← Search

Jinle Zeng

2 accepted papers

2026

AdaGC: Enhancing LLM Pretraining Stability via Adaptive Gradient Clipping

ICML 2026poster

Loss spikes remain a persistent obstacle in large-scale language model pretraining. While previous research has attempted to identify the root cause of loss spikes by investigating individual factors, we observe that, in practice, such spikes are typically triggered by the confluence of heterogeneou…

Cited by 0SourceScholar
2025

FlashMask: Efficient and Rich Mask Extension of FlashAttention

ICLR 2025poster

The computational and memory demands of vanilla attention scale quadratically with the sequence length $N$, posing significant challenges for processing long sequences in Transformer models. FlashAttention alleviates these challenges by eliminating the $\mathcal{O}(N^2)$ memory dependency and reduci…