Zobrazeno 1 - 10
of 17 239
pro vyhledávání: '"An, JunPeng"'
Autor:
Ji, Yanfeng, Wang, Shutong, Xu, Ruyi, Chen, Jingying, Jiang, Xinzhou, Deng, Zhengyu, Quan, Yuxuan, Liu, Junpeng
Children with Autism Spectrum Disorder (ASD) often exhibit atypical facial expressions. However, the specific objective facial features that underlie this subjective perception remain unclear. In this paper, we introduce a novel dataset, Hugging Rain
Externí odkaz:
http://arxiv.org/abs/2411.13797
The thermodynamic limits of the XYZ spin chain with periodic or twisted boundary conditions are studied. By using the technique of characterizing the eigenvalue of the transfer matrix by the $T-Q$ relation and by the zeros of the associated polynomia
Externí odkaz:
http://arxiv.org/abs/2411.12200
Autor:
Yan, Tianyi, Wu, Dongming, Han, Wencheng, Jiang, Junpeng, Zhou, Xia, Zhan, Kun, Xu, Cheng-zhong, Shen, Jianbing
Autonomous driving evaluation requires simulation environments that closely replicate actual road conditions, including real-world sensory data and responsive feedback loops. However, many existing simulations need to predict waypoints along fixed ro
Externí odkaz:
http://arxiv.org/abs/2411.11252
With recent advances in simulating quantum phenomena in cold atoms, the higher-rank spin tensor Hall effect was discovered in larger spin systems with spin-tensor-momentum coupling, which is an extension of the celebrated spin Hall effects in larger
Externí odkaz:
http://arxiv.org/abs/2411.01736
Low-Earth orbit (LEO) satellites utilizing beam hopping (BH) technology offer extensive coverage, low latency, high bandwidth, and significant flexibility. However, the uneven geographical distribution and temporal variability of ground traffic deman
Externí odkaz:
http://arxiv.org/abs/2411.08896
Autor:
Liu, Junpeng, Ou, Tianyue, Song, Yifan, Qu, Yuxiao, Lam, Wai, Xiong, Chenyan, Chen, Wenhu, Neubig, Graham, Yue, Xiang
Text-rich visual understanding-the ability to process environments where dense textual content is integrated with visuals-is crucial for multimodal large language models (MLLMs) to interact effectively with structured environments. To enhance this ca
Externí odkaz:
http://arxiv.org/abs/2410.13824
Very recently, Alon and Frankl, and Gerbner studied the maximum number of edges in $n$-vertex $F$-free graphs with bounded matching number, respectively. We consider the analogous Tur\'{a}n problems on hypergraphs with bounded matching number, and we
Externí odkaz:
http://arxiv.org/abs/2410.07455
Autor:
Zhang, Yuan, Fan, Chun-Kai, Ma, Junpeng, Zheng, Wenzhao, Huang, Tao, Cheng, Kuan, Gudovskiy, Denis, Okuno, Tomoyuki, Nakata, Yohei, Keutzer, Kurt, Zhang, Shanghang
In vision-language models (VLMs), visual tokens usually consume a significant amount of computational overhead, despite their sparser information density compared to text tokens. To address this, most existing methods learn a network to prune redunda
Externí odkaz:
http://arxiv.org/abs/2410.04417
MLLM agents demonstrate potential for complex embodied tasks by retrieving multimodal task-relevant trajectory data. However, current retrieval methods primarily focus on surface-level similarities of textual or visual cues in trajectories, neglectin
Externí odkaz:
http://arxiv.org/abs/2410.03450
Video stereo matching is the task of estimating consistent disparity maps from rectified stereo videos. There is considerable scope for improvement in both datasets and methods within this area. Recent learning-based methods often focus on optimizing
Externí odkaz:
http://arxiv.org/abs/2409.20283