# SymVD: Symmetric Vision Language Action Distillation for Robot Manipulation

arXiv: https://arxiv.org/abs/2608.29828 · HTML: https://mlsanity.com/paper/2608.29828/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reinforcement learning and post-training, one of 13 directions in Vision-language-action models.
- Builds on 18 of its 24 references that are in the map.
- First posted on arXiv 30 Aug 2026.

## Placed in

- Vision-language-action models / [Reinforcement learning and post-training](https://mlsanity.com/vla/reinforcement-learning-and-post-training/)
- Deep reinforcement learning methods / [RL for robot locomotion and manipulation](https://mlsanity.com/deeprl/rl-for-robot-locomotion-and-manipulation/)

## Builds on (most cited first, 18 of 18)

- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes](https://mlsanity.com/paper/2306.13649/) (2023)
- [QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation](https://mlsanity.com/paper/1806.10293/) (2018)
- [General E(2)-Equivariant Steerable CNNs](https://mlsanity.com/paper/1911.08251/) (2019)
- [Policy Distillation](https://mlsanity.com/paper/1511.06295/) (2015)
- [Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learning](https://mlsanity.com/paper/1910.11956/) (2019)
- [ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL](https://mlsanity.com/paper/2402.19446/) (2024)
- [Foundation Models in Robotics: Applications, Challenges, and the Future](https://mlsanity.com/paper/2312.07843/) (2023)
- [Steering Your Generalists: Improving Robotic Foundation Models via Value Guidance](https://mlsanity.com/paper/2410.13816/) (2024)
- [Provably Strict Generalisation Benefit for Equivariant Models](https://mlsanity.com/paper/2102.10333/) (2021)
- [Policy Agnostic RL: Offline RL and Online RL Fine-Tuning of Any Class and Backbone](https://mlsanity.com/paper/2412.06685/) (2024)
- [RLDG: Robotic Generalist Policy Distillation via Reinforcement Learning](https://mlsanity.com/paper/2412.09858/) (2024)
- [Equivariant Transporter Network](https://mlsanity.com/paper/2202.09400/) (2022)
- [Robot Learning in the Era of Foundation Models: A Survey](https://mlsanity.com/paper/2311.14379/) (2023)
- [Adaptive Behavior Cloning Regularization for Stable Offline-to-Online Reinforcement Learning](https://mlsanity.com/paper/2210.13846/) (2022)
- [Group Equivariant Deep Reinforcement Learning](https://mlsanity.com/paper/2007.03437/) (2020)
- [Refined Policy Distillation: From VLA Generalists to RL Experts](https://mlsanity.com/paper/2503.05833/) (2025)
- [Transferring Foundation Models for Generalizable Robotic Manipulation](https://mlsanity.com/paper/2306.05716/) (2023)

## Abstract (arXiv)

While pretrained Vision-Language-Action (VLA) models offer broad generalization capabilities in robotic manipulation tasks, adapting them to real-world environments or handling task shifts often requires substantial additional data and retraining. To address this, we propose Symmetric VLA Distillation (SymVD), a distillation framework that transfers knowledge from a large VLA teacher to a compact student policy by explicitly exploiting geometric symmetries in manipulation tasks, such as rotational and reflectional invariance. SymVD employs an equivariant actor-critic architecture and trains the student using a symmetry-aware objective that aligns with teacher actions under group-invariant properties. We demonstrate that by enforcing the policy to respect equivariance, SymVD reduces redundant exploration across configurations related by group transformations and improves sample efficiency during distillation. To further stabilize and improve distillation, SymVD introduces an adaptive weighting scheme that dynamically balances the distillation objective and reinforcement learning updates based on training progress, enabling robust transfer even when the teacher signal is imperfect or misaligned. Experimental results on robotic manipulation tasks demonstrate that SymVD consistently improves over standard distillation and also outperforms SAC in terms of sample efficiency and generalization to previously unseen symmetric transformations of the environment.