Massive Activation Gating Channel in Large Language Models
cs.AI
Submitted: 2026-10-06
Updated: 2026-10-06
Code: https://github.com/MinjiaMao/magc
Sources
- Sparks of Artificial General Intelligence: Early experiments with GPT-4
- Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs
- GLU Variants Improve Transformer
- The Spike, the Sparse and the Sink: Anatomy of Massive Activations and Attention Sinks
- LLaMA: Open and Efficient Foundation Language Models
- Efficient Streaming Language Models with Attention Sinks
- Unveiling and Controlling Anomalous Attention Distribution in Transformers
- Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibration
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems