Author

Jun Wei

h-index 5 View on Semantic Scholar

We have 1 of 10 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Jul 2026

Prox: Training-Free FFN Activation Sparsity via Approximate Intermediate-Channel Salience in LLMs

Prox is a two-stage training-free framework for sparse SwiGLU FFNs that outperforms training-free baselines at all sparsity levels, achieves up to a $1.99\times end-to-end decoding speedup at 70\% FFN sparsity, and is compatible with quantization and sparse attention.

Jinyi Liu, Wei Chen, Pengyu Chen et al. · arXiv.org · 0 citations