7 accepted papers
Large language models (LLMs) have advanced to encompass extensive knowledge across diverse domains. Yet controlling what a LLMs should not know is important for ensuring alignment and thus safe use. However, effective unlearning in LLMs is difficult due to the fuzzy boundary between knowledge retent
Soft robotics, renowned for its robust adaptability to complex environments, holds great promise for a wide array of applications. Among the various actuation methods, magnetic fields stand out as particularly advantageous for soft robotics due to their ability to enable remote control and their bio
In continual learning, networks confront a trade-off between stability and plasticity when trained on a sequence of tasks. To bolster plasticity without sacrificing stability, we propose a novel training algorithm called LRFR. This approach optimizes network parameters in the null space of the past…
Surgical incision is a pervasive procedure in medical environments. Stapling is an incision closure method that is comparable to stitching. While incision closure is performed immediately after a surgery, staples are removed several weeks after the closure. The workload of surgeons and the probabili
The massive sensing data generated by Internet-of-Things will provide fuel for ubiquitous artificial intelligence (AI), while tremendous labels are required for AI model training via supervised learning. To tackle this challenge, a novel framework of wireless crowd labelling is proposed that downloa…
A modified nested linear array (MNLA) has been reported recently for a greater potential in increasing the degree-of-freedom. However, there exist some "holes" in the difference co-array, which results in missing "lags" and limited performance of direction-of-arrival (DOA) estimation. In order to ta…
We study a spoofing attack happened in the physical layer of a multiple-antenna system, where an adversary tries to spoof the transmitter by sending the identical pilot (training) signal as that of a legitimate receiver in the uplink channel estimation phase. This attack, named as pilot spoofing att…