Ting-Jung Lin

Dr. Ting-Jung Lin

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
23 May 2025 in ACM Transactions on Design Automation of Electronic Systems
Verified
Journal Article
Open access
YSYichen Shi
Yichen Shi
ZTZhuofu Tao
Zhuofu Tao
YGYuHao Gao
YuHao Gao
TZTianjia Zhou
Tianjia Zhou
CCCheng Chang
Cheng Chang
LHLei He
Lei He
High-performance analog and mixed-signal (AMS) circuits are mainly full-custom designed, which is time-consuming and labor-intensive. A significant portion of the effort is experience-driven, which makes the automation of AMS circuit design a formidable challenge. Large language models (LLMs) have emerged as powerful tools for Electronic Design Automation (EDA) applications, fostering advancements in the automatic design process for large-scale AMS circuits. However, the absence of high-quality datasets has led to issues such as model hallucination, which undermines the robustness of automatically generated circuit designs. To address this issue, this paper introduces AMSnet-KG, a dataset encompassing various AMS circuit schematics and netlists. We construct a knowledge graph with annotations on detailed functional and performance characteristics. Facilitated by AMSnet-KG, we propose an automated AMS circuit generation framework that utilizes the comprehensive knowledge embedded in LLMs. The flow first formulate a design strategy (e.g., circuit architecture using a number of circuit components) based on required specifications. Next, matched subcircuits are retrieved and assembled into a complete topology, and transistor sizing is obtained through Bayesian optimization. Simulation results of the netlist are automatically fed back to the LLM for further topology refinement, ensuring the circuit design specifications are met. We perform case studies of operational amplifier and comparator design to verify the automatic design flow from specifications to netlists with minimal human effort. The dataset used in this paper is available at https://ams-net.github.io/.

20 May 2025 in ACM Transactions on Design Automation of Electronic Systems
Verified
Journal Article
Open access
YWYangbo Wei
Yangbo Wei
LHLi Huang
Li Huang
QFQi Feng
Qi Feng
ZCZhanfei Chen
Zhanfei Chen
JYJinlong Yan
Jinlong Yan
LHLei He
Lei He
Device models require large numbers of parameters to characterize complex physical effects. Although the latest advancements in machine learning and automated tools have drastically improved efficiency over the classic methods, they still demand a considerable amount of human intervention in the loop to gain accuracy. This drastically limits further automation. Inspired by the success of Multimodal Large Language Models (MLLMs) in addressing tasks across diverse fields, we propose ModelGen, the first in-depth study to leverage MLLMs with RAG (Retrieval-Augmented Generation) to significantly reduce human effort in parameter extraction for compact model. Our contributions include (1) Automated Agentic Workflow Construction that learns to build and refine extraction workflows through iterative optimization, (2) MLLM Judge, a visual scoring mechanism that evaluates fitting quality using actual device characteristic plots rather than simple numerical metrics, and (3) Model-specific RAG for providing relevant domain knowledge during the extraction process. Experimental results demonstrate that ModelGen achieves a 26.8%-33.1% improvement in pass@1,3,5 compared to base LLM methods. The system completes complex model extractions for BSIMs and ASM-HEMT in hours (up to 168× faster) rather than days or weeks, making parameter extraction more accessible to non-experts while maintaining professional engineer-level accuracy.

18 August 2025 in ACM Transactions on Reconfigurable Technology and Systems
Verified
Journal Article
Open access
SLShaoqiang Lu
Shaoqiang Lu
TZTiandong Zhao
Tiandong Zhao
TLTing-Jung Lin
Ting-Jung Lin
RZRumin Zhang
Rumin Zhang
CWChen Wu
Chen Wu
LHLei He
Lei He
Transformer-based models have achieved extensive success with increasingly large numbers of parameters and computations, for which many multi-core accelerators have been developed. Nevertheless, they suffer from limited throughput due to either low operating frequency or high communication overhead between cores. This article proposes an FPGA-based multi-core overlay processor, named MCoreOPU, to optimize intra-core computation and inter-core communication. First, we boost the operating frequency of the processing element (PE) array to double the rest of the processor to improve the intra-core throughput. Second, we develop on-chip synchronization routers to reduce off-chip memory traffic, where only the partial sum and maximum are communicated between cores rather than entire vectors for layer normalization and softmax. Moreover, we pipeline synchronization to reduce synchronization latency and develop a bypass of the interconnect bus to reduce the off-chip memory access latency. Finally, we optimize the multi-core model allocation and scheduling to minimize the inter-core communications and maximize the intra-core computation efficiency. The MCoreOPU is implemented in 8-bit fixed-point precision with four cores and four DDRs on the Xilinx U200 FPGA, where the PE array runs at 600 MHz while the rest runs at 300 MHz. Experimental results show that the throughput per MAC of MCoreOPU for BERT, ViT, GPT-2, and LLaMA inference is 1.31 \(\times\) –7.18 \(\times\) higher than other FPGA-based accelerators. Compared with the A100 GPU, the throughput per equivalent MAC efficiency is improved by 22.52 \(\times\) –27.12 \(\times\) .


23 June 2024
Verified
Conference Paper
Open access
JZJunzhuo Zhou
Junzhuo Zhou
LHLi Huang
Li Huang
HXHaoxuan Xia
Haoxuan Xia
YCYihui Cai
Yihui Cai
LJLeilei Jin
Leilei Jin
LHLei He
Lei He
As transistor size continues to scale down, process variation has become an essential factor determining semiconductor yield and economic return. The Liberty Variation Format (LVF) is the current industrial standard that expresses statistical timing behaviors based on single Gaussian model. However, it loses accuracy when the timing distribution is non-Gaussian due to growing process variations. This paper proposes a novel LVF2 distribution model that combines two weighted skewed-normal (SN) distributions, which better captures the multi-Gaussian timing distribution while maintaining backward compatibility with LVF. Experiments using TSMC 22nm standard cells show that, compared to LVF, LVF2 reduces binning error by 7.74X in delay and 9.56X in transition time, and reduces 3σ-yield error by 4.79X and 7.18X in delay and transition time, respectively. The error reduction for path delay is diminished due to Central Limit Theorem (CLT). But it is still 2X for a typical circuit path with 8 Fanout-of-4 (FO4) inverter delays.

17 January 2024 in Water
Verified
Journal Article
Open access
PDF file
KWKai Wang
Kai Wang
LHLi Huang
Li Huang
JZJingting Zhang
Jingting Zhang
XZXiaojie Zhen
Xiaojie Zhen
LSLin-lin Shi
Lin-lin Shi
YWYin Wang
Yin Wang
The reliable observation and accurate estimates of land–atmosphere water vapor (H2O) flux is essential for ecosystem management and the development of Earth system models. Currently, the most direct measurement method for H2O flux is eddy covariance (EC), which depends on the development of fast-response H2O sensors. In this study, we presented a cost-efficient open-path H2O analyzer (model: HT1800) based on the tunable diode laser absorption spectroscopy (TDLAS) technique, and investigated its applicability for measuring atmospheric turbulent flux of H2O using the EC method. We prepared two HT1800 analyzers with lasers that operate at wavelengths of 1392 nm and 1877 nm, respectively. The field performance of the two analyzers was evaluated through inter-comparative experiments with LI-7500RS and IRGASON, two of the most commonly used H2O analyzers in the EC community. Water vapor densities measured by the three types of analyzers had high overall agreement with the reference sensor; however, they all experienced drift. The mean density drifts of HT1800, LI-7500 and IRGASON were 3.7–5.2%, 4.0% and 3.8%, respectively. Even so, the half-hourly H2O fluxes measured by HT1800 were highly consistent with those by LI-7500RS and IRGASON (with a difference of less than 2%), suggesting that HT1800 can obtain H2O fluxes with high confidence. The HT1800 was also proved to be suitable for EC application in terms of data availability, flux detection limit and response to the high-frequency turbulent variation. Furthermore, we investigated how the spectroscopic effect influences the measurements of H2O density and flux. Despite the fact that the 1392 nm laser was much more susceptible to the spectroscopic effect, the fluxes after correcting for this bias showed excellent agreement with the IRGASON fluxes. Considering the cost advantage in laser and photodetector, the HT1800 analyzer using a 1392 nm infrared laser is a promising and economical solution for EC measurement studies of water vapor.