# Policy Contrastive Decoding for Robotic Foundation Models

arXiv: https://arxiv.org/abs/2505.13255 · HTML: https://mlsanity.com/paper/2505.13255/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning and post-training, one of 13 directions in Vision-language-action models.
- Builds on 46 of its 55 references that are in the map.
- First posted on arXiv 19 May 2025.

## Placed in

- Vision-language-action models / [Reinforcement learning and post-training](https://mlsanity.com/vla/reinforcement-learning-and-post-training/)

## Builds on (most cited first, 30 of 46)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [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)
- [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)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [Octo: An Open-Source Generalist Robot Policy](https://mlsanity.com/paper/2405.12213/) (2024)
- [LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning](https://mlsanity.com/paper/2306.03310/) (2023)
- [Resolution-robust Large Mask Inpainting with Fourier Convolutions](https://mlsanity.com/paper/2109.07161/) (2021)
- [RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation](https://mlsanity.com/paper/2410.07864/) (2024)
- [Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding](https://mlsanity.com/paper/2311.16922/) (2023)
- [FAST: Efficient Action Tokenization for Vision-Language-Action Models](https://mlsanity.com/paper/2501.09747/) (2025)
- [SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model](https://mlsanity.com/paper/2501.15830/) (2025)
- [YOLO-World: Real-Time Open-Vocabulary Object Detection](https://mlsanity.com/paper/2401.17270/) (2024)
- [Evaluating Real-World Robot Manipulation Policies in Simulation](https://mlsanity.com/paper/2405.05941/) (2024)
- [CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models](https://mlsanity.com/paper/2503.22020/) (2025)
- [Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning](https://mlsanity.com/paper/2306.14565/) (2023)
- [A Survey of Hallucination in Large Foundation Models](https://mlsanity.com/paper/2309.05922/) (2023)
- [Robotic Control via Embodied Chain-of-Thought Reasoning](https://mlsanity.com/paper/2407.08693/) (2024)
- [Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models](https://mlsanity.com/paper/2402.07865/) (2024)
- [Detecting and Preventing Hallucinations in Large Vision Language Models](https://mlsanity.com/paper/2308.06394/) (2023)

## Built on by (most cited first, 8 of 8)

- [Shortcut Learning in Generalist Robot Policies: The Role of Dataset Diversity and Fragmentation](https://mlsanity.com/paper/2508.06426/) (2025)
- [SCALE: Self-uncertainty Conditioned Adaptive Looking and Execution for Vision-Language-Action Models](https://mlsanity.com/paper/2602.04208/) (2026)
- [What to Ignore, What to React: Visually Robust RL Fine-Tuning of VLA Models](https://mlsanity.com/paper/2605.13105/) (2026)
- [Self-Improving VLA Policies: Selected Diffusion Noise for Spurious-Robust Action Smoothing](https://mlsanity.com/paper/2606.14084/) (2026)
- [Sim-and-Human Co-training for Data-Efficient and Scene-Generalizable Bimanual Manipulation](https://mlsanity.com/paper/2601.19406/) (2026)
- [Beyond the Majority: Long-tail Imitation Learning for Robotic Manipulation](https://mlsanity.com/paper/2602.06512/) (2026)
- [Scale Up Strategically: Learning Compositional Generalization via Bias-Aware Evaluation and Data Collection for Robotic Manipulation](https://mlsanity.com/paper/2607.21582/) (2026)
- [Beyond Appearance Shifts: Task-Semantic Action Calibration for VLA Models](https://mlsanity.com/paper/2609.23650/) (2026)

## Abstract (arXiv)

Robotic foundation models, or generalist robot policies, hold immense potential to enable flexible, general-purpose and dexterous robotic systems. Despite their advancements, our empirical experiments reveal that existing robot policies are prone to learning spurious correlations from pre-training trajectories, adversely affecting their generalization capabilities beyond the training data. To tackle this, we propose a novel Policy Contrastive Decoding (PCD) approach, which redirects the robot policy's focus toward object-relevant visual clues by contrasting action probability distributions derived from original and object-masked visual inputs. As a training-free method, our PCD can be used as a plugin to improve different types of robot policies without needing to finetune or access model weights. We conduct extensive experiments on top of three open-source robot policies, including the autoregressive policy OpenVLA and the diffusion-based policies Octo and π0. The obtained results in both simulation and real-world environments prove PCD's flexibility and effectiveness, e.g., PCD enhances the state-of-the-art policy π0 by 8.9% in the simulation environment and by 108% in the real-world environment. Code and demos are publicly available at: https://koorye.github.io/PCD.