Goto

Collaborating Authors

 Jiangsu Province





Single Image Unlearning: Efficient Machine Unlearning in Multimodal Large Language Models Jiaqi Li

Neural Information Processing Systems

Machine unlearning (MU) empowers individuals with the'right to be forgotten' by removing their private or sensitive information encoded in machine learning models. However, it remains uncertain whether MU can be effectively applied to Multimodal Large Language Models (MLLMs), particularly in scenarios of forgetting the leaked visual data of concepts.



Twelve killed in China fireworks shop blast during Lunar New Year

Al Jazeera

An explosion at a fireworks shop in central China's Hubei province has killed at least 12 people, state media reported, marking the second deadly blast linked to fireworks as the country celebrates the Lunar New Year . The explosion tore through the shop in Xiangyang on Wednesday afternoon. Officials said five children and seven adults died in the explosion. The victims included the shop owner and customers who had been buying fireworks for holiday celebrations. Some had travelled from other areas to visit relatives during the festive period .


1e5cff01121223de917a84a242de30a5-Paper-Conference.pdf

Neural Information Processing Systems

InOrMo, momentum isincorporated into ASGD byorganizing the gradients in order based on their iteration indexes. We theoretically prove the convergence of OrMo with both constant and delay-adaptive learning rates for non-convexproblems.




LOG: ActiveModelAdaptationforLabel-Efficient OODGeneralization

Neural Information Processing Systems

Thisworkdiscusses howtoachieveworst-case Out-Of-Distribution(OOD) generalization for avariety of distributions based on arelatively small labeling cost.