Alert button
Picture for Mengdi Xu

Mengdi Xu

Alert button

Creative Robot Tool Use with Large Language Models

Oct 19, 2023
Mengdi Xu, Peide Huang, Wenhao Yu, Shiqi Liu, Xilun Zhang, Yaru Niu, Tingnan Zhang, Fei Xia, Jie Tan, Ding Zhao

Viaarxiv icon

Adaptive Online Replanning with Diffusion Models

Oct 14, 2023
Siyuan Zhou, Yilun Du, Shun Zhang, Mengdi Xu, Yikang Shen, Wei Xiao, Dit-Yan Yeung, Chuang Gan

Figure 1 for Adaptive Online Replanning with Diffusion Models
Figure 2 for Adaptive Online Replanning with Diffusion Models
Figure 3 for Adaptive Online Replanning with Diffusion Models
Figure 4 for Adaptive Online Replanning with Diffusion Models
Viaarxiv icon

Guardians as You Fall: Active Mode Transition for Safe Falling

Oct 07, 2023
Yikai Wang, Mengdi Xu, Guanya Shi, Ding Zhao

Viaarxiv icon

What Went Wrong? Closing the Sim-to-Real Gap via Differentiable Causal Discovery

Jun 28, 2023
Peide Huang, Xilun Zhang, Ziang Cao, Shiqi Liu, Mengdi Xu, Wenhao Ding, Jonathan Francis, Bingqing Chen, Ding Zhao

Figure 1 for What Went Wrong? Closing the Sim-to-Real Gap via Differentiable Causal Discovery
Figure 2 for What Went Wrong? Closing the Sim-to-Real Gap via Differentiable Causal Discovery
Figure 3 for What Went Wrong? Closing the Sim-to-Real Gap via Differentiable Causal Discovery
Figure 4 for What Went Wrong? Closing the Sim-to-Real Gap via Differentiable Causal Discovery
Viaarxiv icon

Embodied Executable Policy Learning with Language-based Scene Summarization

Jun 09, 2023
Jielin Qiu, Mengdi Xu, William Han, Seungwhan Moon, Ding Zhao

Figure 1 for Embodied Executable Policy Learning with Language-based Scene Summarization
Figure 2 for Embodied Executable Policy Learning with Language-based Scene Summarization
Figure 3 for Embodied Executable Policy Learning with Language-based Scene Summarization
Figure 4 for Embodied Executable Policy Learning with Language-based Scene Summarization
Viaarxiv icon

Hyper-Decision Transformer for Efficient Online Policy Adaptation

Apr 17, 2023
Mengdi Xu, Yuchen Lu, Yikang Shen, Shun Zhang, Ding Zhao, Chuang Gan

Figure 1 for Hyper-Decision Transformer for Efficient Online Policy Adaptation
Figure 2 for Hyper-Decision Transformer for Efficient Online Policy Adaptation
Figure 3 for Hyper-Decision Transformer for Efficient Online Policy Adaptation
Figure 4 for Hyper-Decision Transformer for Efficient Online Policy Adaptation
Viaarxiv icon

Transfer Knowledge from Natural Language to Electrocardiography: Can We Detect Cardiovascular Disease Through Language Models?

Jan 21, 2023
Jielin Qiu, William Han, Jiacheng Zhu, Mengdi Xu, Michael Rosenberg, Emerson Liu, Douglas Weber, Ding Zhao

Figure 1 for Transfer Knowledge from Natural Language to Electrocardiography: Can We Detect Cardiovascular Disease Through Language Models?
Figure 2 for Transfer Knowledge from Natural Language to Electrocardiography: Can We Detect Cardiovascular Disease Through Language Models?
Figure 3 for Transfer Knowledge from Natural Language to Electrocardiography: Can We Detect Cardiovascular Disease Through Language Models?
Figure 4 for Transfer Knowledge from Natural Language to Electrocardiography: Can We Detect Cardiovascular Disease Through Language Models?
Viaarxiv icon

Curriculum Reinforcement Learning using Optimal Transport via Gradual Domain Adaptation

Oct 18, 2022
Peide Huang, Mengdi Xu, Jiacheng Zhu, Laixi Shi, Fei Fang, Ding Zhao

Figure 1 for Curriculum Reinforcement Learning using Optimal Transport via Gradual Domain Adaptation
Figure 2 for Curriculum Reinforcement Learning using Optimal Transport via Gradual Domain Adaptation
Figure 3 for Curriculum Reinforcement Learning using Optimal Transport via Gradual Domain Adaptation
Figure 4 for Curriculum Reinforcement Learning using Optimal Transport via Gradual Domain Adaptation
Viaarxiv icon

Semantics-Consistent Cross-domain Summarization via Optimal Transport Alignment

Oct 10, 2022
Jielin Qiu, Jiacheng Zhu, Mengdi Xu, Franck Dernoncourt, Trung Bui, Zhaowen Wang, Bo Li, Ding Zhao, Hailin Jin

Figure 1 for Semantics-Consistent Cross-domain Summarization via Optimal Transport Alignment
Figure 2 for Semantics-Consistent Cross-domain Summarization via Optimal Transport Alignment
Figure 3 for Semantics-Consistent Cross-domain Summarization via Optimal Transport Alignment
Figure 4 for Semantics-Consistent Cross-domain Summarization via Optimal Transport Alignment
Viaarxiv icon

Trustworthy Reinforcement Learning Against Intrinsic Vulnerabilities: Robustness, Safety, and Generalizability

Sep 16, 2022
Mengdi Xu, Zuxin Liu, Peide Huang, Wenhao Ding, Zhepeng Cen, Bo Li, Ding Zhao

Figure 1 for Trustworthy Reinforcement Learning Against Intrinsic Vulnerabilities: Robustness, Safety, and Generalizability
Figure 2 for Trustworthy Reinforcement Learning Against Intrinsic Vulnerabilities: Robustness, Safety, and Generalizability
Figure 3 for Trustworthy Reinforcement Learning Against Intrinsic Vulnerabilities: Robustness, Safety, and Generalizability
Figure 4 for Trustworthy Reinforcement Learning Against Intrinsic Vulnerabilities: Robustness, Safety, and Generalizability
Viaarxiv icon