Sökresultat - Zhao, Yanpeng

Unsupervised Transfer of Semantic Role Models from Verbal to Nominal Domain av Zhao, Yanpeng, Titov, Ivan

Hämta fulltext
Hämta fulltext

Visually Grounded Compound PCFGs av Zhao, Yanpeng, Titov, Ivan

Hämta fulltext
Hämta fulltext

An Empirical Study of Compound PCFGs av Zhao, Yanpeng, Titov, Ivan

Hämta fulltext
Hämta fulltext

On the Transferability of Visually Grounded PCFGs av Zhao, Yanpeng, Titov, Ivan

Hämta fulltext
Hämta fulltext

PCFGs Can Do Better: Inducing Probabilistic Context-Free Grammars with Many Symbols av Yang, Songlin, Zhao, Yanpeng, Tu, Kewei

Hämta fulltext
Hämta fulltext

Neural Bi-Lexicalized PCFG Induction av Yang, Songlin, Zhao, Yanpeng, Tu, Kewei

Hämta fulltext
Hämta fulltext

An Efficient Recipe for Long Context Extension via Middle-Focused Positional Encoding av Wu, Tong, Zhao, Yanpeng, Zheng, Zilong

Hämta fulltext
Hämta fulltext

DynaVol: Unsupervised Learning for Dynamic Scenes through Object-Centric Voxelization av Zhao, Yanpeng, Gao, Siyu, Wang, Yunbo, Yang, Xiaokang

Hämta fulltext
Hämta fulltext

AgentSentinel: An End-to-End and Real-Time Security Defense Framework for Computer-Use Agents av Hu, Haitao, Chen, Peng, Zhao, Yanpeng, Chen, Yuqi

Hämta fulltext
Hämta fulltext

Dynamic Scene Understanding through Object-Centric Voxelization and Neural Rendering av Zhao, Yanpeng, Hao, Yiwei, Gao, Siyu, Wang, Yunbo, Yang, Xiaokang

Hämta fulltext
Hämta fulltext

NEP: Autoregressive Image Editing via Next Editing Token Prediction av Wu, Huimin, Ma, Xiaojian, Zhao, Haozhe, Zhao, Yanpeng, Li, Qing

Hämta fulltext
Hämta fulltext

ESPIRE: A Diagnostic Benchmark for Embodied Spatial Reasoning of Vision-Language Models av Zhao, Yanpeng, Ding, Wentao, Li, Hongtao, Jia, Baoxiong, Zheng, Zilong

Hämta fulltext
Hämta fulltext

Probing Visual Planning in Image Editing Models av Zhou, Zhimu, Zhao, Yanpeng, Liao, Qiuyu, Zhao, Bo, Ma, Xiaojian

Hämta fulltext
Hämta fulltext

Back to the Future: Reverse-Consequence Modeling for Long-Horizon Particle Dynamics av Zhang, Leyan, He, Nantian, Ma, Jiajun, Zhao, Yanpeng, Wang, Yunbo

Hämta fulltext
Hämta fulltext

Connecting the Dots between Audio and Text without Parallel Data through Visual Knowledge Transfer av Zhao, Yanpeng, Hessel, Jack, Yu, Youngjae, Lu, Ximing, Zellers, Rowan, Choi, Yejin

Hämta fulltext
Hämta fulltext

NeoWorld: Neural Simulation of Explorable Virtual Worlds via Progressive 3D Unfolding av Zhao, Yanpeng, Guan, Shanyan, Wang, Yunbo, Ge, Yanhao, Li, Wei, Yang, Xiaokang

Hämta fulltext
Hämta fulltext

v-HUB: A Benchmark for Video Humor Understanding from Vision and Sound av Shi, Zhengpeng, Zhao, Yanpeng, Zhou, Jianqun, Wang, Yuxuan, Cui, Qinrong, Bi, Wei, Zhu, Songchun, Zhao, Bo, Zheng, Zilong

Hämta fulltext
Hämta fulltext

MERLOT Reserve: Neural Script Knowledge through Vision and Language and Sound av Zellers, Rowan, Lu, Jiasen, Lu, Ximing, Yu, Youngjae, Zhao, Yanpeng, Salehi, Mohammadreza, Kusupati, Aditya, Hessel, Jack, Farhadi, Ali, Choi, Yejin

Hämta fulltext
Hämta fulltext

MILR: Improving Multimodal Image Generation via Test-Time Latent Reasoning av Mi, Yapeng, Zhao, Yanpeng, Li, Hengli, Li, Chenxi, Wu, Huimin, Ma, Xiaojian, Zhu, Song-Chun, Wu, Ying Nian, Li, Qing

Hämta fulltext
Hämta fulltext