papers

Publications (58)

cs.CV2026

All-Optical Segmentation via Diffractive Neural Networks for Autonomous Driving

Yingjie Li, Daniel Robinson, Weilu Gao +1

Semantic segmentation and lane detection are crucial tasks in autonomous driving systems. Conventional approaches predominantly rely on deep neural networks (DNNs), which incur hig…

cs.AI2025

e-boost: Boosted E-Graph Extraction with Adaptive Heuristics and Exact Solving

Jiaqi Yin, Zhan Song, Chen Chen +3

E-graphs have attracted growing interest in many fields, particularly in logic synthesis and formal verification. E-graph extraction is a challenging NP-hard combinatorial optimiza…

cs.AR2024

DAG-aware Synthesis Orchestration

Yingjie Li, Mingju Liu, Mark Ren +2

The key methodologies of modern logic synthesis techniques are conducted on multi-level technology-independent representations such as And-Inverter-Graphs (AIGs) of the digital log…

cs.DM2025

Differentiable Quadratic Optimization For The Maximum Independent Set Problem

Ismail Alkhouri, Cedric Le Denmat, Yingjie Li +4

Combinatorial Optimization (CO) addresses many important problems, including the challenging Maximum Independent Set (MIS) problem. Alongside exact and heuristic solvers, different…

cs.AR2024

MapTune: Advancing ASIC Technology Mapping via Reinforcement Learning Guided Library Tuning

Mingju Liu, Daniel Robinson, Yingjie Li +1

Technology mapping involves mapping logical circuits to a library of cells. Traditionally, the full technology library is used, leading to a large search space and potential overhe…

cs.AR2025

Mapping Fusion: Improving FPGA Technology Mapping with ASIC Mapper

Cunxi Yu

LUT (Look-Up Table) mapping is a critical step in FPGA logic synthesis, where a logic network is transformed into a form that can be directly implemented using the FPGA's LUTs. An…

cs.LO2026

GaloisSAT: Differentiable Boolean Satisfiability Solving via Finite Field Algebra

Curie Kim, Carsten Portner, Mingju Liu +6

Boolean satisfiability (SAT) problem, the first problem proven to be NP-complete, has become a fundamental challenge in computational complexity, with widespread applications in op…

cs.LG2026

Differentiable Initialization-Accelerated CPU-GPU Hybrid Combinatorial Scheduling

Mingju Liu, Jiaqi Yin, Alvaro Velasquez +1

This paper presents a hybrid CPU-GPU framework for solving combinatorial scheduling problems formulated as Integer Linear Programming (ILP). While scheduling underpins many optimiz…

cs.SC2016

Reverse Engineering of Irreducible Polynomials in GF(2^m) Arithmetic

Cunxi Yu, Daniel Holcomb, Maciej Ciesielski

Current techniques for formally verifying circuits implemented in Galois field (GF) arithmetic are limited to those with a known irreducible polynomial P(x). This paper presents a…

cs.ET2020

Artificial Intelligence Accelerators based on Graphene Optoelectronic Devices

Weilu Gao, Cunxi Yu, Ruiyang Chen

Optical and optoelectronic approaches of performing matrix-vector multiplication (MVM) operations have shown the great promise of accelerating machine learning (ML) algorithms with…

cs.ET2026

HoloGraph: All-Optical Graph Learning via Light Diffraction

Yingjie Li, Shanglin Zhou, Caiwen Ding +1

As a representative of next-generation device/circuit technology beyond CMOS, physics-based neural networks such as Diffractive Optical Neural Networks (DONNs) have demonstrated pr…

cs.AR2026

Agentic Hardware Design as Repository-Level Code Evolution

Cunxi Yu, Chenhui Deng, Nathaniel Pinckney +1

We present HORIZON, a self-evolving agent framework that treats hardware design as repository-level code evolution. A Markdown harness is compiled into a project pack containing do…

cs.LG2023

Physics-aware Roughness Optimization for Diffractive Optical Neural Networks

Shanglin Zhou, Yingjie Li, Minhan Lou +4

As a representative next-generation device/circuit technology beyond CMOS, diffractive optical neural networks (DONNs) have shown promising advantages over conventional deep neural…

cs.AR2026

FVRuleLearner: Operator-Level Reasoning Tree (Op-Tree)-Based Rules Learning for Formal Verification

Lily Jiaxin Wan, Chia-Tung Ho, Yunsheng Bai +4

The remarkable reasoning and code generation capabilities of large language models (LLMs) have recently motivated increasing interest in automating formal verification (FV), a proc…

physics.optics2024

Optical Neural Engine for Solving Scientific Partial Differential Equations

Yingheng Tang, Ruiyang Chen, Minhan Lou +5

Solving partial differential equations (PDEs) is the cornerstone of scientific research and development. Data-driven machine learning (ML) approaches are emerging to accelerate tim…

cs.LG2020

Contrastive Weight Regularization for Large Minibatch SGD

Qiwei Yuan, Weizhe Hua, Yi Zhou +1

The minibatch stochastic gradient descent method (SGD) is widely applied in deep learning due to its efficiency and scalability that enable training deep networks with a large volu…

cs.SC2019

Efficient Parallel Verification of Galois Field Multipliers

Cunxi Yu, Maciej Ciesielski

Galois field (GF) arithmetic is used to implement critical arithmetic components in communication and security-related hardware, and verification of such components is of prime imp…

cs.SC2019

Spectral Approach to Verifying Non-linear Arithmetic Circuits

Cunxi Yu, Tiankai Su, Atif Yasin +1

This paper presents a fast and effective computer algebraic method for analyzing and verifying non-linear integer arithmetic circuits using a novel algebraic spectral model. It int…

cs.LG2019

Painting on Placement: Forecasting Routing Congestion using Conditional Generative Adversarial Nets

Cunxi Yu, Zhiru Zhang

Physical design process commonly consumes hours to days for large designs, and routing is known as the most critical step. Demands for accurate routing quality prediction raise to…

cs.DM2026

A Scalable Lift-and-Project Differentiable Approach For the Maximum Cut Problem

Ismail Alkhouri, Mian Wu, Cunxi Yu +3

We propose a scalable framework for solving the Maximum Cut (MaxCut) problem in large graphs using projected gradient ascent on quadratic objectives. Our approach is differentiable…

cs.DC2019

Developing Synthesis Flows Without Human Knowledge

Cunxi Yu, Houping Xiao, Giovanni De Micheli

Design flows are the explicit combinations of design transformations, primarily involved in synthesis, placement and routing processes, to accomplish the design of Integrated Circu…

cs.AR2023

LightRidge: An End-to-end Agile Design Framework for Diffractive Optical Neural Networks

Yingjie Li, Ruiyang Chen, Minhan Lou +3

To lower the barrier to diffractive optical neural networks (DONNs) design, exploration, and deployment, we propose LightRidge, the first end-to-end optical ML compilation framewor…

cs.ET2022

Device-system Co-design of Photonic Neuromorphic Processor using Reinforcement Learning

Yingheng Tang, Princess Tara Zamani, Ruiyang Chen +4

The incorporation of high-performance optoelectronic devices into photonic neuromorphic processors can substantially accelerate computationally intensive operations in machine lear…

cs.LG2023

Rubik's Optical Neural Networks: Multi-task Learning with Physics-aware Rotation Architecture

Yingjie Li, Weilu Gao, Cunxi Yu

Recently, there are increasing efforts on advancing optical neural networks (ONNs), which bring significant advantages for machine learning (ML) in terms of power efficiency, paral…

cs.LG2023

Accelerating Exact Combinatorial Optimization via RL-based Initialization -- A Case Study in Scheduling

Jiaqi Yin, Cunxi Yu

Scheduling on dataflow graphs (also known as computation graphs) is an NP-hard problem. The traditional exact methods are limited by runtime complexity, while reinforcement learnin…

cs.AI2026

VeriTrace: Human-Like Temporal Exploration Completes Agentic Action Space

Yu-Tung Liu, Cunxi Yu

Large language models have shown promise for automated Verilog RTL generation, yet state-of-the-art multi-agent systems plateau at ~95% accuracy on standard benchmarks. We trace th…

cs.AI2022

Physics-aware Differentiable Discrete Codesign for Diffractive Optical Neural Networks

Yingjie Li, Ruiyang Chen, Weilu Gao +1

Diffractive optical neural networks (DONNs) have attracted lots of attention as they bring significant advantages in terms of power efficiency, parallelism, and computational speed…

cs.AR2026

AUTOGATE: Automated Clock Gating via Toggling-Aware LLM-based RTL Rewriting

Yiting Wang, Chenhui Deng, Chia-Tung Ho +6

Fine-grain clock gating (FGCG) is among the most effective techniques for reducing dynamic power, yet current FGCG optimization flows remain largely manual. Recent LLM-based RTL op…

cs.LO2025

TurboSAT: Gradient-Guided Boolean Satisfiability Accelerated on GPU-CPU Hybrid System

Steve Dai, Cunxi Yu, Kalyan Krishnamani +1

While accelerated computing has transformed many domains of computing, its impact on logical reasoning, specifically Boolean satisfiability (SAT), remains limited. State-of-the-art…

cs.LG2026

TOPCELL: Topology Optimization of Standard Cell via LLMs

Zhan Song, Yu-Tung Liu, Chen Chen +6

Transistor topology optimization is a critical step in standard cell design, directly dictating diffusion sharing efficiency and downstream routability. However, identifying optima…

cs.LG2025

GROOT: Graph Edge Re-growth and Partitioning for the Verification of Large Designs in Logic Synthesis

Kiran Thorat, Hongwu Peng, Yuebo Luo +8

Traditional verification methods in chip design are highly time-consuming and computationally demanding, especially for large scale circuits. Graph neural networks (GNNs) have gain…

cs.AR2023

RESPECT: Reinforcement Learning based Edge Scheduling on Pipelined Coral Edge TPUs

Jiaqi Yin, Yingjie Li, Daniel Robinson +1

Deep neural networks (DNNs) have substantial computational and memory requirements, and the compilation of its computational graphs has a great impact on the performance of resourc…

cs.LG2023

Verilog-to-PyG -- A Framework for Graph Learning and Augmentation on RTL Designs

Yingjie Li, Mingju Liu, Alan Mishchenko +1

The complexity of modern hardware designs necessitates advanced methodologies for optimizing and analyzing modern digital systems. In recent times, machine learning (ML) methodolog…

cs.AR2025

HEC: Equivalence Verification Checking for Code Transformation via Equality Saturation

Jiaqi Yin, Zhan Song, Nicolas Bohm Agostini +2

In modern computing systems, compilation employs numerous optimization techniques to enhance code performance. Source-to-source code transformations, which include control flow and…

cs.AR2023

AIM: Accelerating Arbitrary-precision Integer Multiplication on Heterogeneous Reconfigurable Computing Platform Versal ACAP

Zhuoping Yang, Jinming Zhuang, Jiaqi Yin +3

Arbitrary-precision integer multiplication is the core kernel of many applications in simulation, cryptography, etc. Existing acceleration of arbitrary-precision integer multiplica…

cs.LO2025

ReVEAL: GNN-Guided Reverse Engineering for Formal Verification of Optimized Multipliers

Chen Chen, Daniela Kaufmann, Chenhui Deng +3

We present ReVEAL, a graph-learning-based method for reverse engineering of multiplier architectures to improve algebraic circuit verification techniques. Our framework leverages s…

cs.AR2017

Advanced Datapath Synthesis using Graph Isomorphism

Cunxi Yu, Mihir Choudhury, Andrew Sullivan +1

This paper presents an advanced DAG-based algorithm for datapath synthesis that targets area minimization using logic-level resource sharing. The problem of identifying common spec…

cs.ET2022

Physics-aware Complex-valued Adversarial Machine Learning in Reconfigurable Diffractive All-optical Neural Network

Ruiyang Chen, Yingjie Li, Minhan Lou +5

Diffractive optical neural networks have shown promising advantages over electronic circuits for accelerating modern machine learning (ML) algorithms. However, it is challenging to…

cs.LG2024

Differentiable Combinatorial Scheduling at Scale

Mingju Liu, Yingjie Li, Jiaqi Yin +2

This paper addresses the complex issue of resource-constrained scheduling, an NP-hard problem that spans critical areas including chip design and high-performance computing. Tradit…

cs.AR2025

BoolE: Exact Symbolic Reasoning via Boolean Equality Saturation

Jiaqi Yin, Zhan Song, Chen Chen +2

Boolean symbolic reasoning for gate-level netlists is a critical step in verification, logic and datapath synthesis, and hardware security. Specifically, reasoning datapath and add…

cs.LG2018

Performance Estimation of Synthesis Flows cross Technologies using LSTMs and Transfer Learning

Cunxi Yu, Wang Zhou

Due to the increasing complexity of Integrated Circuits (ICs) and System-on-Chip (SoC), developing high-quality synthesis flows within a short market time becomes more challenging.…

cs.LG2024

Less is More: Hop-Wise Graph Attention for Scalable and Generalizable Learning on Circuits

Chenhui Deng, Zichao Yue, Cunxi Yu +4

While graph neural networks (GNNs) have gained popularity for learning circuit representations in various electronic design automation (EDA) tasks, they face challenges in scalabil…

cs.SC2018

Formal Analysis of Galois Field Arithmetics - Parallel Verification and Reverse Engineering

Cunxi Yu, Maciej Ciesielski

Galois field (GF) arithmetic circuits find numerous applications in communications, signal processing, and security engineering. Formal verification techniques of GF circuits are s…

cs.AR2025

E-morphic: Scalable Equality Saturation for Structural Exploration in Logic Synthesis

Chen Chen, Guangyu HU, Cunxi Yu +2

In technology mapping, the quality of the final implementation heavily relies on the circuit structure after technology-independent optimization. Recent studies have introduced equ…

cs.AR2023

Gamora: Graph Learning based Symbolic Reasoning for Large-Scale Boolean Networks

Nan Wu, Yingjie Li, Cong Hao +3

Reasoning high-level abstractions from bit-blasted Boolean networks (BNs) such as gate-level netlists can significantly benefit functional verification, logic minimization, datapat…

cs.AI2025

Autonomous Code Evolution Meets NP-Completeness

Cunxi Yu, Rongjian Liang, Chia-Tung Ho +1

Large language models (LLMs) have recently shown strong coding abilities, enabling not only static code generation but also iterative code self-evolving through agentic frameworks.…

cs.AR2026

Autonomous Evolution of EDA Tools: Multi-Agent Self-Evolved ABC

Cunxi Yu, Haoxing Ren

This paper introduces the first \emph{self-evolving} logic synthesis framework, which leverages Large Language Model (LLM) agents to autonomously improve the source code of \textsc…

cs.AR2025

Revisit Choice Network for Synthesis and Technology Mapping

Chen Chen, Jiaqi Yin, Cunxi Yu

Choice network construction is a critical technique for alleviating structural bias issues in Boolean optimization, equivalence checking, and technology mapping. Previous works on…

cs.LG2021

Real-time Multi-Task Diffractive Deep Neural Networks via Hardware-Software Co-design

Yingjie Li, Ruiyang Chen, Berardi Sensale Rodriguez +2

Deep neural networks (DNNs) have substantial computational requirements, which greatly limit their performance in resource-constrained environments. Recently, there are increasing…

cs.AI2025

SchemaCoder: Automatic Log Schema Extraction Coder with Residual Q-Tree Boosting

Lily Jiaxin Wan, Chia-Tung Ho, Rongjian Liang +3

Log schema extraction is the process of deriving human-readable templates from massive volumes of log data, which is essential yet notoriously labor-intensive. Recent studies have…

cs.AR2024

E-Syn: E-Graph Rewriting with Technology-Aware Cost Functions for Logic Synthesis

Chen Chen, Guangyu Hu, Dongsheng Zuo +3

Logic synthesis plays a crucial role in the digital design flow. It has a decisive influence on the final Quality of Results (QoR) of the circuit implementations. However, existing…

cs.CV2026

SCALE: Self-Supervised Constraint-Aware Layout GEneration for Local P&R DRV Fixing at Advanced Nodes

Chia-Tung Ho, Haoyu Yang, Guanglei Zhou +6

As semiconductor manufacturing advances toward sub-2nm nodes, local place-and-route (P&R) design-rule violation (DRV) fixing is increasingly limited by complex rule interactions, d…

cs.AR2023

FlowTune: End-to-end Automatic Logic Optimization Exploration via Domain-specific Multi-armed Bandit

Walter Lau Neto, Yingjie Li, Pierre-Emmanuel Gaillardon +1

Recent years have seen increasing employment of decision intelligence in electronic design automation (EDA), which aims to reduce the manual efforts and boost the design closure pr…

cs.LG2026

GauS: Differentiable Scheduling Optimization via Gaussian Reparameterization

Yaohui Cai, Vesal Bakhtazad, Cunxi Yu +1

Efficient operator scheduling is a fundamental challenge in software compilation and hardware synthesis. While recent differentiable approaches have sought to replace traditional o…

cs.CR2018

Algorithmic Obfuscation over GF()

Cunxi Yu, Daniel Holcomb

Galois Field arithmetic blocks are the key components in many security applications, such as Elliptic Curve Cryptography (ECC) and the S-Boxes of the Advanced Encryption Standard (…

physics.optics2021

Physics-Guided and Physics-Explainable Recurrent Neural Network for Time Dynamics in Optical Resonances

Yingheng Tang, Jichao Fan, Xinwei Li +4

Understanding the time evolution of physical systems is crucial to revealing fundamental characteristics that are hidden in frequency domain. In optical science, high-quality reson…

physics.optics2024

Digitized Phase Change Material Heterostack for Diffractive Optical Neural Network

Ruiyang Chen, Cunxi Yu, Weilu Gao

All-optical and fully reconfigurable diffractive optical neural network (DONN) architectures are promising for high-throughput and energy-efficient machine learning (ML) hardware a…

cs.AR2024

BoolGebra: Attributed Graph-learning for Boolean Algebraic Manipulation

Yingjie Li, Anthony Agnesina, Yanqing Zhang +2

Boolean algebraic manipulation is at the core of logic synthesis in Electronic Design Automation (EDA) design flow. Existing methods struggle to fully exploit optimization opportun…