Accelerating Distributed MoE Training and Inference with Lina (2022 · 92 citations)
Mixture-of-Experts (MoE) models keep per-token compute low by sending each token to only one or two expert FFNs.
Contrastive Prompting Enhances Sentence Embeddings in LLMs through Inference-Time Steering (2025 · 8 citations)
Large language models can produce sentence embeddings without any training data or fine-tuning: a prompt wraps the sentence, and the hidden state of the final token serves as the vector.
AEA: Adaptive Expert Allocation Improves Sentence Embeddings from Mixture-of-Experts LLM (2026)
The paper addresses training-free sentence embeddings taken directly from Mixture-of-Experts (MoE) LLMs. Earlier work, such as MoEE, keeps the same Top-K number of experts for every layer and every token. The authors show that this uniform budget wastes capacity. In DeepSeekMoE-16B and OLMoE-1B-7B, expert outputs are…
Investigating More Explainable and Partition-Free Compositionality Estimation for LLMs: A Rule-Generation Perspective (2026)
LLM compositionality is usually measured with compositional generalization tests, which have two weaknesses.

Co-authors here

10 co-authors with a page, the most papers together first.

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

Papers of our library cite their works 98 times (of the 149,439 papers whose bibliographies we read); 10 citing papers with a page here →.

Updated 2 November 2026