Adaptive Two-Stage Visual Token Pruning for Efficient Inference in Video-Language Models

• URL: http://arxiv.org/abs/2608.03112v1
• Date: Tue, 04 Aug 2026 04:32:48 GMT
• Title: Adaptive Two-Stage Visual Token Pruning for Efficient Inference in Video-Language Models
• Abstract summary: Vision-language models excel at image and video understanding but suffer from high inference latency.<n>We propose a two-stage adaptive token pruning strategy specifically designed for video processing.<n>Our method is entirely post-hoc and requires no additional training or fine-tuning, while achieving strong empirical gains.
• Score: 6.202364388194408
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Vision-language models excel at image and video understanding but suffer from high inference latency due to the need to process thousands of tokens per image, limiting their deployment on resource-constrained edge devices and in real-time surveillance applications. This challenge is further amplified in video processing, where multiple frames must be analyzed simultaneously. Existing token reduction techniques are largely developed for single-image inputs and therefore fail to account for the temporal and inter-frame redundancies present in video sequences. In addition, these methods generally rely on a fixed, uniform pruning ratio applied across all inputs, which is suboptimal because the degree of redundancy can vary significantly between different videos, necessitating content-dependent pruning levels to preserve critical information. To address these limitations, we propose a two-stage adaptive token pruning strategy specifically designed for video processing. In the first stage, we prune out the redundant frames, and in the second stage, token-level pruning is applied within the retained frames. Crucially, the pruning ratio in the second stage is determined adaptively based on the content of each video. This is achieved by analyzing the correlation structure of token embeddings to quantify redundancy, which is used to determine the ratio. Importantly, our method is entirely post-hoc and requires no additional training or fine-tuning, while achieving strong empirical gains; notably, it improves accuracy by +7\% on a video captioning benchmark at 10\% token retention, while reducing computation TFLOPs by 95\%.

Related papers

• Adaptive Tokenisation Via Temporal Redundancy Masking And Latent Inpainting [18.71433885255431]
  Adaptive video tokenisation seeks to dynamically allocate token budgets based on the underlying visual complexity of a sequence.<n>We show that the latent space of a frozen continuous video tokeniser inherently encodes temporal redundancy that can be exploited directly.<n>We introduce a parameter-free adaptive token allocation mechanism that applies a fixed threshold to per-position temporal-L1 differences.
  arXiv  Detail & Related papers  (2026-06-04T13:31:12Z)
• PARE: Pruning and Adaptive Routing for Efficient Video Generation [71.54959622788608]
  Video Diffusion Transformers (DiTs) generate high-quality videos but demand substantial compute due to wide blocks, deep architectures, and iterative sampling.<n>Recent methods reduce cost by compressing width, depth, or sampling steps, but typically commit to a fixed architecture that cannot adapt to individual inputs or denoising stages.<n>We propose PARE, which jointly compresses width and depth with structure-aware pruning and input-adaptive routing.
  arXiv  Detail & Related papers  (2026-05-26T17:43:25Z)
• StreamingAssistant: Efficient Visual Token Pruning for Accelerating Online Video Understanding [29.539015046656615]
  We propose token pruning as a means to reduce context length while retaining critical information.<n>Specifically, we introduce a novel redundancy metric, Maximum Similarity to Spatially Adjacent Video Tokens (MSSAVT)<n>We also design a masked pruning strategy that ensures only mutually unadjacent tokens are pruned.
  arXiv  Detail & Related papers  (2025-12-14T05:35:11Z)
• Dense Video Understanding with Gated Residual Tokenization [49.17263029080152]
  High temporal resolution is essential for capturing fine-grained details in video understanding.<n>Current benchmarks rely mostly on low-frame-rate sampling.<n>Dense Video Understanding (DVU) enables high-FPS video comprehension by reducing both tokenization time and token overhead.
  arXiv  Detail & Related papers  (2025-09-17T17:34:40Z)
• FullDiT2: Efficient In-Context Conditioning for Video Diffusion Transformers [63.788600404496115]
  FullDiT2 is an efficient in-context conditioning framework for general controllability in both video generation and editing tasks.<n>FullDiT2 achieves significant computation reduction and 2-3 times speedup in averaged time cost per diffusion step.
  arXiv  Detail & Related papers  (2025-06-04T17:57:09Z)
• VideoScan: Enabling Efficient Streaming Video Understanding via Frame-level Semantic Carriers [23.541896057977745]
  VideoScan is an efficient vision-language model (VLM) inference framework for real-time video interaction.<n>VideoScan employs a single semantic carrier token to represent each frame.
  arXiv  Detail & Related papers  (2025-03-12T13:30:40Z)
• Transform-Equivariant Consistency Learning for Temporal Sentence Grounding [66.10949751429781]
  We introduce a novel Equivariant Consistency Regulation Learning framework to learn more discriminative representations for each video. Our motivation comes from that the temporal boundary of the query-guided activity should be consistently predicted. In particular, we devise a self-supervised consistency loss module to enhance the completeness and smoothness of the augmented video.
  arXiv  Detail & Related papers  (2023-05-06T19:29:28Z)
• ASCNet: Self-supervised Video Representation Learning with Appearance-Speed Consistency [62.38914747727636]
  We study self-supervised video representation learning, which is a challenging task due to 1) a lack of labels for explicit supervision and 2) unstructured and noisy visual information. Existing methods mainly use contrastive loss with video clips as the instances and learn visual representation by discriminating instances from each other. In this paper, we observe that the consistency between positive samples is the key to learn robust video representations.
  arXiv  Detail & Related papers  (2021-06-04T08:44:50Z)
• Temporal Distinct Representation Learning for Action Recognition [139.93983070642412]
  Two-Dimensional Convolutional Neural Network (2D CNN) is used to characterize videos. Different frames of a video share the same 2D CNN kernels, which may result in repeated and redundant information utilization. We propose a sequential channel filtering mechanism to excite the discriminative channels of features from different frames step by step, and thus avoid repeated information extraction. Our method is evaluated on benchmark temporal reasoning datasets Something-Something V1 and V2, and it achieves visible improvements over the best competitor by 2.4% and 1.3%, respectively.
  arXiv  Detail & Related papers  (2020-07-15T11:30:40Z)

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.