papers

Publications (42)

cs.NI2016

SICS: Secure In-Cloud Service Function Chaining

Huazhe Wang, Xin Li, Yu Zhao +3

There is an increasing trend that enterprises outsource their network functions to the cloud for lower cost and ease of management. However, network function outsourcing brings thr…

cs.CV2021

MUSE: Feature Self-Distillation with Mutual Information and Self-Information

Yu Gong, Ye Yu, Gaurav Mittal +2

We present a novel information-theoretic approach to introduce dependency among features of a deep convolutional neural network (CNN). The core idea of our proposed method, called…

cs.CL2026

Nemotron-Labs-Diffusion: A Tri-Mode Language Model Unifying Autoregressive, Diffusion, and Self-Speculation Decoding

Yonggan Fu, Lexington Whalen, Abhinav Garg +23

We introduce Nemotron-Labs-Diffusion, a tri-mode language model (LM) that unifies AR, diffusion, and self-speculation decoding within a single architecture. Trained with a joint AR…

cs.MA2026

MiroBench: Benchmarking Realism in Agentic Simulation of Real-world Discussions

Yaoning Yu, Ye Yu, Haojing Luo +1

LLM agents are increasingly used to simulate real world interactions, but it remains unclear whether simulated behaviors preserve the content patterns and interaction dynamics of r…

cond-mat.mtrl-sci2022

Mid- and far-infrared localized surface plasmon resonances in chalcogen-hyperdoped silicon

Mao Wang, Ye Yu, Slawomir Prucnal +13

Plasmonic sensing in the infrared region employs the direct interaction of the vibrational fingerprints of molecules with the plasmonic resonances, creating surface-enhanced sensin…

cs.CV2026

DDR-Net: Haze-Aware Dual-Domain Refinement for Single-Image Dehazing

Xinye Zheng, Ye Yu, Qiang Lu +3

DDR-Net is a neural network that improves single-image dehazing by extracting multi-scale haze priors, enhancing structural details with gradient-aware convolutions, and refining b…

#single-image dehazing#dual-domain refinement#haze prior extraction#detail enhancement