4 papers
PIDT: Physics-Informed Digital Twin for Optical Fiber Parameter Estimation
Zicong Jiang, Magnus Karlsson, Erik Agrell +1
We propose physics-informed digital twin (PIDT): a fiber parameter estimation approach that combines a parameterized split-step method with a physics-informed loss. PIDT improves a…
AhaKV: Adaptive Holistic Attention-Driven KV Cache Eviction for Efficient Inference of Large Language Models
Yifeng Gu, Zicong Jiang, Jianxiu Jin +3
Large Language Models (LLMs) have significantly advanced the field of Artificial Intelligence. However, their deployment is resource-intensive, not only due to the large number of…
LogQuant: Log-Distributed 2-Bit Quantization of KV Cache with Superior Accuracy Preservation
Han Chen, Zicong Jiang, Zining Zhang +4
We introduce LogQuant, a groundbreaking 2-bit quantization technique for KV Cache in large language model (LLM) inference, delivering substantial memory savings while preserving su…
FDS: Frequency-Aware Denoising Score for Text-Guided Latent Diffusion Image Editing
Yufan Ren, Zicong Jiang, Tong Zhang +2
Text-guided image editing using Text-to-Image (T2I) models often fails to yield satisfactory results, frequently introducing unintended modifications, such as the loss of local det…