# Distillation for Efficient Multitask Manipulation Policies via Conditional Flow Matching

arXiv: https://arxiv.org/abs/2609.28107 · HTML: https://mlsanity.com/paper/2609.28107/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Diffusion and flow policies for robotics, one of 14 directions in Diffusion models.
- Builds on 14 of its 19 references that are in the map.
- First posted on arXiv 23 Sep 2026.

## Placed in

- Diffusion models / [Diffusion and flow policies for robotics](https://mlsanity.com/diffusion/diffusion-and-flow-policies-for-robotics/)

## Builds on (most cited first, 14 of 14)

- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware](https://mlsanity.com/paper/2304.13705/) (2023)
- [GR00T N1: An Open Foundation Model for Generalist Humanoid Robots](https://mlsanity.com/paper/2503.14734/) (2025)
- [RLBench: The Robot Learning Benchmark & Learning Environment](https://mlsanity.com/paper/1909.12271/) (2019)
- [SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics](https://mlsanity.com/paper/2506.01844/) (2025)
- [Learning Robotic Manipulation Policies from Point Clouds with Conditional Flow Matching](https://mlsanity.com/paper/2409.07343/) (2024)
- [DiWA: Diffusion Policy Adaptation with World Models](https://mlsanity.com/paper/2508.03645/) (2025)
- [Knowledge Amalgamation from Heterogeneous Networks by Common Feature Learning](https://mlsanity.com/paper/1906.10546/) (2019)
- [Mitigating Negative Transfer in Multi-Task Learning with Exponential Moving Average Loss Weighting Strategies](https://mlsanity.com/paper/2211.12999/) (2022)
- [CoVAR: Co-generation of Video and Action for Robotic Manipulation via Multi-Modal Diffusion](https://mlsanity.com/paper/2512.16023/) (2025)
- [cVLA: Towards Efficient Camera-Space VLAs](https://mlsanity.com/paper/2507.02190/) (2025)
- [Scaling Single Human Demonstrations for Imitation Learning using Generative Foundational Models](https://mlsanity.com/paper/2602.12734/) (2026)

## Abstract (arXiv)

Advances in generative modeling have recently been extensively employed in robotics for policy learning. In particular, Conditional Flow Matching (CFM) trained with expert demonstrations has been shown to outperform existing methods on robot manipulation benchmarks. While prior work has mainly focused on single-task settings, we study the problem from a multi-task perspective, as training independent models for each task is computationally expensive. Multi-Task policy learning comes with its own set of challenges, as naively training on a concatenated dataset of demonstrations would either require increased model capacity to accommodate the added complexity or result in drops in performance. We propose to distill knowledge from single-task CFM experts into a shared multi-task policy by transferring their learned velocity fields. We combine this distillation signal with the original CFM objective to retain fidelity to the demonstrations. Experiments on RLBench show that our approach improves multi-task policy performance over naive training while maintaining a fixed model size.