activity
20242026
most citedSlow-Fast Inference: Training-Free Inference Acceleration via Within-Sentence Support Stability

1 citations · 1 across the 4 of their papers we have counts for

collaborators

9 papers

math.OC2026

Establishing Boundary KKT Convergence of Mirror Descent through Reparameterization

Kuangyu Ding, Kim-Chuan Toh

Sequence convergence to a boundary Karush--Kuhn--Tucker (KKT) point has long remained unclear for nonconvex mirror descent with Legendre kernels. The difficulty arises from the blo…

math.OC2026

Non-KKT Accumulation in Entropic Mirror Descent

Kuangyu Ding, Kim-Chuan Toh

For mirror descent generated by a Legendre kernel, perhaps one of the most basic question in optimization is this: must every accumulation point of a bounded mirror descent sequenc…

cs.LG2026

Optimization Hyper-parameter Laws for Large Language Models

Xingyu Xie, Kuangyu Ding, Shuicheng Yan +2

Large Language Models have driven significant AI advancements, yet their training is resource-intensive and highly sensitive to hyper-parameter selection. While scaling laws provid…

cs.LG20261 cited

Slow-Fast Inference: Training-Free Inference Acceleration via Within-Sentence Support Stability

Xingyu Xie, Zhaochen Yu, Yue Liao +3

Long-context autoregressive decoding remains expensive because each decoding step must repeatedly process a growing history. We observe a consistent pattern during decoding: within…

cs.CL2025

GRIFFIN: Effective Token Alignment for Faster Speculative Decoding

Shijing Hu, Jingyang Li, Xingyu Xie +3

Speculative decoding accelerates inference in large language models (LLMs) by generating multiple draft tokens simultaneously. However, existing methods often struggle with token m…

cs.LG2025

Memory-Efficient 4-bit Preconditioned Stochastic Optimization

Jingyang Li, Kuangyu Ding, Kim-Chuan Toh +1

Preconditioned stochastic optimization algorithms, exemplified by Shampoo, outperform first-order optimizers by offering theoretical convergence benefits and practical gains in lar…