作者位次 #2/5ECCV 2026Poster
EatVid-Bench: A Multimodal Fine-Grained Eating Behavior Video Dataset
Xiangpeng Zheng · Zhenbo Xu · Gong Huang · Zhu Li · Qinghong Yang
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。
Xiangpeng Zheng · Zhenbo Xu · Gong Huang · Zhu Li · Qinghong Yang
Zicheng Kong · Dehua Ma · Zhenbo Xu · Anwen Yang · Yiwei Ru · Haoran Wang · Zixuan Zhou · Fuqing Bie · Liuyu Xiang · Huijia Wu · Jian Zhao · Zhaofeng He
Dianyun Wang · Qingsen Ma · Yuhu Shang · Zhifeng Lu · Zhenbo Xu · Lechen Ning · Huijia Wu · Zhaofeng He
Safety alignment—training large language models (LLMs) to refuse harmful requests while remaining helpful—is critical for responsible deployment. Prior work established that safety behaviors are governed by low-rank structures, suggesting parameter-efficient fine-tuning (PEFT) should be well-suit...
Zixuan Zhou · Yujun Diao · Zicheng Kong · Dehua Ma · Zhenbo Xu · Pei Pei Li · Zhaofeng He
Large Language Models (LLMs) are primarily constrained by memory and bandwidth bottlenecks during deployment. Although Vector Quantization (VQ) has emerged as a promising solution, existing methods incur inference overhead due to massive codebook storage and intensive index lookups. Moreover, the...