1 code implementation • 22 Dec 2024 • Yuxiang Zhang, YuQi Yang, Jiangming Shu, Yuhang Wang, Jinlin Xiao, Jitao Sang
OpenAI's recent introduction of Reinforcement Fine-Tuning (RFT) showcases the potential of reasoning foundation model and offers a new paradigm for fine-tuning beyond simple pattern imitation.
1 code implementation • 29 Nov 2024 • Yuxiang Zhang, Shangxi Wu, YuQi Yang, Jiangming Shu, Jinlin Xiao, Chao Kong, Jitao Sang
The technical report introduces O1-CODER, an attempt to replicate OpenAI's o1 model with a focus on coding tasks.
no code implementations • 21 Nov 2024 • Guanzhou Lan, YuQi Yang, Zhigang Wang, Dong Wang, Bin Zhao, Xuelong Li
Specifically, our method comprises a degradation disentanglement module and a degradation-aware contrastive learning module.
no code implementations • 16 Oct 2024 • Guanzhou Lan, Qianli Ma, YuQi Yang, Zhigang Wang, Dong Wang, Xuelong Li, Bin Zhao
In this paper, we identify two primary factors contributing to performance degradation: fitting errors and the inference gap.
no code implementations • 27 Mar 2024 • YuQi Yang, Xiaowen Huang, Jitao Sang
Large language models (LLMs), renowned for their impressive capabilities in various tasks, have significantly advanced artificial intelligence.
1 code implementation • CVPR 2024 • YuQi Yang, Peng-Tao Jiang, Qibin Hou, Hao Zhang, Jinwei Chen, Bo Li
Furthermore, to control the parameters and computational cost brought by the increase in the number of experts, we take inspiration from LoRA and propose to leverage the low-rank format of a vanilla convolution in the expert network.
no code implementations • 21 Mar 2024 • YuQi Yang, Peng-Tao Jiang, Jing Wang, Hao Zhang, Kai Zhao, Jinwei Chen, Bo Li
Multi-modal large language models (MLLMs) can understand image-language prompts and demonstrate impressive reasoning ability.
1 code implementation • CVPR 2024 • Boyuan Sun, YuQi Yang, Le Zhang, Ming-Ming Cheng, Qibin Hou
Motivated by these, we aim to improve the use efficiency of unlabeled data by designing two novel label propagation strategies.
no code implementations • 14 May 2023 • Wentao Hu, Xiurong Jiang, Jiarun Liu, YuQi Yang, Hui Tian
In the field of few-shot learning (FSL), extensive research has focused on improving network structures and training strategies.
Few-Shot Learning
Unsupervised Few-Shot Image Classification
no code implementations • 2 May 2023 • Peng-Tao Jiang, YuQi Yang
Weakly supervised semantic segmentation with weak labels is a long-lived ill-posed problem.
1 code implementation • 14 Apr 2023 • Siming Yan, YuQi Yang, YuXiao Guo, Hao Pan, Peng-Shuai Wang, Xin Tong, Yang Liu, QiXing Huang
Masked autoencoders (MAE) have recently been introduced to 3D self-supervised pretraining for point clouds due to their great success in NLP and computer vision.
1 code implementation • CVPR 2024 • Peng-Tao Jiang, YuQi Yang, Yang Cao, Qibin Hou, Ming-Ming Cheng, Chunhua Shen
To date, most existing datasets focus on autonomous driving scenes.
no code implementations • 20 Dec 2022 • YuQi Yang, Songyun Yang, Jiyang Xie. Zhongwei Si, Kai Guo, Ke Zhang, Kongming Liang
We adopt a multi-head architecture with multiple prediction heads (i. e., classifiers) to obtain predictions from different depths in the DNNs and introduce shallow information for the UI.
1 code implementation • CVPR 2022 • Peng-Tao Jiang, YuQi Yang, Qibin Hou, Yunchao Wei
Our framework conducts the global network to learn the captured rich object detail knowledge from a global view and thereby produces high-quality attention maps that can be directly used as pseudo annotations for semantic segmentation networks.
Ranked #17 on
Weakly-Supervised Semantic Segmentation
on PASCAL VOC 2012 test
(using extra training data)