No article text was recorded for this version.
adaptive expert selection
Version 1 of 138 papers45 conceptsfrozen 2026-10-04
Papers in this version
- Blog: ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing
- Blog: ProbMoE: Differentiable Probabilistic Routing for Mixture-of-Experts
- Blog: AutoMoE: Heterogeneous Mixture-of-Experts with Adaptive Computation for Efficient Neural Machine Translation
- Blog: How Many Layers and Why? An Analysis of the Model Depth in Transformers
- Blog: Mixture-of-Experts with Expert Choice Routing
- Blog: Flextron: Many-in-One Flexible Large Language Model
- Blog: Adaptive LoRA Experts Allocation and Selection for Federated Fine-Tuning
- Blog: On-Demand Resource Management for 6G Wireless Networks Using Knowledge-Assisted Dynamic Neural Networks
- Blog: Mixture of Cache-Conditional Experts for Efficient Mobile Device Inference
- Blog: BlockFFN: Towards End-Side Acceleration-Friendly Mixture-of-Experts with Chunk-Level Activation Sparsity
- Blog: Mixture of Diverse Size Experts
- Blog: Advancing SMoE for Continuous Domain Adaptation of MLLMs: Adaptive Router and Domain-Specific Loss
- Blog: XMoE: Sparse Models with Fine-grained and Adaptive Expert Selection
- Blog: FlexOLMo: Open Language Models for Flexible Data Use
- Blog: Universal Transformers
- Blog: TimeExpert: An Expert-Guided Video LLM for Video Temporal Grounding
- Blog: MoSE: Mixture of Slimmable Experts for Efficient and Adaptive Language Models
- Blog: DiffMoE: Dynamic Token Selection for Scalable Diffusion Transformers
- Blog: Dense-to-Sparse Gate for Mixture-of-Experts
- Blog: Ada-K Routing: Boosting the Efficiency of MoE-based LLMs
- Blog: TC-MoE: Augmenting Mixture of Experts with Ternary Expert Choice
- Blog: Dynamic Experts Search: Enhancing Reasoning in Mixture-of-Experts LLMs at Test Time
- Blog: Expert Race: A Flexible Routing Strategy for Scaling Diffusion Transformer with Mixture of Experts
- Blog: Scaling Vision with Sparse Mixture of Experts
- Blog: Why Ask One When You Can Ask $k$? Learning-to-Defer to the Top-$k$ Experts
- Blog: Towards Being Parameter-Efficient: A Stratified Sparsely Activated Transformer with Dynamic Capacity
- Blog: Dynamic Mixture of Experts: An Auto-Tuning Approach for Efficient Transformer Models
- Blog: Exploiting Activation Sparsity with Dense to Dynamic-k Mixture-of-Experts Conversion
- Blog: Adaptive Gating in Mixture-of-Experts based Language Models
- Blog: CoTFormer: A Chain of Thought Driven Architecture with Budget-Adaptive Computation Cost at Inference
- Blog: Ban&Pick: Ehancing Performance and Efficiency of MoE-LLMs via Smarter Routing
- Blog: Training Matryoshka Mixture-of-Experts for Elastic Inference-Time Expert Utilization
- Blog: BrownoutServe: SLO-Aware Inference Serving under Bursty Workloads for MoE-based LLMs
- Blog: AdaMoE: Token-Adaptive Routing with Null Experts for Mixture-of-Experts Language Models
- Blog: ShiftAddViT: Mixture of Multiplication Primitives Towards Efficient Vision Transformer
- Blog: MoE Jetpack: From Dense Checkpoints to Adaptive Mixture of Experts for Vision Tasks
- Blog: From Dense to Dynamic: Token-Difficulty Driven MoEfication of Pre-Trained LLMs
- Blog: Long-tailed Recognition by Routing Diverse Distribution-Aware Experts
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_adaptive_expert_selection_80a63e3b,
title = {adaptive expert selection},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/adaptive-expert-selection/rdr_80a63e3bbc2649efb4a8a4061bf14bb6},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 1, frozen text):
@misc{lacuna_adaptive_expert_selection_80a63e3b_v1,
title = {adaptive expert selection},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/adaptive-expert-selection/rdr_80a63e3bbc2649efb4a8a4061bf14bb6/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-19},
}