mlsanityData to 14 Oct 2026

RIV: Recursive Introspection Mask Diffusion Vision Language Model

arXiv 2509.23625 ↗First posted 28 Sep 2025cs.CV cs.AI cs.CLcited by 2

On the map: Multimodal LLMs / vision-language models → VLM benchmarks and visual reasoning

Abstract (arXiv)

Mask Diffusion-based Vision Language Models (MDVLMs) have achieved remarkable progress in multimodal understanding tasks. However, these models are unable to correct errors in generated tokens, meaning they lack self-correction capability. In this paper, we propose Recursive Introspection Mask Diffusion Vision Language Model (RIV), which equips the model with self-correction ability through two novel mechanisms. The first is Introspection Training, where an Introspection Model is introduced to identify errors within generated sequences. Introspection Training enables the model to detect not only grammatical and spelling mistakes, but more importantly, logical errors. The second is Recursive Inference. Beginning with the standard unmasking step, the learned Introspection Model helps to identify errors in the output sequence and remask them. This alternating (unmaskrightarrowintrospectionrightarrowremask) process is repeated recursively until reliable results are obtained. Experimental results on multiple benchmarks demonstrate that the proposed RIV achieves state-of-the-art performance, outperforming most existing MDVLMs.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 41 of its 47 references that are in the map. First posted on arXiv 28 Sep 2025.

Builds on

41 of 47 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024Are We on the Right Way for Evaluating Large Vision-Language Models?29 Mar
  2. 2024MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?21 Mar

Other references · 39

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2024The Llama 3 Herd of Modelscited by 14,715
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  4. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  5. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  6. 2025Qwen3 Technical Reportcited by 8,820
  7. 2023Visual Instruction Tuningcited by 7,869
  8. 2024Qwen2.5 Technical Reportcited by 4,942
  9. 2023Improved Baselines with Visual Instruction Tuningcited by 4,418
  10. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,234
  11. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,780
  12. 2024LLaVA-OneVision: Easy Visual Task Transfercited by 2,719
27 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. 2021Structured Denoising Diffusion Models in Discrete State-Spacescited by 1,719
  4. 2023MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Modelscited by 1,652
  5. 2022ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoningcited by 1,479
  6. 2020DocVQA: A Dataset for VQA on Document Imagescited by 1,317
  7. 2023SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehensioncited by 940
  8. 2025Large Language Diffusion Modelscited by 912
  9. 2024Simple and Effective Masked Diffusion Language Modelscited by 848
  10. 2016A Diagram Is Worth A Dozen Imagescited by 804
  11. 2024DeepSeek LLM: Scaling Open-Source Language Models with Longtermismcited by 642
  12. 2024Simplified and Generalized Masked Diffusion for Discrete Datacited by 626
  13. 2023Textbooks Are All You Need II: phi-1.5 technical reportcited by 565
  14. 2025Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decodingcited by 420
  15. 2024Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Datacited by 381
  16. 2025LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Modelscited by 285
  17. 2024Scaling Diffusion Language Models via Adaptation from Autoregressive Modelscited by 274
  18. 2025Remasking Discrete Diffusion Models with Inference-Time Scalingcited by 189
  19. 2025Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inferencecited by 178
  20. 2025dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Cachingcited by 169
  21. 2025LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuningcited by 148
  22. 2025dKV-Cache: The Cache for Diffusion Language Modelscited by 143
  23. 2024MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scalecited by 127
  24. 2025Dimple: Discrete Diffusion Multimodal Large Language Model with Parallel Decodingcited by 101
  25. 2025LaViDa: A Large Diffusion Language Model for Multimodal Understandingcited by 84
  26. 2025FlashDLM: Accelerating Diffusion Language Model Inference via Efficient KV Caching and Guided Diffusioncited by 77
  27. 2025Generalized Interpolating Discrete Diffusioncited by 70

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025Fine-Tuning Masked Diffusion for Provable Self-Correctioncited by 39
  2. 2026BARD: Bridging AutoRegressive and Diffusion Vision-Language Models Via Highly Efficient Progressive Block Merging and Stage-Wise Distillationcited by 2

Similar, not cited

Close in wording, no citation either way

  1. 2025From Denoising to Refining: A Corrective Framework for Vision-Language Diffusion Model
  2. 2025MDiff4STR: Mask Diffusion Model for Scene Text Recognition
  3. 2021Data Efficient Masked Language Modeling for Vision and Language
  4. 2025RedVTP: Training-Free Acceleration of Diffusion Vision-Language Models Inference via Masked Token-Guided Visual Token Pruning
  5. 2025SDAR-VL: Stable and Efficient Block-wise Diffusion for Vision-Language Understanding
  6. 2025Vision-Language-Vision Auto-Encoder: Scalable Knowledge Distillation from Diffusion Models
  7. 2025Diffusion-based Cumulative Adversarial Purification for Vision Language Models
  8. 2025DiffusionVL: Translating Any Autoregressive Models into Diffusion Vision Language Models