# Towards Human-Like Manipulation through RL-Augmented Teleoperation and Mixture-of-Dexterous-Experts VLA

arXiv: https://arxiv.org/abs/2603.08122 · HTML: https://mlsanity.com/paper/2603.08122/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Human-video and latent-action pretraining, one of 13 directions in Vision-language-action models.
- Builds on 36 of its 42 references that are in the map.
- First posted on arXiv 9 Mar 2026.

## Placed in

- Vision-language-action models / [Human-video and latent-action pretraining](https://mlsanity.com/vla/human-video-and-latent-action-pretraining/)

## Builds on (most cited first, 30 of 36)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [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)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware](https://mlsanity.com/paper/2304.13705/) (2023)
- [Scaling Vision with Sparse Mixture of Experts](https://mlsanity.com/paper/2106.05974/) (2021)
- [PaliGemma: A versatile 3B VLM for transfer](https://mlsanity.com/paper/2407.07726/) (2024)
- [DexMV: Imitation Learning for Dexterous Manipulation from Human Videos](https://mlsanity.com/paper/2108.05877/) (2021)
- [DexCap: Scalable and Portable Mocap Data Collection System for Dexterous Manipulation](https://mlsanity.com/paper/2403.07788/) (2024)
- [AnyTeleop: A General Vision-Based Dexterous Robot Arm-Hand Teleoperation System](https://mlsanity.com/paper/2307.04577/) (2023)
- [Open-TeleVision: Teleoperation with Immersive Active Visual Feedback](https://mlsanity.com/paper/2407.01512/) (2024)
- [In-Hand Object Rotation via Rapid Motor Adaptation](https://mlsanity.com/paper/2210.04887/) (2022)
- [Reactive Diffusion Policy: Slow-Fast Visual-Tactile Policy Learning for Contact-Rich Manipulation](https://mlsanity.com/paper/2503.02881/) (2025)
- [A Pragmatic VLA Foundation Model](https://mlsanity.com/paper/2601.18692/) (2026)
- [ForceVLA: Enhancing VLA Models with a Force-aware MoE for Contact-rich Manipulation](https://mlsanity.com/paper/2505.22159/) (2025)
- [Vision-Language-Action (VLA) Models: Concepts, Progress, Applications and Challenges](https://mlsanity.com/paper/2505.04769/) (2025)
- [3D-ViTac: Learning Fine-Grained Manipulation with Visuo-Tactile Sensing](https://mlsanity.com/paper/2410.24091/) (2024)
- [Shared Autonomy via Deep Reinforcement Learning](https://mlsanity.com/paper/1802.01744/) (2018)
- [Sparsh: Self-supervised touch representations for vision-based tactile sensing](https://mlsanity.com/paper/2410.24090/) (2024)
- [ForceMimic: Force-Centric Imitation Learning with Force-Motion Capture System for Contact-Rich Manipulation](https://mlsanity.com/paper/2410.07554/) (2024)
- [FoAR: Force-Aware Reactive Policy for Contact-Rich Robotic Manipulation](https://mlsanity.com/paper/2411.15753/) (2024)
- [TA-VLA: Elucidating the Design Space of Torque-aware Vision-Language-Action Models](https://mlsanity.com/paper/2509.07962/) (2025)
- [Touch in the Wild: Learning Fine-Grained Manipulation with a Portable Visuo-Tactile Gripper](https://mlsanity.com/paper/2507.15062/) (2025)
- [Dexterous Manipulation through Imitation Learning: A Survey](https://mlsanity.com/paper/2504.03515/) (2025)
- [Vision-based Teleoperation of Shadow Dexterous Hand using End-to-End Deep Neural Network](https://mlsanity.com/paper/1809.06268/) (2018)

## Built on by (most cited first, 5 of 5)

- [World Model for Robot Learning: A Comprehensive Survey](https://mlsanity.com/paper/2605.00080/) (2026)
- [From Foundation to Application: Improving VLA Models in Practice](https://mlsanity.com/paper/2607.06403/) (2026)
- [Learning Physical Interaction: A Survey of Tactile- and Force-aware Robot Learning](https://mlsanity.com/paper/2608.07558/) (2026)
- [Assistron: Bayesian Shared Autonomy with Off-the-shelf Vision-Language-Action Models](https://mlsanity.com/paper/2606.23147/) (2026)
- [DexTaG: Tactile-as-Guidance in Reinforcement Learning for Dexterous Manipulation](https://mlsanity.com/paper/2609.33882/) (2026)

## Abstract (arXiv)

While Vision-Language-Action (VLA) models have demonstrated remarkable success in robotic manipulation, their application has largely been confined to low-degree-of-freedom end-effectors performing simple, vision-guided pick-and-place tasks. Extending these models to human-like, bimanual dexterous manipulation-specifically contact-rich in-hand operations-introduces critical challenges in high-fidelity data acquisition, multi-skill learning, and multimodal sensory fusion. In this paper, we propose an integrated framework to address these bottlenecks, built upon two components. First, we introduce IMCopilot (In-hand Manipulation Copilot), a suite of reinforcement learning-trained atomic skills that plays a dual role: it acts as a shared-autonomy assistant to simplify teleoperation data collection, and it serves as a callable low-level execution primitive for the VLA. Second, we present MoDE-VLA (Mixture-of-Dexterous-Experts VLA), an architecture that seamlessly integrates heterogeneous force and tactile modalities into a pretrained VLA backbone. By utilizing a residual injection mechanism, MoDE-VLA enables contact-aware refinement without degrading the model's pretrained knowledge. We validate our approach on four tasks of escalating complexity, demonstrating doubled success rate improvement over the baseline in dexterous contact-rich tasks.