feed-forward network
A type of neural network architecture where connections between the nodes do not form cycles, and data flows in one direction from input to output layers.
- Benford’s Curse: Tracing Digit Bias to Numerical Hallucination in LLMs
- FFN Fusion: Rethinking Sequential Computation in Large Language Models
- HybridNorm: Towards Stable and Efficient Transformer Training via Hybrid Normalization
- Steering Information Utility in Key-Value Memory for Language Model Post-Training
- UMoE: Unifying Attention and FFN with Shared Experts
- Wavy Transformer