FACULTY

Future System?on?Chip (SoC) platforms will integrate hundreds of heterogeneous components — processor cores, DSPs, memory blocks, accelerators, and I/O subsystems — within extremely compact silicon footprints. As integration density increases, these systems are evolving beyond traditional bus?based communication toward sophisticated on?chip networks and vertically integrated architectures.
Our research addresses the key challenges of this transition by exploring advanced on?chip interconnects and 3D?IC technologies, including 3D chiplets, 2.5D/3D packaging, hybrid bonding, and photonic?electronic interconnects. We investigate scalable and energy?efficient 3D NoCs, AI accelerators with stacked memory, and reliability?driven design methodologies to ensure robust operation in deep 3D stacks.

This work tackles critical issues such as fault tolerance, TSV?based vertical integration, photonic communication, low?power mapping, adaptive routing, and emerging reliability challenges inherent to next?generation heterogeneous many?core systems.
...read more

View

Prosthetic limbs can significantly improve the quality of life of people with amputations or neurological disabilities. With the rapid evolution of sensors and mechatronic technology, these devices are becoming widespread therapeutic solutions. However, unlike living agents that combine different sensory inputs to perform a complex task accurately, most prosthetic limbs use uni-sensory input, which affects their accuracy and usability. Moreover, the methods used to control current prosthetic limbs (i.e., arms and legs) generally rely on sequential control and power-hungry strategies with limited natural motion and long and complicated training procedures. This project develops an advanced real-time neuromorphic prosthesis hand, AIzuHand, with sensory integration and feedback sensing. In addition, we investigate a user-friendly software tool for calibration, real-time feedback, and functional tasks.

...read more

View

We are exploring the development of an adaptive ultra-low power neuromorphic chip (NASH) and systems, enhanced by our previously developed fault-tolerant three-dimensional on-chip interconnect technology. The NASH system boasts several features, including an efficient adaptive configuration method that enables the reconfiguration of various SNN parameters such as spike weights, routing, hidden layers, and topology. Additionally, the system incorporates a blend of different deep neural network topologies, an efficient fault-tolerant multicast spike routing algorithm, and an effective on-chip learning mechanism. To demonstrate the performance of the NASH system, we will develop an FPGA implementation and establish a VLSI implementation. The ultimate goal of NASH is to bring brain-inspired processing technology to small-scale embedded sensors and sensor-based devices, such as BCI (EEG/EMG), audio, presence detection, and activity recognition.

...read more

View

Our research in power and energy-efficient computing systems is essential to meeting the growing demand for more powerful and sustainable technology. As society increasingly relies on computing devices, managing their energy consumption becomes crucial. By developing efficient computing systems, we can significantly reduce energy costs, minimize environmental impact, and extend the battery life of portable devices. In large-scale data centers, enhancing energy efficiency leads to substantial cost savings and a reduced carbon footprint. Our work in this field fosters innovation in hardware and software design, paving the way for smarter, greener technologies that benefit both users and the planet.

...read more

View

We investigate next?generation adaptive distributed autonomous systems through the lens of anthropomorphic prosthetics, androids, and intelligent robotic platforms. Our research integrates cutting?edge neuroscience, artificial intelligence, neuromorphic computing, and robotics to create highly responsive, lifelike systems capable of operating autonomously while adapting to human intent and dynamic environments.
Leveraging neuromorphic architectures and spiking neural networks, we develop control frameworks that enable natural, intuitive interaction between artificial limbs, androids, and biological systems. These brain?inspired models support real?time adaptation, low?power operation, and seamless communication across distributed components.
Our work on non?invasive neural interfaces allows prosthetic devices to adjust continuously to user intent, improving precision, comfort, and fluidity of motion. In parallel, our research on advanced sensory processing equips androids with human?like perceptual capabilities, enabling them to interpret complex environmental stimuli, collaborate with humans, and function autonomously within distributed multi?agent settings.
By bridging biomechanical engineering with AI?driven cognition, we are advancing assistive technologies, human augmentation, and adaptive robotics. Our efforts extend to distributed anthropomorphic androids, where multiple embodied agents coordinate intelligently, share sensory information, and adapt collectively to real?world tasks. This work lays the foundation for autonomous systems that are deeply integrated into daily life, scalable across environments, and capable of evolving with human needs.

...read more

View

Our research is dedicated to the design and utilization of computers with minimal environmental impact, encompassing efforts to reduce energy consumption, minimize waste, and employ sustainable materials. By integrating cutting-edge technologies and innovative methodologies, we aim to develop solutions that not only enhance the efficiency and functionality of computing systems but also contribute to the preservation of our planet. Our multidisciplinary approach involves collaboration with companies and experts in various fields, ensuring that our findings and implementations are both practical and impactful.

...read more

View