一作ICML 2026Poster· Deep Learning / Generative Models and Autoencoders
Parameter Manifold Purification
Jiacong Hu · Jinxun Wu · Shengxuming Zhang · Shunyu Liu · Haofei Zhang · Mingli Song · Zunlei Feng
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。
Jiacong Hu · Jinxun Wu · Shengxuming Zhang · Shunyu Liu · Haofei Zhang · Mingli Song · Zunlei Feng
Kejia Chen · Junjun Zheng · Jiawen Zhang · Manxi Lin · Xiao Pan · Jiacong Hu · Jian Lou · Zunlei Feng · Mingli Song
Vision-Language Models (VLMs) often prioritize linguistic fluency over visual fidelity, leading to hallucinations where generated text contradicts the image. Countering this bias typically requires resource-heavy fine-tuning or high-latency verification methods that provide feedback only after th...