Search Results for author: Zhuangdi Zhu

Found 10 papers, 4 papers with code

Dialogue is Better Than Monologue: Instructing Medical LLMs via Strategical Conversations

no code implementations29 Jan 2025 Zijie Liu, Xinyu Zhao, Jie Peng, Zhuangdi Zhu, Qingyu Chen, Xia Hu, Tianlong Chen

Current medical AI systems often fail to replicate real-world clinical reasoning, as they are predominantly trained and evaluated on static text and question-answer tasks.

Language and Multimodal Models in Sports: A Survey of Datasets and Applications

no code implementations18 Jun 2024 Haotian Xia, Zhengbang Yang, Yun Zhao, Yuqing Wang, Jingxi Li, Rhys Tracy, Zhuangdi Zhu, Yuan-Fang Wang, Hanjie Chen, Weining Shen

This survey provides a foundational resource for researchers and practitioners aiming to leverage NLP and multimodal models in sports, offering insights into current trends and future opportunities in the field.

Sports Analytics Survey

Defending Backdoor Data Poisoning Attacks by Using Noisy Label Defense Algorithm

no code implementations29 Sep 2021 Boyang Liu, Zhuangdi Zhu, Pang-Ning Tan, Jiayu Zhou

We first discuss the limitations of directly using the noisy-label defense algorithms to defend against backdoor attacks.

Backdoor Attack Data Poisoning

Data-Free Knowledge Distillation for Heterogeneous Federated Learning

4 code implementations20 May 2021 Zhuangdi Zhu, Junyuan Hong, Jiayu Zhou

Federated Learning (FL) is a decentralized machine-learning paradigm, in which a global server iteratively averages the model parameters of local users without accessing their data.

Data-free Knowledge Distillation Federated Learning +1

Off-Policy Imitation Learning from Observations

1 code implementation NeurIPS 2020 Zhuangdi Zhu, Kaixiang Lin, Bo Dai, Jiayu Zhou

To further accelerate the learning procedure, we regulate the policy update with an inverse action model, which assists distribution matching from the perspective of mode-covering.

Imitation Learning

Learning Sparse Rewarded Tasks from Sub-Optimal Demonstrations

1 code implementation1 Apr 2020 Zhuangdi Zhu, Kaixiang Lin, Bo Dai, Jiayu Zhou

SAIL bridges the advantages of IL and RL to reduce the sample complexity substantially, by effectively exploiting sup-optimal demonstrations and efficiently exploring the environment to surpass the demonstrated performance.

continuous-control Continuous Control +4

Cannot find the paper you are looking for? You can Submit a new open access paper.