State of Vision-Language-Action (VLA) Research at ICLR 2026 – Moritz Reuss
ICLR’s open submission policy gives a rare, real-time view of what the community is actually building. This post distills the state of Vision-Language-Action (VLA) Models research slice of ICLR 2026: what ‘counts’ as a VLA (and why that definition matters), what people are working on in the VLA field (discrete diffusion, embodied reasoning, new tokenizers), how to read benchmark results in VLA research, and the not-so-invisible frontier gap that sim leaderboards hide. Each autumn, the ICLR publicly releases all anonymous submissions a few weeks after the deadline, providing a unique real-time snapshot of ongoing research around the world without the typical six-month delay of other top ML conferences. Given my personal research interests, I wanted to analyze Vision-Language-Action (VLA) Models research and share insights from this year's submissions. In this blog post, I briefly explain what VLAs are, share my findings about current trends and challenges in VLA research, highlighting
State of Vision-Language-Action (VLA) Research at ICLR 2026 – Moritz Reuss State of VLA Research at ICLR 2026 October 2025 • by Moritz Reuss ICLR’s open submission policy gives a rare, real-time view of what the community is actually building. This post distills the state of Vision-Language-Action (VLA) Models research slice of ICLR 2026: what ‘counts’ as a VLA (and why that definition matters), what people are working on in the VLA field (discrete diffusion, embodied reasoning, new tokenizers), how to read benchmark results in VLA research, and the not-so-invisible frontier gap that sim leade
saved by
related reading
- Moritz Reuss — Robotics & VLA Researchmbreuss.github.io
- [2602.10098] VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Modelarxiv.org
- State of Robot Learning, December 2025vedder.io
- Pretrained to Imagine, Fine-Tuned to Act: The Rise of World-Action Models | NVIDIA Technical Blogdeveloper.nvidia.com
- Vision-Language-Action (VLA) Models: A Review of Recent Progressxxxxyu.github.io
- World Action Model Atlasjoeclinton.me
- What Matters for Latent Actions in Robot Learningcarldegio.github.io
- Natural Language Autoencoders \ Anthropicanthropic.com
- State of RL for reasoning LLMs | A. Weersaweers.de
- Natural Language Autoencoders Produce Unsupervised Explanations of LLM Activationstransformer-circuits.pub
- SimpleVLA-RL: Scaling VLA Training via Reinforcement Learningalphaxiv.org
- Sparse Autoencoders Reveal Interpretable and Steerable Features in VLA Modelsarxiv.org