# VLA architectures and generalization

Area: [Vision-language-action models](https://mlsanity.com/vla/index.md). HTML: https://mlsanity.com/vla/vla-architectures-and-generalization/

## Key facts

- VLA architectures and generalization: 43 papers on arXiv since 2024 (data through 7 Oct 2026).
- 4 of its 43 mapped papers (9%) cite “Don't Blind Your VLA: Aligning Visual Representations for OOD Generalization” (2025, arXiv 2510.25616).
- 3 of its 43 mapped papers (7%) cite “A Survey on Vision-Language-Action Models: An Action Tokenization Perspective” (2025, arXiv 2507.01925).
- 13 new papers 17 Sep–7 Oct.

## Most cited here

- [Don't Blind Your VLA: Aligning Visual Representations for OOD Generalization](https://mlsanity.com/paper/2510.25616/) (2025), cited by 4 papers here
- [A Survey on Vision-Language-Action Models: An Action Tokenization Perspective](https://mlsanity.com/paper/2507.01925/) (2025), cited by 3 papers here
- [Emergent World Representations in OpenVLA](https://mlsanity.com/paper/2509.24559/) (2025), cited by 3 papers here
- [VLM4VLA: Revisiting Vision-Language-Models in Vision-Language-Action Models](https://mlsanity.com/paper/2601.03309/) (2026), cited by 3 papers here
- [Seeing to Act, Prompting to Specify: A Bayesian Factorization of Vision Language Action Policy](https://mlsanity.com/paper/2512.11218/) (2025), cited by 2 papers here
- [OmniJARVIS: Unified Vision-Language-Action Tokenization Enables Open-World Instruction Following Agents](https://mlsanity.com/paper/2407.00114/) (2024), cited by 1 papers here
- [NORA-1.5: A Vision-Language-Action Model Trained using World Model- and Action-based Preference Rewards](https://mlsanity.com/paper/2511.14659/) (2025), cited by 1 papers here
- [MAPS: Preserving Vision-Language Representations via Module-Wise Proximity Scheduling for Better Vision-Language-Action Generalization](https://mlsanity.com/paper/2511.19878/) (2025), cited by 1 papers here
- [VLANeXt: Recipes for Building Strong VLA Models](https://mlsanity.com/paper/2602.18532/) (2026), cited by 1 papers here
- [Observing and Controlling Features in Vision-Language-Action Models](https://mlsanity.com/paper/2603.05487/) (2026), cited by 1 papers here

## New (17 Sep–7 Oct)

- [Do Vision-Language-Action Models Understand Instructions? A Mechanistic Interpretability Study on Language Grounding](https://mlsanity.com/paper/2610.10178/) (2026-10-07)
- [DIVA: Dual-Space Intent-Aware Visual Attenuation for Vision-Language-Action Policies](https://mlsanity.com/paper/2610.09144/) (2026-10-06)
- [PAIR: Bridging Perception and Action in Vision-Language-Action Models](https://mlsanity.com/paper/2610.09016/) (2026-10-06)
- [PermVLA: Factorization Order as a Regularizer for VLA Learning](https://mlsanity.com/paper/2610.04659/) (2026-10-03)
- [Continuous Conditioning of VLAs with Augmenting EMG and Visual Task Descriptors](https://mlsanity.com/paper/2610.01794/) (2026-10-01)
- [Disentangling Spurious Correlations in Vision-Language-Action Models via Predicting Domain-Invariant Latent Lookahead](https://mlsanity.com/paper/2609.37165/) (2026-09-29)
- [LexiconVLA: Learning Reusable Atomic Action Codebooks for Unseen Tasks](https://mlsanity.com/paper/2609.36774/) (2026-09-29)
- [The Layer Mystery of VLA: An Information-Theoretical Analysis of VLA Latent Interface](https://mlsanity.com/paper/2609.36118/) (2026-09-28)
- [Does Adversarial Training Improve Generalization in Multi-View VLAs? Revealing and Mitigating View Collapse](https://mlsanity.com/paper/2609.33707/) (2026-09-27)
- [Train Together or Merge Later? Unifying VLA Experts via a Shared Action Interface](https://mlsanity.com/paper/2609.33125/) (2026-09-27)
- [The Linear Representation Hypothesis for Vision-Language-Action Models](https://mlsanity.com/paper/2609.30996/) (2026-09-25)
- [CereVLA: Cerebellum-Inspired Consequence-Aware Residual Governance for Efficient Vision-Language-Action Execution](https://mlsanity.com/paper/2609.27468/) (2026-09-23)
- [VLAQuantBench: Closed-Loop Evaluation of Post-Training Quantization for Vision-Language-Action Models](https://mlsanity.com/paper/2609.25376/) (2026-09-21)