Haiduo Huang

17 papers A* 3B 1Journal 12Unranked 1
YearRankTypeTitle / Venue / Authors
2026 A* conf
Double Rounding: Nearly Lossless Adaptive Bit Switching for QAT.
AAAI
Haiduo Huang, Zhenhua Liu, Tian Xia, Pengju Ren
2026 A* conf
PartialNet: Compute Less, Perform Better.
AAAI
Haiduo Huang, Tian Xia, Wenzhe Zhao, Pengju Ren
2025 J jnl
DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer.
CoRR
Haiduo Huang, Jiangcheng Song, Yadong Zhang, Pengju Ren
2025 J jnl
FastEagle: Cascaded Drafting for Accelerating Speculative Decoding.
CoRR
Haiduo Huang, Jiangcheng Song, Wenzhe Zhao, Pengju Ren
2025 A* conf
Gumiho: A Hybrid Architecture to Prioritize Early Tokens in Speculative Decoding.
ICML
Jinze Li, Yixing Xu, Haiduo Huang, Xuanwu Yin, Dong Li, Edith C. H. Ngai, Emad Barsoum
2025 J jnl
Gumiho: A Hybrid Architecture to Prioritize Early Tokens in Speculative Decoding.
CoRR
Jinze Li, Yixing Xu, Haiduo Huang, Xuanwu Yin, Dong Li, Edith C. H. Ngai, Emad Barsoum
2025 J jnl
Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoE.
CoRR
Haiduo Huang, Fuwei Yang, Zhenhua Liu, Yixing Xu, Jinze Li, Yang Liu, Xuanwu Yin, Dong Li, Pengju Ren, Emad Barsoum
2025 J jnl
KernelDNA: Dynamic Kernel Sharing via Decoupled Naive Adapters.
CoRR
Haiduo Huang, Yadong Zhang, Pengju Ren
2025 J jnl
NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds.
CoRR
Boran Zhao, Haiduo Huang, Qiwei Dang, Wenzhe Zhao, Tian Xia, Pengju Ren
2025 J jnl
Nearly Lossless Adaptive Bit Switching.
CoRR
Haiduo Huang, Zhenhua Liu, Tian Xia, Wenzhe Zhao, Pengju Ren
2025 J jnl
Partial Channel Network: Compute Fewer, Perform Better.
CoRR
Haiduo Huang, Tian Xia, Wenzhe Zhao, Pengju Ren
2025 J jnl
Partial Convolution Meets Visual Attention.
CoRR
Haiduo Huang, Fuwei Yang, Dong Li, Ji Liu, Lu Tian, Jinzhang Peng, Pengju Ren, Emad Barsoum
2025 J jnl
SpecKD: Speculative Decoding for Effective Knowledge Distillation of LLMs.
CoRR
Haiduo Huang, Jiangcheng Song, Yadong Zhang, Pengju Ren
2025 J jnl
SpecVLM: Fast Speculative Decoding in Vision-Language Models.
CoRR
Haiduo Huang, Fuwei Yang, Zhenhua Liu, Xuanwu Yin, Dong Li, Pengju Ren, Emad Barsoum
2024 J jnl
FTP: A Fine-grained Token-wise Pruner for Large Language Models via Token Routing.
CoRR
Zekai Li, Jintu Zheng, Ji Liu, Han Liu, Haowei Zhu, Zeping Li, Fuwei Yang, Haiduo Huang, Jinzhang Peng, Dong Li, Lu Tian, Emad Barsoum
2023 B conf
TAQ: Top-K Attention-Aware Quantization for Vision Transformers.
ICIP
Lili Shi, Haiduo Huang, Bowei Song, Meng Tan, Wenzhe Zhao, Tian Xia, Pengju Ren
2020 — conf
An Outlier Detection Method Based On Symmetry and Curvature Threshold.
ICVIP
Qinqin Dong, Peilin Jiang, Haiduo Huang