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

6 papers

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.LG2026

Evolution of Optimization Methods: Algorithms, Scenarios, and Evaluations

Tong Zhang, Jiangning Zhang, Zhucun Xue +9

Balancing convergence speed, generalization capability, and computational efficiency remains a core challenge in deep learning optimization. First-order gradient descent methods, e…

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.PL2026

(Dis)Proving Spectre Security with Speculation-Passing Style

Santiago Arranz-Olmos, Gilles Barthe, Lionel Blatter +2

Constant-time (CT) verification tools are commonly used for detecting potential side-channel vulnerabilities in cryptographic libraries. Recently, a new class of tools, called spec…

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.LG2024

LoCo: Low-Bit Communication Adaptor for Large-scale Model Training

Xingyu Xie, Zhijie Lin, Kim-Chuan Toh +1

To efficiently train large-scale models, low-bit gradient communication compresses full-precision gradients on local GPU nodes into low-precision ones for higher gradient synchroni…