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

• URL: http://arxiv.org/abs/2508.19257v1
• Date: Fri, 15 Aug 2025 12:03:34 GMT
• Title: TTF-VLA: Temporal Token Fusion via Pixel-Attention Integration for Vision-Language-Action Models
• Authors: Chenghao Liu, Jiachen Zhang, Chengxuan Li, Zhimu Zhou, Shixin Wu, Songfang Huang, Huiling Duan,
• Abstract summary: Vision-Language-Action (VLA) models process visual inputs independently at each timestep, discarding valuable temporal information inherent in robotic manipulation tasks.<n>We propose Temporal Token Fusion (TTF), a training-free approach that integrates historical and current visual representations to enhance VLA inference quality.
• Score: 29.878993349922368
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• BFA++: Hierarchical Best-Feature-Aware Token Prune for Multi-View Vision Language Action Model [44.72361174037017]
  Vision-Language-Action (VLA) models have achieved significant breakthroughs by leveraging Large Vision Language Models (VLMs) to jointly interpret instructions and visual inputs.<n>The substantial increase in visual tokens, particularly from multi-view inputs, poses serious challenges to real-time robotic manipulation.<n>We propose BFA++, a dynamic token pruning framework designed specifically for VLA models.
  arXiv  Detail & Related papers  (2026-02-24T05:31:52Z)
• Global Prior Meets Local Consistency: Dual-Memory Augmented Vision-Language-Action Model for Efficient Robotic Manipulation [95.89924101984566]
  We introduce OptimusVLA, a dual-memory VLA framework with Global Prior Memory (GPM) and Local Consistency Memory (LCM)<n>GPM replaces Gaussian noise with task-level priors retrieved from semantically similar trajectories.<n>LCM injects a learned consistency constraint that enforces temporal coherence and smoothness of trajectory.
  arXiv  Detail & Related papers  (2026-02-22T15:39:34Z)
• FASTer: Toward Efficient Autoregressive Vision Language Action Modeling via Neural Action Tokenization [61.10456021136654]
  We introduce FASTer, a unified framework for efficient and general robot learning.<n>FASTerVQ encodes action chunks as single-channel images, capturing global-temporal dependencies while maintaining a high compression ratio.<n>FASTerVLA builds on this tokenizer with block-wise autoregressive decoding and a lightweight action expert, achieving both faster inference and higher task performance.
  arXiv  Detail & Related papers  (2025-12-04T16:21:38Z)
• ContextVLA: Vision-Language-Action Model with Amortized Multi-Frame Context [54.58057019521198]
  Leveraging temporal context is crucial for success in partially observable robotic tasks.<n>Prior work in behavior cloning has demonstrated inconsistent performance gains when using multi-frame observations.<n>We introduce ContextVLA, a policy model that robustly improves robotic task performance by effectively leveraging multi-frame observations.
  arXiv  Detail & Related papers  (2025-10-05T15:29:57Z)
• dVLA: Diffusion Vision-Language-Action Model with Multimodal Chain-of-Thought [66.78110237549087]
  Vision-Language-Action (VLA) models are emerging as a next-generation paradigm for robotics.<n>We introduce dVLA, a diffusion-based VLA that unifies visual perception, language reasoning, and robotic control in a single system.
  arXiv  Detail & Related papers  (2025-09-30T02:36:11Z)
• Action-aware Dynamic Pruning for Efficient Vision-Language-Action Manipulation [27.007611140797852]
  Existing methods optimize inference speed by reducing visual redundancy within VLA models.<n>We propose textbfAction-aware textbfDynamic textbfPruning (textbfADP), a multi-modal pruning framework that integrates text-driven token selection with action-aware trajectory gating.
  arXiv  Detail & Related papers  (2025-09-26T09:13:02Z)
• CronusVLA: Transferring Latent Motion Across Time for Multi-Frame Prediction in Manipulation [67.1520483301709]
  CronusVLA is a unified framework that extends single-frame VLA models to the multi-frame paradigm through an efficient post-training stage.<n>CronusVLA achieves state-of-the-art performance on SimplerEnv with 70.9% success rate, and 12.7% improvement over OpenVLA on LIBERO.
  arXiv  Detail & Related papers  (2025-06-24T17:30:27Z)
• SP-VLA: A Joint Model Scheduling and Token Pruning Approach for VLA Model Acceleration [69.54069477520534]
  Vision-Language-Action (VLA) models have attracted increasing attention for their strong control capabilities.<n>Their high computational cost and low execution frequency hinder their suitability for real-time tasks such as robotic manipulation and autonomous navigation.<n>We propose SP-VLA, a unified framework that accelerates VLA models by jointly scheduling models and pruning tokens.
  arXiv  Detail & Related papers  (2025-06-15T05:04:17Z)
• Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models [30.7855782696894]
  Vision-Language-Action (VLA) models have emerged as a powerful paradigm for general-purpose robot control through natural language instructions.<n>We propose FlashVLA, the first training-free and plug-and-play acceleration framework that enables action reuse in VLA models.
  arXiv  Detail & Related papers  (2025-05-27T13:47:18Z)
• Skip-Vision: Efficient and Scalable Acceleration of Vision-Language Models via Adaptive Token Skipping [13.846838416902575]
  A key bottleneck stems from the proliferation of visual tokens required for fine-grained image understanding.<n>We propose Skip-Vision, a unified framework addressing both training and inference inefficiencies in vision-language models.<n> Experimental results demonstrate that Skip-Vision reduces training time by up to 35%, inference FLOPs by 75%, and latency by 45%.
  arXiv  Detail & Related papers  (2025-03-26T04:16:48Z)
• Transformer Meets Twicing: Harnessing Unattended Residual Information [2.1605931466490795]
  Transformer-based deep learning models have achieved state-of-the-art performance across numerous language and vision tasks.<n>While the self-attention mechanism has proven capable of handling complex data patterns, it has been observed that the representational capacity of the attention matrix degrades significantly across transformer layers.<n>We propose the Twicing Attention, a novel attention mechanism that uses kernel twicing procedure in nonparametric regression to alleviate the low-pass behavior of associated NLM smoothing.
  arXiv  Detail & Related papers  (2025-03-02T01:56:35Z)
• VeCAF: Vision-language Collaborative Active Finetuning with Training Objective Awareness [56.87603097348203]
  VeCAF uses labels and natural language annotations to perform parametric data selection for PVM finetuning. VeCAF incorporates the finetuning objective to select significant data points that effectively guide the PVM towards faster convergence. On ImageNet, VeCAF uses up to 3.3x less training batches to reach the target performance compared to full finetuning.
  arXiv  Detail & Related papers  (2024-01-15T17:28:37Z)
• Domain Adaptive Robotic Gesture Recognition with Unsupervised Kinematic-Visual Data Alignment [60.31418655784291]
  We propose a novel unsupervised domain adaptation framework which can simultaneously transfer multi-modality knowledge, i.e., both kinematic and visual data, from simulator to real robot. It remedies the domain gap with enhanced transferable features by using temporal cues in videos, and inherent correlations in multi-modal towards recognizing gesture. Results show that our approach recovers the performance with great improvement gains, up to 12.91% in ACC and 20.16% in F1score without using any annotations in real robot.
  arXiv  Detail & Related papers  (2021-03-06T09:10:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.