{"total":106,"rows":[{"id":"2409.18869","title":"Emu3: Next-Token Prediction is All You Need","created":"2024-09-27","cited_by_count":781,"area":"diffusion"},{"id":"2501.13918","title":"Improving Video Generation with Human Feedback","created":"2025-01-23","cited_by_count":284,"area":"diffusion"},{"id":"2508.03789","title":"HPSv3: Towards Wide-Spectrum Human Preference Score","created":"2025-08-05","cited_by_count":211,"area":"alignment"},{"id":"2503.05236","title":"Unified Reward Model for Multimodal Understanding and Generation","created":"2025-03-07","cited_by_count":199,"area":"alignment"},{"id":"2412.21059","title":"VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation","created":"2024-12-30","cited_by_count":156,"area":"alignment"},{"id":"2504.11346","title":"Seedream 3.0 Technical Report","created":"2025-04-15","cited_by_count":154,"area":null},{"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,"area":"alignment"},{"id":"2411.09502","title":"Golden Noise for Diffusion Models: A Learning Framework","created":"2024-11-14","cited_by_count":92,"area":"diffusion"},{"id":"2407.04842","title":"MJ-Bench: Is Your Multimodal Reward Model Really a Good Judge for Text-to-Image Generation?","created":"2024-07-05","cited_by_count":66,"area":"diffusion"},{"id":"2505.22647","title":"Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation","created":"2025-05-28","cited_by_count":66,"area":null},{"id":"2509.23909","title":"EditScore: Unlocking Online RL for Image Editing via High-Fidelity Reward Modeling","created":"2025-09-28","cited_by_count":64,"area":"alignment"},{"id":"2503.07703","title":"Seedream 2.0: A Native Chinese-English Bilingual Image Generation Foundation Model","created":"2025-03-10","cited_by_count":62,"area":"diffusion"},{"id":"2410.08261","title":"Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis","created":"2024-10-10","cited_by_count":56,"area":"diffusion"},{"id":"2412.04814","title":"LiFT: Leveraging Human Feedback for Text-to-Video Model Alignment","created":"2024-12-06","cited_by_count":53,"area":"alignment"},{"id":"2412.15159","title":"OnlineVPO: Align Video Diffusion Model with Online Video-Centric Preference Optimization","created":"2024-12-19","cited_by_count":41,"area":"diffusion"},{"id":"2502.02588","title":"Calibrated Multi-Preference Optimization for Aligning Diffusion Models","created":"2025-02-04","cited_by_count":41,"area":"diffusion"},{"id":"2507.18569","title":"Adversarial Distribution Matching for Diffusion Distillation Towards Efficient Image and Video Synthesis","created":"2025-07-24","cited_by_count":41,"area":"diffusion"},{"id":"2502.01051","title":"Diffusion Model as a Noise-Aware Latent Reward Model for Step-Level Preference Optimization","created":"2025-02-03","cited_by_count":37,"area":"diffusion"},{"id":"2508.09968","title":"Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Models","created":"2025-08-13","cited_by_count":35,"area":"lr"},{"id":"2506.03517","title":"DenseDPO: Fine-Grained Temporal Preference Optimization for Video Diffusion Models","created":"2025-06-04","cited_by_count":34,"area":"diffusion"},{"id":"2410.18013","title":"Scalable Ranked Preference Optimization for Text-to-Image Generation","created":"2024-10-23","cited_by_count":33,"area":"alignment"},{"id":"2501.01097","title":"EliGen: Entity-Level Controlled Image Generation with Regional Attention","created":"2025-01-02","cited_by_count":33,"area":"diffusion"},{"id":"2511.23002","title":"JarvisEvo: Towards a Self-Evolving Photo Editing Agent with Synergistic Editor-Evaluator Optimization","created":"2025-11-28","cited_by_count":31,"area":"alignment"},{"id":"2509.06942","title":"Directly Aligning the Full Diffusion Trajectory with Fine-Grained Human Preference","created":"2025-09-08","cited_by_count":30,"area":"diffusion"},{"id":"2412.15156","title":"Prompt-A-Video: Prompt Your Video Diffusion Model via Preference-Aligned LLM","created":"2024-12-19","cited_by_count":25,"area":"diffusion"},{"id":"2410.18737","title":"Rectified Diffusion Guidance for Conditional Generation","created":"2024-10-24","cited_by_count":18,"area":"diffusion"},{"id":"2511.20549","title":"Flash-DMD: Towards High-Fidelity Few-Step Image Generation with Efficient Distillation and Joint Reinforcement Learning","created":"2025-11-25","cited_by_count":17,"area":"diffusion"},{"id":"2602.01077","title":"PISA: Piecewise Sparse Attention Is Wiser for Efficient Diffusion Transformers","created":"2026-02-01","cited_by_count":17,"area":"diffusion"},{"id":"2506.02698","title":"Smoothed Preference Optimization via ReNoise Inversion for Aligning Diffusion Models with Varied Human Preferences","created":"2025-06-03","cited_by_count":13,"area":"diffusion"},{"id":"2503.06141","title":"Next Token Is Enough: Realistic Image Quality and Aesthetic Scoring with Multimodal Large Language Model","created":"2025-03-08","cited_by_count":12,"area":"mllm"},{"id":"2511.20256","title":"The Image as Its Own Reward: Reinforcement Learning with Adversarial Reward for Image Generation","created":"2025-11-25","cited_by_count":12,"area":"alignment"},{"id":"2508.19104","title":"Composition and Alignment of Diffusion Models using Constrained Learning","created":"2025-08-26","cited_by_count":10,"area":"diffusion"},{"id":"2509.18538","title":"GeoRemover: Removing Objects and Their Causal Visual Artifacts","created":"2025-09-23","cited_by_count":9,"area":null},{"id":"2412.11170","title":"Benchmarking and Learning Multi-Dimensional Quality Evaluator for Text-to-3D Generation","created":"2024-12-15","cited_by_count":8,"area":null},{"id":"2503.01894","title":"LIVS: A Pluralistic Alignment Dataset for Inclusive Public Spaces","created":"2025-02-27","cited_by_count":8,"area":"alignment"},{"id":"2505.22569","title":"ImageReFL: Balancing Quality and Diversity in Human-Aligned Diffusion Models","created":"2025-05-28","cited_by_count":8,"area":"diffusion"},{"id":"2506.01337","title":"NoiseAR: AutoRegressing Initial Noise Prior for Diffusion Models","created":"2025-06-02","cited_by_count":8,"area":"diffusion"},{"id":"2603.03281","title":"CFG-Ctrl: Control-Based Classifier-Free Diffusion Guidance","created":"2026-03-03","cited_by_count":8,"area":"diffusion"},{"id":"2505.11070","title":"Towards Self-Improvement of Diffusion Models via Group Preference Optimization","created":"2025-05-16","cited_by_count":7,"area":"diffusion"},{"id":"2512.04660","title":"I2I-Bench: A Comprehensive Benchmark Suite for Image-to-Image Editing Models","created":"2025-12-04","cited_by_count":7,"area":null},{"id":"2512.04784","title":"PaCo-RL: Advancing Reinforcement Learning for Consistent Image Generation with Pairwise Reward Modeling","created":"2025-12-02","cited_by_count":7,"area":"alignment"},{"id":"2410.09865","title":"SynFER: Towards Boosting Facial Expression Recognition with Synthetic Data","created":"2024-10-13","cited_by_count":6,"area":"synth"},{"id":"2505.16915","title":"DetailMaster: Can Your Text-to-Image Model Handle Long Prompts?","created":"2025-05-22","cited_by_count":6,"area":null},{"id":"2506.10978","title":"Where and How to Perturb: On the Design of Perturbation Guidance in Diffusion and Flow Models","created":"2025-06-12","cited_by_count":6,"area":"diffusion"},{"id":"2602.11146","title":"Beyond VLM-Based Rewards: Diffusion-Native Latent Reward Modeling","created":"2026-02-11","cited_by_count":6,"area":"diffusion"},{"id":"2503.00811","title":"Evaluating and Predicting Distorted Human Body Parts for Generated Images","created":"2025-03-02","cited_by_count":5,"area":null},{"id":"2503.01839","title":"Jailbreaking Safeguarded Text-to-Image Models via Large Language Models","created":"2025-03-03","cited_by_count":5,"area":"safety"},{"id":"2505.17910","title":"DiffusionReward: Enhancing Blind Face Restoration through Reward Feedback Learning","created":"2025-05-23","cited_by_count":5,"area":"alignment"},{"id":"2506.05343","title":"ContentV: Efficient Training of Video Generation Models with Limited Compute","created":"2025-06-05","cited_by_count":5,"area":null},{"id":"2602.02092","title":"FSVideo: Fast Speed Video Diffusion Model in a Highly-Compressed Latent Space","created":"2026-02-02","cited_by_count":5,"area":"diffusion"},{"id":"2608.18607","title":"VA-Judger: Reward Modeling from Human Preference Feedback for Joint Video-Audio Generation","created":"2026-08-19","cited_by_count":5,"area":"alignment"},{"id":"2406.05768","title":"TLCM: Training-efficient Latent Consistency Model for Image Generation with 2-8 Steps","created":"2024-06-09","cited_by_count":4,"area":"diffusion"},{"id":"2505.11257","title":"DRAGON: A Large-Scale Dataset of Realistic Images Generated by Diffusion Models","created":"2025-05-16","cited_by_count":4,"area":"diffusion"},{"id":"2507.07317","title":"ADIEE: Automatic Dataset Creation and Scorer for Instruction-Guided Image Editing Evaluation","created":"2025-07-09","cited_by_count":4,"area":null},{"id":"2510.02987","title":"TIT-Score: Evaluating Long-Prompt Based Text-to-Image Alignment via Text-to-Image-to-Text Consistency","created":"2025-10-03","cited_by_count":4,"area":"mllm"},{"id":"2511.19458","title":"Personalized Reward Modeling for Text-to-Image Generation","created":"2025-11-21","cited_by_count":4,"area":"alignment"},{"id":"2602.22570","title":"Guidance Matters: Rethinking the Evaluation Pitfall for Text-to-Image Generation","created":"2026-02-26","cited_by_count":4,"area":"diffusion"},{"id":"2603.06700","title":"SIQA: Toward Reliable Scientific Image Quality Assessment","created":"2026-03-05","cited_by_count":4,"area":null},{"id":"2603.18991","title":"CRAFT: Aligning Diffusion Models with Fine-Tuning Is Easier Than You Think","created":"2026-03-19","cited_by_count":4,"area":"diffusion"},{"id":"2604.24952","title":"Learning from Noisy Preferences: A Semi-Supervised Learning Approach to Direct Preference Optimization","created":"2026-04-27","cited_by_count":4,"area":"alignment"},{"id":"2605.04461","title":"Stream-T1: Test-Time Scaling for Streaming Video Generation","created":"2026-05-06","cited_by_count":4,"area":"diffusion"},{"id":"2606.09076","title":"Z-Reward: Beyond Scalar Rewards by Internalizing Reasoning into Score Distributions","created":"2026-06-08","cited_by_count":4,"area":"alignment"},{"id":"2503.08377","title":"Layton: Latent Consistency Tokenizer for 1024-pixel Image Reconstruction and Generation by 256 Tokens","created":"2025-03-11","cited_by_count":3,"area":null},{"id":"2507.22100","title":"Trade-offs in Image Generation: How Do Different Dimensions Interact?","created":"2025-07-29","cited_by_count":3,"area":null},{"id":"2511.20629","title":"MapReduce LoRA: Advancing the Pareto Front in Multi-Preference Optimization for Generative Models","created":"2025-11-25","cited_by_count":3,"area":"alignment"},{"id":"2512.22647","title":"FinPercep-RM: A Fine-grained Reward Model and Co-evolutionary Curriculum for RL-based Real-world Super-Resolution","created":"2025-12-27","cited_by_count":3,"area":"alignment"},{"id":"2602.24233","title":"Enhancing Spatial Understanding in Image Generation via Reward Modeling","created":"2026-02-27","cited_by_count":3,"area":"alignment"},{"id":"2411.13787","title":"Adaptive Routing of Text-to-Image Generation Requests Between Large Cloud Model and Light-Weight Edge Model","created":"2024-11-21","cited_by_count":2,"area":null},{"id":"2505.20655","title":"Photography Perspective Composition: Towards Aesthetic Perspective Recommendation","created":"2025-05-27","cited_by_count":2,"area":null},{"id":"2511.01450","title":"Reg-DPO: SFT-Regularized Direct Preference Optimization with GT-Pair for Improving Video Generation","created":"2025-11-03","cited_by_count":2,"area":"alignment"},{"id":"2603.01594","title":"Preference Score Distillation: Leveraging 2D Rewards to Align Text-to-3D Generation with Human Preference","created":"2026-03-02","cited_by_count":2,"area":"diffusion"},{"id":"2606.32020","title":"Cross-Space Distillation: Teaching One-Step Students with Modern Diffusion Teachers","created":"2026-06-30","cited_by_count":2,"area":"diffusion"},{"id":"2412.12888","title":"ArtAug: Enhancing Text-to-Image Generation through Synthesis-Understanding Interaction","created":"2024-12-17","cited_by_count":1,"area":"diffusion"},{"id":"2504.10329","title":"InstructEngine: Instruction-driven Text-to-Image Alignment","created":"2025-04-14","cited_by_count":1,"area":"alignment"},{"id":"2512.10237","title":"Multi-dimensional Preference Alignment by Conditioning Reward Itself","created":"2025-12-11","cited_by_count":1,"area":"diffusion"},{"id":"2512.11883","title":"Position: Universal Aesthetic Alignment Narrows Artistic Expression","created":"2025-12-09","cited_by_count":1,"area":null},{"id":"2603.10990","title":"Too Vivid to Be Real? Benchmarking and Calibrating Generative Color Fidelity","created":"2026-03-11","cited_by_count":1,"area":null},{"id":"2603.24849","title":"Gaze patterns predict preference and confidence in pairwise AI image evaluation","created":"2026-03-25","cited_by_count":1,"area":"alignment"},{"id":"2603.28460","title":"$R_\\text{dm}$: Re-conceptualizing Distribution Matching as a Reward for Diffusion Distillation","created":"2026-03-30","cited_by_count":1,"area":"diffusion"},{"id":"2605.09433","title":"Offline Preference Optimization for Rectified Flow with Noise-Tracked Pairs","created":"2026-05-10","cited_by_count":1,"area":"diffusion"},{"id":"2605.09622","title":"Any2Any 3D Diffusion Models with Knowledge Transfer: A Radiotherapy Planning Study","created":"2026-05-10","cited_by_count":1,"area":"diffusion"},{"id":"2605.25661","title":"DRM: Diffusion-based Reward Model With Step-wise Guidance","created":"2026-05-25","cited_by_count":1,"area":"diffusion"},{"id":"2606.20100","title":"WeGenBench: A Multidimensional Diagnostic Benchmark towards Text-to-Image Model Optimization","created":"2026-06-18","cited_by_count":1,"area":null},{"id":"2609.05968","title":"Test-Time Weak-to-Strong Alignment: Transferring Implicit Rewards from Weak to Strong Flow Models","created":"2026-09-05","cited_by_count":1,"area":"alignment"},{"id":"2609.35947","title":"FluxLite: Inference-Time Proposal Control for Discrete Diffusion Models","created":"2026-09-28","cited_by_count":1,"area":"diffusion"},{"id":"2503.21721","title":"Evaluating Text-to-Image and Text-to-Video Synthesis with a Conditional Fr\\'{e}chet Distance","created":"2025-03-27","cited_by_count":0,"area":null},{"id":"2505.14664","title":"AKRMap: Adaptive Kernel Regression for Trustworthy Visualization of Cross-Modal Embeddings","created":"2025-05-20","cited_by_count":0,"area":null},{"id":"2510.16179","title":"Cost Savings from Automatic Quality Assessment of Generated Images","created":"2025-10-17","cited_by_count":0,"area":null},{"id":"2511.00609","title":"PreferThinker: Reasoning-based Personalized Image Preference Assessment","created":"2025-11-01","cited_by_count":0,"area":null},{"id":"2511.03913","title":"Inference-Time Optimization of Prompt Embeddings in Diffusion Models: A Comparison of sep-CMA-ES and Adam","created":"2025-11-05","cited_by_count":0,"area":"diffusion"},{"id":"2511.16712","title":"PairHuman: A High-Fidelity Photographic Dataset for Customized Dual-Person Generation","created":"2025-11-20","cited_by_count":0,"area":null},{"id":"2511.20563","title":"A Reason-then-Describe Instruction Interpreter for Controllable Video Generation","created":"2025-11-25","cited_by_count":0,"area":"diffusion"},{"id":"2602.23438","title":"DesignSense: A Human Preference Dataset and Reward Modeling Framework for Graphic Layout Generation","created":"2026-02-26","cited_by_count":0,"area":"alignment"},{"id":"2604.07427","title":"Personalizing Text-to-Image Generation to Individual Taste","created":"2026-04-08","cited_by_count":0,"area":null},{"id":"2605.13223","title":"Skill-Aligned Annotation for Reliable Evaluation in Text-to-Image Generation","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.20731","title":"TASTE: A Designer-Annotated Multi-Dimensional Preference Dataset for AI-Generated Graphic Design","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2605.25876","title":"DyCoRM: Dynamic Criterion-Aware Reward Modeling for Text-to-Image Generation","created":"2026-05-25","cited_by_count":0,"area":"alignment"},{"id":"2606.05478","title":"Can We Predict The Human Preference For Text-to-Image Content Prior To Generation And Is It Even Useful To Do So?","created":"2026-06-03","cited_by_count":0,"area":"diffusion"},{"id":"2606.07653","title":"A Dataset for Dynamic Human Preferences for Vision Language Models","created":"2026-06-02","cited_by_count":0,"area":"mllm"},{"id":"2607.24898","title":"Harm is not Universal: Community-Specific Toxicity Detection is Urgently Needed","created":"2026-07-27","cited_by_count":0,"area":null}],"next_cursor":"100"}