Search Results for author:
Found 6 papers, 0 papers with code
LayerConnect: Hypernetwork-Assisted Inter-Layer Connector to Enhance Parameter Efficiency
Pre-trained Language Models (PLMs) are the cornerstone of the modern Natural Language Processing (NLP).
CT-Eval: Benchmarking Chinese Text-to-Table Performance in Large Language Models
Our preliminary analysis of English text-to-table datasets highlights two key factors for dataset construction: data diversity and data hallucination.
A Siamese CNN Architecture for Learning Chinese Sentence Similarity
This paper presents a deep neural architecture which applies the siamese convolutional neural network sharing model parameters for learning a semantic similarity metric between two sentences.
Self-supervised Document Clustering Based on BERT with Data Augment
Contrastive learning is a promising approach to unsupervised learning, as it inherits the advantages of well-studied deep models without a dedicated and complex model design.
Hair Segmentation on Time-of-Flight RGBD Images
Robust segmentation of hair from portrait images remains challenging: hair does not conform to a uniform shape, style or even color; dark hair in particular lacks features.
Sparse Photometric 3D Face Reconstruction Guided by Morphable Models
We present a novel 3D face reconstruction technique that leverages sparse photometric stereo (PS) and latest advances on face registration/modeling from a single image.
