HM

Huizi Mao

0009-0009-7900-0970

cs.CVcs.LGcs.CLcs.AIstat.MLcs.ARcs.DCcs.NE

On Valency

published · living versions

Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training

with Yujun Lin, Song Han, Yu Wang, William J. Dally

1 version

W_swahtmt7v1 · current

Trained Ternary Quantization

W_g85b2fapv1

EIE: Efficient Inference Engine on Compressed Deep Neural Network

W_ddthczd3v1

Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding

W_cm6h3svqv1

Deep Personalization: Continuous Context Observation for Local Proactive Agents

W_s6utu6y2v1

Preprints & journals

19 papers in the corpus · 2015–2026

LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation

Yukang Chen, Luozhou Wang, Wei Huang et al.

0 citations

2605.18739v22026arXiv

Quantization-Aware Distillation for NVFP4 Inference Accuracy Recovery

Meng Xin, Sweta Priyadarshi, Jingyu Xin et al.

0 citations

2601.20088v32026arXiv

NVIDIA Nemotron 3: Efficient and Open Intelligence

NVIDIA: Aaron Blakeman, Aaron Grattafiori, Aarti Basant et al.

1 citation

2512.20856v12025arXiv

Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning

NVIDIA: Aaron Blakeman, Aaron Grattafiori, Aarti Basant et al.

0 citations

2512.20848v12025arXiv

BLASST: Dynamic BLocked Attention Sparsity via Softmax Thresholding

Jiayi Yuan, Cameron Shinn, Kai Xu et al.

0 citations

2512.12087v32025arXiv

Deterministic Inference across Tensor Parallel Sizes That Eliminates Training-Inference Mismatch

Ziyang Zhang, Xinheng Ding, Jiayi Yuan et al.

0 citations

2511.17826v22025arXiv

QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs

Wei Huang, Yi Ge, Shuai Yang et al.

0 citations

2510.11696v12025arXiv

Retrospective: EIE: Efficient Inference Engine on Sparse and Compressed Neural Network

Song Han, Xingyu Liu, Huizi Mao et al.

1 citation

2306.09552v12023arXiv

BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation

Zhijian Liu, Haotian Tang, Alexander Amini et al.

1,297 citations

2205.13542v32022arXiv

PatchNet -- Short-range Template Matching for Efficient Video Processing

Huizi Mao, Sibo Zhu, Song Han et al.

2 citations

2103.07371v12021arXiv

A Delay Metric for Video Object Detection: What Average Precision Fails to Tell

Huizi Mao, Xiaodong Yang, William J. Dally

51 citations

1908.06368v22019arXiv

CaTDet: Cascaded Tracked Detector for Efficient Object Detection from Video

Huizi Mao, Taeyoung Kong, William J. Dally

14 citations

1810.00434v22018arXiv

Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training

Yujun Lin, Song Han, Huizi Mao et al.

1,134 citations

1712.01887v32017ICLR 2018

Exploring the Regularity of Sparse Structure in Convolutional Neural Networks

Huizi Mao, Song Han, Jeff Pool et al.

219 citations

1705.08922v32017arXiv

Trained Ternary Quantization

Chenzhuo Zhu, Song Han, Huizi Mao et al.

820 citations

1612.01064v32016arXiv

ESE: Efficient Speech Recognition Engine with Sparse LSTM on FPGA

Song Han, Junlong Kang, Huizi Mao et al.

140 citations

1612.00694v22016arXiv

DSD: Dense-Sparse-Dense Training for Deep Neural Networks

Song Han, Jeff Pool, Sharan Narang et al.

164 citations

1607.04381v22016arXiv

EIE: Efficient Inference Engine on Compressed Deep Neural Network

Song Han, Xingyu Liu, Huizi Mao et al.

1,077 citations

1602.01528v22016arXiv

Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding

Song Han, Huizi Mao, William J. Dally

4,095 citations

1510.00149v52015arXiv

Career total: 30 works. 19 are in this corpus.

Profile built from the corpus for this byline.

Author records are still filling in while the Hub is in beta. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.