{"total":96,"rows":[{"id":"2505.05470","title":"Flow-GRPO: Training Flow Matching Models via Online RL","created":"2025-05-08","cited_by_count":661,"area":"lr"},{"id":"2503.22020","title":"CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models","created":"2025-03-27","cited_by_count":451,"area":"lr"},{"id":"2505.14362","title":"DeepEyes: Incentivizing \"Thinking with Images\" via Reinforcement Learning","created":"2025-05-20","cited_by_count":410,"area":"lr"},{"id":"2503.07536","title":"LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL","created":"2025-03-10","cited_by_count":248,"area":"lr"},{"id":"2506.23918","title":"Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers","created":"2025-06-30","cited_by_count":199,"area":"lr"},{"id":"2508.11630","title":"Thyme: Think Beyond Images","created":"2025-08-15","cited_by_count":167,"area":"lr"},{"id":"2505.00703","title":"T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT","created":"2025-05-01","cited_by_count":166,"area":"lr"},{"id":"2501.13926","title":"Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step","created":"2025-01-23","cited_by_count":131,"area":"lr"},{"id":"2508.04324","title":"TempFlow-GRPO: When Timing Matters for GRPO in Flow Models","created":"2025-08-06","cited_by_count":97,"area":"lr"},{"id":"2504.13055","title":"NoisyRollout: Reinforcing Visual Reasoning with Data Augmentation","created":"2025-04-17","cited_by_count":86,"area":"lr"},{"id":"2508.05606","title":"Uni-cot: Towards Unified Chain-of-Thought Reasoning Across Text and Vision","created":"2025-08-07","cited_by_count":56,"area":"lr"},{"id":"2508.17472","title":"T2I-ReasonBench: Benchmarking Reasoning-Informed Text-to-Image Generation","created":"2025-08-24","cited_by_count":38,"area":"lr"},{"id":"2503.19312","title":"ImageGen-CoT: Enhancing Text-to-Image In-context Learning with Chain-of-Thought Reasoning","created":"2025-03-25","cited_by_count":37,"area":"lr"},{"id":"2505.23590","title":"Jigsaw-R1: A Study of Rule-based Visual Reinforcement Learning with Jigsaw Puzzles","created":"2025-05-29","cited_by_count":36,"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":"2505.17017","title":"Delving into RL for Image Generation with CoT: A Study on DPO vs. GRPO","created":"2025-05-22","cited_by_count":31,"area":"lr"},{"id":"2508.21112","title":"EO-1: An Open Unified Embodied Foundation Model for General Robot Control","created":"2025-08-28","cited_by_count":31,"area":"lr"},{"id":"2505.13031","title":"MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO","created":"2025-05-19","cited_by_count":30,"area":"lr"},{"id":"2505.24875","title":"ReasonGen-R1: CoT for Autoregressive Image generation models through SFT and RL","created":"2025-05-30","cited_by_count":30,"area":"lr"},{"id":"2509.25681","title":"dVLA: Diffusion Vision-Language-Action Model with Multimodal Chain-of-Thought","created":"2025-09-30","cited_by_count":30,"area":"lr"},{"id":"2603.09877","title":"InternVL-U: Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and Editing","created":"2026-03-10","cited_by_count":28,"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":"2504.03641","title":"MME-Unify: A Comprehensive Benchmark for Unified Multimodal Understanding and Generation Models","created":"2025-04-04","cited_by_count":24,"area":"lr"},{"id":"2601.18543","title":"GenAgent: Scaling Text-to-Image Generation via Agentic Multimodal Reasoning","created":"2026-01-26","cited_by_count":24,"area":"lr"},{"id":"2505.17540","title":"RePrompt: Reasoning-Augmented Reprompting for Text-to-Image Generation via Reinforcement Learning","created":"2025-05-23","cited_by_count":23,"area":"lr"},{"id":"2511.02779","title":"When Visualizing is the First Step to Reasoning: MIRA, a Benchmark for Visual Chain-of-Thought","created":"2025-11-04","cited_by_count":21,"area":"lr"},{"id":"2504.00010","title":"LayerCraft: Enhancing Text-to-Image Generation with CoT Reasoning and Layered Object Integration","created":"2025-03-25","cited_by_count":19,"area":"lr"},{"id":"2511.16671","title":"Thinking-while-Generating: Interleaving Textual Reasoning throughout Visual Generation","created":"2025-11-20","cited_by_count":18,"area":"lr"},{"id":"2505.17534","title":"Co-Reinforcement Learning for Unified Multimodal Understanding and Generation","created":"2025-05-23","cited_by_count":15,"area":"lr"},{"id":"2507.18537","title":"TTS-VAR: A Test-Time Scaling Framework for Visual Auto-Regressive Generation","created":"2025-07-24","cited_by_count":15,"area":"lr"},{"id":"2509.25027","title":"STAGE: Stable and Generalizable GRPO for Autoregressive Image Generation","created":"2025-09-29","cited_by_count":15,"area":"lr"},{"id":"2503.01298","title":"Towards Enhanced Image Generation Via Multi-modal Chain of Thought in Unified Generative Models","created":"2025-03-03","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":"2510.13418","title":"Reinforcement Learning Meets Masked Generative Models: Mask-GRPO for Text-to-Image Generation","created":"2025-10-15","cited_by_count":14,"area":"lr"},{"id":"2512.02622","title":"RULER-Bench: Probing Rule-based Reasoning Abilities of Next-level Video Generation Models for Vision Foundation Intelligence","created":"2025-12-02","cited_by_count":13,"area":"lr"},{"id":"2512.05112","title":"DraCo: Draft as CoT for Text-to-Image Preview and Rare Concept Generation","created":"2025-12-04","cited_by_count":13,"area":"lr"},{"id":"2510.02880","title":"Consolidating Reinforcement Learning for Multimodal Discrete Diffusion Models","created":"2025-10-03","cited_by_count":12,"area":"lr"},{"id":"2602.02437","title":"UniReason 1.0: A Unified Reasoning Framework for World Knowledge Aligned Image Generation and Editing","created":"2026-02-02","cited_by_count":12,"area":"lr"},{"id":"2605.22344","title":"Bernini: Latent Semantic Planning for Video Diffusion","created":"2026-05-21","cited_by_count":12,"area":"lr"},{"id":"2509.18639","title":"Understanding-in-Generation: Reinforcing Generative Capability of Unified Model via Infusing Understanding into Generation","created":"2025-09-23","cited_by_count":11,"area":"lr"},{"id":"2512.19686","title":"Visual-Aware CoT: Achieving High-Fidelity Visual Consistency in Unified Models","created":"2025-12-22","cited_by_count":10,"area":"lr"},{"id":"2512.04563","title":"COOPER: A Unified Model for Cooperative Perception and Reasoning in Spatial Intelligence","created":"2025-12-04","cited_by_count":9,"area":"lr"},{"id":"2508.05954","title":"Bifrost-1: Bridging Multimodal LLMs and Diffusion Models with Patch-level CLIP Latents","created":"2025-08-08","cited_by_count":8,"area":"lr"},{"id":"2510.01010","title":"ImageDoctor: Diagnosing Text-to-Image Generation via Grounded Image Reasoning","created":"2025-10-01","cited_by_count":7,"area":"lr"},{"id":"2604.02355","title":"From Broad Exploration to Stable Synthesis: Entropy-Guided Optimization for Autoregressive Image Generation","created":"2026-03-12","cited_by_count":7,"area":"lr"},{"id":"2505.17768","title":"R-Genie: Reasoning-Guided Generative Image Editing","created":"2025-05-23","cited_by_count":6,"area":"lr"},{"id":"2507.01756","title":"Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis","created":"2025-07-02","cited_by_count":6,"area":"lr"},{"id":"2512.22288","title":"Co-GRPO: Co-Optimized Group Relative Policy Optimization for Masked Diffusion Model","created":"2025-12-25","cited_by_count":6,"area":"lr"},{"id":"2602.06166","title":"M3: High-fidelity Text-to-Image Generation via Multi-Modal, Multi-Agent and Multi-Round Visual Reasoning","created":"2026-02-05","cited_by_count":6,"area":"lr"},{"id":"2603.08652","title":"CoCo: Code as CoT for Text-to-Image Preview and Rare Concept Generation","created":"2026-03-09","cited_by_count":6,"area":"lr"},{"id":"2604.20328","title":"HyLaR: Hybrid Latent Reasoning with Decoupled Policy Optimization","created":"2026-04-22","cited_by_count":6,"area":"lr"},{"id":"2510.17937","title":"UniRL-Zero: Reinforcement Learning on Unified Models with Joint Language Model and Diffusion Model Experts","created":"2025-10-20","cited_by_count":5,"area":"lr"},{"id":"2510.21122","title":"NoisyGRPO: Incentivizing Multimodal CoT Reasoning via Noise Injection and Bayesian Estimation","created":"2025-10-24","cited_by_count":5,"area":"lr"},{"id":"2604.05377","title":"Can Vision-Language Models Think from the Sky? Unifying UAV Reasoning and Generation","created":"2026-04-07","cited_by_count":5,"area":"lr"},{"id":"2607.03748","title":"Bridging Interleaved Multi-Modal Reasoning as a Unified Decision Process","created":"2026-07-04","cited_by_count":5,"area":"lr"},{"id":"2602.06663","title":"PlanViz: Evaluating Planning-Oriented Image Generation and Editing for Computer-Use Tasks","created":"2026-02-06","cited_by_count":4,"area":"lr"},{"id":"2603.09538","title":"Towards Unified Multimodal Interleaved Generation via Group Relative Policy Optimization","created":"2026-03-10","cited_by_count":4,"area":"lr"},{"id":"2603.15724","title":"Meta-TTRL: A Metacognitive Framework for Self-Improving Test-Time Reinforcement Learning in Unified Multimodal Models","created":"2026-03-16","cited_by_count":4,"area":"lr"},{"id":"2605.12495","title":"AlphaGRPO: Unlocking Self-Reflective Multimodal Generation in UMMs via Decompositional Verifiable Reward","created":"2026-05-12","cited_by_count":4,"area":"lr"},{"id":"2601.12126","title":"UniMo: Unified Motion Generation and Understanding with Chain of Thought","created":"2026-01-17","cited_by_count":3,"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":"2604.24625","title":"Meta-CoT: Enhancing Granularity and Generalization in Image Editing","created":"2026-04-27","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":"2605.15198","title":"ATLAS: Agentic or Latent Visual Reasoning? One Word is Enough for Both","created":"2026-05-14","cited_by_count":3,"area":"lr"},{"id":"2509.23014","title":"Planning with Unified Multimodal Models","created":"2025-09-27","cited_by_count":2,"area":"lr"},{"id":"2511.21185","title":"Progress by Pieces: Test-Time Scaling for Autoregressive Image Generation","created":"2025-11-26","cited_by_count":2,"area":"lr"},{"id":"2512.19433","title":"dMLLM-TTS: Self-Verified and Efficient Test-Time Scaling for Diffusion Multi-Modal Large Language Models","created":"2025-12-22","cited_by_count":2,"area":"lr"},{"id":"2601.16538","title":"OnlineSI: Taming Large Language Model for Online 3D Understanding and Grounding","created":"2026-01-23","cited_by_count":2,"area":"lr"},{"id":"2602.06034","title":"V-Retrver: Evidence-Driven Agentic Reasoning for Universal Multimodal Retrieval","created":"2026-02-05","cited_by_count":2,"area":"lr"},{"id":"2602.11980","title":"Spatial Chain-of-Thought: Bridging Understanding and Generation Models for Spatial Reasoning Generation","created":"2026-02-12","cited_by_count":2,"area":"lr"},{"id":"2603.06014","title":"EffectMaker: Unifying Reasoning and Generation for Customized Visual Effect Creation","created":"2026-03-06","cited_by_count":2,"area":"lr"},{"id":"2603.25823","title":"ViGoR-Bench: How Far Are Visual Generative Models From Zero-Shot Visual Reasoners?","created":"2026-03-26","cited_by_count":2,"area":"lr"},{"id":"2604.19193","title":"How Far Are Video Models from True Multimodal Reasoning?","created":"2026-04-21","cited_by_count":2,"area":"lr"},{"id":"2605.23897","title":"ETCHR: Editing To Clarify and Harness Reasoning","created":"2026-05-22","cited_by_count":2,"area":"lr"},{"id":"2606.29712","title":"Why Struggle with Continuous Latents? Interpretable Discrete Latent Reasoning via Rendered Compression","created":"2026-06-29","cited_by_count":2,"area":"lr"},{"id":"2512.24555","title":"From Perception to Punchline: Empowering VLM with the Art of In-the-wild Meme","created":"2025-12-31","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":"2604.10949","title":"Pseudo-Unification: Entropy Probing Reveals Divergent Information Patterns in Unified Multimodal Models","created":"2026-04-13","cited_by_count":1,"area":"lr"},{"id":"2605.10588","title":"Thinking with Novel Views: A Systematic Analysis of Generative-Augmented Spatial Intelligence","created":"2026-05-11","cited_by_count":1,"area":"lr"},{"id":"2605.24687","title":"HoloFair: Unified T2I Fairness Evaluation and Fair-GRPO Debiasing","created":"2026-05-23","cited_by_count":1,"area":"lr"},{"id":"2606.30124","title":"SciIR: A Large-scale Training Dataset and Benchmark for Scientific Image Reasoning Generation","created":"2026-06-29","cited_by_count":1,"area":"lr"},{"id":"2607.16409","title":"Think, Plan, Paint: Layout-Aware Reasoning for Controllable Image Generation in Unified Models","created":"2026-07-17","cited_by_count":1,"area":"lr"},{"id":"2608.15869","title":"Beyond Visual CoT: Internalized Visual Thinking for Proactive Video Reasoning","created":"2026-08-16","cited_by_count":1,"area":"lr"},{"id":"2507.12761","title":"Think-Before-Draw: Decomposing Emotion Semantics & Fine-Grained Controllable Expressive Talking Head Generation","created":"2025-07-17","cited_by_count":0,"area":"lr"},{"id":"2507.13401","title":"MADI: Masking-Augmented Diffusion with Inference-Time Scaling for Visual Editing","created":"2025-07-16","cited_by_count":0,"area":"lr"},{"id":"2512.00438","title":"FR-TTS: Test-Time Scaling for NTP-based Image Generation with Effective Filling-based Reward Signal","created":"2025-11-29","cited_by_count":0,"area":"lr"},{"id":"2602.01554","title":"InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs","created":"2026-02-02","cited_by_count":0,"area":"lr"},{"id":"2602.21435","title":"Synergizing Understanding and Generation with Interleaved Analyzing-Drafting Thinking","created":"2026-02-24","cited_by_count":0,"area":"lr"},{"id":"2603.02712","title":"From \"What\" to \"How\": Constrained Reasoning for Autoregressive Image Generation","created":"2026-03-03","cited_by_count":0,"area":"lr"},{"id":"2605.18956","title":"MotionMERGE: A Multi-granular Framework for Human Motion Editing, Reasoning, Generation, and Explanation","created":"2026-05-18","cited_by_count":0,"area":"lr"},{"id":"2606.15188","title":"Adaptive Inference-Time Scaling via Early-Step Latent Verification for Image Editing","created":"2026-06-13","cited_by_count":0,"area":"lr"},{"id":"2606.24548","title":"Are Text-to-Image Models Inductivist Turkeys? A Counterfactual Benchmark for Causal Reasoning","created":"2026-06-23","cited_by_count":0,"area":"lr"},{"id":"2609.07815","title":"VoT: Vision-of-Thought for Unified Multimodal Representation Alignment","created":"2026-09-07","cited_by_count":0,"area":"lr"},{"id":"2609.19878","title":"Uni-LaDiR: Latent Diffusion Unifies Multimodal Reasoning","created":"2026-09-17","cited_by_count":0,"area":"lr"},{"id":"2610.13316","title":"ThinkDrag: Semantic Drag-Based Image Editing with Visual Reasoning","created":"2026-10-09","cited_by_count":0,"area":"lr"}],"next_cursor":null}