ffn

Prox is a training-free framework for sparse SwiGLU FFNs in LLMs, using approximate intermediate-channel salience to build channel masks without dense computation. It outperforms training-free baselines across ten LLMs, achieving up to 1.99x end-to-end decoding speedup at 70% sparsity.

This paper proposes FADE, a training-free method that mitigates hallucinations in Large Vision-Language Models by attenuating FFN outputs at critical layers to reduce language-prior dominance, demonstrating effectiveness across multiple benchmarks.

A student introduces Silia, a novel transformer architecture that combines attention and FFN into a unified operation to save parameters at scales ≤10M, achieving comparable performance to GPT-2 with fewer parameters despite limited compute resources.