Showing 2025Show all
2 papers · 1 filter
cs.LG2025
Route Experts by Sequence, not by Token
Tiansheng Wen, Yifei Wang, Aosong Feng +7
Mixture-of-Experts (MoE) architectures scale large language models (LLMs) by activating only a subset of experts per token, but the standard TopK routing assigns the same fixed num…
cs.LG2025
Beyond Matryoshka: Revisiting Sparse Coding for Adaptive Representation
Tiansheng Wen, Yifei Wang, Zequn Zeng +7
Many large-scale systems rely on high-quality deep representations (embeddings) to facilitate tasks like retrieval, search, and generative modeling. Matryoshka Representation Learn…