Haibing Guan

Speculative decoding can be sped up by >2x without sacrificing accuracy by rescuing previously rejected tokens that are semantically valid but lexically different.

Xuwen Zhou, Chao Wang, Xiao Zheng +1

Architecture Design (Transformers, SSMs, MoE)Inference & Quantization Natural Language Processing

Apr 2, 2026

GEMM-GS: Accelerating 3D Gaussian Splatting on Tensor Cores with GEMM-Compatible Blending

Unlock the full potential of your GPU's Tensor Cores for 3D Gaussian Splatting with a GEMM-friendly blending transformation that delivers up to 2x speedups.

Haomin Li, Bowen Zhu, Fangxin Liu +4

Computer Vision Distributed Systems & Hardware Inference & Quantization

Search

Haibing Guan

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (3)