Jiashi Feng

Deep Adversarial Subspace Clustering

2018

Most existing subspace clustering methods hinge on self-expression of handcrafted representations and are unaware of potential clustering errors. Thus they perform unsatisfactorily on real data with complex underlying subspaces. To solve this issue, we propose …

Evaluation of Combined Artificial Intelligence and Radiologist Assessment to Interpret Screening Mammograms

2020 · JAMA Network Open

Importance: Mammography screening currently relies on subjective human interpretation. Artificial intelligence (AI) advances could be used to increase mammography screening accuracy by reducing missed cancers and false positives. Objective: To evaluate whether AI can overcome …

CIFS: Improving Adversarial Robustness of CNNs via Channel-wise Importance-based Feature Selection

2021 · arXiv (Cornell University)

We investigate the adversarial robustness of CNNs from the perspective of channel-wise activations. By comparing \textit{non-robust} (normally trained) and \textit{robustified} (adversarially trained) models, we observe that adversarial training (AT) robustifies CNNs by aligning the channel-wise …

LV-BERT: Exploiting Layer Variety for BERT

2021 · arXiv (Cornell University)

Modern pre-trained language models are mostly built upon backbones stacking self-attention and feed-forward layers in an interleaved order. In this paper, beyond this stereotyped layer pattern, we aim to improve pre-trained models by exploiting layer …

The Scalability of Simplicity: Empirical Analysis of Vision-Language Learning with a Single Transformer

2025

This paper introduces SAIL, a single transformer unified multimodal large language model (MLLM) that integrates raw pixel encoding and language decoding within a singular architecture. Unlike existing modular MLLMs, which rely on a pre-trained vision …

ReClor: A Reading Comprehension Dataset Requiring Logical Reasoning

2020 · arXiv (Cornell University)

Recent powerful pre-trained language models have achieved remarkable performance on most of the popular datasets for reading comprehension. It is time to introduce more challenging datasets to push the development of this field towards more …

ConvBERT: Improving BERT with Span-based Dynamic Convolution

2020 · arXiv (Cornell University)

Pre-trained language models like BERT and its variants have recently achieved impressive performance in various natural language understanding tasks. However, BERT heavily relies on the global self-attention block and thus suffers large memory footprint and …