一作ICML 2026Poster· Deep Learning / Generative Models and Autoencoders
Mitigating Noise-Induced Layout Priors for Object Counting in Diffusion Models
Xiaoling Gu · Xuelong Li · Shengqi Wu · Yongkang Wong · wu · Huan Li · Zhou Yu · Mohan Kankanhalli
首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。
实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。
Xiaoling Gu · Xuelong Li · Shengqi Wu · Yongkang Wong · wu · Huan Li · Zhou Yu · Mohan Kankanhalli
Bowen Zeng · Feiyang Ren · Jun Zhang · Xiaoling Gu · Ke Chen · Lidan Shou · Huan Li
Multimodal Large Language Models (MLLMs) have advanced unified reasoning over text, images, and videos, but their inference is hindered by the rapid growth of key–value (KV) caches. Each visual input expands into thousands of tokens, causing caches to scale linearly with context length and remain...
Wei Bi · Jingfang Miao · Zizhao Wu · Xiaoling Gu · Hongcheng Wang · Xiaofei Zhou