Showing 2025Show all
2 papers · 1 filter
cs.LG2025
DipSVD: Dual-importance Protected SVD for Efficient LLM Compression
Xuan Ding, Rui Sun, Yunjian Zhang +6
The ever-increasing computational demands and deployment costs of large language models (LLMs) have spurred numerous compressing methods. Compared to quantization and unstructured…
cs.CV2025
Sliding-Window Merging for Compacting Patch-Redundant Layers in LLMs
Xuan Ding, Rui Sun, Yunjian Zhang +7
Depth-wise pruning accelerates LLM inference in resource-constrained scenarios but suffers from performance degradation due to direct removal of entire Transformer layers. This pap…