Model Casting and Low-Parameter Gating: Towards More Sparsely Activated FFNs
cs.LG
Submitted: 2026-09-25
Updated: 2026-09-25
Terminology
Sources
- Program Synthesis with Large Language Models
- Structural Correspondence and Universal Approximation in Diagonal plus Low-Rank Neural Networks
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
- Training Compute-Optimal Large Language Models
- LoRA: Low-Rank Adaptation of Large Language Models
- Mistral 7B
- Mixtral of Experts
- TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension
- Decoupled Weight Decay Regularization
- Gemma 2: Improving Open Language Models at a Practical Size
- GLU Variants Improve Transformer
- RoFormer: Enhanced Transformer with Rotary Position Embedding
- LLaMA: Open and Efficient Foundation Language Models
- Llama 2: Open Foundation and Fine-Tuned Chat Models
- Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models
- Qwen2.5 Technical Report
- Root Mean Square Layer Normalization
- OPT: Open Pre-trained Transformer Language Models
- ReLU$^2$ Wins: Discovering Efficient Activation Functions for Sparse LLMs
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: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks