{"list":"other","total":75,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"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":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"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":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2208.12242","title":"DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation","created":"2022-08-25","cited_by_count":3300},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"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":"2404.14219","title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","created":"2024-04-22","cited_by_count":1917},{"id":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"id":"2412.03603","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","created":"2024-12-03","cited_by_count":1660},{"id":"2308.06721","title":"IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models","created":"2023-08-13","cited_by_count":1464},{"id":"2210.09276","title":"Imagic: Text-Based Real Image Editing with Diffusion Models","created":"2022-10-17","cited_by_count":1178},{"id":"2406.12793","title":"ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools","created":"2024-06-18","cited_by_count":1121},{"id":"2212.04488","title":"Multi-Concept Customization of Text-to-Image Diffusion","created":"2022-12-08","cited_by_count":1106},{"id":"2205.15868","title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","created":"2022-05-29","cited_by_count":985},{"id":"2412.20404","title":"Open-Sora: Democratizing Efficient Video Production for All","created":"2024-12-29","cited_by_count":652},{"id":"2305.14720","title":"BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing","created":"2023-05-24","cited_by_count":442},{"id":"2302.13848","title":"ELITE: Encoding Visual Concepts into Textual Embeddings for Customized Text-to-Image Generation","created":"2023-02-27","cited_by_count":416},{"id":"2410.10629","title":"SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers","created":"2024-10-14","cited_by_count":340},{"id":"2303.11305","title":"SVDiff: Compact Parameter Space for Diffusion Fine-Tuning","created":"2023-03-20","cited_by_count":338},{"id":"2303.09522","title":"P+: Extended Textual Conditioning in Text-to-Image Generation","created":"2023-03-16","cited_by_count":242},{"id":"2307.06949","title":"HyperDreamBooth: HyperNetworks for Fast Personalization of Text-to-Image Models","created":"2023-07-13","cited_by_count":225},{"id":"2302.12228","title":"Encoder-based Domain Tuning for Fast Personalization of Text-to-Image Models","created":"2023-02-23","cited_by_count":203},{"id":"2307.11410","title":"Subject-Diffusion:Open Domain Personalized Text-to-Image Generation without Test-time Fine-tuning","created":"2023-07-21","cited_by_count":191},{"id":"2411.17440","title":"Identity-Preserving Text-to-Video Generation by Frequency Decomposition","created":"2024-11-26","cited_by_count":158},{"id":"2311.17009","title":"Space-Time Diffusion Features for Zero-Shot Text-Driven Motion Transfer","created":"2023-11-28","cited_by_count":124},{"id":"2305.15391","title":"A Neural Space-Time Representation for Text-to-Image Personalization","created":"2023-05-24","cited_by_count":123},{"id":"1310.0150","title":"Stability","created":"2013-10-01","cited_by_count":120},{"id":"2304.02642","title":"Taming Encoder for Zero Fine-tuning Image Customization with Text-to-Image Diffusion Models","created":"2023-04-05","cited_by_count":117},{"id":"2406.05338","title":"MotionClone: Training-Free Motion Cloning for Controllable Video Generation","created":"2024-06-08","cited_by_count":105},{"id":"2308.09710","title":"SimDA: Simple Diffusion Adapter for Efficient Video Generation","created":"2023-08-18","cited_by_count":101},{"id":"2406.17758","title":"MotionBooth: Motion-Aware Customized Text-to-Video Generation","created":"2024-06-25","cited_by_count":93},{"id":"2411.02265","title":"Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent","created":"2024-11-04","cited_by_count":90},{"id":"2410.10306","title":"Animate-X: Universal Character Image Animation with Enhanced Motion Representation","created":"2024-10-14","cited_by_count":88},{"id":"2307.06925","title":"Domain-Agnostic Tuning-Encoder for Fast Personalization of Text-To-Image Models","created":"2023-07-13","cited_by_count":85},{"id":"2303.13495","title":"ReVersion: Diffusion-Based Relation Inversion from Images","created":"2023-03-23","cited_by_count":82},{"id":"2404.01647","title":"EDTalk: Efficient Disentanglement for Emotional Talking Head Synthesis","created":"2024-04-02","cited_by_count":80},{"id":"2311.17002","title":"Ranni: Taming Text-to-Image Diffusion for Accurate Instruction Following","created":"2023-11-28","cited_by_count":77},{"id":"2305.18247","title":"TaleCrafter: Interactive Story Visualization with Multiple Characters","created":"2023-05-29","cited_by_count":73},{"id":"2305.16223","title":"Prompt-Free Diffusion: Taking \"Text\" out of Text-to-Image Diffusion Models","created":"2023-05-25","cited_by_count":62},{"id":"2408.13239","title":"CustomCrafter: Customized Video Generation with Preserving Motion and Concept Composition Abilities","created":"2024-08-23","cited_by_count":60},{"id":"2305.15779","title":"Custom-Edit: Text-Guided Image Editing with Customized Diffusion Models","created":"2023-05-25","cited_by_count":54},{"id":"2308.00301","title":"Online Prototype Learning for Online Continual Learning","created":"2023-08-01","cited_by_count":53},{"id":"2305.13579","title":"Enhancing Detail Preservation for Customized Text-to-Image Generation: A Regularization-Free Approach","created":"2023-05-23","cited_by_count":43},{"id":"2403.06375","title":"FlowVQTalker: High-Quality Emotional Talking Face Generation through Normalizing Flow and Quantization","created":"2024-03-11","cited_by_count":39},{"id":"2403.06365","title":"Style2Talker: High-Resolution Talking Head Generation with Emotion Style and Art Style","created":"2024-03-11","cited_by_count":33},{"id":"2412.08614","title":"Benchmarking Large Vision-Language Models via Directed Scene Graph for Comprehensive Image Captioning","created":"2024-12-11","cited_by_count":31},{"id":"2403.20193","title":"Motion Inversion for Video Customization","created":"2024-03-29","cited_by_count":30},{"id":"2404.05680","title":"SphereHead: Stable 3D Full-head Synthesis with Spherical Tri-plane Representation","created":"2024-04-08","cited_by_count":30},{"id":"2403.06363","title":"Say Anything with Any Style","created":"2024-03-11","cited_by_count":26},{"id":"2505.03730","title":"FlexiAct: Towards Flexible Action Control in Heterogeneous Scenarios","created":"2025-05-06","cited_by_count":25},{"id":"2311.15841","title":"Learning Disentangled Identifiers for Action-Customized Text-to-Image Generation","created":"2023-11-27","cited_by_count":24},{"id":"2503.07602","title":"DreamRelation: Relation-Centric Video Customization","created":"2025-03-10","cited_by_count":23},{"id":"2311.15773","title":"Check, Locate, Rectify: A Training-Free Layout Calibration System for Text-to-Image Generation","created":"2023-11-27","cited_by_count":19},{"id":"2502.13995","title":"FantasyID: Face Knowledge Enhanced ID-Preserving Video Generation","created":"2025-02-19","cited_by_count":18},{"id":"2501.07563","title":"Training-Free Motion-Guided Video Generation with Enhanced Temporal Consistency Using Motion Consistency Loss","created":"2025-01-13","cited_by_count":15},{"id":"2302.06891","title":"UKnow: A Unified Knowledge Protocol with Multimodal Knowledge Graph Datasets for Reasoning and Vision-Language Pre-Training","created":"2023-02-14","cited_by_count":14},{"id":"2306.17154","title":"Generate Anything Anywhere in Any Scene","created":"2023-06-29","cited_by_count":14},{"id":"2505.02471","title":"Ming-Lite-Uni: Advancements in Unified Architecture for Natural Multimodal Interaction","created":"2025-05-05","cited_by_count":13},{"id":"2412.10533","title":"SUGAR: Subject-Driven Video Customization in a Zero-Shot Manner","created":"2024-12-13","cited_by_count":12},{"id":"2503.12035","title":"MOS: Modeling Object-Scene Associations in Generalized Category Discovery","created":"2025-03-15","cited_by_count":10},{"id":"2506.04228","title":"LayerFlow: A Unified Model for Layer-aware Video Generation","created":"2025-06-04","cited_by_count":10},{"id":"2311.11525","title":"Generalized Category Discovery in Semantic Segmentation","created":"2023-11-20","cited_by_count":4},{"id":"2409.15650","title":"ImPoster: Text and Frequency Guidance for Subject Driven Action Personalization using Diffusion Models","created":"2024-09-24","cited_by_count":2}],"next_cursor":null}