4 citations · 6 across the 5 of their papers we have counts for
5 papers
TEAM: Temporal-Spatial Consistency Guided Expert Activation for MoE Diffusion Language Model Acceleration
Linye Wei, Zixiang Luo, Pingzhi Tang +1
Diffusion large language models (dLLMs) have recently gained significant attention due to their inherent support for parallel decoding. Building on this paradigm, Mixture-of-Expert…
Perturbing a Neural Network to Infer Effective Connectivity: Evidence from Synthetic EEG Data
Peizhen Yang, Xinke Shen, Zongsheng Li +3
Identifying causal relationships among distinct brain areas, known as effective connectivity, holds key insights into the brain's information processing and cognitive functions. El…
Mapping effective connectivity by virtually perturbing a surrogate brain
Zixiang Luo, Kaining Peng, Zhichao Liang +6
Effective connectivity (EC), indicative of the causal interactions between brain regions, is fundamental to understanding information processing in the brain. Traditional approache…
UIA-ViT: Unsupervised Inconsistency-Aware Method based on Vision Transformer for Face Forgery Detection
Wanyi Zhuang, Qi Chu, Zhentao Tan +5
Intra-frame inconsistency has been proved to be effective for the generalization of face forgery detection. However, learning to focus on these inconsistency requires extra pixel-l…
Online Learning Koopman operator for closed-loop electrical neurostimulation in epilepsy
Zhichao Liang, Zixiang Luo, Keyin Liu +2
Electrical neuromodulation as a palliative treatment has been increasingly used in the control of epilepsy. However, current neuromodulations commonly implement predetermined actua…