DivMoE: Fine-Grained MoE Upcycling via Cross-Domain Expert Composition
cs.AI, cs.LG
Submitted: 2026-10-08
Updated: 2026-10-08
Comments: 19 pages, published as a conference paper at NeurIPS 2026
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Program Synthesis with Large Language Models
- Evaluating Large Language Models Trained on Code
- BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models
- DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
- Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity
- Continual Pre-Training of Large Language Models: How to (re)warm your model?
- Upcycling Large Language Models into Mixture of Experts
- Measuring Massive Multitask Language Understanding
- Measuring Mathematical Problem Solving With the MATH Dataset
- Simple and Scalable Strategies to Continually Pre-train Large Language Models
- Mixtral of Experts
- Tulu 3: Pushing Frontiers in Open Language Model Post-Training
- Branch-Train-Merge: Embarrassingly Parallel Training of Expert Language Models
- Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering
- Drop-Upcycling: Training Sparse Mixture of Experts with Partial Re-initialization
- 2 OLMo 2 Furious
- Know What You Don't Know: Unanswerable Questions for SQuAD
- GPQA: A Graduate-Level Google-Proof Q&A Benchmark
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