Liao Wu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Liao Wu has a total of 165 co-authors. Here are the top co-authors by number of shared publications:
- Hongliang Ren
The Chinese University of Hong Kong
12 shared publications Jonathan Roberts
10 shared publicationsRoss Crawford
9 shared publicationsKeyu Wu
Department of Biomedical Engineering, National University of Singapore, Singapore
8 shared publications- Ajay Kumar Pandey
Queensland University of Technology
7 shared publications - Jiaole Wang
School of Space and Earth Sciences, Beihang University, Beijing, China
7 shared publications
Latest Publications
- Open Access
- 12 October 2026
- Published by IOP Publishing in Neuromorphic Computing and Engineering
- Vol. 6 (4) , 044002
Continuous attribution on discrete spikes: revealing the explainability paradox in spiking neural networks
Spiking neural networks (SNNs) offer a highly energy-efficient, neuromorphic alternative to standard deep learning, but their real-world deployment necessitates trustworthy and explainable outputs. Class Activation Mapping (CAM) methods are a robust and popular way of implementing this explainability in continuous artificial neural networks, but translating these methods to the discrete, temporal domain of SNNs introduces distinct theoretical failure modes. In this work, we formalize these limitations, establishing a fundamental Sensitivity-Faithfulness Tradeoff in gradient-based attributions and expose systematic binary threshold effects in perturbation-based approaches. Building on this, we identify a severe domain mismatch when applying continuous attribution smoothing to sparse neuromorphic data. To correct the resulting out-of-distribution hallucinations, we introduce Poisson SmoothGrad , a physically-consistent noise injection method that safely marginalizes threshold volatility to yield the strongest gradient-based attributions we measure on native event data. Benchmarking six attribution methods on a spiking VGG-11 across CIFAR-10, CIFAR-10-DVS and DVSGesture, we find that no single method dominates: domain-native smoothing leads the gradient family on sparse event streams, while the activation-based spike activation map is the strongest overall. Ultimately, we measure the network-level dynamics that allow CAMs to keep working despite these neuron-level mathematical flaws, and synthesize our empirical benchmarks into a Practitioner’s Guide that provides actionable heuristics for deploying robust, domain-aware visual explanations in SNNs.
- 12 October 2026
- Published by IOP Publishing in Neuromorphic Computing and Engineering
- Vol. 6 (4) , 044002
Open AccessContinuous attribution on discrete spikes: revealing the explainability paradox in spiking neural networks
Spiking neural networks (SNNs) offer a highly energy-efficient, neuromorphic alternative to standard deep learning, but their real-world deployment necessitates trustworthy and explainable outputs. Class Activation Mapping (CAM) methods are a robust and popular way of implementing this explainability in continuous artificial neural networks, but translating these methods to the discrete, temporal domain of SNNs introduces distinct theoretical failure modes. In this work, we formalize these limitations, establishing a fundamental Sensitivity-Faithfulness Tradeoff in gradient-based attributions and expose systematic binary threshold effects in perturbation-based approaches. Building on this, we identify a severe domain mismatch when applying continuous attribution smoothing to sparse neuromorphic data. To correct the resulting out-of-distribution hallucinations, we introduce Poisson SmoothGrad , a physically-consistent noise injection method that safely marginalizes threshold volatility to yield the strongest gradient-based attributions we measure on native event data. Benchmarking six attribution methods on a spiking VGG-11 across CIFAR-10, CIFAR-10-DVS and DVSGesture, we find that no single method dominates: domain-native smoothing leads the gradient family on sparse event streams, while the activation-based spike activation map is the strongest overall. Ultimately, we measure the network-level dynamics that allow CAMs to keep working despite these neuron-level mathematical flaws, and synthesize our empirical benchmarks into a Practitioner’s Guide that provides actionable heuristics for deploying robust, domain-aware visual explanations in SNNs.
- Open Access
- 7 August 2026
- Published by Elsevier in TrAC Trends in Analytical Chemistry
- Vol. 204
Artificial intelligence for CRISPR-based biosensing: From molecular design to assay intelligence
- 7 August 2026
- Published by Elsevier in TrAC Trends in Analytical Chemistry
- Vol. 204
Open AccessArtificial intelligence for CRISPR-based biosensing: From molecular design to assay intelligence
- Open Access
- 22 January 2026
- Published by Wiley in Advanced Science
- Vol. 13 (18) , e19398
Understanding the Roles of Microstructure and Viscoelasticity of Soft Ionic Elastomer for Super‐Capacitive Pressure Sensors
Soft ionic conductive elastomers offer unique advantages for super‐capacitive pressure sensors, where the electrical double layer (EDL) effect enables high sensitivity and rapid response. However, the roles of microstructure and viscoelasticity on EDL‐driven sensing remain poorly understood. This study establishes detailed correlations between elastomer microstructure, intrinsic viscoelastic properties, and sensor performance by integrating mechanical and electrical analyses. Validation of the EDL mechanism reveals how microstructural optimization and viscoelastic tuning enhance sensitivity, linear range, and stability. Height‐graded architectures yield a sensor with a sensitivity of 2.70 nF/kPa, a broad linear range of 0–2000 kPa, and robust durability over 10 000 cycles. These devices demonstrate multifunctionality in robotic electronic skin, pressure mapping, and real‐time physiological monitoring such as wrist pulse detection. The findings establish key structure–property–performance relationships, providing design guidelines for next‐generation, high‐performance super‐capacitive sensors.
- 22 January 2026
- Published by Wiley in Advanced Science
- Vol. 13 (18) , e19398
Open AccessUnderstanding the Roles of Microstructure and Viscoelasticity of Soft Ionic Elastomer for Super‐Capacitive Pressure Sensors
Soft ionic conductive elastomers offer unique advantages for super‐capacitive pressure sensors, where the electrical double layer (EDL) effect enables high sensitivity and rapid response. However, the roles of microstructure and viscoelasticity on EDL‐driven sensing remain poorly understood. This study establishes detailed correlations between elastomer microstructure, intrinsic viscoelastic properties, and sensor performance by integrating mechanical and electrical analyses. Validation of the EDL mechanism reveals how microstructural optimization and viscoelastic tuning enhance sensitivity, linear range, and stability. Height‐graded architectures yield a sensor with a sensitivity of 2.70 nF/kPa, a broad linear range of 0–2000 kPa, and robust durability over 10 000 cycles. These devices demonstrate multifunctionality in robotic electronic skin, pressure mapping, and real‐time physiological monitoring such as wrist pulse detection. The findings establish key structure–property–performance relationships, providing design guidelines for next‐generation, high‐performance super‐capacitive sensors.
- 20 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Practice
- Vol. 1, 40-44
Comparatively Evaluating Stereo-Matching Algorithms for Minimally Invasive Surgery
3D reconstructing surgical scenes for medical robotics is a desired capability to allow new visualization methods through mixed reality and enable a higher level of autonomy. A popular approach to achieving 3D reconstruction is stereo-matching with binocular cameras. Over the years, many different approaches to stereo-matching have been proposed for non-surgical robotic tasks. Their performance in Minimally Invasive Surgery (MIS) tasks, which is often more challenging due to various image artifacts, has not been sufficiently studied. As such, this paper evaluates the performance of various stereo-matching algorithms, including traditional and deep learning-based approaches, on stereo-endoscopic datasets (quantitatively on SERV-CT and SCARED; qualitatively on Hamlyn). It was found that performance between algorithms varied significantly, and the lack of a large labeled stereo-endoscopic dataset severely affected the performance of some deep learning models. Image artifacts such as texture-less surfaces, specularities, smoke, motion blur, and other obscuring features remain difficult challenges for stereo-matching algorithms. The results of this study could provide directions for further development of stereo-matching algorithms for MIS and encourage the creation of more stereo-endoscopic datasets.
- 20 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Practice
- Vol. 1, 40-44
Comparatively Evaluating Stereo-Matching Algorithms for Minimally Invasive Surgery
3D reconstructing surgical scenes for medical robotics is a desired capability to allow new visualization methods through mixed reality and enable a higher level of autonomy. A popular approach to achieving 3D reconstruction is stereo-matching with binocular cameras. Over the years, many different approaches to stereo-matching have been proposed for non-surgical robotic tasks. Their performance in Minimally Invasive Surgery (MIS) tasks, which is often more challenging due to various image artifacts, has not been sufficiently studied. As such, this paper evaluates the performance of various stereo-matching algorithms, including traditional and deep learning-based approaches, on stereo-endoscopic datasets (quantitatively on SERV-CT and SCARED; qualitatively on Hamlyn). It was found that performance between algorithms varied significantly, and the lack of a large labeled stereo-endoscopic dataset severely affected the performance of some deep learning models. Image artifacts such as texture-less surfaces, specularities, smoke, motion blur, and other obscuring features remain difficult challenges for stereo-matching algorithms. The results of this study could provide directions for further development of stereo-matching algorithms for MIS and encourage the creation of more stereo-endoscopic datasets.
- Open Access
Reinforcement Learning for Follow-the-Leader Robotic Endoscopic Navigation via Synthetic Data
Autonomous navigation is crucial for both medical and industrial endoscopic robots, enabling safe and efficient exploration of narrow tubular environments without continuous human intervention, where avoiding contact with the inner walls has been a longstanding challenge for prior approaches. We present a follow-the-leader endoscopic robot based on a flexible continuum structure designed to minimize contact between the endoscope body and intestinal walls, thereby reducing patient discomfort. To achieve this objective, we propose a vision-based deep reinforcement learning framework guided by monocular depth estimation. A realistic intestinal simulation environment was constructed in \textit{NVIDIA Omniverse} to train and evaluate autonomous navigation strategies. Furthermore, thousands of synthetic intraluminal images were generated using NVIDIA Replicator to fine-tune the Depth Anything model, enabling dense three-dimensional perception of the intestinal environment with a single monocular camera. Subsequently, we introduce a geometry-aware reward and penalty mechanism to enable accurate lumen tracking. Compared with the original Depth Anything model, our method improves $δ_{1}$ depth accuracy by 39.2% and reduces the navigation J-index by 0.67 relative to the second-best method, demonstrating the robustness and effectiveness of the proposed approach.Open AccessReinforcement Learning for Follow-the-Leader Robotic Endoscopic Navigation via Synthetic Data
Autonomous navigation is crucial for both medical and industrial endoscopic robots, enabling safe and efficient exploration of narrow tubular environments without continuous human intervention, where avoiding contact with the inner walls has been a longstanding challenge for prior approaches. We present a follow-the-leader endoscopic robot based on a flexible continuum structure designed to minimize contact between the endoscope body and intestinal walls, thereby reducing patient discomfort. To achieve this objective, we propose a vision-based deep reinforcement learning framework guided by monocular depth estimation. A realistic intestinal simulation environment was constructed in \textit{NVIDIA Omniverse} to train and evaluate autonomous navigation strategies. Furthermore, thousands of synthetic intraluminal images were generated using NVIDIA Replicator to fine-tune the Depth Anything model, enabling dense three-dimensional perception of the intestinal environment with a single monocular camera. Subsequently, we introduce a geometry-aware reward and penalty mechanism to enable accurate lumen tracking. Compared with the original Depth Anything model, our method improves $δ_{1}$ depth accuracy by 39.2% and reduces the navigation J-index by 0.67 relative to the second-best method, demonstrating the robustness and effectiveness of the proposed approach. - Open Access
Towards Closing the Domain Gap with Event Cameras
Although traditional cameras are the primary sensor for end-to-end driving, their performance suffers greatly when the conditions of the data they were trained on does not match the deployment environment, a problem known as the domain gap. In this work, we consider the day-night lighting difference domain gap. Instead of traditional cameras we propose event cameras as a potential alternative which can maintain performance across lighting condition domain gaps without requiring additional adjustments. Our results show that event cameras maintain more consistent performance across lighting conditions, exhibiting domain-shift penalties that are generally comparable to or smaller than grayscale frames and provide superior baseline performance in cross-domain scenarios.
Open AccessTowards Closing the Domain Gap with Event Cameras
Although traditional cameras are the primary sensor for end-to-end driving, their performance suffers greatly when the conditions of the data they were trained on does not match the deployment environment, a problem known as the domain gap. In this work, we consider the day-night lighting difference domain gap. Instead of traditional cameras we propose event cameras as a potential alternative which can maintain performance across lighting condition domain gaps without requiring additional adjustments. Our results show that event cameras maintain more consistent performance across lighting conditions, exhibiting domain-shift penalties that are generally comparable to or smaller than grayscale frames and provide superior baseline performance in cross-domain scenarios.
- 20 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. PP (00189456) , 1
A Wearable Strain-Sensor-Based Shoulder Patch for Fatigue Detection in Bicep Curls
A common challenge in home-based rehabilitation is muscle compensation induced by pain or fatigue, where patients with weakened primary muscles recruit secondary muscle groups to assist their movement, causing issues such as delayed rehabilitation progress or risk of further injury. In a home-based setting, the subtle compensatory actions may not be perceived since physiotherapists cannot directly observe patients. To address this problem, this study develops a novel wearable strain-sensor-based shoulder patch to detect fatigue-induced muscle compensation during bicep curl exercises. Built on an observation that the amplitude of a strain sensor’s resistance is correlated to the motion of a joint that the sensor is attached to, we develop an algorithm that can robustly detect the state when significant changes appear in the shoulder joint motion, which indicates fatigue-induced muscle compensation in bicep curls. The developed shoulder patch is tested on 13 subjects who perform bicep curl exercises with a 5 kg dumbbell until reaching fatigue. During the experiment, the performance of the shoulder patch is also benchmarked with optical tracking sensors and surface electromyography (sEMG) sensors. Results reveal that the proposed wearable sensor and detection methods effectively monitor fatigue-induced muscle compensation during bicep curl exercises in both Real-Time and Post Hoc modes. This development marks a significant step toward enhancing the effectiveness of home-based rehabilitation by providing physiotherapists with a tool to monitor and adjust treatment plans remotely.
- 20 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. PP (00189456) , 1
A Wearable Strain-Sensor-Based Shoulder Patch for Fatigue Detection in Bicep Curls
A common challenge in home-based rehabilitation is muscle compensation induced by pain or fatigue, where patients with weakened primary muscles recruit secondary muscle groups to assist their movement, causing issues such as delayed rehabilitation progress or risk of further injury. In a home-based setting, the subtle compensatory actions may not be perceived since physiotherapists cannot directly observe patients. To address this problem, this study develops a novel wearable strain-sensor-based shoulder patch to detect fatigue-induced muscle compensation during bicep curl exercises. Built on an observation that the amplitude of a strain sensor’s resistance is correlated to the motion of a joint that the sensor is attached to, we develop an algorithm that can robustly detect the state when significant changes appear in the shoulder joint motion, which indicates fatigue-induced muscle compensation in bicep curls. The developed shoulder patch is tested on 13 subjects who perform bicep curl exercises with a 5 kg dumbbell until reaching fatigue. During the experiment, the performance of the shoulder patch is also benchmarked with optical tracking sensors and surface electromyography (sEMG) sensors. Results reveal that the proposed wearable sensor and detection methods effectively monitor fatigue-induced muscle compensation during bicep curl exercises in both Real-Time and Post Hoc modes. This development marks a significant step toward enhancing the effectiveness of home-based rehabilitation by providing physiotherapists with a tool to monitor and adjust treatment plans remotely.
- 18 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-10
Robotic Intracorporeal Palpation With a Miniature Force-Sensing Probe for Minimally Invasive Surgery
Intraoperative tissue palpation is crucial in surgical procedures to ensure operational safety and clinical outcomes. However, current robotic minimally invasive surgery (MIS) fundamentally decouples surgeons’ haptic perception from tissue interaction, posing substantial challenges for intracorporeal stiffness assessment. To address this limitation, we present an intracorporeal robotic palpation framework integrating our team’s recently developed vision-based multi-axis force sensing module. This miniature sensing module (φ5mm) enables real-time tissue interaction force measurement during endoscopic operations. The proposed system employs teleoperated robotic control with remote center of motion (RCM) constraints to ensure safe instrument manipulation. It continuously correlates tissue deformation data with contact forces to reconstruct spatial stiffness distributions. Through iterative palpation maneuvers, the system dynamically updates the stiffness map of target anatomical regions. Comprehensive validation experiments were conducted using ex-vivo chicken tissues under simulated MIS conditions, demonstrating: 1) The system’s capability to reconstruct heterogeneous tissue stiffness distributions by resolving contact forces and tissue deformation estimation; 2) Effective implementation of the proposed framework to MIS considering RCM constraint. These results substantiate the clinical viability of the miniature force-sensing module for robotic intracorporeal palpation and establish a paradigm for enhancing haptic feedback in MIS applications.
- 18 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-10
Robotic Intracorporeal Palpation With a Miniature Force-Sensing Probe for Minimally Invasive Surgery
Intraoperative tissue palpation is crucial in surgical procedures to ensure operational safety and clinical outcomes. However, current robotic minimally invasive surgery (MIS) fundamentally decouples surgeons’ haptic perception from tissue interaction, posing substantial challenges for intracorporeal stiffness assessment. To address this limitation, we present an intracorporeal robotic palpation framework integrating our team’s recently developed vision-based multi-axis force sensing module. This miniature sensing module (φ5mm) enables real-time tissue interaction force measurement during endoscopic operations. The proposed system employs teleoperated robotic control with remote center of motion (RCM) constraints to ensure safe instrument manipulation. It continuously correlates tissue deformation data with contact forces to reconstruct spatial stiffness distributions. Through iterative palpation maneuvers, the system dynamically updates the stiffness map of target anatomical regions. Comprehensive validation experiments were conducted using ex-vivo chicken tissues under simulated MIS conditions, demonstrating: 1) The system’s capability to reconstruct heterogeneous tissue stiffness distributions by resolving contact forces and tissue deformation estimation; 2) Effective implementation of the proposed framework to MIS considering RCM constraint. These results substantiate the clinical viability of the miniature force-sensing module for robotic intracorporeal palpation and establish a paradigm for enhancing haptic feedback in MIS applications.