27 citations · 71 across the 15 of their papers we have counts for
15 papers
MemFine: Memory-Aware Fine-Grained Scheduling for MoE Training
Lu Zhao, Rong Shi, Shaoqing Zhang +21
The training of large-scale Mixture of Experts (MoE) models faces a critical memory bottleneck due to severe load imbalance caused by dynamic token routing. This imbalance leads to…
MELA: Multilingual Evaluation of Linguistic Acceptability
Ziyin Zhang, Yikang Liu, Weifang Huang +3
In this work, we present the largest benchmark to date on linguistic acceptability: Multilingual Evaluation of Linguistic Acceptability -- MELA, with 46K samples covering 10 langua…
Self-Supervised Neuron Segmentation with Multi-Agent Reinforcement Learning
Yinda Chen, Wei Huang, Shenglong Zhou +2
The performance of existing supervised neuron segmentation methods is highly dependent on the number of accurate annotations, especially when applied to large scale electron micros…
Learning Multiscale Consistency for Self-supervised Electron Microscopy Instance Segmentation
Yinda Chen, Wei Huang, Xiaoyu Liu +3
Instance segmentation in electron microscopy (EM) volumes is tough due to complex shapes and sparse annotations. Self-supervised learning helps but still struggles with intricate v…
Domain Adaptive Synapse Detection with Weak Point Annotations
Qi Chen, Wei Huang, Yueyi Zhang +1
The development of learning-based methods has greatly improved the detection of synapses from electron microscopy (EM) images. However, training a model for each dataset is time-co…
Toward Transparent Sequence Models with Model-Based Tree Markov Model
Chan Hsu, Wei-Chun Huang, Jun-Ting Wu +2
In this study, we address the interpretability issue in complex, black-box Machine Learning models applied to sequence data. We introduce the Model-Based tree Hidden Semi-Markov Mo…
Generative Text-Guided 3D Vision-Language Pretraining for Unified Medical Image Segmentation
Yinda Chen, Che Liu, Wei Huang +3
Vision-Language Pretraining (VLP) has demonstrated remarkable capabilities in learning visual representations from textual descriptions of images without annotations. Yet, effectiv…
Why We Should Report the Details in Subjective Evaluation of TTS More Rigorously
Cheng-Han Chiang, Wei-Ping Huang, Hung-yi Lee
This paper emphasizes the importance of reporting experiment details in subjective evaluations and demonstrates how such details can significantly impact evaluation results in the…
Revisiting Acceptability Judgements
Hai Hu, Ziyin Zhang, Weifang Huang +7
In this work, we revisit linguistic acceptability in the context of large language models. We introduce CoLAC - Corpus of Linguistic Acceptability in Chinese, the first large-scale…
VLSNR:Vision-Linguistics Coordination Time Sequence-aware News Recommendation
Songhao Han, Wei Huang, Xiaotian Luan
News representation and user-oriented modeling are both essential for news recommendation. Most existing methods are based on textual information but ignore the visual information…
The hybrid approach -- Convolutional Neural Networks and Expectation Maximization Algorithm -- for Tomographic Reconstruction of Hyperspectral Images
Mads J. Ahlebæk, Mads S. Peters, Wei-Chih Huang +3
We present a simple but novel hybrid approach to hyperspectral data cube reconstruction from computed tomography imaging spectrometry (CTIS) images that sequentially combines neura…
Deep Architecture Connectivity Matters for Its Convergence: A Fine-Grained Analysis
Wuyang Chen, Wei Huang, Xinyu Gong +2
Advanced deep neural networks (DNNs), designed by either human or AutoML algorithms, are growing increasingly complex. Diverse operations are connected by complicated connectivity…
Auto-scaling Vision Transformers without Training
Wuyang Chen, Wei Huang, Xianzhi Du +3
This work targets automated designing and scaling of Vision Transformers (ViTs). The motivation comes from two pain spots: 1) the lack of efficient and principled methods for desig…
Improving Cross-Lingual Reading Comprehension with Self-Training
Wei-Cheng Huang, Chien-yu Huang, Hung-yi Lee
Substantial improvements have been made in machine reading comprehension, where the machine answers questions based on a given context. Current state-of-the-art models even surpass…
Advanced Deep Networks for 3D Mitochondria Instance Segmentation
Mingxing Li, Chang Chen, Xiaoyu Liu +3
Mitochondria instance segmentation from electron microscopy (EM) images has seen notable progress since the introduction of deep learning methods. In this paper, we propose two adv…