{"list":"other","total":71,"rows":[{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"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":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"2303.01469","title":"Consistency Models","created":"2023-03-02","cited_by_count":1822},{"id":"2212.08051","title":"Objaverse: A Universe of Annotated 3D Objects","created":"2022-12-15","cited_by_count":1540},{"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":"2406.09414","title":"Depth Anything V2","created":"2024-06-13","cited_by_count":1422},{"id":"2209.14687","title":"Diffusion Posterior Sampling for General Noisy Inverse Problems","created":"2022-09-29","cited_by_count":1416},{"id":"2311.18828","title":"One-step Diffusion with Distribution Matching Distillation","created":"2023-11-30","cited_by_count":1019},{"id":"2305.13301","title":"Training Diffusion Models with Reinforcement Learning","created":"2023-05-22","cited_by_count":982},{"id":"2305.01569","title":"Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation","created":"2023-05-02","cited_by_count":977},{"id":"2211.01324","title":"eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers","created":"2022-11-02","cited_by_count":931},{"id":"2301.07093","title":"GLIGEN: Open-Set Grounded Text-to-Image Generation","created":"2023-01-17","cited_by_count":781},{"id":"2311.17042","title":"Adversarial Diffusion Distillation","created":"2023-11-28","cited_by_count":759},{"id":"2109.07161","title":"Resolution-robust Large Mask Inpainting with Fourier Convolutions","created":"2021-09-15","cited_by_count":738},{"id":"2302.08113","title":"MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation","created":"2023-02-16","cited_by_count":536},{"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":"2404.01291","title":"Evaluating Text-to-Visual Generation with Image-to-Text Generation","created":"2024-04-01","cited_by_count":474},{"id":"2310.02279","title":"Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion","created":"2023-10-01","cited_by_count":459},{"id":"2305.16381","title":"DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Models","created":"2023-05-25","cited_by_count":450},{"id":"2302.07121","title":"Universal Guidance for Diffusion Models","created":"2023-02-14","cited_by_count":437},{"id":"2309.06380","title":"InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generation","created":"2023-09-12","cited_by_count":395},{"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":"1901.04780","title":"DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion","created":"2019-01-15","cited_by_count":355},{"id":"2204.00227","title":"Perception Prioritized Training of Diffusion Models","created":"2022-04-01","cited_by_count":303},{"id":"2303.09833","title":"FreeDoM: Training-Free Energy-Guided Conditional Diffusion Model","created":"2023-03-17","cited_by_count":294},{"id":"2310.03739","title":"Aligning Text-to-Image Diffusion Models with Reward Backpropagation","created":"2023-10-05","cited_by_count":288},{"id":"2402.13929","title":"SDXL-Lightning: Progressive Adversarial Diffusion Distillation","created":"2024-02-21","cited_by_count":266},{"id":"1702.03849","title":"Non-convex learning via Stochastic Gradient Langevin Dynamics: a nonasymptotic analysis","created":"2017-02-13","cited_by_count":243},{"id":"2211.14305","title":"SpaText: Spatio-Textual Representation for Controllable Image Generation","created":"2022-11-25","cited_by_count":217},{"id":"1711.08848","title":"Real-Time Seamless Single Shot 6D Object Pose Prediction","created":"2017-11-24","cited_by_count":210},{"id":"2306.07279","title":"Scalable 3D Captioning with Pretrained Models","created":"2023-06-12","cited_by_count":203},{"id":"1902.01275","title":"Implicit 3D Orientation Learning for 6D Object Detection from RGB Images","created":"2019-02-04","cited_by_count":170},{"id":"2311.16424","title":"Manifold Preserving Guided Diffusion","created":"2023-11-28","cited_by_count":157},{"id":"2402.15194","title":"Fine-Tuning of Continuous-Time Diffusion Models as Entropy-Regularized Control","created":"2024-02-23","cited_by_count":143},{"id":"2404.04650","title":"InitNO: Boosting Text-to-Image Diffusion Models via Initial Noise Optimization","created":"2024-04-06","cited_by_count":123},{"id":"2402.14017","title":"D-Flow: Differentiating through Flows for Controlled Generation","created":"2024-02-21","cited_by_count":122},{"id":"2406.04312","title":"ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimization","created":"2024-06-06","cited_by_count":119},{"id":"2412.03632","title":"MV-Adapter: Multi-view Consistent Image Generation Made Easy","created":"2024-12-04","cited_by_count":112},{"id":"2303.13703","title":"End-to-End Diffusion Latent Optimization Improves Classifier Guidance","created":"2023-03-23","cited_by_count":108},{"id":"2409.15761","title":"TFG: Unified Training-Free Guidance for Diffusion Models","created":"2024-09-24","cited_by_count":107},{"id":"1812.02541","title":"Segmentation-driven 6D Object Pose Estimation","created":"2018-12-06","cited_by_count":104},{"id":"2304.05390","title":"HRS-Bench: Holistic, Reliable and Scalable Benchmark for Text-to-Image Models","created":"2023-04-11","cited_by_count":95},{"id":"2501.05803","title":"Test-time Alignment of Diffusion Models without Reward Over-optimization","created":"2025-01-10","cited_by_count":93},{"id":"2304.14530","title":"Generating images of rare concepts using pre-trained diffusion models","created":"2023-04-27","cited_by_count":79},{"id":"2410.16794","title":"One-Step Diffusion Distillation through Score Implicit Matching","created":"2024-10-22","cited_by_count":71},{"id":"2302.13153","title":"Directed Diffusion: Direct Control of Object Placement through Attention Guidance","created":"2023-02-25","cited_by_count":69},{"id":"2312.03079","title":"LooseControl: Lifting ControlNet for Generalized Depth Conditioning","created":"2023-12-05","cited_by_count":68},{"id":"2306.13754","title":"Zero-shot spatial layout conditioning for text-to-image diffusion models","created":"2023-06-23","cited_by_count":64},{"id":"2412.18605","title":"Orient Anything: Learning Robust Object Orientation Estimation from Rendering 3D Models","created":"2024-12-24","cited_by_count":45},{"id":"2306.08687","title":"Norm-guided latent space exploration for text-to-image generation","created":"2023-06-14","cited_by_count":43},{"id":"2403.16131","title":"Salience DETR: Enhancing Detection Transformer with Hierarchical Salience Filtering Refinement","created":"2024-03-24","cited_by_count":31},{"id":"2410.18881","title":"Diff-Instruct++: Training One-step Text-to-image Generator Model to Align with Human Preferences","created":"2024-10-24","cited_by_count":31},{"id":"2410.20474","title":"GrounDiT: Grounding Diffusion Transformers via Noisy Patch Transplantation","created":"2024-10-27","cited_by_count":24},{"id":"2408.14819","title":"Build-A-Scene: Interactive 3D Layout Control for Diffusion-Based Image Generation","created":"2024-08-27","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":"2403.19279","title":"Fine-Tuning Language Models with Reward Learning on Policy","created":"2024-03-28","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":"2409.06493","title":"Elucidating Optimal Reward-Diversity Tradeoffs in Text-to-Image Diffusion Models","created":"2024-09-09","cited_by_count":13},{"id":"2212.08861","title":"DAG: Depth-Aware Guidance with Denoising Diffusion Probabilistic Models","created":"2022-12-17","cited_by_count":12},{"id":"2407.06642","title":"Powerful and Flexible: Personalized Text-to-Image Generation via Reinforcement Learning","created":"2024-07-09","cited_by_count":11},{"id":"2309.07986","title":"Viewpoint Textual Inversion: Discovering Scene Representations and 3D View Control in 2D Diffusion Models","created":"2023-09-14","cited_by_count":7},{"id":"2403.13589","title":"ReGround: Improving Textual and Spatial Grounding at No Cost","created":"2024-03-20","cited_by_count":6},{"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}