mlsanityData to 14 Oct 2026

UniRL-Zero: Reinforcement Learning on Unified Models with Joint Language Model and Diffusion Model Experts

arXiv 2510.17937 ↗First posted 20 Oct 2025cs.LG cs.AIcited by 5

On the map: LLM reasoning → Reinforcement learning for reasoning

also in 2 more
Abstract (arXiv)

We present UniRL-Zero, a unified reinforcement learning (RL) framework that boosts, multimodal language model understanding and reasoning, diffusion model multimedia generation, and their beneficial interaction capabilities within a unified model. Our work defines six scenarios for unified model reinforcement learning, providing systematic baselines for reinforcement learning of unified understanding and generation model. Our code is available at https://github.com/G-U-N/UniRL.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning. Builds on 49 of its 59 references that are in the map. First posted on arXiv 20 Oct 2025.

Builds on

49 of 59 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025DanceGRPO: Unleashing GRPO on Visual Generation12 May
  2. 2025Flow-GRPO: Training Flow Matching Models via Online RL8 May
  3. 2017Proximal Policy Optimization Algorithms20 Jul

Other references · 46

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2022Training language models to follow instructions with human feedbackcited by 15,971
  4. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  5. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  6. 2025Qwen2.5-VL Technical Reportcited by 5,587
  7. 2024GPT-4o System Cardcited by 4,588
  8. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,356
  9. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,181
  10. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,224
  11. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 3,045
  12. 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 2,611
34 more
  1. 2023MMBench: Is Your Multi-modal Model an All-around Player?cited by 2,141
  2. 2023MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGIcited by 2,080
  3. 2023MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilitiescited by 1,239
  4. 2025FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Spacecited by 1,006
  5. 2023Training Diffusion Models with Reinforcement Learningcited by 982
  6. 2023Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generationcited by 977
  7. 2023GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignmentcited by 972
  8. 2023SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehensioncited by 940
  9. 2024Chameleon: Mixed-Modal Early-Fusion Foundation Modelscited by 927
  10. 2023A Survey on Multimodal Large Language Modelscited by 909
  11. 2025Emerging Properties in Unified Multimodal Pretrainingcited by 897
  12. 2024WorldSimBench: Towards Video Generation Models as World Simulatorscited by 881
  13. 2023PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesiscited by 864
  14. 2025Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scalingcited by 812
  15. 2024Emu3: Next-Token Prediction is All You Needcited by 781
  16. 2024Show-o: One Single Transformer to Unify Multimodal Understanding and Generationcited by 752
  17. 2024Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Modelcited by 483
  18. 2024Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generationcited by 457
  19. 2024SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformerscited by 340
  20. 2024PixArt-Sigma: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generationcited by 329
  21. 2024Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understandingcited by 298
  22. 2023DreamLLM: Synergistic Multimodal Comprehension and Creationcited by 297
  23. 2024VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generationcited by 295
  24. 2022Rectified Flow: A Marginal Preserving Approach to Optimal Transportcited by 283
  25. 2025Transfer between Modalities with MetaQueriescited by 236
  26. 2025Video models are zero-shot learners and reasonerscited by 220
  27. 2024Deep Compression Autoencoder for Efficient High-Resolution Diffusion Modelscited by 217
  28. 2024MetaMorph: Multimodal Understanding and Generation via Instruction Tuningcited by 206
  29. 2024TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generationcited by 202
  30. 2024JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generationcited by 163
  31. 2024Lumina-Next: Making Lumina-T2X Stronger and Faster with Next-DiTcited by 132
  32. 2024LMFusion: Adapting Pretrained Language Models for Multimodal Generationcited by 120
  33. 2024Rectified Diffusion: Straightness Is Not Your Need in Rectified Flowcited by 61
  34. 2025NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scalecited by 57

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 5.

5 papers.

  1. 2026LLaMo: Scaling Pretrained Language Models for Unified Motion Understanding and Generation with Continuous Autoregressive Tokenscited by 11
  2. 2026Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modelingcited by 5
  3. 2026Advances in GRPO for Generation Models: A Surveycited by 2
  4. 2026Model Guides You How to Draw: Adaptive Visual Gating for Unified Multimodal Reasoningcited by 0
  5. 2026RSIgen: Reciprocal Self-Improvement for Agentic Visual Generationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning
  2. 2025Co-Reinforcement Learning for Unified Multimodal Understanding and Generation
  3. 2026UniRRM: Unified Reasoning Reward Models Across Languages and Evaluation Paradigms
  4. 2025Zero Reinforcement Learning Towards General Domains
  5. 2024Unsupervised-to-Online Reinforcement Learning
  6. 2026Co-RL: Unsupervised Reasoning Emerges from Diverse Cohort in Multi-agent RL
  7. 2024Uni-RLHF: Universal Platform and Benchmark Suite for Reinforcement Learning with Diverse Human Feedback
  8. 2026UNIPO: Unified Interactive Visual Explanation for RL Fine-Tuning Policy Optimization