Sitemap
A list of all the posts and pages found on the site. For you robots out there, there is an XML version available for digesting as well.
Pages
Posts
Future Blog Post
Published:
This post will show up by default. To disable scheduling of future posts, edit config.yml and set future: false.
Blog Post number 4
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
Blog Post number 3
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
Blog Post number 2
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
Blog Post number 1
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
publications
[NeurIPS’22] TREC: Transient Redundancy Elimination-based Convolution
Jiawei Guan, Feng Zhang, Jiesong Liu, Hsing-Hsuan Sung, Ruofan Wu, Xiaoyong Du, Xipeng ShenPublished in Conference on Neural Information Processing Systems (NeurIPS), 2022
We propose TREC, a method that significantly reduces transient redundancy in convolutional computations.
Recommended citation: Jiawei Guan, Feng Zhang, Jiesong Liu, Hsing-Hsuan Sung, Ruofan Wu, Xiaoyong Du, Xipeng Shen. (2022). "TREC: Transient Redundancy Elimination-based Convolution." NeurIPS 2022.
Paper
[TPDS’22] Exploring Query Processing on CPU-GPU Integrated Edge Device
Jiesong Liu, Feng Zhang, Hourun Li, Dalin Wang, Weitao Wan, Xiaokun Fang, Jidong Zhai, Xiaoyong DuPublished in IEEE Transactions on Parallel and Distributed Systems (TPDS), 2022
This paper explores efficient query processing techniques on CPU-GPU integrated edge devices.
Recommended citation: Jiesong Liu, Feng Zhang, Hourun Li, Dalin Wang, Weitao Wan, Xiaokun Fang, Jidong Zhai, Xiaoyong Du. (2022). "Exploring Query Processing on CPU-GPU Integrated Edge Device." TPDS 2022.
Paper
[ASPLOS’23] Space Efficient TREC for Enabling Deep Learning on Microcontrollers
Jiesong Liu, Feng Zhang, Jiawei Guan, Hsing-Hsuan Sung, Xiaoyong Du, Xipeng ShenPublished in The ACM International Conference on Architecture Support for Programming Languages and Operating Systems (ASPLOS), 2023
This paper presents a space-efficient approach to transient redundancy elimination for deep learning on MCUs.
Recommended citation: Jiesong Liu, Feng Zhang, Jiawei Guan, Hsing-Hsuan Sung, Xiaoyong Du, Xipeng Shen. (2023). "Space Efficient TREC for Enabling Deep Learning on Microcontrollers." ASPLOS 2023.
Paper | Slides
[VLDB’23] Approximating Probabilistic Group Steiner Trees in Graphs
Shuang Yang, Yahui Sun, Jiesong Liu, Xiaokui Xiao, Ronghua Li, Zhewei WeiPublished in Proceedings of the VLDB Endowment (PVLDB), 2023
This paper presents a new approach to approximating probabilistic group Steiner trees in large-scale graphs.
Recommended citation: Shuang Yang, Yahui Sun, Jiesong Liu, Xiaokui Xiao, Ronghua Li, Zhewei Wei. (2023). "Approximating Probabilistic Group Steiner Trees in Graphs." VLDB 2023.
Paper
[NeurIPS’24] UQ-guided Hyperparameter Optimization for Iterative Learners
Jiesong Liu, Feng Zhang, Jiawei Guan, Xipeng ShenPublished in Conference on Neural Information Processing Systems (NeurIPS), 2024
This work explores uncertainty-guided hyperparameter optimization for iterative learning models.
Recommended citation: Jiesong Liu, Feng Zhang, Jiawei Guan, Xipeng Shen. (2024). "UQ-guided Hyperparameter Optimization for Iterative Learners." NeurIPS 2024.
Paper | Slides
[TC’24] Enabling Efficient Deep Learning on MCU with Transient Redundancy Elimination
Jiesong Liu, Feng Zhang, Jiawei Guan, Hsing-Hsuan Sung, Xiaoyong Du, Xipeng ShenPublished in IEEE Transactions on Computers (TC), 2024
We introduce a method for eliminating transient redundancy to improve deep learning efficiency on microcontrollers.
Recommended citation: Jiesong Liu, Feng Zhang, Jiawei Guan, Hsing-Hsuan Sung, Xiaoyong Du, Xipeng Shen. (2024). "Enabling Efficient Deep Learning on MCU with Transient Redundancy Elimination." IEEE TC.
Paper
[TPDS’24] G-Learned Index: Enabling Efficient Learned Index on GPU
Jiesong Liu, Feng Zhang, Lv Lu, Xiaoyong Du, Guoliang Li, Dong DengPublished in IEEE Transactions on Parallel and Distributed Systems (TPDS), 2024
This work explores the efficient implementation of learned indexes optimized for GPU architectures.
Recommended citation: Jiesong Liu, Feng Zhang, Lv Lu, Xiaoyong Du, Guoliang Li, Dong Deng. (2024). "G-Learned Index: Enabling Efficient Learned Index on GPU." TPDS 2024.
Paper
[VLDB’24] A Systematic Study on Early Stop Metrics in HPO and the Implications of Uncertainty
Jiawei Guan, Feng Zhang, Jiesong Liu, Xipeng ShenPublished in International Conference on Very Large Data Bases (VLDB), 2024
This paper systematically studies the impact of different early stop metrics in hyperparameter optimization.
Recommended citation: Jiawei Guan, Feng Zhang, Jiesong Liu, Xipeng Shen. (2024). "A Systematic Study on Early Stop Metrics in HPO and the Implications of Uncertainty." VLDB 2024.
[ACL’25 (In submission)] A Drop-In Solution for On-the-Fly Adaptation of Speculative Decoding in Large Language Models
Jiesong Liu, Brian Park, Xipeng ShenPublished in openreivew, 2025
We propose a drop-in solution for dynamically adapting speculative decoding in LLMs, improving efficiency while maintaining accuracy.
Recommended citation: Jiesong Liu, Brian Park, Xipeng Shen. (2025). "A Drop-In Solution for On-the-Fly Adaptation of Speculative Decoding in Large Language Models."
[ASPLOS’25] Generalizing Reuse Patterns for Efficient DNN on Microcontrollers
Jiesong Liu, Bin Ren, Xipeng ShenPublished in The 30th ACM International Conference on Architecture Support for Programming Languages and Operating Systems (ASPLOS), 2025
Proposed Generalized Reuse, a framework that expands computation reuse strategies in neural networks, yielding 1.03-2.2× inference speedups or 1-8% accuracy improvements across diverse architectures.
Recommended citation: Jiesong Liu, Brian Park, Xipeng Shen. (2025). "Generalizing Reuse Patterns for Efficient DNN on Microcontrollers." ASPLOS 2025
Paper