{"list":"other","total":68,"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"1907.05600","title":"Generative Modeling by Estimating Gradients of the Data Distribution","created":"2019-07-12","cited_by_count":4101},{"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":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"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":"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":"2111.02114","title":"LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs","created":"2021-11-03","cited_by_count":1555},{"id":"2303.11328","title":"Zero-1-to-3: Zero-shot One Image to 3D Object","created":"2023-03-20","cited_by_count":1489},{"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":"2302.08453","title":"T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models","created":"2023-02-16","cited_by_count":1351},{"id":"2304.05977","title":"ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation","created":"2023-04-12","cited_by_count":1045},{"id":"2305.13301","title":"Training Diffusion Models with Reinforcement Learning","created":"2023-05-22","cited_by_count":982},{"id":"2303.08797","title":"Stochastic Interpolants: A Unifying Framework for Flows and Diffusions","created":"2023-03-15","cited_by_count":939},{"id":"2311.12908","title":"Diffusion Model Alignment Using Direct Preference Optimization","created":"2023-11-21","cited_by_count":790},{"id":"2301.07093","title":"GLIGEN: Open-Set Grounded Text-to-Image Generation","created":"2023-01-17","cited_by_count":781},{"id":"1901.02970","title":"Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation","created":"2019-01-09","cited_by_count":495},{"id":"2305.16381","title":"DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Models","created":"2023-05-25","cited_by_count":450},{"id":"2401.07519","title":"InstantID: Zero-shot Identity-Preserving Generation in Seconds","created":"2024-01-15","cited_by_count":436},{"id":"1905.07088","title":"Sliced Score Matching: A Scalable Approach to Density and Score Estimation","created":"2019-05-17","cited_by_count":384},{"id":"2305.16322","title":"Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Models","created":"2023-05-25","cited_by_count":359},{"id":"2312.04461","title":"PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding","created":"2023-12-07","cited_by_count":328},{"id":"2410.19115","title":"MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision","created":"2024-10-24","cited_by_count":299},{"id":"2310.03739","title":"Aligning Text-to-Image Diffusion Models with Reward Backpropagation","created":"2023-10-05","cited_by_count":288},{"id":"2307.10816","title":"BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion","created":"2023-07-20","cited_by_count":282},{"id":"2305.16311","title":"Break-A-Scene: Extracting Multiple Concepts from a Single Image","created":"2023-05-25","cited_by_count":231},{"id":"2305.11147","title":"UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wild","created":"2023-05-18","cited_by_count":200},{"id":"2402.03290","title":"InstanceDiffusion: Instance-level Control for Image Generation","created":"2024-02-05","cited_by_count":175},{"id":"2012.09988","title":"Objectron: A Large Scale Dataset of Object-Centric Videos in the Wild with Pose Annotations","created":"2020-12-18","cited_by_count":155},{"id":"2305.15391","title":"A Neural Space-Time Representation for Text-to-Image Personalization","created":"2023-05-24","cited_by_count":123},{"id":"2402.01566","title":"Boximator: Generating Rich and Controllable Motions for Video Synthesis","created":"2024-02-02","cited_by_count":107},{"id":"2312.07536","title":"FreeControl: Training-Free Spatial Control of Any Text-to-Image Diffusion Model with Any Condition","created":"2023-12-12","cited_by_count":91},{"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":"2412.07759","title":"3DTrajMaster: Mastering 3D Trajectory for Multi-Entity Motion in Video Generation","created":"2024-12-10","cited_by_count":71},{"id":"2312.03079","title":"LooseControl: Lifting ControlNet for Generalized Depth Conditioning","created":"2023-12-05","cited_by_count":68},{"id":"2307.11073","title":"OBJECT 3DIT: Language-guided 3D-aware Image Editing","created":"2023-07-20","cited_by_count":63},{"id":"2312.02190","title":"Diffusion Handles: Enabling 3D Edits for Diffusion Models by Lifting Activations to 3D","created":"2023-12-02","cited_by_count":59},{"id":"2406.14555","title":"A Survey of Multimodal-Guided Image Editing with Text-to-Image Diffusion Models","created":"2024-06-20","cited_by_count":52},{"id":"2401.01702","title":"Image Sculpting: Precise Object Editing with 3D Geometry Control","created":"2024-01-02","cited_by_count":45},{"id":"2412.18605","title":"Orient Anything: Learning Robust Object Orientation Estimation from Rendering 3D Models","created":"2024-12-24","cited_by_count":45},{"id":"2405.08246","title":"Compositional Text-to-Image Generation with Dense Blob Representations","created":"2024-05-14","cited_by_count":38},{"id":"2312.11392","title":"SCEdit: Efficient and Controllable Image Diffusion Generation via Skip Connection Editing","created":"2023-12-18","cited_by_count":37},{"id":"2406.09292","title":"Neural Assets: 3D-Aware Multi-Object Scene Synthesis with Image Diffusion Models","created":"2024-06-13","cited_by_count":30},{"id":"2405.18424","title":"3DitScene: Editing Any Scene via Language-guided Disentangled Gaussian Splatting","created":"2024-05-28","cited_by_count":25},{"id":"2407.08711","title":"OmniNOCS: A unified NOCS dataset and model for 3D lifting of 2D objects","created":"2024-07-11","cited_by_count":22},{"id":"2508.09977","title":"A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generation","created":"2025-08-13","cited_by_count":19},{"id":"2507.11533","title":"CharaConsist: Fine-Grained Consistent Character Generation","created":"2025-07-15","cited_by_count":18},{"id":"2402.08654","title":"Learning Continuous 3D Words for Text-to-Image Generation","created":"2024-02-13","cited_by_count":16},{"id":"2501.01425","title":"Free-Form Motion Control: Controlling the 6D Poses of Camera and Objects in Video Generation","created":"2025-01-02","cited_by_count":15},{"id":"2404.12333","title":"Customizing Text-to-Image Diffusion with Object Viewpoint Control","created":"2024-04-18","cited_by_count":13},{"id":"2306.00964","title":"Cocktail: Mixing Multi-Modality Controls for Text-Conditional Image Generation","created":"2023-06-01","cited_by_count":12},{"id":"2403.11503","title":"Diffusion Models are Geometry Critics: Single Image 3D Editing Using Pre-Trained Diffusion Priors","created":"2024-03-18","cited_by_count":12},{"id":"2504.06752","title":"Compass Control: Multi Object Orientation Control for Text-to-Image Generation","created":"2025-04-09","cited_by_count":11},{"id":"2507.02857","title":"AnyI2V: Animating Any Conditional Image with Motion Control","created":"2025-07-03","cited_by_count":11},{"id":"2503.22194","title":"ORIGEN: Zero-Shot 3D Orientation Grounding in Text-to-Image Generation","created":"2025-03-28","cited_by_count":10},{"id":"2406.10000","title":"OrientDream: Streamlining Text-to-3D Generation with Explicit Orientation Control","created":"2024-06-14","cited_by_count":2}],"next_cursor":null}