mlsanityData to 7 Oct 2026

LaViDa-R1: Advancing Reasoning for Unified Multimodal Diffusion Language Models

arXiv 2602.14147 ↗First posted 15 Feb 2026cs.CVcited by 6

On the map: LLM reasoning → Multimodal reasoning

also in 1 more
Abstract (arXiv)

Diffusion language models (dLLMs) recently emerged as a promising alternative to auto-regressive LLMs. The latest works further extended it to multimodal understanding and generation tasks. In this work, we propose LaViDa-R1, a multimodal, general-purpose reasoning dLLM. Unlike existing works that build reasoning dLLMs through task-specific reinforcement learning, LaViDa-R1 incorporates diverse multimodal understanding and generation tasks in a unified manner. In particular, LaViDa-R1 is built with a novel unified post-training framework that seamlessly integrates supervised finetuning (SFT) and multi-task reinforcement learning (RL). It employs several novel training techniques, including answer-forcing, tree search, and complementary likelihood estimation, to enhance effectiveness and scalability. Extensive experiments demonstrate LaViDa-R1's strong performance on a wide range of multimodal tasks, including visual math reasoning, reason-intensive grounding, and image editing.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Placed in Multimodal reasoning, one of 17 directions in LLM reasoning. Builds on 84 of its 114 references that are in the map. First posted on arXiv 15 Feb 2026.

Builds on

84 of 114 references.

Closest ancestors · 13

Same direction, newest first

  1. 2025VL-Cogito: Progressive Curriculum Reinforcement Learning for Advanced Multimodal Reasoning30 Jul
  2. 2025LaViDa: A Large Diffusion Language Model for Multimodal Understanding22 May
  3. 2025VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning10 Apr
  4. 2025SoTA with Less: MCTS-Guided Sample Selection for Data-Efficient Visual Reasoning Self-Improvement10 Apr
  5. 2025VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model10 Apr
  6. 2025GoT: Unleashing Reasoning Capability of Multimodal Large Language Model for Visual Generation and Editing13 Mar
  7. 2025R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization13 Mar
  8. 2025MM-Eureka: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning10 Mar
  9. 2025Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models9 Mar
  10. 2025R1-Zero's "Aha Moment" in Visual Reasoning on a 2B Non-SFT Model7 Mar
  11. 2024MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale6 Dec
  12. 2023LISA++: An Improved Baseline for Reasoning Segmentation with Large Language Model28 Dec
1 more
  1. 2023MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts3 Oct

Other references · 71

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  3. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  4. 2025Qwen3 Technical Reportcited by 8,195
  5. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,146
  6. 2025Qwen2.5-VL Technical Reportcited by 5,418
  7. 2024GPT-4o System Cardcited by 4,467
  8. 2023Let's Verify Step by Stepcited by 3,598
  9. 2025Qwen3-VL Technical Reportcited by 2,534
  10. 2023MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Modelscited by 1,624
  11. 2025Qwen-Image Technical Reportcited by 973
  12. 2025FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Spacecited by 960
38 more
  1. 2025Large Language Diffusion Modelscited by 872
  2. 2025Emerging Properties in Unified Multimodal Pretrainingcited by 855
  3. 2025Group Sequence Policy Optimizationcited by 788
  4. 2023Discrete Diffusion Modeling by Estimating the Ratios of the Data Distributioncited by 712
  5. 2025Flow-GRPO: Training Flow Matching Models via Online RLcited by 605
  6. 2024MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?cited by 573
  7. 2024Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Modelscited by 552
  8. 2025Step1X-Edit: A Practical Framework for General Image Editingcited by 417
  9. 2025Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decodingcited by 404
  10. 2023SLiC-HF: Sequence Likelihood Calibration with Human Feedbackcited by 395
  11. 2024Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Datacited by 371
  12. 2025BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Datasetcited by 363
  13. 2025Learning to Reason under Off-Policy Guidancecited by 266
  14. 2024Direct Language Model Alignment from Online AI Feedbackcited by 257
  15. 2025MMaDA: Multimodal Large Diffusion Language Modelscited by 241
  16. 2025OmniGen2: Towards Instruction-Aligned Multimodal Generationcited by 241
  17. 2024Self-Play Preference Optimization for Language Model Alignmentcited by 228
  18. 2025ImgEdit: A Unified Image Editing Dataset and Benchmarkcited by 225
  19. 2025Mercury: Ultra-Fast Language Models Based on Diffusioncited by 225
  20. 2025DiffusionNFT: Online Diffusion Reinforcement with Forward Processcited by 204
  21. 2025Unified Reward Model for Multimodal Understanding and Generationcited by 194
  22. 2025DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generationcited by 184
  23. 2025d1: Scaling Reasoning in Diffusion Large Language Models via Reinforcement Learningcited by 178
  24. 2024Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferencescited by 176
  25. 2025LLaDA2.0: Scaling Up Diffusion Language Models to 100Bcited by 154
  26. 2025LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuningcited by 145
  27. 2024A Minimaximalist Approach to Reinforcement Learning from Human Feedbackcited by 141
  28. 2025Emu3.5: Native Multimodal Models are World Learnerscited by 119
  29. 2025X-Omni: Reinforcement Learning Makes Discrete Autoregressive Image Generative Models Great Againcited by 105
  30. 2025Dimple: Discrete Diffusion Multimodal Large Language Model with Parallel Decodingcited by 101
  31. 2025Learning What Reinforcement Learning Can't: Interleaved Online Fine-Tuning for Hardest Questionscited by 95
  32. 2025ShareGPT-4o-Image: Aligning Multimodal Models with GPT-4o-Level Image Generationcited by 94
  33. 2024On Designing Effective RL Reward at Training Time for LLM Reasoningcited by 87
  34. 2025Lumina-DiMOO: An Omni Diffusion Large Language Model for Multi-Modal Generation and Understandingcited by 83
  35. 2025Retaining by Doing: The Role of On-Policy Data in Mitigating Forgettingcited by 82
  36. 2025SRFT: A Single-Stage Method with Supervised and Reinforcement Fine-Tuning for Reasoningcited by 80
  37. 2025Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Modelscited by 80
  38. 2025Uniworld-V2: Reinforce Image Editing with Diffusion Negative-aware Finetuning and MLLM Implicit Feedbackcited by 78

50 most cited of 71 All 71 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 6.

6 papers.

  1. 2026SNCE: Geometry-Aware Supervision for Scalable Discrete Image Generationcited by 1
  2. 2026dFlowGRPO: Rate-Aware Policy Optimization for Discrete Flow Modelscited by 1
  3. 2026FluxLite: Inference-Time Proposal Control for Discrete Diffusion Modelscited by 1
  4. 2026Nemotron-Labs-Diffusion-Image: Advancing Masked Discrete Diffusion for High-Resolution Image Synthesiscited by 0
  5. 2026STBridge: Shared-Target Alignment for Bridging Understanding and Generation in UMMscited by 0
  6. 2026CT-OPD: Counterfactual Trace On-Policy Distillation for Diffusion Vision-Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Reinforced MLLM: A Survey on RL-Based Reasoning in Multimodal Large Language Models
  2. 2026Thinking Diffusion: Penalize and Guide Visual-Grounded Reasoning in Diffusion Multimodal Language Models
  3. 2025Advancing Multimodal Reasoning: From Optimized Cold Start to Staged Reinforcement Learning
  4. 2026DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
  5. 2025LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL
  6. 2025Observe-R1: Unlocking Reasoning Abilities of MLLMs with Dynamic Progressive Reinforcement Learning
  7. 2025Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start
  8. 2025DiffThinker: Towards Generative Multimodal Reasoning with Diffusion Models