SGA-Sparse: Training Native SwiGLU Gates for Activation-Sparse and Low-Bit LLMs
cs.LG, cs.AI, cs.CL
Submitted: 2026-11-08
Updated: 2026-11-08
Terminology
Sources
- gpt-oss-120b & gpt-oss-20b Model Card
- Sparser, Faster, Lighter Transformer Language Models
- MobileMoE: Scaling On-Device Mixture of Experts
- BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- Training Verifiers to Solve Math Word Problems
- Learned Step Size Quantization
- GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
- The Llama 3 Herd of Models
- Measuring Massive Multitask Language Understanding
- Instruction-Following Pruning for Large Language Models
- The Lazy Neuron Phenomenon: On Emergence of Activation Sparsity in Transformers
- MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases
- Decoupled Weight Decay Regularization
- Pointer Sentinel Mixture Models
- Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering
- Q-Sparse: All Large Language Models can be Fully Sparsely-Activated
- Resting Neurons, Active Insights: Robustifying Activation Sparsity in LLMs via Spontaneity
- HellaSwag: Can a Machine Really Finish Your Sentence?
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis