Zobrazeno 1 - 10
of 826
pro vyhledávání: '"Yang, Cheng Fu"'
Humans recognize objects after observing only a few examples, a remarkable capability enabled by their inherent language understanding of the real-world environment. Developing verbalized and interpretable representation can significantly improve mod
Externí odkaz:
http://arxiv.org/abs/2411.18651
Autor:
Li, Cheng-Yi, Chang, Kao-Jung, Yang, Cheng-Fu, Wu, Hsin-Yu, Chen, Wenting, Bansal, Hritik, Chen, Ling, Yang, Yi-Ping, Chen, Yu-Chun, Chen, Shih-Pin, Lirng, Jiing-Feng, Chang, Kai-Wei, Chiou, Shih-Hwa
Multi-modal large language models (MLLMs) have been given free rein to explore exciting medical applications with a primary focus on radiology report generation. Nevertheless, the preliminary success in 2D radiology captioning is incompetent to refle
Externí odkaz:
http://arxiv.org/abs/2407.02235
Path planning is a fundamental scientific problem in robotics and autonomous navigation, requiring the derivation of efficient routes from starting to destination points while avoiding obstacles. Traditional algorithms like A* and its variants are ca
Externí odkaz:
http://arxiv.org/abs/2407.02511
Finetuning language agents with reasoning-action trajectories is effective, but obtaining these trajectories from human annotations or stronger models is costly and sometimes impractical. In this paper, we investigate the use of self-training in lang
Externí odkaz:
http://arxiv.org/abs/2406.01495
Task planning for embodied AI has been one of the most challenging problems where the community does not meet a consensus in terms of formulation. In this paper, we aim to tackle this problem with a unified framework consisting of an end-to-end train
Externí odkaz:
http://arxiv.org/abs/2312.01097
Autor:
Yang, Cheng-Fu, Chen, Yen-Chun, Yang, Jianwei, Dai, Xiyang, Yuan, Lu, Wang, Yu-Chiang Frank, Chang, Kai-Wei
End-to-end Transformers have demonstrated an impressive success rate for Embodied Instruction Following when the environment has been seen in training. However, they tend to struggle when deployed in an unseen environment. This lack of generalizabili
Externí odkaz:
http://arxiv.org/abs/2310.12344
We tackle the problem of target-free text-guided image manipulation, which requires one to modify the input reference image based on the given text instruction, while no ground truth target image is observed during training. To address this challengi
Externí odkaz:
http://arxiv.org/abs/2211.14544
Autor:
Yang, Cheng-Fu, Tsai, Yao-Hung Hubert, Fan, Wan-Cyuan, Salakhutdinov, Ruslan, Morency, Louis-Philippe, Wang, Yu-Chiang Frank
Novel object captioning (NOC) aims to describe images containing objects without observing their ground truth captions during training. Due to the absence of caption annotation, captioning models cannot be directly optimized via sequence-to-sequence
Externí odkaz:
http://arxiv.org/abs/2209.12343
Autor:
Yang, Chiao-An, Tan, Cheng-Yo, Fan, Wan-Cyuan, Yang, Cheng-Fu, Wu, Meng-Lin, Wang, Yu-Chiang Frank
In this paper, we address the task of semantics-guided image outpainting, which is to complete an image by generating semantically practical content. Different from most existing image outpainting works, we approach the above task by understanding an
Externí odkaz:
http://arxiv.org/abs/2205.02958
Publikováno v:
In Calphad December 2024 87
