NeurIPS "structured pruning" Papers
2 papers found
Layer as Puzzle Pieces: Compressing Large Language Models through Layer Concatenation
Fei Wang, Li Shen, Liang Ding et al.
NeurIPS 2025posterarXiv:2510.15304
ModHiFi: Identifying High Fidelity predictive components for Model Modification
Dhruva Kashyap, Chaitanya Murti, Pranav K Nayak et al.
NeurIPS 2025spotlightarXiv:2511.19566