Huixin Zhan

Prof. Huixin Zhan

CSE, New Mexico Institute of Mining and Technology, Socorro, New Mexico, USA
orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
4 March 2021 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
Huixin ZhanHuixin Zhan
Huixin Zhan
FTFeng Tao
Feng Tao
YCYongcan Cao
Yongcan Cao
Human demonstrations can provide trustful samples to train reinforcement learning algorithms for robots to learn complex behaviors in real-world environments. However, obtaining sufficient demonstrations may be impractical because many behaviors are difficult for humans to demonstrate. A more practical approach is to replace human demonstrations by human queries, i.e., preference-based reinforcement learning. One key limitation of the existing algorithms is the need for a significant amount of human queries because a large number of labeled data is needed to train neural networks for the approximation of a continuous, high-dimensional reward function. To reduce and minimize the need for human queries, we propose a new GAN-assisted human preference-based reinforcement learning approach that uses a generative adversarial network (GAN) to learn human preferences and then replace the role of human in assigning preferences. The adversarial neural network is simple and only has a binary output, hence requiring much less human queries to train. Moreover, a maximum entropy based reinforcement learning algorithm is designed to shape the loss towards the desired regions or away from the undesired regions. To show the effectiveness of the proposed approach, we present some studies on complex robotic tasks without access to the environment reward in a typical MuJoCo robot locomotion environment. The obtained results show our method can achieve a reduction of about 99.8% human time without performance sacrifice.

28 July 2023 in Neural Processing Letters
Verified
Journal Article
Closed access
PDF file
LGLiyuan Gao
Liyuan Gao
Huixin ZhanHuixin Zhan
Huixin Zhan
VSVictor Sheng
Victor Sheng

10 September 2021
Verified
Book Chapter
Closed access
PDF file
Huixin ZhanHuixin Zhan
Huixin Zhan
WLWei-Ming Lin
Wei-Ming Lin
YCYongcan Cao
Yongcan Cao

24 March 2025 in Nature Machine Intelligence
Verified
Journal Article
Closed access
PDF file
Huixin ZhanHuixin Zhan
Huixin Zhan
JMJason H. Moore
Jason H. Moore
ZZZijun Zhang
Zijun Zhang

21 October 2023
Verified
Conference Paper
Open access
Huixin ZhanHuixin Zhan
Huixin Zhan
KZKun Zhang
Kun Zhang
Zhong ChenZhong Chen
Zhong Chen
VSVictor Sheng
Victor Sheng

12 February 2024 in arXiv
Verified
Preprint
Open access
PDF file
Huixin ZhanHuixin Zhan
Huixin Zhan
YWYingnian Wu
Yingnian Wu
ZZZijun Zhang
Zijun Zhang
Although DNA foundation models have advanced the understanding of genomes, they still face significant challenges in the limited scale and diversity of genomic data. This limitation starkly contrasts with the success of natural language foundation models, which thrive on substantially larger scales. Furthermore, genome understanding involves numerous downstream genome annotation tasks with inherent data heterogeneity, thereby necessitating more efficient and robust fine-tuning methods tailored for genomics. Here, we present \textsc{Lingo}: \textsc{L}anguage prefix f\textsc{In}e-tuning for \textsc{G}en\textsc{O}mes. Unlike DNA foundation models, \textsc{Lingo} strategically leverages natural language foundation models' contextual cues, recalibrating their linguistic knowledge to genomic sequences. \textsc{Lingo} further accommodates numerous, heterogeneous downstream fine-tune tasks by an adaptive rank sampling method that prunes and stochastically reintroduces pruned singular vectors within small computational budgets. Adaptive rank sampling outperformed existing fine-tuning methods on all benchmarked 14 genome understanding tasks, while requiring fewer than 2\% of trainable parameters as genomic-specific adapters. Impressively, applying these adapters on natural language foundation models matched or even exceeded the performance of DNA foundation models. \textsc{Lingo} presents a new paradigm of efficient and scalable genome understanding via genomic-specific adapters on language models.