# TTF-VLA: Temporal Token Fusion via Pixel-Attention Integration for Vision-Language-Action Models

arXiv: https://arxiv.org/abs/2508.19257 · HTML: https://mlsanity.com/paper/2508.19257/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Placed in Efficient VLA inference and adaptation, one of 13 directions in Vision-language-action models.
- Builds on 10 of its 22 references that are in the map.
- First posted on arXiv 15 Aug 2025.

## Placed in

- Vision-language-action models / [Efficient VLA inference and adaptation](https://mlsanity.com/vla/efficient-vla-inference-and-adaptation/)

## Builds on (most cited first, 10 of 10)

- [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)
- [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)
- [Token Merging: Your ViT But Faster](https://mlsanity.com/paper/2210.09461/) (2022)
- [DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification](https://mlsanity.com/paper/2106.02034/) (2021)
- [Evaluating Real-World Robot Manipulation Policies in Simulation](https://mlsanity.com/paper/2405.05941/) (2024)
- [SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference](https://mlsanity.com/paper/2410.04417/) (2024)

## Built on by (most cited first, 12 of 12)

- [MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulation](https://mlsanity.com/paper/2508.19236/) (2025)
- [Pure Vision Language Action (VLA) Models: A Comprehensive Survey](https://mlsanity.com/paper/2509.19012/) (2025)
- [Efficient Vision-Language-Action Models for Embodied Manipulation: A Systematic Survey](https://mlsanity.com/paper/2510.17111/) (2025)
- [SwiftVLA: Unlocking Spatiotemporal Dynamics for Lightweight VLA Models at Minimal Overhead](https://mlsanity.com/paper/2512.00903/) (2025)
- [Towards Generalizable Robotic Manipulation in Dynamic Environments](https://mlsanity.com/paper/2603.15620/) (2026)
- [Mask World Model: Predicting What Matters for Robust Robot Policy Learning](https://mlsanity.com/paper/2604.19683/) (2026)
- [MemoryVLA++: Temporal Modeling via Memory and Imagination in Vision-Language-Action Models](https://mlsanity.com/paper/2606.09827/) (2026)
- [Token Expand-Merge: Training-Free Token Compression for Vision-Language-Action Models](https://mlsanity.com/paper/2512.09927/) (2025)
- [Efficient Long-Horizon Vision-Language-Action Models via Static-Dynamic Disentanglement](https://mlsanity.com/paper/2602.03983/) (2026)
- [DA-PTQ: Drift-Aware Post-Training Quantization for Efficient Vision-Language-Action Models](https://mlsanity.com/paper/2604.11572/) (2026)
- [StateMem: Single-State Residual Memory with Adaptive Inference for Vision-Language-Action Policies](https://mlsanity.com/paper/2609.22684/) (2026)
- [FailPatch: Failure Residual Patching for Vision-Language-Action Models](https://mlsanity.com/paper/2609.34175/) (2026)

## Abstract (arXiv)

Vision-Language-Action (VLA) models process visual inputs independently at each timestep, discarding valuable temporal information inherent in robotic manipulation tasks. This frame-by-frame processing makes models vulnerable to visual noise while ignoring the substantial coherence between consecutive frames in manipulation sequences. We propose Temporal Token Fusion (TTF), a training-free approach that intelligently integrates historical and current visual representations to enhance VLA inference quality. Our method employs dual-dimension detection combining efficient grayscale pixel difference analysis with attention-based semantic relevance assessment, enabling selective temporal token fusion through hard fusion strategies and keyframe anchoring to prevent error accumulation. Comprehensive experiments across LIBERO, SimplerEnv, and real robot tasks demonstrate consistent improvements: 4.0 percentage points average on LIBERO (72.4% vs 68.4% baseline), cross-environment validation on SimplerEnv (4.8% relative improvement), and 8.7% relative improvement on real robot tasks. Our approach proves model-agnostic, working across OpenVLA and VLA-Cache architectures. Notably, TTF reveals that selective Query matrix reuse in attention mechanisms enhances rather than compromises performance, suggesting promising directions for direct KQV matrix reuse strategies that achieve computational acceleration while improving task success rates.