Adaptive Inverted-Index Routing for Granular Mixtures-of-Experts
cs.LG
Submitted: 2026-05-06
Updated: 2026-10-03
Terminology
Sources
- Layer Normalization
- Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
- Datasheet for the Pile
- On the Role of Discrete Representation in Sparse Mixture of Experts
- Kimi-VL Technical Report
- The Llama 3 Herd of Models
- Mixture of A Million Experts
- Mixtral of Experts
- QuantMoE-Bench: Examining Post-Training Quantization for Mixture-of-Experts
- Statistical Advantages of Perturbing Cosine Router in Mixture of Experts
- GLU Variants Improve Transformer
- Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism
- MaskMoE: Boosting Token-Level Learning via Routing Mask in Mixture-of-Experts
- Pangu Pro MoE: Mixture of Grouped Experts for Efficient Sparsity
- Bridging the Gap Between Indexing and Retrieval for Differentiable Search Index with Query Generation
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: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks