ST-SimDiff: Balancing Spatiotemporal Similarity and Difference for Efficient Video Understanding with MLLMs

• URL: http://arxiv.org/abs/2605.22158v1
• Date: Thu, 21 May 2026 08:27:15 GMT
• Title: ST-SimDiff: Balancing Spatiotemporal Similarity and Difference for Efficient Video Understanding with MLLMs
• Abstract summary: We develop a training-free framework named ST-Sim-Diff to handle complex video relationships.<n>Our method significantly outperforms state-of-the-art approaches while substantially reducing computational costs.
• Score: 20.712141528369553
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multimodal Large Language Models (MLLMs) face significant computational overhead when processing long videos due to the massive number of visual tokens required. To improve efficiency, existing methods primarily reduce redundancy by pruning or merging tokens based on importance or similarity. However, these approaches largely overlook a critical dimension of video content, i.e., changes and turning points, and they lack a collaborative model for spatio-temporal relationships. To address this, we propose a new perspective: similarity is for identifying redundancy, while difference is for capturing key events. Based on this, we designed a training-free framework named ST-SimDiff. We first construct a spatio-temporal graph from the visual tokens to uniformly model their complex associations. Subsequently, we employ a parallel dual-selection strategy: 1) similarity-based selection uses community detection to retain representative tokens, compressing static information; 2) temporal difference-based selection precisely locates content-changing points to preserve tokens that capture key dynamic shifts. This allows it to preserve both static and dynamic content with a minimal number of tokens. Extensive experiments show our method significantly outperforms state-of-the-art approaches while substantially reducing computational costs. Our code is available in https://github.com/bingjunluo/ST-SimDiff.

Related papers

• YOSE: You Only Select Essential Tokens for Efficient DiT-based Video Object Removal [83.78619790270523]
  YOSE introduces two key components: Batch Variable-length Indexing (BVI) and Diffusion Process Simulator (DiffSim) Module.<n>BVI selects essential tokens based on mask information enabling variable-length token processing across samples.<n>DiffSim provides a diffusion process approximation mechanism for unmasked tokens.<n>Experiments demonstrate YOSE achieves up to 2.5X speedup in 70% of cases.
  arXiv  Detail & Related papers  (2026-04-30T02:08:13Z)
• 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)
• MomentSeg: Moment-Centric Sampling for Enhanced Video Pixel Understanding [40.37010049965347]
  Referring Video Object (RefVOS) seeks to segment target objects in videos guided by natural language descriptions.<n>We propose a unified framework that jointly optimize Temporal Sentence Grounding (TSG) and RefVOS, naturally incorporating key moment grounding capability.
  arXiv  Detail & Related papers  (2025-10-10T11:18:21Z)
• VQToken: Neural Discrete Token Representation Learning for Extreme Token Reduction in Video Large Language Models [35.38573641029626]
  We introduce the novel task of Extreme Short Token Reduction, which aims to represent entire videos using a minimal set of discrete tokens.<n>On the Extreme Short Token Reduction task, our VQToken compresses sequences to just 0.07 percent of their original length while incurring only a 0.66 percent drop in accuracy on the NextQA-MC benchmark.
  arXiv  Detail & Related papers  (2025-03-21T09:46:31Z)
• The Devil is in Temporal Token: High Quality Video Reasoning Segmentation [68.33080352141653]
  Methods for Video Reasoning rely heavily on a single special token to represent the object in the video.<n>We propose VRS-HQ, an end-to-end video reasoning segmentation approach.<n>Our results highlight the strong temporal reasoning and segmentation capabilities of our method.
  arXiv  Detail & Related papers  (2025-01-15T03:17:24Z)
• Sparsity Meets Similarity: Leveraging Long-Tail Distribution for Dynamic Optimized Token Representation in Multimodal Large Language Models [6.467840081978855]
  multimodal large language models (MM-LLMs) have achieved significant success in various tasks.<n>Main computational burden arises from processingd text and visual tokens.<n>We propose a dynamic pruning algorithm that identifies the inflection point in the visual CLS token similarity curve.
  arXiv  Detail & Related papers  (2024-09-02T10:49:10Z)
• SIGMA:Sinkhorn-Guided Masked Video Modeling [69.31715194419091]
  Sinkhorn-guided Masked Video Modelling ( SIGMA) is a novel video pretraining method. We distribute features of space-time tubes evenly across a limited number of learnable clusters. Experimental results on ten datasets validate the effectiveness of SIGMA in learning more performant, temporally-aware, and robust video representations.
  arXiv  Detail & Related papers  (2024-07-22T08:04:09Z)
• LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models [35.88374542519597]
  Large Multimodal Models (LMMs) have shown significant visual reasoning capabilities by connecting a visual encoder and a large language model. Recent LMMs incorporate more complex visual inputs, such as high-resolution images and videos, which further increases the number of visual tokens significantly. We propose PruMerge, a novel adaptive visual token reduction strategy that significantly reduces the number of visual tokens without compromising the performance of LMMs.
  arXiv  Detail & Related papers  (2024-03-22T17:59:52Z)
• CenterCLIP: Token Clustering for Efficient Text-Video Retrieval [67.21528544724546]
  In CLIP, the essential visual tokenization process, which produces discrete visual token sequences, generates many homogeneous tokens due to the redundancy nature of consecutive frames in videos. This significantly increases computation costs and hinders the deployment of video retrieval models in web applications. In this paper, we design a multi-segment token clustering algorithm to find the most representative tokens and drop the non-essential ones.
  arXiv  Detail & Related papers  (2022-05-02T12:02:09Z)
• VIMPAC: Video Pre-Training via Masked Token Prediction and Contrastive Learning [82.09856883441044]
  Video understanding relies on perceiving the global content modeling its internal connections. We propose a block-wise strategy where we mask neighboring video tokens in both spatial and temporal domains. We also add an augmentation-free contrastive learning method to further capture global content.
  arXiv  Detail & Related papers  (2021-06-21T16:48:19Z)
• Efficient Transformer based Method for Remote Sensing Image Change Detection [17.553240434628087]
  High-resolution remote sensing CD remains challenging due to the complexity of objects in the scene. We propose a bitemporal image transformer (BiT) to efficiently and effectively model contexts within the spatial-temporal domain. BiT-based model significantly outperforms the purely convolutional baseline using only 3 times lower computational costs and model parameters.
  arXiv  Detail & Related papers  (2021-02-27T13:08:46Z)

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.