most citedState Rank Dynamics in Linear Attention LLMs

1 citations · 1 across the 6 of their papers we have counts for

collaborators

6 papers

cs.LG2026

The Stability of Singular Distribution: A Spectral Perspective on the Two-Phase Dynamics of Language Model Pre-training

Hongtao Zhang, Wenjie Zhou, Chenxi Jia +2

Large language model pre-training typically exhibits a two-phase trajectory: a fast initial loss drop followed by a prolonged slow improvement. We identify an underlying spectral p…

cs.LG2026

Extra-Merge: Tracing the Rank-1 Subspace of Model Merging in Language Model Pre-Training

Wenjie Zhou, Bohan Wang, Hongtao Zhang +3

Model merging has emerged as a lightweight paradigm for enhancing Large Language Models (LLMs), yet its underlying mechanisms remain poorly understood. In this work, we analyze lat…

cs.DC2026

DynaFlow: Transparent and Flexible Intra-Device Parallelism via Programmable Operator Scheduling

Yi Pan, Yile Gu, Jinbin Luo +7

Intra-device parallelism addresses resource under-utilization in ML inference and training by overlapping the execution of operators with different resource usage. However, its wid…

cs.LG2026

When and Why Grouping Attention Heads Accelerates Muon Optimization

Hongtao Zhang, Wenjie Zhou, Wei Chen +1

Muon orthogonalizes matrix updates, but multi-head attention naturally operates at the level of heads. This granularity mismatch raises the question of whether Muon should be appli…

cs.LG2026★ 1 cited

State Rank Dynamics in Linear Attention LLMs

Ao Sun, Hongtao Zhang, Heng Zhou +9

Linear Attention Large Language Models (LLMs) offer a compelling recurrent formulation that compresses context into a fixed-size state matrix, enabling constant-time inference. How…

cs.NI2025

SHIFT: Exploring the Boundary of RDMA Network Fault Tolerance

Shengkai Lin, Kairui Zhou, Hongtao Zhang +7

Under gang scheduling for large-scale distributed large language model (LLM) training, a single network anomaly can stall or abort an entire job. Current network fault tolerance me…