EAT: Expert Account Tracker for Efficient MoE Inference
cs.AI
Submitted: 2026-09-27
Updated: 2026-09-27
Code: https://github.com/open-compass/opencompass
Terminology
Sources
- Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
- DA-MoE: Towards Dynamic Expert Allocation for Mixture-of-Experts Models
- PIQA: Reasoning about Physical Commonsense in Natural Language
- 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
- Exploiting Mixture-of-Experts Redundancy Unlocks Multimodal Generative Abilities
- Harder Tasks Need More Experts: Dynamic Routing in MoE Models
- Mixtral of Experts
- GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding
- CMMLU: Measuring massive multitask language understanding in Chinese
- Sub-MoE: Efficient Mixture-of-Expert LLMs Compression via Subspace Expert Merging
- Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models
- Analytical FFN-to-MoE Restructuring via Activation Pattern Analysis
- WiC: the Word-in-Context Dataset for Evaluating Context-Sensitive Meaning Representations
- GPQA: A Graduate-Level Google-Proof Q&A Benchmark
- Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer
- GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding
- Measuring short-form factuality in large language models
- MoE-Pruner: Pruning Mixture-of-Experts Large Language Model using the Hints from Its Router
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
- 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
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection