Unified Spatio-Temporal Token Scoring for Efficient Video VLMs

• URL: http://arxiv.org/abs/2603.18004v1
• Date: Wed, 18 Mar 2026 17:59:56 GMT
• Title: Unified Spatio-Temporal Token Scoring for Efficient Video VLMs
• Abstract summary: Token pruning is essential for enhancing the computational efficiency of vision-language models.<n>We introduce Spatio-Temporal Token Scoring (STTS), a simple and lightweight module that prunes vision tokens across both the ViT and the LLM.<n>STTS prunes 50% of vision tokens throughout the entire architecture, resulting in a 62% improvement in efficiency during both training and inference.
• Score: 61.08183446817756
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Token pruning is essential for enhancing the computational efficiency of vision-language models (VLMs), particularly for video-based tasks where temporal redundancy is prevalent. Prior approaches typically prune tokens either (1) within the vision transformer (ViT) exclusively for unimodal perception tasks such as action recognition and object segmentation, without adapting to downstream vision-language tasks; or (2) only within the LLM while leaving the ViT output intact, often requiring complex text-conditioned token selection mechanisms. In this paper, we introduce Spatio-Temporal Token Scoring (STTS), a simple and lightweight module that prunes vision tokens across both the ViT and the LLM without text conditioning or token merging, and is fully compatible with end-to-end training. By learning how to score temporally via an auxiliary loss and spatially via LLM downstream gradients, aided by our efficient packing algorithm, STTS prunes 50% of vision tokens throughout the entire architecture, resulting in a 62% improvement in efficiency during both training and inference with only a 0.7% drop in average performance across 13 short and long video QA tasks. Efficiency gains increase with more sampled frames per video. Applying test-time scaling for long-video QA further yields performance gains of 0.5-1% compared to the baseline. Overall, STTS represents a novel, simple yet effective technique for unified, architecture-wide vision token pruning.

Related papers

• Decoupled Similarity for Task-Aware Token Pruning in Large Vision-Language Models [73.07332521794093]
  Token pruning has emerged as an effective approach to reduce the substantial computational overhead of Large Vision-Language Models.<n>We propose DeSAP, a novel Decoupled Similarity-Aware Pruning method for precise, task-aware token pruning within the visual encoder.<n>DeSAP consistently outperforms SOTA methods in both accuracy and efficiency.
  arXiv  Detail & Related papers  (2026-04-13T09:44:52Z)
• TrajTok: Learning Trajectory Tokens enables better Video Understanding [63.1260672430712]
  Tokenization in video models, typically through patchification, generates an excessive and redundant number of tokens.<n>We propose TrajTok, an end-to-end video tokenizer module that is fully integrated and co-trained with video models for a downstream objective.<n>We show that it can be seamlessly integrated as either a probing head for pretrained visual features (TrajAdapter) or an alignment connector in vision-language models (TrajVLM) with especially strong performance in long-video reasoning.
  arXiv  Detail & Related papers  (2026-02-26T09:15:34Z)
• ViCA: Efficient Multimodal LLMs with Vision-Only Cross-Attention [22.397648349603696]
  ViCA is a minimal MLLM architecture in which visual tokens bypass all self-attention and feed-forward layers, interacting with text solely through sparse cross-attention at selected layers.<n>ViCA preserves 98% of baseline accuracy while reducing visual-side to 4%, consistently achieving superior performance-efficiency trade-offs.
  arXiv  Detail & Related papers  (2026-02-07T14:46:05Z)
• Nüwa: Mending the Spatial Integrity Torn by VLM Token Pruning [82.39668822222386]
  Vision token pruning has proven to be an effective acceleration technique for the efficient Vision Language Model (VLM)<n>We propose $textNwa$, a two-stage token pruning framework that enables efficient feature aggregation while maintaining spatial integrity.<n>Experiments demonstrate that $textNwa$ achieves SOTA performance on multiple VQA benchmarks (from 94% to 95%) and yields substantial improvements on visual grounding tasks (from 7% to 47%)
  arXiv  Detail & Related papers  (2026-02-03T00:51:03Z)
• Fast SAM2 with Text-Driven Token Pruning [52.8350457627401]
  Segment Anything Model 2 (SAM2), a vision computation model has significantly advanced in prompt-driven video object segmentation.<n>SAM2 pipelines propagate all visual tokens produced by the image encoder through downstream temporal reasoning modules, regardless of their relevance to the target object.<n>We introduce a text-guided token pruning framework that improves inference efficiency by selectively reducing token density prior to temporal propagation.
  arXiv  Detail & Related papers  (2025-12-24T18:59:05Z)
• Variation-aware Vision Token Dropping for Faster Large Vision-Language Models [24.952668143243542]
  Large vision-language models (LVLMs) have demonstrated remarkable capabilities in multimodal understanding tasks.<n> Token compression offers a direct solution by reducing the number of tokens to be processed, thereby improving computational efficiency.<n>We propose Variation-aware Vision Token Dropping (textiti.e., textbfV$2$Drop), which progressively removes visual tokens with minimal variation during LVLM inference.
  arXiv  Detail & Related papers  (2025-09-01T15:28:44Z)
• HoliTom: Holistic Token Merging for Fast Video Large Language Models [32.620504076794795]
  Video language models (video LLMs) excel at video comprehension but face significant computational inefficiency due to redundant video tokens.<n>We introduce HoliTom, a novel training-free holistic token framework.<n>We also introduce a robust inner-LLM token similarity-based merging approach, designed for superior performance and compatibility with outer-LLM pruning.
  arXiv  Detail & Related papers  (2025-05-27T15:28:45Z)
• DyMU: Dynamic Merging and Virtual Unmerging for Efficient VLMs [124.52164183968145]
  We present DyMU, an efficient, training-free framework that reduces the computational burden of vision-language models (VLMs)<n>Our approach comprises two key components. First, Dynamic Token Merging (DToMe) reduces the number of visual token embeddings by merging similar tokens based on image complexity.<n>Second, Virtual Token Unmerging (VTU) simulates the expected token sequence for large language models (LLMs) by efficiently reconstructing the attention dynamics of a full sequence.
  arXiv  Detail & Related papers  (2025-04-23T18:38:18Z)
• InternVL-X: Advancing and Accelerating InternVL Series with Efficient Visual Token Compression [1.8893427856534721]
  We propose InternVL-X, which outperforms the InternVL model in both performance and efficiency.<n>By utilizing 20% or fewer visual tokens, InternVL-X achieves state-of-the-art performance on 7 public MLLM benchmarks, and improves the average metric by 2.34% across 12 tasks.
  arXiv  Detail & Related papers  (2025-03-27T09:31:35Z)
• 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)

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.