Demonstration venue · read-only. Every page can be browsed; the buttons that would change it are switched off. Create an account to run TaxoReview on your own data. A simulation from public publication records: the people listed were not invited and did not agree to review.
? Tutorial for this page
Demo Data from VLDB 2026 / reviewers in the wild / expert

Jicheng Wen

dblp:331/1891 · DBLP profile ↗
← Back
2ranked-venue papers
0as first author
2since 2021 · last 2024
—ORCID · none

Domains — the database's venue-derived domains; a paper can count in several

Artificial intelligence and machine learning · 1 · 1 since 2021Computer networks · 1 · 1 since 2021

Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.

Artificial intelligence
1 paper
Efficient and distributed learning · 91% Language models and text generation · 9%
Software engineering, system software, and programming languages
1 paper
Compilers and program optimization · 100%
Computer architecture, parallel and distributed computing, and storage systems
1 paper
GPUs and heterogeneous computing · 100%

Topics — the 5 heaviest of 6, each with the papers that count most for it

TopicWeightPapersLastEvidence papers
Machine learning › Efficient and distributed learning › model compression › quantization
post-training quantization		 0.812024
VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Models · EMNLP 2024
Machine learning › Efficient and distributed learning › model compression › quantization › low-bit quantization
ultra-low-bit quantization		 0.812024
VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Models · EMNLP 2024
Compilers and program optimization
code generation		 0.612022
Romou: rapidly generate high-performance tensor kernels for mobile GPUs · MobiCom 2022
Natural language and speech › Language models and text generation
large language model inference		 0.212024
VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Models · EMNLP 2024
GPUs and heterogeneous computing › embedded GPU
mobile GPU		 0.212022
Romou: rapidly generate high-performance tensor kernels for mobile GPUs · MobiCom 2022

Methods — techniques the papers use, named apart from their topics

automatic kernel generation · 1.1vector post-training quantization · 0.8
YearPublicationVenuePosition
2024 VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Models
abstract
Scaling model size significantly challenges the deployment and inference of Large Language Models (LLMs).Due to the redundancy in LLM weights, recent research has focused on pushing weight-only quantization to extremely low-bit (even down to 2 bits).It reduces memory requirements, optimizes storage costs, and * Contribution during internship at Microsoft Research
Jicheng Wen, Yang Wang 0053, Shengyu Ye, Li Lyna Zhang, Ting Cao 0003, Cheng Li 0001, Mao Yang 0004
 EMNLP2
2022 Romou: rapidly generate high-performance tensor kernels for mobile GPUs
abstract
Mobile GPU, as a ubiquitous and powerful accelerator, plays an important role in accelerating on-device DNN (Deep Neural Network) inference. The frequent-upgrade and diversity of mobile GPUs require automatic kernel generation to empower fast DNN deployment. However, current generated kernels have poor performance.
Rendong Liang, Ting Cao 0003, Jicheng Wen, Manni Wang, Yang Wang 0053, Jianhua Zou, Yunxin Liu 0001
 MobiCom3