1 code implementation • 26 Mar 2024 • Wangyue Li, Liangzhi Li, Tong Xiang, Xiao Liu, Wei Deng, Noa Garcia
Additionally, we propose two methods to quantify the consistency and confidence of LLMs' output, which can be generalized to other QA evaluation benchmarks.
no code implementations • 13 Dec 2023 • Xiaojie Hong, Zixin Song, Liangzhi Li, Xiaoli Wang, Feiyan Liu
Medical Visual Question Answering (Med-VQA) is a very important task in healthcare industry, which answers a natural language question with a medical image.
no code implementations • 18 Nov 2023 • Qi Li, Liangzhi Li, Zhouqiang Jiang, Bowen Wang
Visual prompting, an efficient method for transfer learning, has shown its potential in vision tasks.
1 code implementation • 7 Nov 2023 • Jiahao Zhang, Bowen Wang, Liangzhi Li, Yuta Nakashima, Hajime Nagahara
Our findings suggest that InMeMo offers a versatile and efficient way to enhance the performance of visual ICL with lightweight training.
1 code implementation • 2 Nov 2023 • Zhouqiang Jiang, Bowen Wang, Tong Xiang, Zhaofeng Niu, Hong Tang, Guangshun Li, Liangzhi Li
Learning representations from videos requires understanding continuous motion and visual correspondences between frames.
1 code implementation • 27 Oct 2023 • Guoxin Chen, Yiming Qian, Bowen Wang, Liangzhi Li
The large language models have achieved superior performance on various natural language tasks.
no code implementations • 24 Oct 2023 • Junyi Liu, Liangzhi Li, Tong Xiang, Bowen Wang, Yiming Qian
Our summarization compression can reduce 65% of the retrieval token size with further 0. 3% improvement on the accuracy; semantic compression provides a more flexible way to trade-off the token size with performance, for which we can reduce the token size by 20% with only 1. 6% of accuracy drop.
no code implementations • 23 Oct 2023 • Tianyuan Shi, Liangzhi Li, Zijian Lin, Tao Yang, Xiaojun Quan, Qifan Wang
Efficient knowledge retrieval plays a pivotal role in ensuring the success of end-to-end task-oriented dialogue systems by facilitating the selection of relevant information necessary to fulfill user requests.
1 code implementation • 27 Sep 2023 • Bowen Wang, Jiaxing Zhang, Ran Zhang, Yunqin Li, Liangzhi Li, Yuta Nakashima
We introduce a new pipeline known as Revision-based Transformer Facade Parsing (RTFP).
1 code implementation • 23 Aug 2023 • Feiyu Zhang, Liangzhi Li, JunHao Chen, Zhouqiang Jiang, Bowen Wang, Yiming Qian
This approach is different from the pruning method as it is not limited by the initial number of training parameters, and each parameter matrix has a higher rank upper bound for the same training overhead.
1 code implementation • NeurIPS 2023 • Tong Xiang, Liangzhi Li, Wangyue Li, Mingbai Bai, Lu Wei, Bowen Wang, Noa Garcia
In an effort to minimize the reliance on human resources for performance evaluation, we offer off-the-shelf judgment models for automatically assessing the LF output of LLMs given benchmark questions.
1 code implementation • CVPR 2023 • Bowen Wang, Liangzhi Li, Yuta Nakashima, Hajime Nagahara
Using some image classification tasks as our testbed, we demonstrate BotCL's potential to rebuild neural networks for better interpretability.
no code implementations • 7 Apr 2021 • Vivek Singh Bawa, Gurkirt Singh, Francis KapingA, Inna Skarga-Bandurova, Elettra Oleari, Alice Leporini, Carmela Landolfo, Pengfei Zhao, Xi Xiang, Gongning Luo, Kuanquan Wang, Liangzhi Li, Bowen Wang, Shang Zhao, Li Li, Armando Stabile, Francesco Setti, Riccardo Muradore, Fabio Cuzzolin
For an autonomous robotic system, monitoring surgeon actions and assisting the main surgeon during a procedure can be very challenging.
1 code implementation • 25 Nov 2020 • Bowen Wang, Liangzhi Li, Manisha Verma, Yuta Nakashima, Ryo Kawasaki, Hajime Nagahara
Few-shot learning (FSL) approaches are usually based on an assumption that the pre-trained knowledge can be obtained from base (seen) categories and can be well transferred to novel (unseen) categories.
Ranked #34 on Few-Shot Image Classification on CIFAR-FS 5-way (5-shot)
1 code implementation • 7 Nov 2020 • Liangzhi Li, Manisha Verma, Bowen Wang, Yuta Nakashima, Hajime Nagahara, Ryo Kawasaki
Our severity grading method was able to validate crossing points with precision and recall of 96. 3% and 96. 3%, respectively.
no code implementations • 19 Oct 2020 • Bowen Wang, Liangzhi Li, Yuta Nakashima, Ryo Kawasaki, Hajime Nagahara, Yasushi Yagi
Semantic video segmentation is a key challenge for various applications.
1 code implementation • ICCV 2021 • Liangzhi Li, Bowen Wang, Manisha Verma, Yuta Nakashima, Ryo Kawasaki, Hajime Nagahara
Explainable artificial intelligence has been gaining attention in the past few years.
1 code implementation • MIDL 2019 • Liangzhi Li, Manisha Verma, Yuta Nakashima, Ryo Kawasaki, Hajime Nagahara
Retinal imaging serves as a valuable tool for diagnosis of various diseases.
2 code implementations • 12 Dec 2019 • Liangzhi Li, Manisha Verma, Yuta Nakashima, Hajime Nagahara, Ryo Kawasaki
Retinal vessel segmentation is of great interest for diagnosis of retinal vascular diseases.
Ranked #5 on Retinal Vessel Segmentation on CHASE_DB1