# DTP: A Simple yet Effective Distracting Token Pruning Framework for Vision-Language Action Models

arXiv: https://arxiv.org/abs/2601.16065 · HTML: https://mlsanity.com/paper/2601.16065/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 16 of its 23 references that are in the map.
- First posted on arXiv 22 Jan 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)
- Vision-language-action models / [Efficient VLA inference and adaptation](https://mlsanity.com/vla/efficient-vla-inference-and-adaptation/)
- Efficient LLM inference and serving / [Visual token pruning in multimodal models](https://mlsanity.com/inference/visual-token-pruning-in-multimodal-models/)

## Builds on (most cited first, 16 of 16)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning](https://mlsanity.com/paper/2306.03310/) (2023)
- [EVA-CLIP: Improved Training Techniques for CLIP at Scale](https://mlsanity.com/paper/2303.15389/) (2023)
- [FAST: Efficient Action Tokenization for Vision-Language-Action Models](https://mlsanity.com/paper/2501.09747/) (2025)
- [Evaluating Real-World Robot Manipulation Policies in Simulation](https://mlsanity.com/paper/2405.05941/) (2024)
- [Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models](https://mlsanity.com/paper/2402.07865/) (2024)
- [Unified Vision-Language-Action Model](https://mlsanity.com/paper/2506.19850/) (2025)
- [NORA: A Small Open-Sourced Generalist Vision Language Action Model for Embodied Tasks](https://mlsanity.com/paper/2504.19854/) (2025)
- [Evo-0: Vision-Language-Action Model with Implicit Spatial Understanding](https://mlsanity.com/paper/2507.00416/) (2025)
- [OTTER: A Vision-Language-Action Model with Text-Aware Visual Feature Extraction](https://mlsanity.com/paper/2503.03734/) (2025)
- [Run-time Observation Interventions Make Vision-Language-Action Models More Visually Robust](https://mlsanity.com/paper/2410.01971/) (2024)
- [STARE-VLA: Progressive Stage-Aware Reinforcement for Fine-Tuning Vision-Language-Action Models](https://mlsanity.com/paper/2512.05107/) (2025)

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

- [Overcoming Visual Clutter in Vision Language Action Models via Concept-Gated Visual Distillation](https://mlsanity.com/paper/2603.10340/) (2026)
- [Embodied Interpretability: Linking Causal Understanding to Generalization in Vision-Language-Action Models](https://mlsanity.com/paper/2605.00321/) (2026)
- [Robust Bimanual Vision-Language-Action Models via Embarrassingly Simple Modality Masking](https://mlsanity.com/paper/2608.22419/) (2026)
- [A Deformable Attention-Based Detection Transformer with Cross-Scale Feature Fusion for Industrial Coil Spring Inspection](https://mlsanity.com/paper/2603.13429/) (2026)
- [Rank-Consistent Set Reasoning for Co-Salient Object Detection](https://mlsanity.com/paper/2609.13706/) (2026)
- [OGAM: Connecting Systematic Testing to Runtime Assurance through Object-Grounded Attention Monitoring for VLA Policies](https://mlsanity.com/paper/2610.05878/) (2026)
- [DIVA: Dual-Space Intent-Aware Visual Attenuation for Vision-Language-Action Policies](https://mlsanity.com/paper/2610.09144/) (2026)
- [BridgeWAM: Bridging Video and Action Experts via Latent Bridge Queries](https://mlsanity.com/paper/2610.14746/) (2026)

## Abstract (arXiv)

Vision-Language Action (VLA) models have shown remarkable progress in robotic manipulation by leveraging the powerful perception abilities of Vision-Language Models (VLMs) to understand environments and directly output actions. However, by default, VLA models may overly attend to image tokens in the task-irrelevant region, which we describe as 'distracting tokens'. This behavior can disturb the model from the generation of the desired action tokens in each step, affecting the success rate of tasks. In this paper, we introduce a simple yet effective plug-and-play Distracting Token Pruning (DTP) framework, which dynamically detects and prunes these distracting image tokens. By correcting the model's visual attention patterns, we aim to improve the task success rate, as well as exploring the performance upper boundaries of the model without altering its original architecture or adding additional inputs. Experiments on the SIMPLER Benchmark (Li et al., 2024) show that our method consistently achieving relative improvements in task success rates across different types of novel VLA models, demonstrating generalizability to transformer-based VLAs. Further analysis reveals a negative correlation between the task success rate and the amount of attentions in the task-irrelevant region for all models tested, highlighting a common phenomenon of VLA models that could guide future research. We also publish our code at: https://anonymous.4open.science/r/CBD3.