mlsanityData to 14 Oct 2026

LoopVL: Recurrent Visual Intelligence

arXiv 2609.38426 ↗First posted 29 Sep 2026cs.CV cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

We introduce LoopVL to study whether Loop Transformers can be effectively extended to vision- language models. LoopVL combines Module-Loop and Model-Loop computation to iteratively update a unified vision-language state through shared modules. We train LoopVL from scratch through language pre-training, multimodal training, and post-training. LoopVL outperforms a range of similarly sized and larger non-recurrent models on multimodal understanding and visual reasoning benchmarks. We also observe Visual Aha Moments in LoopVL, characterized by pronounced shifts in visual attention across loops. LoopVL provides practical evidence for recurrent vision-language modeling and offers an intuitive perspective on how shared parameters can support deeper multimodal computation over continuously evolving visual-language states.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 51 of its 55 references that are in the map. First posted on arXiv 29 Sep 2026.

Builds on

51 of 55 references.

References · 51

  1. 2020Scaling Laws for Neural Language Modelscited by 6,586
  2. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,137
  3. 2023Improved Baselines with Visual Instruction Tuningcited by 4,418
  4. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,386
  5. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,234
  6. 2022Training Compute-Optimal Large Language Modelscited by 3,019
  7. 2019ALBERT: A Lite BERT for Self-supervised Learning of Language Representationscited by 2,790
  8. 2019Attention is not Explanationcited by 929
  9. 2020Quantifying Attention Flow in Transformerscited by 775
  10. 2025Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Modelscited by 665
  11. 2018Universal Transformerscited by 647
  12. 2024An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Modelscited by 642
38 more
  1. 2019Designing and Interpreting Probes with Control Taskscited by 640
  2. 2019Attention is not not Explanationcited by 636
  3. 2023Eliciting Latent Predictions from Transformers with the Tuned Lenscited by 623
  4. 2019Deep Equilibrium Modelscited by 615
  5. 2016Adaptive Computation Time for Recurrent Neural Networkscited by 506
  6. 2025Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approachcited by 415
  7. 2023Scaling Data-Constrained Language Modelscited by 403
  8. 2025LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Trainingcited by 244
  9. 2025Reasoning with Latent Thoughts: On the Power of Looped Transformerscited by 240
  10. 2023Looped Transformers as Programmable Computerscited by 237
  11. 2023Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolutioncited by 229
  12. 2022Recurrent Memory Transformercited by 203
  13. 2023Honeybee: Locality-enhanced Projector for Multimodal LLMcited by 197
  14. 2024LLaVA-UHD: an LMM Perceiving Any Aspect Ratio and High-Resolution Imagescited by 195
  15. 2025Hierarchical Reasoning Modelcited by 177
  16. 2023Beyond Chinchilla-Optimal: Accounting for Inference in Language Model Scaling Lawscited by 159
  17. 2023Looped Transformers are Better at Learning Learning Algorithmscited by 149
  18. 2025Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computationcited by 133
  19. 2015Neural GPUs Learn Algorithmscited by 121
  20. 2021Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networkscited by 117
  21. 2019On Identifiability in Transformerscited by 116
  22. 2022Block-Recurrent Transformerscited by 110
  23. 2016Hierarchical Multiscale Recurrent Neural Networkscited by 104
  24. 2024Looped Transformers for Length Generalizationcited by 99
  25. 2021The Efficiency Misnomercited by 98
  26. 2024Relaxed Recursive Transformers: Effective Parameter Sharing with Layer-wise LoRAcited by 78
  27. 2014A Clockwork RNNcited by 72
  28. 2024Can Looped Transformers Learn to Implement Multi-step Gradient Descent for In-context Learning?cited by 65
  29. 2024MoEUT: Mixture-of-Experts Universal Transformerscited by 59
  30. 2026A Mechanistic Analysis of Looped Reasoning Language Modelscited by 33
  31. 2025Latent Chain-of-Thought? Decoding the Depth-Recurrent Transformercited by 27
  32. 2026How Much Is One Recurrence Worth? Iso-Depth Scaling Laws for Looped Language Modelscited by 24
  33. 2026LoopViT: Scaling Visual ARC with Looped Transformerscited by 15
  34. 2025Hierarchical Reasoning Models: Perspectives and Misconceptionscited by 13
  35. 2025Tiny Recursive Models on ARC-AGI-1: Inductive Biases, Identity Conditioning, and Test-Time Computecited by 9
  36. 2026HRM-Text: Efficient Pretraining Beyond Scalingcited by 9
  37. 2026Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoderscited by 7
  38. 2025RingFormer: Rethinking Recurrent Transformer with Adaptive Level Signalscited by 6

50 most cited of 51 All 51 (JSON)

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Looping Back to Move Forward: Recursive Transformers for Efficient and Flexible Large Multimodal Models
  2. 2024NPHardEval4V: Dynamic Evaluation of Large Vision-Language Models with Effects of Vision
  3. 2024UniBench: Visual Reasoning Requires Rethinking Vision-Language Beyond Scaling
  4. 2026LoopVLA: Learning Sufficiency in Recurrent Refinement for Vision-Language-Action Models
  5. 2026Dynamo: Dynamic Skill-Tool Evolution for Vision-Language Agents
  6. 2023ReForm-Eval: Evaluating Large Vision Language Models via Unified Re-Formulation of Task-Oriented Benchmarks
  7. 2024Enhancing Advanced Visual Reasoning Ability of Large Language Models
  8. 2026Youtu-VL: Unleashing Visual Potential via Unified Vision-Language Supervision