Score: 1

Language-Guided Temporal Token Pruning for Efficient VideoLLM Processing

Published: August 25, 2025 | arXiv ID: 2508.17686v1

By: Yogesh Kumar

Potential Business Impact:

Lets computers watch long videos faster.

Business Areas:
Natural Language Processing Artificial Intelligence, Data and Analytics, Software

Vision Language Models (VLMs) struggle with long-form videos due to the quadratic complexity of attention mechanisms. We propose Language-Guided Temporal Token Pruning (LGTTP), which leverages temporal cues from queries to adaptively prune video tokens, preserving contextual continuity while reducing computational overhead. Unlike uniform pruning or keyframe selection, LGTTP retains higher token density in temporally relevant segments. Our model-agnostic framework integrates with TimeChat and LLaVA-Video, achieving a 65% reduction in computation while preserving 97-99% of the original performance. On QVHighlights, LGTTP improves HIT@1 by +9.5%, and on Charades-STA, it retains 99.6% of R@1. It excels on queries with explicit temporal markers and remains effective across general video understanding tasks.

Country of Origin
🇮🇳 India

Repos / Data Links

Page Count
8 pages

Category
Computer Science:
CV and Pattern Recognition