Xiangyu Wen

Orcid: 0000-0002-7327-7786

Affiliations:
  • Chinese University of Hong Kong, Department of Computer Science and Engineering, Hong Kong


According to our database1, Xiangyu Wen authored at least 30 papers between 2020 and 2026.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

Online presence:

On csauthors.net:

Bibliography

2026
Context Distillation as Latent Memory Management.
CoRR, May, 2026

From Craft to Kernel: A Governance-First Execution Architecture and Semantic ISA for Agentic Computers.
CoRR, April, 2026

FormalRTL: Verified RTL Synthesis at Scale.
CoRR, March, 2026

Solve-Detect-Verify: Inference-Time Scaling with Flexible Generative Verifier.
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2026

2025
Trojan Attacks and Countermeasures on Deep Neural Networks from Life-Cycle Perspective: A Review.
ACM Comput. Surv., October, 2025

From Craft to Constitution: A Governance-First Paradigm for Principled Agent Engineering.
CoRR, October, 2025

Reasoning Scaffolding: Distilling the Flow of Thought from LLMs.
CoRR, September, 2025

Compressing Chain-of-Thought in LLMs via Step Entropy.
CoRR, August, 2025

MMCircuitEval: A Comprehensive Multimodal Circuit-Focused Benchmark for Evaluating LLMs.
CoRR, July, 2025

Solve-Detect-Verify: Inference-Time Scaling with Flexible Generative Verifier.
CoRR, May, 2025

ThermoHands: A Benchmark for 3D Hand Pose Estimation from Egocentric Thermal Images.
Proceedings of the 23rd ACM Conference on Embedded Networked Sensor Systems, 2025

Guideline Compliance in Task-Oriented Dialogue: The Chained Prior Approach.
Proceedings of the Findings of the Association for Computational Linguistics: NAACL 2025, Albuquerque, New Mexico, USA, April 29, 2025

MMCircuitEval: A Comprehensive Multimodal Circuit-Focused Benchmark for Evaluating LLMs.
Proceedings of the IEEE/ACM International Conference On Computer Aided Design, 2025

Dyve: Thinking Fast and Slow for Dynamic Process Verification.
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

2024
On Function-Coupled Watermarks for Deep Neural Networks.
IEEE J. Emerg. Sel. Topics Circuits Syst., December, 2024

Highly Evasive Targeted Bit-Trojan on Deep Neural Networks.
IEEE Trans. Computers, September, 2024

Critical Path-Based Backdoor Detection for Deep Neural Networks.
IEEE Trans. Neural Networks Learn. Syst., March, 2024

Beyond Trend and Periodicity: Guiding Time Series Forecasting with Textual Cues.
CoRR, 2024

ThermoHands: A Benchmark for 3D Hand Pose Estimation from Egocentric Thermal Image.
CoRR, 2024

RadarOcc: Robust 3D Occupancy Prediction with 4D Imaging Radar.
Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

Multimodal Indoor Localization Using Crowdsourced Radio Maps.
Proceedings of the IEEE International Conference on Robotics and Automation, 2024

2023
Poster Abstract: Multimodal Indoor Localization Using Crowdsourced Radio Maps.
Proceedings of the 21st ACM Conference on Embedded Networked Sensor Systems, 2023

2022
Interpretability-Guided Defense Against Backdoor Attacks to Deep Neural Networks.
IEEE Trans. Comput. Aided Des. Integr. Circuits Syst., 2022

2021
Generative strategy based backdoor attacks to 3D point clouds: work-in-progress.
Proceedings of the EMSOFT '21: Proceedings of the 2021 International Conference on Embedded Software, Virtual Event, October 8, 2021

Critical-weight based locking scheme for DNN IP protection in edge computing: work-in-progress.
Proceedings of the CODES/ISSS 2021, 2021

A physically realizable backdoor attack on 3D point cloud deep learning: work-in-progress.
Proceedings of the CODES/ISSS 2021, 2021

2020
Optimized co-scheduling of mixed-precision neural network accelerator for real-time multitasking applications.
J. Syst. Archit., 2020

ArchNet: Data Hiding Model in Distributed Machine Learning System.
CoRR, 2020

Interpretability Derived Backdoor Attacks Detection in Deep Neural Networks: Work-in-Progress.
Proceedings of the 20th International Conference on Embedded Software, 2020

Heatmap-Aware Low-Cost Design to Resist Adversarial Attacks: Work-in-Progress.
Proceedings of the International Conference on Hardware/Software Codesign and System Synthesis, 2020


  Loading...