4 papers
On-Policy Replay for Continual Supervised Fine-Tuning
Yan Chen, Taojie Zhu, Meng Zhang +4
Continual supervised fine-tuning (SFT) is the de facto recipe for adapting large language models (LLMs) to a stream of downstream tasks, but it suffers from catastrophic forgetting…
3D surface profiling via photonic integrated geometric sensor
Ziyao Zhang, Yizhi Wang, Chunhui Yao +11
Measurements of microscale surface patterns are essential for process and quality control in industries across semiconductors, micro-machining, and biomedicines. However, the devel…
Seamless Optical Cloud Computing across Edge-Metro Network for Generative AI
Sizhe Xing, Aolong Sun, Chengxi Wang +18
The rapid advancement of generative artificial intelligence (AI) in recent years has profoundly reshaped modern lifestyles, necessitating a revolutionary architecture to support th…
Asymmetrical estimator for training encapsulated deep photonic neural networks
Yizhi Wang, Minjia Chen, Chunhui Yao +4
Photonic neural networks (PNNs) are fast in-propagation and high bandwidth paradigms that aim to popularize reproducible NN acceleration with higher efficiency and lower cost. Howe…