最新论文
每日更新的前沿 AI 研究论文，助您把握人工智能最新动向
LangScene-X：利用TriMap视频扩散重建可泛化的3D语言嵌入场景
Fangfu Liu, Hao Li, Jiawei Chi, et al.
8 days ago
基于图像的多模态推理：基础、方法与未来前沿
Zhaochen Su; Peng Xia; Hangyu Guo; Zhenhua Liu; Yan Ma; Xiaoye Qu; Jiaqi Liu; Yanshu Li; Kaide Zeng; Zhengyuan Yang; Linjie Li; Yu Cheng; Heng Ji; Junxian He; Yi R.
8 days ago
WebSailor：用于网络代理的超人类推理导航
Kuan Li, Zhongwang Zhang, Huifeng Yin, et al.
8 days ago
机器学习中的AI研究代理：在MLE-bench中进行搜索、探索与泛化
Edan Toledo, Karen Hambardzumyan, Martin Josifoski, et al.
10 days ago
局部感知的并行解码用于高效的自回归图像生成
Zhuoyang Zhang, Luke J. Huang, Chengyue Wu, et al.
11 days ago
FreeMorph：无需调参的扩散模型通用图像变形
Yukang Cao, Chenyang Si, Jinghao Wang, et al.
11 days ago
视觉-语言-动作模型综述：从动作分词的角度出发
Yifan Zhong, Fengshuo Bai, Shaofei Cai, et al.
11 days ago
在任意条件下测量任何深度
Boyuan Sun, Modi Jin, Bowen Yin, et al.
11 days ago
LongAnimation：基于动态全局-局部记忆的长动画生成
Nan Chen, Mengqi Huang, Yihao Meng, et al.
11 days ago
快手 Keye-VL 技术报告
Kwai Keye Team, Biao Yang, Bin Wen, et al.
11 days ago