Is SwiGLU's Open Positive Tail Necessary? Evidence from Closed-Tail Gating with MemGLU
Yuting Ge, Pengju Yang, Mingkai Nie
cs.LG
Submitted: 2026-08-07
Updated: 2026-08-10
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Qwen Technical Report
- PaLM: Scaling Language Modeling with Pathways
- Scaling FP8 training to trillion-token LLMs
- Expanded Gating Ranges Improve Activation Functions
- Deriving Activation Functions Using Integration
- PowLU: An Activation Function for Stable Pre-Training of LLMs
- CATS: Contextually-Aware Thresholding for Sparsity in Large Language Models
- GLU Variants Improve Transformer
- LLaMA: Open and Efficient Foundation Language Models
- More Expressive Feedforward Layers: Part I. Token-Adaptive Mixing of Activations
- Polynomial Composition Activations: Unleashing the Dynamics of Large Language Models
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks