A training-free two-stage token compression framework preserves 92.9% of Qwen2.5-Omni-7B's audio-visual understanding accuracy while using 6.8% of the original multimodal-token FLOPs.
Unified spatiotemporal token compression for video-llms at ultra-low retention
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
OmniPack: Unified Token Compression for Efficient Omni-modal Large Language Models
A training-free two-stage token compression framework preserves 92.9% of Qwen2.5-Omni-7B's audio-visual understanding accuracy while using 6.8% of the original multimodal-token FLOPs.