Research
I work on accelerating generative models, neuromorphic computing, and efficient models. My research spans brain-inspired computing (spiking neural networks and neuromorphic systems), efficient modeling (acceleration algorithms, pruning, and quantization), and AI safety (adversarial attacks and model interpretability).
My PhD work focuses on SNNs, neuromorphic computing, and efficient models. As a research intern in Alibaba's Wan team, I also explore acceleration methods for video generation.
Google ScholarPublished works
2026
-
Proxy target: Bridging the gap between discrete spiking neural networks and continuous control
Advances in Neural Information Processing Systems 38, 159158-159184Conference
-
Uncertainty-Aware Token Importance Estimation in Spiking Transformers
arXiv preprint arXiv:2605.09276Preprint
-
Activity Pruning for Efficient Spiking Neural Networks
Advances in Neural Information Processing Systems 38, 171134-171153Conference
-
Generalized Threshold Optimization with Harmony Multi-Threshold Neurons for Accurate ANN-to-SNN Conversion
Proceedings of the AAAI Conference on Artificial Intelligence 40 (3), 2227-2235Conference
-
Reducing ANN-SNN Conversion Error via Residual Membrane Potential Alignment
arXiv preprint arXiv:2608.13952Preprint
-
UniSparse: Combining Weight Pruning and Spike Sparsification in Spiking Neural Networks
The 43rd International Conference on Machine LearningConference
2025
-
Differential coding for training-free ANN-to-SNN conversion
arXiv preprint arXiv:2503.00301Preprint
-
Ultrafast probabilistic neuron in an artificial spin ice for robust deep neural networks
Advanced Functional Materials 35 (11), 2417334Journal
-
PredNext: Explicit Cross-View Temporal Prediction for Unsupervised Learning in Spiking Neural Networks
arXiv preprint arXiv:2509.24844Preprint
2024
-
Towards high-performance spiking transformers from ANN to SNN conversion
Proceedings of the 32nd ACM International Conference on Multimedia, 10688-10697Conference
-
A progressive training framework for spiking neural networks with learnable multi-hierarchical model
International Conference on Learning Representations 2024, 4925-4941Conference
-
Enhancing adversarial robustness in SNNs with sparse gradients
arXiv preprint arXiv:2405.20355Preprint
-
Threaten spiking neural networks through combining rate and temporal information
International Conference on Learning Representations 2024, 55658-55674Conference
-
Robust decoding of rich dynamical visual scenes with retinal spikes
IEEE Transactions on Neural Networks and Learning Systems 36 (2), 3396-3409Journal
-
Inference-Scale Complexity in ANN-SNN Conversion for High-Performance and Low-Power Applications
arXiv preprint arXiv:2409.03368Preprint
2023
-
Optimal ANN-SNN conversion for high-accuracy and ultra-low-latency spiking neural networks
arXiv preprint arXiv:2303.04347Preprint
-
Reducing ANN-SNN conversion error through residual membrane potential
Proceedings of the AAAI Conference on Artificial Intelligence 37 (1), 11-21Conference
-
Bridging the gap between ANNs and SNNs by calibrating offset spikes
arXiv preprint arXiv:2302.10685Preprint
-
Rate gradient approximation attack threats deep spiking neural networks
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern RecognitionConference
-
Red teaming deep neural networks with feature synthesis tools
Advances in Neural Information Processing Systems 36, 80470-80516Conference
2022
-
Optimized potential initialization for low-latency spiking neural networks
Proceedings of the AAAI Conference on Artificial Intelligence 36 (1), 11-20Conference
-
SNN-RAT: Robustness-enhanced spiking neural network through regularized adversarial training
Advances in Neural Information Processing Systems 35, 24780-24793Conference
-
Decoding pixel-level image features from two-photon calcium signals of macaque visual cortex
Neural Computation 34 (6), 1369-1397Journal