2024-12-06","cited_by_count":40},{"id":"1907.06571","title":"Adversarial Video Generation on Complex Datasets","created":"2019-07-15","cited_by_count":33},{"id":"2402.17403","title":"Sora Generates Videos with Stunning Geometrical Consistency","created":"2024-02-27","cited_by_count":31},{"id":"2411.17048","title":"PersonalVideo: High ID-Fidelity Video Customization without Dynamic and Semantic Degradation","created":"2024-11-26","cited_by_count":29},{"id":"2401.01651","title":"AIGCBench: Comprehensive Evaluation of Image-to-Video Content Generated by AI","created":"2024-01-03","cited_by_count":27},{"id":"2311.18827","title":"Motion-Conditioned Image Animation for Video Editing","created":"2023-11-30","cited_by_count":26},{"id":"2410.10076","title":"VideoAgent: Self-Improving Video Generation","created":"2024-10-14","cited_by_count":25},{"id":"2412.07730","title":"STIV: Scalable Text and Image Conditioned Video Generation","created":"2024-12-10","cited_by_count":25},{"id":"2312.02936","title":"Drag-A-Video: Non-rigid Video Editing with Point-based Interaction","created":"2023-12-05","cited_by_count":22},{"id":"2502.14844","title":"Dynamic Concepts Personalization from Single Videos","created":"2025-02-20","cited_by_count":20},{"id":"2412.07721","title":"ObjCtrl-2.5D: Training-free Object Control with Camera Poses","created":"2024-12-10","cited_by_count":18},{"id":"2504.12717","title":"Post-pre-training for Modality Alignment in Vision-Language Foundation Models","created":"2025-04-17","cited_by_count":18},{"id":"2312.09767","title":"DreamTalk: When Emotional Talking Head Generation Meets Diffusion Probabilistic Models","created":"2023-12-15","cited_by_count":16},{"id":"2312.02503","title":"SAVE: Protagonist Diversification with Structure Agnostic Video Editing","created":"2023-12-05","cited_by_count":15},{"id":"2412.06340","title":"UniPaint: Unified Space-time Video Inpainting via Mixture-of-Experts","created":"2024-12-09","cited_by_count":13},{"id":"2311.16254","title":"Safe-CLIP: Removing NSFW Concepts from Vision-and-Language Models","created":"2023-11-27","cited_by_count":12}],"next_cursor":"100"}