A Glimpse to Compress: Dynamic Visual Token Pruning for Large Vision-Language Models. https://github.com/HVision-NKU/GlimpsePrune
Quan-Sheng Zeng (SII)
ashun989
·
AI & ML interests
None yet
Recent Activity
upvoted a paper 1 day ago
Direct 3D-Aware Object Insertion via Decomposed Visual Proxies upvoted a paper 8 days ago
COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation liked a dataset 3 months ago
AudioVisual-Caption/ASID-1MOrganizations
None yet
models 5
ashun989/GlimpsePrune-Plus_Qwen2.5-VL-7B-Instruct
Updated
ashun989/GlimpsePrune_LLaVA-1.5-7B
Image-Text-to-Text • Updated • 2
ashun989/GlimpsePrune-LLaVA-1.5-13B
Image-Text-to-Text • Updated
ashun989/GlimpsePrune_Qwen2.5-VL-3B-Instruct
Image-Text-to-Text • Updated • 4 • 2
ashun989/GlimpsePrune_Qwen2.5-VL-7B-Instruct
Image-Text-to-Text • Updated • 9 • 2
datasets 0
None public yet