Spatio-Temporal Token Pruning for Efficient High-Resolution GUI Agents

• URL: http://arxiv.org/abs/2602.23235v1
• Date: Thu, 26 Feb 2026 17:12:40 GMT
• Title: Spatio-Temporal Token Pruning for Efficient High-Resolution GUI Agents
• Authors: Zhou Xu, Bowen Zhou, Qi Wang, Shuwen Feng, Jingyu Xiao,
• Abstract summary: GUIPruner is a training-free framework tailored for high-resolution GUI navigation.<n>It synergizes Temporal-temporal Resolution (TAR) and Stratified Structure-aware Pruning (SSP)<n>It consistently achieves state-of-the-art performance, effectively preventing the collapse observed in large-scale models under high-resolution compression.
• Score: 10.559617160878227
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Pure-vision GUI agents provide universal interaction capabilities but suffer from severe efficiency bottlenecks due to the massive spatiotemporal redundancy inherent in high-resolution screenshots and historical trajectories. We identify two critical misalignments in existing compression paradigms: the temporal mismatch, where uniform history encoding diverges from the agent's "fading memory" attention pattern, and the spatial topology conflict, where unstructured pruning compromises the grid integrity required for precise coordinate grounding, inducing spatial hallucinations. To address these challenges, we introduce GUIPruner, a training-free framework tailored for high-resolution GUI navigation. It synergizes Temporal-Adaptive Resolution (TAR), which eliminates historical redundancy via decay-based resizing, and Stratified Structure-aware Pruning (SSP), which prioritizes interactive foregrounds and semantic anchors while safeguarding global layout. Extensive evaluations across diverse benchmarks demonstrate that GUIPruner consistently achieves state-of-the-art performance, effectively preventing the collapse observed in large-scale models under high compression. Notably, on Qwen2-VL-2B, our method delivers a 3.4x reduction in FLOPs and a 3.3x speedup in vision encoding latency while retaining over 94% of the original performance, enabling real-time, high-precision navigation with minimal resource consumption.

Related papers

• Rethinking Multi-Condition DiTs: Eliminating Redundant Attention via Position-Alignment and Keyword-Scoping [61.459927600301654]
  Multi-condition control is bottlenecked by the conventional concatenate-and-attend'' strategy.<n>Our analysis reveals that much of this cross-modal interaction is spatially or semantically redundant.<n>We propose Position-aligned and Keyword-scoped Attention (PKA), a highly efficient framework designed to eliminate these redundancies.
  arXiv  Detail & Related papers  (2026-02-06T16:39:10Z)
• PPMStereo: Pick-and-Play Memory Construction for Consistent Dynamic Stereo Matching [51.98089287914147]
  textbfPick-and-textbflay textbfMemory (PM) construction module for dynamic bfStereo matching, dubbed as bftextPPMStereo.<n>Inspired by the two-stage decision-making process in humans, we propose a textbfPick-and-textbflay textbfMemory (PM) construction module for dynamic bfStereo matching, dubbed as bftextPPMStereo.
  arXiv  Detail & Related papers  (2025-10-23T03:52:39Z)
• Towards Robust and Generalizable Continuous Space-Time Video Super-Resolution with Events [71.2439653098351]
  Continuous space-time video super-STVSR has garnered increasing interest for its capability to reconstruct high-resolution and high-frame-rate videos at arbitrary temporal scales.<n>We present EvEnhancer, a novel approach that marries unique properties of high temporal and high dynamic range encapsulated in event streams.<n>Our method achieves state-of-the-art performance on both synthetic and real-world datasets, while maintaining generalizability at OOD scales.
  arXiv  Detail & Related papers  (2025-10-04T15:23:07Z)
• DVLO4D: Deep Visual-Lidar Odometry with Sparse Spatial-temporal Fusion [28.146811420532455]
  We introduce DVLO4D, a novel visual-LiDAR odometry framework that leverages sparse spatial-temporal fusion to enhance accuracy and robustness.<n>Our method has high efficiency, with an inference time of 82 ms, possessing the potential for the real-time deployment.
  arXiv  Detail & Related papers  (2025-09-07T11:43:11Z)
• Occupancy Learning with Spatiotemporal Memory [39.41175479685905]
  We propose a scene-level occupancy representation learning framework that effectively learns 3D occupancy feature with temporal consistency.<n>Our method significantly enhances thetemporal representation learned for 3D occupancy prediction tasks by exploiting the temporal dependency between multi-frame inputs.
  arXiv  Detail & Related papers  (2025-08-06T17:59:52Z)
• Ultra3D: Efficient and High-Fidelity 3D Generation with Part Attention [54.15345846343084]
  We propose Ultra3D, an efficient 3D generation framework that significantly accelerates sparse voxel modeling without compromising quality.<n>Part Attention is a geometry-aware localized attention mechanism that restricts attention computation within semantically consistent part regions.<n>Experiments demonstrate that Ultra3D supports high-resolution 3D generation at 1024 resolution and achieves state-of-the-art performance in both visual fidelity and user preference.
  arXiv  Detail & Related papers  (2025-07-23T17:57:16Z)
• EfficientVLA: Training-Free Acceleration and Compression for Vision-Language-Action Models [21.42353501209045]
  Vision-Language-Action (VLA) models demonstrate transformative potential for embodied intelligence but are severely hampered by high computational and memory demands.<n>We introduce EfficientVLA, a structured and training-free inference acceleration framework.<n>We apply our method to a standard VLA model CogACT, yielding a 1.93X inference speedup and reduces FLOPs to 28.9%, with only a 0.6% success rate drop in the SIMPLER benchmark.
  arXiv  Detail & Related papers  (2025-06-11T18:34:57Z)
• Fully Spiking Neural Networks for Unified Frame-Event Object Tracking [17.626181371045575]
  We propose the first fully Spiking Frame-Event Tracking framework called SpikeFET.<n>This network achieves synergistic integration of convolutional local feature extraction and Transformer-based global modeling within the spiking paradigm.<n>We show that proposed framework achieves superior tracking accuracy over existing methods while significantly reducing power consumption.
  arXiv  Detail & Related papers  (2025-05-27T07:53:50Z)
• Temporal Feature Matters: A Framework for Diffusion Model Quantization [105.3033493564844]
  Diffusion models rely on the time-step for the multi-round denoising.<n>We introduce a novel quantization framework that includes three strategies.<n>This framework preserves most of the temporal information and ensures high-quality end-to-end generation.
  arXiv  Detail & Related papers  (2024-07-28T17:46:15Z)
• HDNet: High-resolution Dual-domain Learning for Spectral Compressive Imaging [138.04956118993934]
  We propose a high-resolution dual-domain learning network (HDNet) for HSI reconstruction. On the one hand, the proposed HR spatial-spectral attention module with its efficient feature fusion provides continuous and fine pixel-level features. On the other hand, frequency domain learning (FDL) is introduced for HSI reconstruction to narrow the frequency domain discrepancy.
  arXiv  Detail & Related papers  (2022-03-04T06:37:45Z)

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.