# PEAfowl: Perception-Enhanced Multi-View Vision-Language-Action for Bimanual Manipulation

arXiv: https://arxiv.org/abs/2601.17885 · HTML: https://mlsanity.com/paper/2601.17885/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in 3D and spatial-aware VLA, one of 13 directions in Vision-language-action models.
- Builds on 32 of its 39 references that are in the map.
- First posted on arXiv 25 Jan 2026.

## Placed in

- Vision-language-action models / [3D and spatial-aware VLA](https://mlsanity.com/vla/3d-and-spatial-aware-vla/)

## Builds on (most cited first, 30 of 32)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (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)
- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware](https://mlsanity.com/paper/2304.13705/) (2023)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [Octo: An Open-Source Generalist Robot Policy](https://mlsanity.com/paper/2405.12213/) (2024)
- [MVSNet: Depth Inference for Unstructured Multi-view Stereo](https://mlsanity.com/paper/1804.02505/) (2018)
- [RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation](https://mlsanity.com/paper/2410.07864/) (2024)
- [Perceiver IO: A General Architecture for Structured Inputs & Outputs](https://mlsanity.com/paper/2107.14795/) (2021)
- [SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model](https://mlsanity.com/paper/2501.15830/) (2025)
- [RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation](https://mlsanity.com/paper/2506.18088/) (2025)
- [ReZero is All You Need: Fast Convergence at Large Depth](https://mlsanity.com/paper/2003.04887/) (2020)
- [RVT: Robotic View Transformer for 3D Object Manipulation](https://mlsanity.com/paper/2306.14896/) (2023)
- [RVT-2: Learning Precise Manipulation from Few Demonstrations](https://mlsanity.com/paper/2406.08545/) (2024)
- [RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twins](https://mlsanity.com/paper/2504.13059/) (2025)
- [ClearCLIP: Decomposing CLIP Representations for Dense Vision-Language Inference](https://mlsanity.com/paper/2407.12442/) (2024)
- [Multi-View Masked World Models for Visual Robotic Manipulation](https://mlsanity.com/paper/2302.02408/) (2023)
- [GeoVLA: Empowering 3D Representations in Vision-Language-Action Models](https://mlsanity.com/paper/2508.09071/) (2025)
- [OTTER: A Vision-Language-Action Model with Text-Aware Visual Feature Extraction](https://mlsanity.com/paper/2503.03734/) (2025)
- [FP3: A 3D Foundation Policy for Robotic Manipulation](https://mlsanity.com/paper/2503.08950/) (2025)
- [CLIP-RT: Learning Language-Conditioned Robotic Policies from Natural Language Supervision](https://mlsanity.com/paper/2411.00508/) (2024)
- [Manipulation as in Simulation: Enabling Accurate Geometry Perception in Robots](https://mlsanity.com/paper/2509.02530/) (2025)
- [3D-MVP: 3D Multiview Pretraining for Robotic Manipulation](https://mlsanity.com/paper/2406.18158/) (2024)
- [BFA: Best-Feature-Aware Fusion for Multi-View Fine-grained Manipulation](https://mlsanity.com/paper/2502.11161/) (2025)
- [SEM: Enhancing Spatial Understanding for Robust Robot Manipulation](https://mlsanity.com/paper/2505.16196/) (2025)

## Built on by (most cited first, 6 of 6)

- [GuidedVLA: Specifying Task-Relevant Factors via Plug-and-Play Action Attention Specialization](https://mlsanity.com/paper/2605.12369/) (2026)
- [Improving Robustness of Vision-Language-Action Models by Restoring Corrupted Visual Inputs](https://mlsanity.com/paper/2602.01158/) (2026)
- [DepthCache: Depth-Guided Training-Free Visual Token Merging for Vision-Language-Action Model Inference](https://mlsanity.com/paper/2603.10469/) (2026)
- [GRAFT: Grounded and Efficient Online Reinforcement Adaptation for Fine-Grained Robot Manipulation](https://mlsanity.com/paper/2608.27079/) (2026)
- [TAO-DA: Towards Autonomous Operation--A Dual-Arm Vision-Language-Action Model for Coordinated Manipulation](https://mlsanity.com/paper/2609.33197/) (2026)
- [VersaCamVLA: Camera-Configurable VLA Policies for Robotic Manipulation](https://mlsanity.com/paper/2610.12451/) (2026)

## Abstract (arXiv)

Bimanual manipulation in cluttered scenes requires policies that remain stable under occlusions, viewpoint changes and scene variations. Existing vision-language-action models often lack such robustness because (i) multi-view features are fused via view-agnostic token concatenation, yielding limited cross-view spatial representations, and (ii) language is injected as global conditioning, resulting in coarse instruction grounding. In this paper, we introduce PEAfowl, a perception-enhanced multi-view VLA policy for bimanual manipulation. For spatial perception, PEAfowl predicts per-token depth distributions, performs differentiable 3D lifting, and aggregates local cross-view neighbors to form geometrically grounded, cross-view aligned representations. For language utilization, we propose to replace global conditioning with a Perceiver-style text-aware readout over frozen CLIP visual features, enabling iterative evidence accumulation. To better exploit commodity RGB-D sensing despite noisy and incomplete depth, PEAfowl's depth-distribution lifting naturally supports training-only depth distillation, where a pretrained depth teacher supervises the depth-distribution head to inject refined geometric priors without adding inference overhead. On RoboTwin 2.0 under domain-randomized setting, PEAfowl improves the strongest baseline by 23.0 pp in success rate, and physical experiments further demonstrate improved performance on the evaluated real-robot tasks. Project website: https://peafowlvla.github.io/.