314 citations · 344 across the 8 of their papers we have counts for
9 papers
Learn from Your Mistakes: Tree-like Self-Play for Secure Code LLMs
Wenqi Chen, Ziyan Zhang, Bin Wang +3
While Large Language Models (LLMs) excel in code generation, they remain prone to replicating subtle yet critical vulnerabilities endemic to their training data. Current alignment…
Confidence Before Answering: A Paradigm Shift for Efficient LLM Uncertainty Estimation
Changcheng Li, Jiancan Wu, Hengheng Zhang +5
Reliable deployment of large language models (LLMs) requires accurate uncertainty estimation. Existing methods are predominantly answer-first, producing confidence only after gener…
Punctuation-aware Hybrid Trainable Sparse Attention for Large Language Models
Junxiang Qiu, Shuo Wang, Zhengsu Chen +4
Attention serves as the fundamental mechanism for long-context modeling in large language models (LLMs), yet dense attention becomes structurally prohibitive for long sequences due…
Visformer: The Vision-friendly Transformer
Zhengsu Chen, Lingxi Xie, Jianwei Niu +3
The past year has witnessed the rapid development of applying the Transformer module to vision problems. While some researchers have demonstrated that Transformer-based models enjo…
SelectScale: Mining More Patterns from Images via Selective and Soft Dropout
Zhengsu Chen, Jianwei Niu, Xuefeng Liu +1
Convolutional neural networks (CNNs) have achieved remarkable success in image recognition. Although the internal patterns of the input images are effectively learned by the CNNs,…
Weight-Sharing Neural Architecture Search: A Battle to Shrink the Optimization Gap
Lingxi Xie, Xin Chen, Kaifeng Bi +8
Neural architecture search (NAS) has attracted increasing attentions in both academia and industry. In the early age, researchers mostly applied individual search methods which sam…
Network Adjustment: Channel Search Guided by FLOPs Utilization Ratio
Zhengsu Chen, Jianwei Niu, Lingxi Xie +3
Automatic designing computationally efficient neural networks has received much attention in recent years. Existing approaches either utilize network pruning or leverage the networ…
A Survey on Incorporating Domain Knowledge into Deep Learning for Medical Image Analysis
Xiaozheng Xie, Jianwei Niu, Xuefeng Liu +3
Although deep learning models like CNNs have achieved great success in medical image analysis, the small size of medical datasets remains a major bottleneck in this area. To addres…
DropFilter: Dropout for Convolutions
Zhengsu Chen Jianwei Niu Qi Tian
Using a large number of parameters , deep neural networks have achieved remarkable performance on computer vison and natural language processing tasks. However the networks usually…