Search papers, labs, and topics across Lattice.
School of Artificial Intelligence, Beijing University of Posts and Telecommunications 3 National Library of China, Beijing, China 4 School of Cyberspace Security, Beijing University of Posts and Telecommunications {ytgao92,maoyuanshao}@muc.edu.cn, {chuangzhu,xinyanghuang,sunlijuan}@bupt.edu.cn
1
0
2
Vision-language models can learn to correct their own systematic errors by explicitly modeling confusion patterns between similar categories, leading to a 50% reduction in misclassifications.
