mlsanityData to 14 Oct 2026

T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT

arXiv 2505.00703 ↗First posted 1 May 2025cs.CV cs.AI cs.CLcited by 166

On the map: LLM reasoning → Multimodal reasoning

Abstract (arXiv)

Recent advancements in large language models have demonstrated how chain-of-thought (CoT) and reinforcement learning (RL) can improve performance. However, applying such reasoning strategies to the visual generation domain remains largely unexplored. In this paper, we present T2I-R1, a novel reasoning-enhanced text-to-image generation model, powered by RL with a bi-level CoT reasoning process. Specifically, we identify two levels of CoT that can be utilized to enhance different stages of generation: (1) the semantic-level CoT for high-level planning of the prompt and (2) the token-level CoT for low-level pixel processing during patch-by-patch generation. To better coordinate these two levels of CoT, we introduce BiCoT-GRPO with an ensemble of generation rewards, which seamlessly optimizes both generation CoTs within the same training step. By applying our reasoning strategies to the baseline model, Janus-Pro, we achieve superior performance with 13% improvement on T2I-CompBench and 19% improvement on the WISE benchmark, even surpassing the state-of-the-art model FLUX.1. Code is available at: https://github.com/CaraJ7/T2I-R1

Key facts. Cited by 166 papers in the map (data through 14 Oct 2026). Placed in Multimodal reasoning, one of 17 directions in LLM reasoning. Builds on 82 of its 112 references that are in the map. First posted on arXiv 1 May 2025.

Builds on

82 of 112 references.

Closest ancestors · 6

Same direction, newest first

  1. 2025SciVerse: Unveiling the Knowledge Comprehension and Visual Reasoning of LMMs on Multi-modal Scientific Problems13 Mar
  2. 2025R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization13 Mar
  3. 2025Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models9 Mar
  4. 2025Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement9 Mar
  5. 2025MME-CoT: Benchmarking Chain-of-Thought in Large Multimodal Models for Reasoning Quality, Robustness, and Efficiency13 Feb
  6. 2025Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step23 Jan

Other references · 76

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2017Proximal Policy Optimization Algorithmscited by 15,215
  5. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  6. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  7. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  8. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  9. 2023Visual Instruction Tuningcited by 7,869
  10. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  11. 2025Qwen2.5-VL Technical Reportcited by 5,587
  12. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,371
38 more
  1. 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
  2. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,356
  3. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,322
  4. 2021Program Synthesis with Large Language Modelscited by 3,637
  5. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,332
  6. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,253
  7. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,879
  8. 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scalecited by 2,810
  9. 2024LLaVA-OneVision: Easy Visual Task Transfercited by 2,719
  10. 2024Qwen2 Technical Reportcited by 2,120
  11. 2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Codecited by 2,004
  12. 2023ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generationcited by 1,045
  13. 2024Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Predictioncited by 1,023
  14. 2023Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesiscited by 890
  15. 2023PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesiscited by 864
  16. 2025Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scalingcited by 812
  17. 2024Emu3: Next-Token Prediction is All You Needcited by 781
  18. 2024Autoregressive Model Beats Diffusion: Llama for Scalable Image Generationcited by 777
  19. 2024Show-o: One Single Transformer to Unify Multimodal Understanding and Generationcited by 752
  20. 2023Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Modelscited by 702
  21. 2019MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalismscited by 662
  22. 2022Compositional Visual Generation with Composable Diffusion Modelscited by 624
  23. 2024MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?cited by 586
  24. 2022GIT: A Generative Image-to-text Transformer for Vision and Languagecited by 537
  25. 2024YOLO-World: Real-Time Open-Vocabulary Object Detectioncited by 503
  26. 2024Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Modelcited by 483
  27. 2024Evaluating Text-to-Visual Generation with Image-to-Text Generationcited by 474
  28. 2024Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generationcited by 457
  29. 2024Lumiere: A Space-Time Diffusion Model for Video Generationcited by 455
  30. 2023Generative Multimodal Models are In-Context Learnerscited by 446
  31. 2022Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesiscited by 388
  32. 2024Mini-Gemini: Mining the Potential of Multi-modality Vision Language Modelscited by 365
  33. 2022The Vendi Score: A Diversity Evaluation Metric for Machine Learningcited by 311
  34. 2024Infinity: Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesiscited by 304
  35. 2025R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimizationcited by 301
  36. 2023DreamLLM: Synergistic Multimodal Comprehension and Creationcited by 297
  37. 2024VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generationcited by 295
  38. 2024Playground v2.5: Three Insights towards Enhancing Aesthetic Quality in Text-to-Image Generationcited by 256

50 most cited of 76 All 76 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 85; 2026: 81.

166 papers.

Sort:

By area:

  1. 2025The Landscape of Agentic Reinforcement Learning for LLMs: A Surveycited by 205
  2. 2025Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontierscited by 199
  3. 2025A Survey of Reinforcement Learning for Large Reasoning Modelscited by 180
  4. 2025Echo-4o: Harnessing the Power of GPT-4o Synthetic Images for Improved Image Generationcited by 100
  5. 2025Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Modelscited by 90
  6. 2025Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunitiescited by 85
  7. 2025Visual Planning: Let's Think Only with Imagescited by 85
  8. 2025WebGen-Bench: Evaluating LLMs on Generating Interactive and Functional Websites from Scratchcited by 72
  9. 2025TIIF-Bench: How Does Your T2I Model Follow Your Instructions?cited by 69
  10. 2025UniCTokens: Boosting Personalized Understanding and Generation via Unified Concept Tokenscited by 56
  11. 2025Uni-cot: Towards Unified Chain-of-Thought Reasoning Across Text and Visioncited by 56
  12. 2025GoT-R1: Unleashing Reasoning Capability of MLLM for Visual Generation with Reinforcement Learningcited by 52
38 more
  1. 2025TokLIP: Marry Visual Tokens to CLIP for Multimodal Comprehension and Generationcited by 51
  2. 2025MINT-CoT: Enabling Interleaved Visual Tokens in Mathematical Chain-of-Thought Reasoningcited by 49
  3. 2025Interleaving Reasoning for Better Text-to-Image Generationcited by 41
  4. 2025Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecyclecited by 35
  5. 2025R2I-Bench: Benchmarking Reasoning-Driven Text-to-Image Generationcited by 32
  6. 2025Delving into RL for Image Generation with CoT: A Study on DPO vs. GRPOcited by 31
  7. 2025JarvisEvo: Towards a Self-Evolving Photo Editing Agent with Synergistic Editor-Evaluator Optimizationcited by 31
  8. 2025Draw ALL Your Imagine: A Holistic Benchmark and Agent Framework for Complex Instruction-based Image Generationcited by 30
  9. 2025AlphaOne: Reasoning Models Thinking Slow and Fast at Test Timecited by 29
  10. 2025VQ-Insight: Teaching VLMs for AI-Generated Video Quality Understanding via Progressive Visual Reinforcement Learningcited by 26
  11. 2026UniCorn: Towards Self-Improving Unified Multimodal Models through Self-Generated Supervisioncited by 26
  12. 2025VeriThinker: Learning to Verify Makes Reasoning Model Efficientcited by 24
  13. 2025RePrompt: Reasoning-Augmented Reprompting for Text-to-Image Generation via Reinforcement Learningcited by 23
  14. 2026Mind-Brush: Integrating Agentic Cognitive Search and Reasoning into Image Generationcited by 23
  15. 2025AR-GRPO: Training Autoregressive Image Generation Models via Reinforcement Learningcited by 22
  16. 2026Qwen-Image-Bench: From Generation to Creation in Text-to-Image Evaluationcited by 22
  17. 2026GEMS: Agent-Native Multimodal Generation with Memory and Skillscited by 21
  18. 2025Thinking-while-Generating: Interleaving Textual Reasoning throughout Visual Generationcited by 18
  19. 2025Group Critical-token Policy Optimization for Autoregressive Image Generationcited by 17
  20. 2025Generative Universal Verifier as Multimodal Meta-Reasonercited by 17
  21. 2025MMMG: A Massive, Multidisciplinary, Multi-Tier Generation Benchmark for Text-to-Image Reasoningcited by 16
  22. 2025Co-Reinforcement Learning for Unified Multimodal Understanding and Generationcited by 15
  23. 2025TTS-VAR: A Test-Time Scaling Framework for Visual Auto-Regressive Generationcited by 15
  24. 2025STAGE: Stable and Generalizable GRPO for Autoregressive Image Generationcited by 15
  25. 2026Think-Then-Generate: Reasoning-Aware Text-to-Image Diffusion with LLM Encoderscited by 15
  26. 2025Reinforcement Fine-Tuning Powers Reasoning Capability of Multimodal Large Language Modelscited by 14
  27. 2026NextFlow: Unified Sequential Modeling Activates Multimodal Understanding and Generationcited by 14
  28. 2026Demystifying Video Reasoningcited by 14
  29. 2026RationalRewards: Reasoning Rewards Scale Visual Generation Both Training and Test Timecited by 14
  30. 2025FocusDiff: Advancing Fine-Grained Text-Image Alignment for Autoregressive Visual Generation through RLcited by 13
  31. 2025Unified Multimodal Models as Auto-Encoderscited by 13
  32. 2025DraCo: Draft as CoT for Text-to-Image Preview and Rare Concept Generationcited by 13
  33. 2025ThinkGen: Generalized Thinking for Visual Generationcited by 13
  34. 2025Integrating Reinforcement Learning with Visual Generative Models: Foundations and Advancescited by 12
  35. 2026UniReason 1.0: A Unified Reasoning Framework for World Knowledge Aligned Image Generation and Editingcited by 12
  36. 2026GENIUS: Generative Fluid Intelligence Evaluation Suitecited by 12
  37. 2025CrossLMM: Decoupling Long Video Sequences from LMMs via Dual Cross-Attention Mechanismscited by 11
  38. 2025Geoint-R1: Formalizing Multimodal Geometric Reasoning with Dynamic Auxiliary Constructionscited by 11

50 most cited of 166 All 166 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025ReasonGen-R1: CoT for Autoregressive Image generation models through SFT and RL
  2. 2026UniGRPO: Unified Policy Optimization for Reasoning-Driven Visual Generation
  3. 2025Towards Enhanced Image Generation Via Multi-modal Chain of Thought in Unified Generative Models
  4. 2025GoT: Unleashing Reasoning Capability of Multimodal Large Language Model for Visual Generation and Editing
  5. 2025MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO
  6. 2025ImageGen-CoT: Enhancing Text-to-Image In-context Learning with Chain-of-Thought Reasoning
  7. 2026FiRe: Fine-grained Multimodal Reasoning for Enhanced Image Generation
  8. 2026Genesis: Visual Augmentation Primitives for Multimodal Chain-of-Thought Reasoning