Yu Liang

PhD Student

University of Electronic Science and Technology of China

Research Interests

Model Compression

Neurocomputing

Large Language model

About

I work on efficient AI: making large models smaller, faster, and more energy-efficient through model compression and brain-inspired computation.

I am a Ph.D. student in the School of Computer Science at the University of Electronic Science and Technology of China (UESTC), advised by Prof. Malu Zhang, and part of a joint Ph.D. program with the Shenzhen Loop Area Institute. I received my B.Eng. from UESTC. My research focuses on model compression, combining large models with spiking neural networks, and neuromorphic computing.

Phone & WeChat(+86) 18935255267

Phone(+86) 15828375248

News

2026-05ICML 2026 — Five of our papers have been accepted, including SpikingLM and one Spotlight paper, SmoothSpike.
2025-11AAAI 2026 — Our work on training-free ANN-to-SNN conversion via activation-aware redistribution has been accepted.
2025-05ICML 2025 — Our paper BSO, on online optimization for binary spiking neural networks, has been accepted.
2025-04IJCAI 2025 — Our paper on binary event-driven spiking transformers has been accepted.
2025-01ICLR 2025 — Two of our papers have been accepted, covering saccadic attention in spiking vision transformers and quantization and pruning of spiking neural networks.

Earlier news

2024-12AAAI 2025 — Our paper on adaptive gradient modulation for binary spiking neural networks has been accepted for an Oral presentation.
2024-07ACM Multimedia 2024 — Our paper Q-SNNs, on quantized spiking neural networks, has been accepted.

Publications

View All →

SpikingLM architecture with Distribution-aware Scaling and Spike2Max attention

ICML 2026

SpikingLM: Towards Fully Spiking Language Model

Yu Liang, Zijian Zhou, Wenjie Wei, Shuai Wang, Honglin Cao, Ammar Belatreche, Yu Yang, Malu Zhang, Yang Yang, Haizhou Li
Distribution-aware Scaling and Spike2Max attention enable fully spiking language models with stable training and energy-efficient language understanding.
Project Paper Code

Network architecture and backpropagation of Adaptive Gradient Modulation Mechanism

AAAI 2025Oral

Towards Accurate Binary Spiking Neural Networks: Learning with Adaptive Gradient Modulation Mechanism

Yu Liang, Wenjie Wei, Ammar Belatreche, Honglin Cao, Zijian Zhou, Shuai Wang, Malu Zhang, Yang Yang
Adaptive gradient modulation reduces weight sign flipping to improve convergence and accuracy in binary spiking neural networks.
Project Paper Code

Binary weight update strategies in BSO and temporal-aware T-BSO

ICML 2025

BSO: Binary Spiking Online Optimization Algorithm

Yu Liang, Yu Yang, Wenjie Wei, Ammar Belatreche, Shuai Wang, Malu Zhang, Yang Yang
Direct binary weight updates reduce training memory; a temporal-aware variant adapts update thresholds using gradient information across time steps.
Project Paper Code

Others

2026

ICML 2026 Positional Encoding for Spiking Transformers
Zijian Zhou, Yu Liang, Honglin Cao, Ammar Belatreche, Jieyuan Zhang, Wenjie Wei, Shuai Wang, Malu Zhang, Yang Yang, Haizhou Li
Paper · Code
ICML 2026 SEPS: Semantic-Enhanced Patch Slimming Framework for Fine-Grained Cross-Modal Alignment
Xinyu Mao, Junsi Li, Haoji Zhang, Yu Liang, Ming Sun
Paper · Code
ICML 2026 AdaS: Adaptive Gradient Descent for Spiking Transformers
Zijian Zhou, Honglin Cao, Ammar Belatreche, Wenjie Wei, Yimeng Shan, Yu Liang, Yu Yang, Shuai Wang, Yalan Ye, Malu Zhang, Yang Yang, Haizhou Li
Paper · Code
ICML 2026Spotlight SmoothSpike: Spiking Transformer with Learnable Hadamard Transformation
Zijian Zhou, Wenjie Wei, Yu Liang, Jialin Li, Ammar Belatreche, Honglin Cao, Shuai Wang, Malu Zhang, Yang Yang, Haizhou Li
Paper · Code
AAAI 2026 Towards Training-Free and Accurate ANN-to-SNN Conversion via Activation-Aware Redistribution
Honglin Cao, Shuai Wang, Zijian Zhou, Ammar Belatreche, Wenjie Wei, Yu Liang, Yu Yang, Rui Xi, Malu Zhang, Haizhou Li
Paper

2025

IJCAI 2025 Binary Event-Driven Spiking Transformer
Honglin Cao, Zijian Zhou, Wenjie Wei, Yu Liang, Ammar Belatreche, Dehao Zhang, Malu Zhang, Yang Yang, Haizhou Li
Paper · Code
ICLR 2025 Spiking Vision Transformer with Saccadic Attention
Shuai Wang, Malu Zhang, Dehao Zhang, Ammar Belatreche, Yichen Xiao, Yu Liang, Yimeng Shan, Qian Sun, Enqi Zhang, Yang Yang
Paper
ICLR 2025 QP-SNN: Quantized and Pruned Spiking Neural Networks
Wenjie Wei, Malu Zhang, Zijian Zhou, Ammar Belatreche, Yimeng Shan, Yu Liang, Honglin Cao, Jieyuan Zhang, Yang Yang
Paper · Code

2024

ACM MM 2024 Q-SNNs: Quantized Spiking Neural Networks
Wenjie Wei, Yu Liang, Ammar Belatreche, Yichen Xiao, Honglin Cao, Zhenbang Ren, Guoqing Wang, Malu Zhang, Yang Yang
Paper · Code

Services