MuCRASP prunes VLMs in a CoT-aware manner, outperforming baselines by preserving reasoning quality at 30-50% compression rates on models like Qwen2.5-VL-7B.
InEuro- pean conference on computer vision, pages 235–251
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Zigzag persistent homology on layer-wise hidden-state point clouds guides adaptive layer pruning of LVLMs and reportedly beats prior pruning methods across sparsity levels.
citing papers explorer
-
MuCRASP: Multimodal Chain-of-thought Reasoning aware Structured Pruning
MuCRASP prunes VLMs in a CoT-aware manner, outperforming baselines by preserving reasoning quality at 30-50% compression rates on models like Qwen2.5-VL-7B.
-
Topology-Aware Layer Pruning for Large Vision-Language Models
Zigzag persistent homology on layer-wise hidden-state point clouds guides adaptive layer pruning of LVLMs and reportedly beats prior pruning methods across sparsity levels.