{"total":101,"rows":[{"id":"2406.03520","title":"VideoPhy: Evaluating Physical Commonsense for Video Generation","created":"2024-06-05","cited_by_count":228,"area":null},{"id":"2509.02547","title":"The Landscape of Agentic Reinforcement Learning for LLMs: A Survey","created":"2025-09-02","cited_by_count":205,"area":"agents"},{"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":"2407.21035","title":"Direct Unlearning Optimization for Robust and Safe Text-to-Image Models","created":"2024-07-17","cited_by_count":50,"area":"safety"},{"id":"2406.06424","title":"Margin-aware Preference Optimization for Aligning Diffusion Models without Reference","created":"2024-06-10","cited_by_count":46,"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":"2503.11701","title":"A Survey of Direct Preference Optimization","created":"2025-03-12","cited_by_count":36,"area":"alignment"},{"id":"2409.07253","title":"Alignment of Diffusion Models: Fundamentals, Challenges, and Future","created":"2024-09-11","cited_by_count":35,"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":"2503.11240","title":"Towards Better Alignment: Training Diffusion Models with Reinforcement Learning Against Sparse Rewards","created":"2025-03-14","cited_by_count":32,"area":"diffusion"},{"id":"2506.21656","title":"Fine-Grained Preference Optimization Improves Spatial Reasoning in VLMs","created":"2025-06-26","cited_by_count":32,"area":"lr"},{"id":"2503.21765","title":"Exploring the Evolution of Physics Cognition in Video Generation: A Survey","created":"2025-03-27","cited_by_count":31,"area":"diffusion"},{"id":"2503.00897","title":"A Simple and Effective Reinforcement Learning Method for Text-to-Image Diffusion Fine-tuning","created":"2025-03-02","cited_by_count":30,"area":"diffusion"},{"id":"2412.00759","title":"DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling","created":"2024-12-01","cited_by_count":27,"area":"diffusion"},{"id":"2501.06655","title":"Personalized Preference Fine-tuning of Diffusion Models","created":"2025-01-11","cited_by_count":22,"area":"diffusion"},{"id":"2503.18454","title":"InPO: Inversion Preference Optimization with Reparametrized DDIM for Efficient Diffusion Model Alignment","created":"2025-03-24","cited_by_count":19,"area":"diffusion"},{"id":"2409.09774","title":"Generalizing Alignment Paradigm of Text-to-Image Generation with Preferences through $f$-divergence Minimization","created":"2024-09-15","cited_by_count":15,"area":"alignment"},{"id":"2412.05101","title":"The Silent Assistant: NoiseQuery as Implicit Guidance for Goal-Driven Image Generation","created":"2024-12-06","cited_by_count":14,"area":null},{"id":"2502.02088","title":"Dual-IPO: Dual-Iterative Preference Optimization for Text-to-Video Generation","created":"2025-02-04","cited_by_count":13,"area":"diffusion"},{"id":"2503.08295","title":"Preference-Based Alignment of Discrete Diffusion Models","created":"2025-03-11","cited_by_count":13,"area":"diffusion"},{"id":"2504.08291","title":"DreamFuse: Adaptive Image Fusion with Diffusion Transformer","created":"2025-04-11","cited_by_count":13,"area":"diffusion"},{"id":"2504.15176","title":"DSPO: Direct Semantic Preference Optimization for Real-World Image Super-Resolution","created":"2025-04-21","cited_by_count":13,"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":"2411.11727","title":"Aligning Few-Step Diffusion Models with Dense Reward Difference Learning","created":"2024-11-18","cited_by_count":12,"area":"diffusion"},{"id":"2501.02790","title":"Segmenting Text and Learning Their Rewards for Improved RLHF in Language Model","created":"2025-01-06","cited_by_count":12,"area":"alignment"},{"id":"2507.04832","title":"Discrete Diffusion Trajectory Alignment via Stepwise Decomposition","created":"2025-07-07","cited_by_count":12,"area":"diffusion"},{"id":"2508.19104","title":"Composition and Alignment of Diffusion Models using Constrained Learning","created":"2025-08-26","cited_by_count":10,"area":"diffusion"},{"id":"2406.17636","title":"Aligning Diffusion Models with Noise-Conditioned Perception","created":"2024-06-25","cited_by_count":9,"area":"diffusion"},{"id":"2506.18655","title":"RDPO: Real Data Preference Optimization for Physics Consistency Video Generation","created":"2025-06-23","cited_by_count":9,"area":"alignment"},{"id":"2508.08189","title":"Reinforcement Learning for Large Model: A Survey","created":"2025-08-11","cited_by_count":9,"area":"deeprl"},{"id":"2507.07510","title":"Divergence Minimization Preference Optimization for Diffusion Model Alignment","created":"2025-07-10","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":"2508.00319","title":"Steering Guidance for Personalized Text-to-Image Diffusion Models","created":"2025-08-01","cited_by_count":7,"area":"diffusion"},{"id":"2510.01540","title":"Towards Better Optimization For Listwise Preference in Diffusion Models","created":"2025-10-02","cited_by_count":7,"area":"diffusion"},{"id":"2511.03317","title":"Diffusion-SDPO: Safeguarded Direct Preference Optimization for Diffusion Models","created":"2025-11-05","cited_by_count":7,"area":"diffusion"},{"id":"2504.08542","title":"Discriminator-Free Direct Preference Optimization for Video Diffusion","created":"2025-04-11","cited_by_count":6,"area":"diffusion"},{"id":"2604.15311","title":"LeapAlign: Post-Training Flow Matching Models at Any Generation Step by Building Two-Step Trajectories","created":"2026-04-16","cited_by_count":6,"area":"diffusion"},{"id":"2605.15855","title":"Do Less, Achieve More: Do We Need Every-Step Optimization for RL Fine-tuning of Diffusion Models?","created":"2026-05-15","cited_by_count":6,"area":"diffusion"},{"id":"2605.21573","title":"Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models","created":"2026-05-20","cited_by_count":6,"area":null},{"id":"2502.02954","title":"Direct Distributional Optimization for Provable Alignment of Diffusion Models","created":"2025-02-05","cited_by_count":5,"area":"diffusion"},{"id":"2507.22604","title":"ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning","created":"2025-07-30","cited_by_count":5,"area":"diffusion"},{"id":"2601.12401","title":"Beyond the Dirac Delta: Mitigating Diversity Collapse in Reinforcement Fine-Tuning for Versatile Image Generation","created":"2026-01-18","cited_by_count":5,"area":"deeprl"},{"id":"2602.02033","title":"One Size, Many Fits: Aligning Diverse Group-Wise Click Preferences in Large-Scale Advertising Image Generation","created":"2026-02-02","cited_by_count":5,"area":"alignment"},{"id":"2504.15217","title":"DRAGON: Distributional Rewards Optimize Diffusion Generative Models","created":"2025-04-21","cited_by_count":4,"area":"diffusion"},{"id":"2505.11178","title":"CompAlign: Improving Compositional Text-to-Image Generation with a Complex Benchmark and Fine-Grained Feedback","created":"2025-05-16","cited_by_count":4,"area":"diffusion"},{"id":"2510.00502","title":"Diffusion Alignment as Variational Expectation-Maximization","created":"2025-10-01","cited_by_count":4,"area":"diffusion"},{"id":"2510.02692","title":"Fine-Tuning Diffusion Models via Intermediate Distribution Shaping","created":"2025-10-03","cited_by_count":4,"area":"diffusion"},{"id":"2601.15968","title":"HyperAlign: Hypernetwork for Efficient Test-Time Alignment of Diffusion Models","created":"2026-01-22","cited_by_count":4,"area":"diffusion"},{"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":"2605.21123","title":"Linear-DPO: Linear Direct Preference Optimization for Diffusion and Flow-Matching Generative Models","created":"2026-05-20","cited_by_count":4,"area":"diffusion"},{"id":"2411.14871","title":"Preference Alignment for Diffusion Model via Explicit Denoised Distribution Estimation","created":"2024-11-22","cited_by_count":3,"area":"diffusion"},{"id":"2504.14534","title":"SUDO: Enhancing Text-to-Image Diffusion Models with Self-Supervised Direct Preference Optimization","created":"2025-04-20","cited_by_count":3,"area":"diffusion"},{"id":"2505.17352","title":"Alignment and Safety of Diffusion Models via Reinforcement Learning and Reward Modeling: A Survey","created":"2025-05-23","cited_by_count":3,"area":"diffusion"},{"id":"2510.18353","title":"Ranking-based Preference Optimization for Diffusion Models from Implicit User Feedback","created":"2025-10-21","cited_by_count":3,"area":"diffusion"},{"id":"2602.05380","title":"SAIL: Self-Amplified Iterative Learning for Diffusion Model Alignment with Minimal Human Feedback","created":"2026-02-05","cited_by_count":3,"area":"diffusion"},{"id":"2602.18799","title":"Rethinking Preference Alignment for Diffusion Models with Classifier-Free Guidance","created":"2026-02-21","cited_by_count":3,"area":"diffusion"},{"id":"2605.07503","title":"Diffusion-APO: Trajectory-Aware Direct Preference Alignment for Video Diffusion Transformers","created":"2026-05-08","cited_by_count":3,"area":"diffusion"},{"id":"2605.10937","title":"Power Reinforcement Post-Training of Text-to-Image Models with Super-Linear Advantage Shaping","created":"2026-05-11","cited_by_count":3,"area":"lr"},{"id":"2605.26552","title":"Aligning Few-Step Generative Models by Amortizing Sample-based Variational Inference","created":"2026-05-26","cited_by_count":3,"area":null},{"id":"2607.04423","title":"Transferability Between Understanding and Generation in Unified Multimodal Models","created":"2026-07-05","cited_by_count":3,"area":null},{"id":"2509.25771","title":"Free Lunch Alignment of Text-to-Image Diffusion Models without Preference Image Pairs","created":"2025-09-30","cited_by_count":2,"area":"diffusion"},{"id":"2510.17917","title":"Not Every Time and Frequency Need to Be Forgotten in Diffusion Unlearning","created":"2025-10-20","cited_by_count":2,"area":"diffusion"},{"id":"2512.23426","title":"Direct Diffusion Score Preference Optimization via Stepwise Contrastive Policy-Pair Supervision","created":"2025-12-29","cited_by_count":2,"area":"diffusion"},{"id":"2602.09583","title":"Preference Aligned Visuomotor Diffusion Policies for Deformable Object Manipulation","created":"2026-02-10","cited_by_count":2,"area":"diffusion"},{"id":"2602.19180","title":"VLM-Guided Group Preference Alignment for Diffusion-based Human Mesh Recovery","created":"2026-02-22","cited_by_count":2,"area":"alignment"},{"id":"2604.24953","title":"ViPO: Visual Preference Optimization at Scale","created":"2026-04-27","cited_by_count":2,"area":"alignment"},{"id":"2605.04653","title":"Threshold-Guided Optimization for Visual Generative Models","created":"2026-05-06","cited_by_count":2,"area":"alignment"},{"id":"2605.07456","title":"Inference-Time Attribute Distribution Alignment for Unconditional Diffusion","created":"2026-05-08","cited_by_count":2,"area":"diffusion"},{"id":"2503.16921","title":"When Preferences Diverge: Aligning Diffusion Models with Minority-Aware Adaptive DPO","created":"2025-03-21","cited_by_count":1,"area":"diffusion"},{"id":"2505.16425","title":"$I^2G$: Generating Instructional Illustrations via Text-Conditioned Diffusion","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2510.23658","title":"Aligning Diffusion Language Models via Unpaired Preference Optimization","created":"2025-10-26","cited_by_count":1,"area":"diffusion"},{"id":"2510.25897","title":"MIRO: MultI-Reward cOnditioned pretraining improves T2I quality and efficiency","created":"2025-10-29","cited_by_count":1,"area":"alignment"},{"id":"2511.04753","title":"CPO: Condition Preference Optimization for Controllable Image Generation","created":"2025-11-06","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":"2603.20828","title":"EruDiff: Refactoring Knowledge in Diffusion Models for Advanced Text-to-Image Synthesis","created":"2026-03-21","cited_by_count":1,"area":"diffusion"},{"id":"2604.08723","title":"Decomposing the Delta: What Do Models Actually Learn from Preference Pairs?","created":"2026-04-09","cited_by_count":1,"area":"alignment"},{"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":"2605.12650","title":"CRAFT: Clinical Reward-Aligned Finetuning for Medical Image Synthesis","created":"2026-05-12","cited_by_count":1,"area":"mllm"},{"id":"2605.26491","title":"Beyond Pairwise Preferences: Listwise Reward-Aware Alignment for Diffusion Models","created":"2026-05-26","cited_by_count":1,"area":"diffusion"},{"id":"2607.29025","title":"Evaluation-Verification Reward for Consistent Multi-Reference Image Editing","created":"2026-07-31","cited_by_count":1,"area":"alignment"},{"id":"2510.17519","title":"MUG-V 10B: High-efficiency Training Pipeline for Large Video Generation Models","created":"2025-10-20","cited_by_count":0,"area":null},{"id":"2511.07806","title":"PC-Diffusion: Aligning Diffusion Models with Human Preferences via Preference Classifier","created":"2025-11-11","cited_by_count":0,"area":"diffusion"},{"id":"2512.22681","title":"CritiFusion: Semantic Critique and Spectral Alignment for Faithful Text-to-Image Generation","created":"2025-12-27","cited_by_count":0,"area":"diffusion"},{"id":"2602.19423","title":"Prefer-DAS: Learning from Local Preferences and Sparse Prompts for Domain Adaptive Segmentation of Electron Microscopy","created":"2026-02-23","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":"2605.04494","title":"Towards General Preference Alignment: Diffusion Models at Nash Equilibrium","created":"2026-05-06","cited_by_count":0,"area":"diffusion"},{"id":"2605.06070","title":"Arena as Offline Reward: Efficient Fine-Grained Preference Optimization for Diffusion Models","created":"2026-05-07","cited_by_count":0,"area":"diffusion"},{"id":"2605.07545","title":"Implicit Preference Alignment for Human Image Animation","created":"2026-05-08","cited_by_count":0,"area":"alignment"},{"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":"2605.27736","title":"Explicit Critic Guidance for Aligning Diffusion Models","created":"2026-05-26","cited_by_count":0,"area":"diffusion"},{"id":"2608.06794","title":"PAST: Prompt-Adaptive Sampling Termination for Efficient Diffusion Model","created":"2026-08-07","cited_by_count":0,"area":"diffusion"},{"id":"2608.20011","title":"Manifold Drift in Flow Preference Optimization: A Root Cause of Reward Hacking","created":"2026-08-20","cited_by_count":0,"area":"diffusion"},{"id":"2608.21869","title":"GuardPaint:SpeculativeSafetyDecodingforText-to-ImageGeneration","created":"2026-08-22","cited_by_count":0,"area":"diffusion"},{"id":"2609.03688","title":"ToPO: Token-Conditioned Preference Routing for Attention-Based Latent Diffusion Models","created":"2026-09-03","cited_by_count":0,"area":"diffusion"},{"id":"2609.06651","title":"SwiftExplorer: Training-free Diffusion Model Alignment with Swift Diversity Exploration","created":"2026-09-06","cited_by_count":0,"area":"diffusion"},{"id":"2610.01789","title":"iADD: Improving Alignment and Diversity in Diffusion Policy Optimization","created":"2026-10-01","cited_by_count":0,"area":"diffusion"},{"id":"2610.04980","title":"Geometry-Aware Preference Optimization for Text-to-Image Diffusion Models","created":"2026-10-04","cited_by_count":0,"area":"diffusion"}],"next_cursor":"100"}