We further examine the factors influencing the causal structure of the implied SCM, revealing that in-context learning, supervised fine-tuning, and reinforcement learning on human feedback significantly impact the causal relations.
1 code implementation • 16 Jan 2024 • Xu Yan, Haiming Zhang, Yingjie Cai, Jingming Guo, Weichao Qiu, Bin Gao, Kaiqiang Zhou, Yue Zhao, Huan Jin, Jiantao Gao, Zhen Li, Lihui Jiang, Wei zhang, Hongbo Zhang, Dengxin Dai, Bingbing Liu
The rise of large foundation models, trained on extensive datasets, is revolutionizing the field of AI.
In this paper, to lower the annotation cost, we propose a self-supervised event-based monocular depth estimation framework named EMoDepth.
By treating the quantization discrepancy as relative noise and identifying sensitive part(s) of a model, we propose an efficient quantization approach encompassing both global and local strategies.
1 code implementation • 16 Nov 2023 • Junying Chen, Xidong Wang, Anningzhe Gao, Feng Jiang, Shunian Chen, Hongbo Zhang, Dingjie Song, Wenya Xie, Chuyi Kong, Jianquan Li, Xiang Wan, Haizhou Li, Benyou Wang
We validate the new protocol in the domains where proprietary LLMs like ChatGPT perform relatively poorly, such as Traditional Chinese Medicine.
2) The enhanced performance of the larger model further boosts the performance of the smaller model.
In this paper, we evaluate different abilities of GPT-4V including visual understanding, language understanding, visual puzzle solving, and understanding of other modalities such as depth, thermal, video, and audio.
The adaptive graph convolution learns the relationship between different water quality parameters, updates the state information of each parameter, and improves the learning ability of the update relationship between nodes.
Further analysis also shows that our representation learning framework can fill the semantic gap by coagulating representations of both text and graph knowledge.
This gives us a hint that relational knowledge might not be redundant to the stored knowledge of PLMs, but rather be complementary.
1 code implementation • 24 May 2023 • Hongbo Zhang, Junying Chen, Feng Jiang, Fei Yu, Zhihong Chen, Jianquan Li, Guiming Chen, Xiangbo Wu, Zhiyi Zhang, Qingying Xiao, Xiang Wan, Benyou Wang, Haizhou Li
Experimental results demonstrate that HuatuoGPT achieves state-of-the-art results in performing medical consultation among open-source LLMs in GPT-4 evaluation, human evaluation, and medical benchmark datasets.
In this paper, we propose a novel context-aware graph-attention model (Context-aware GAT), which can effectively incorporate global features of relevant knowledge graphs based on a context-enhanced knowledge aggregation process.
1 code implementation • 20 Apr 2023 • Zhihong Chen, Feng Jiang, Junying Chen, Tiannan Wang, Fei Yu, Guiming Chen, Hongbo Zhang, Juhao Liang, Chen Zhang, Zhiyi Zhang, Jianquan Li, Xiang Wan, Benyou Wang, Haizhou Li
This paper presents our efforts to democratize ChatGPT across language.
This survey paper proposes a clearer view of natural language reasoning in the field of Natural Language Processing (NLP), both conceptually and practically.
The great potential of unsupervised monocular depth estimation has been demonstrated by many works due to low annotation cost and impressive accuracy comparable to supervised methods.
In this paper, we propose a novel framework to improve medical dialogue generation by considering features centered on domain-specific terminology.
In this work, we introduce a framework for training generalized locomotion (GenLoco) controllers for quadrupedal robots.
An efficient 3D scene perception algorithm is a vital component for autonomous driving and robotics systems.
Ranked #6 on 3D Semantic Scene Completion on SemanticKITTI
Specifically, the network takes a raw point cloud as input, and merges the features from the segmentation branch into the completion branch hierarchically to provide semantic information.
Ranked #4 on 3D Semantic Scene Completion on SemanticKITTI
LiDAR-based SLAM system is admittedly more accurate and stable than others, while its loop closure detection is still an open issue.
In this paper, we present an uncertainty-aware INVASE to quantify predictive confidence of healthcare problem.
We capture map-centric features that correspond to intersection structures under a spatial-temporal graph representation, and use two MAAMs (mutually auxiliary attention module) that cover respectively lane-level and exitlevel intentions to predict a target that best matches intersection elements in map-centric feature space.
3 code implementations • 19 Oct 2020 • Ming Zhou, Jun Luo, Julian Villella, Yaodong Yang, David Rusu, Jiayu Miao, Weinan Zhang, Montgomery Alban, Iman Fadakar, Zheng Chen, Aurora Chongxi Huang, Ying Wen, Kimia Hassanzadeh, Daniel Graves, Dong Chen, Zhengbang Zhu, Nhat Nguyen, Mohamed Elsayed, Kun Shao, Sanjeevan Ahilan, Baokuan Zhang, Jiannan Wu, Zhengang Fu, Kasra Rezaee, Peyman Yadmellat, Mohsen Rohani, Nicolas Perez Nieves, Yihan Ni, Seyedershad Banijamali, Alexander Cowen Rivers, Zheng Tian, Daniel Palenicek, Haitham Bou Ammar, Hongbo Zhang, Wulong Liu, Jianye Hao, Jun Wang
We open-source the SMARTS platform and the associated benchmark tasks and evaluation metrics to encourage and empower research on multi-agent learning for autonomous driving.
Generative adversarial imitation learning (GAIL) has shown promising results by taking advantage of generative adversarial nets, especially in the field of robot learning.