Showing 2026Show all
2 papers · 1 filter
cs.LG2026
SinkRouter: Sink-Aware Routing for Efficient Long-Context Decoding in Large Language and Multimodal Models
Junnan Liu, Xinyan Liu, Peifeng Gao +4
In long-context decoding for LLMs and LMMs, attention becomes increasingly memory-bound because each decoding step must load a large amount of KV-cache data from GPU memory. Existi…
stat.ML2026
A Mechanism Study of Delayed Loss Spikes in Batch-Normalized Linear Models
Peifeng Gao, Wenyi Fang, Yang Zheng +1
Delayed loss spikes have been reported in neural-network training, but existing theory mainly explains earlier non-monotone behavior caused by overly large fixed learning rates. We…