{"total":44,"rows":[{"id":"2508.20751","title":"Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning","created":"2025-08-28","cited_by_count":92,"area":"lr"},{"id":"2505.23614","title":"Inference-time Scaling of Diffusion Models through Classical Search","created":"2025-05-29","cited_by_count":49,"area":"lr"},{"id":"2503.12271","title":"Reflect-DiT: Inference-Time Scaling for Text-to-Image Diffusion Transformers via In-Context Reflection","created":"2025-03-15","cited_by_count":43,"area":"lr"},{"id":"2505.17618","title":"Scaling Image and Video Generation via Test-Time Evolutionary Search","created":"2025-05-23","cited_by_count":40,"area":"lr"},{"id":"2503.19385","title":"Inference-Time Scaling for Flow Models via Stochastic Generation and Rollover Budget Forcing","created":"2025-03-25","cited_by_count":38,"area":"lr"},{"id":"2508.09968","title":"Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Models","created":"2025-08-13","cited_by_count":35,"area":"lr"},{"id":"2505.07538","title":"Selftok: Discrete Visual Tokens of Autoregression, by Diffusion, and for Reasoning","created":"2025-05-12","cited_by_count":33,"area":"lr"},{"id":"2506.21656","title":"Fine-Grained Preference Optimization Improves Spatial Reasoning in VLMs","created":"2025-06-26","cited_by_count":32,"area":"lr"},{"id":"2410.15595","title":"A Comprehensive Survey of Direct Preference Optimization: Datasets, Theories, Variants, and Applications","created":"2024-10-21","cited_by_count":27,"area":"lr"},{"id":"2503.21819","title":"Optimizing Safe and Aligned Language Generation: A Multi-Objective GRPO Approach","created":"2025-03-26","cited_by_count":24,"area":"lr"},{"id":"2504.00640","title":"POPEN: Preference-Based Optimization and Ensemble for LVLM-Based Reasoning Segmentation","created":"2025-04-01","cited_by_count":22,"area":"lr"},{"id":"2601.20218","title":"DenseGRPO: From Sparse to Dense Reward for Flow Matching Model Alignment","created":"2026-01-28","cited_by_count":21,"area":"lr"},{"id":"2512.21514","title":"DiverseGRPO: Mitigating Mode Collapse in Image Generation via Diversity-Aware GRPO","created":"2025-12-25","cited_by_count":17,"area":"lr"},{"id":"2603.21872","title":"Manifold-Aware Exploration for Reinforcement Learning in Video Generation","created":"2026-03-23","cited_by_count":15,"area":"lr"},{"id":"2505.02686","title":"Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards","created":"2025-05-05","cited_by_count":14,"area":"lr"},{"id":"2510.08425","title":"Reinforcing Diffusion Models by Direct Group Preference Optimization","created":"2025-10-09","cited_by_count":14,"area":"lr"},{"id":"2510.21583","title":"Principled RL for Flow Matching Emerges from the Chunk-level Policy Optimization","created":"2025-10-24","cited_by_count":14,"area":"lr"},{"id":"2510.02654","title":"Smart-GRPO: Smartly Sampling Noise for Efficient RL of Flow-Matching Models","created":"2025-10-03","cited_by_count":12,"area":"lr"},{"id":"2601.05729","title":"TAGRPO: Boosting GRPO on Image-to-Video Generation with Direct Trajectory Alignment","created":"2026-01-09","cited_by_count":10,"area":"lr"},{"id":"2602.06422","title":"Alleviating Sparse Rewards by Modeling Step-Wise and Long-Term Sampling Effects in Flow-Based GRPO","created":"2026-02-06","cited_by_count":9,"area":"lr"},{"id":"2605.15458","title":"Video Models Can Reason with Verifiable Rewards","created":"2026-05-14","cited_by_count":9,"area":"lr"},{"id":"2507.08390","title":"Inference-Time Scaling of Diffusion Language Models via Trajectory Refinement","created":"2025-07-11","cited_by_count":7,"area":"lr"},{"id":"2505.18601","title":"Flex-Judge: Text-Only Reasoning Unleashes Zero-Shot Multimodal Evaluators","created":"2025-05-24","cited_by_count":6,"area":"lr"},{"id":"2512.12387","title":"Anchoring Values in Temporal and Group Dimensions for Flow Matching Model Alignment","created":"2025-12-13","cited_by_count":6,"area":"lr"},{"id":"2603.09094","title":"Chain of Event-Centric Causal Thought for Physically Plausible Video Generation","created":"2026-03-10","cited_by_count":6,"area":"lr"},{"id":"2606.29150","title":"Flow Reasoning Models: Turning Flows Into Efficient Recurrent Reasoners","created":"2026-06-28","cited_by_count":6,"area":"lr"},{"id":"2604.18518","title":"UDM-GRPO: Stable and Efficient Group Relative Policy Optimization for Uniform Discrete Diffusion Models","created":"2026-04-20","cited_by_count":3,"area":"lr"},{"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":"2607.00535","title":"Flow-Map GRPO: Reinforcement Learning for Few-Step Flow-Map Generators via Anchored Stochastic Composition","created":"2026-07-01","cited_by_count":3,"area":"lr"},{"id":"2506.22832","title":"Listener-Rewarded Thinking in VLMs for Image Preferences","created":"2025-06-28","cited_by_count":2,"area":"lr"},{"id":"2510.16751","title":"Visual Autoregressive Models Beat Diffusion Models on Inference Time Scaling","created":"2025-10-19","cited_by_count":1,"area":"lr"},{"id":"2511.22242","title":"Rethinking Test Time Scaling for Flow-Matching Generative Models","created":"2025-11-27","cited_by_count":1,"area":"lr"},{"id":"2602.12221","title":"Best of Both Worlds: Multimodal Reasoning and Generation via Unified Discrete Flow Matching","created":"2026-02-12","cited_by_count":1,"area":"lr"},{"id":"2603.27693","title":"LVRPO: Language-Visual Alignment with GRPO for Multimodal Understanding and Generation","created":"2026-03-29","cited_by_count":1,"area":"lr"},{"id":"2602.03208","title":"Spectral Evolution Search: Efficient Inference-Time Scaling for Reward-Aligned Image Generation","created":"2026-02-03","cited_by_count":0,"area":"lr"},{"id":"2602.19974","title":"RL-RIG: A Generative Spatial Reasoner via Intrinsic Reflection","created":"2026-02-23","cited_by_count":0,"area":"lr"},{"id":"2603.06140","title":"Place-it-R1: Unlocking Environment-aware Reasoning Potential of MLLM for Video Object Insertion","created":"2026-03-06","cited_by_count":0,"area":"lr"},{"id":"2605.19995","title":"CogOmniControl: Reasoning-Driven Controllable Video Generation via Creative Intent Cognition","created":"2026-05-19","cited_by_count":0,"area":"lr"},{"id":"2605.29198","title":"Guidance Contrastive Token Credit Assignment for Discrete Policy Optimization","created":"2026-05-28","cited_by_count":0,"area":"lr"},{"id":"2608.05600","title":"LC-GRPO: Bridging Train-Inference Gap for Flow-Based GRPO with Langevin Correction","created":"2026-08-06","cited_by_count":0,"area":"lr"},{"id":"2609.36826","title":"Learning via Self-Consistency for Diffusion-based Video Reasoning","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2610.02774","title":"LatticeSMC: Where to Spend Inference-Time Compute in Chunked Sequence Generators","created":"2026-10-02","cited_by_count":0,"area":"lr"},{"id":"2610.12572","title":"DiffusionART: Efficient, Stable and Scalable Reinforcement of Diffusion Models","created":"2026-10-08","cited_by_count":0,"area":"lr"},{"id":"2610.17246","title":"LLM-to-Flow Distillation: Teaching Natural Language Goals to Scientific Generators","created":"2026-10-12","cited_by_count":0,"area":"lr"}],"next_cursor":null}