2 citations · 2 across the 8 of their papers we have counts for
8 papers
Selective Prior Synchronization via SYNC Loss
Ishan Mishra, Jiajie Li, Deepak Mishra +1
Prediction under uncertainty is a critical requirement for the deep neural network to succeed responsibly. This paper focuses on selective prediction, which allows DNNs to make inf…
A New Workflow for Materials Discovery Bridging the Gap Between Experimental Databases and Graph Neural Networks
Brandon Schoener, Yuting Hu, Pasit Wanlapha +6
Incorporating Machine Learning (ML) into material property prediction has become a crucial step in accelerating materials discovery. A key challenge is the severe lack of training…
MaskOpt: A Large-Scale Mask Optimization Dataset to Advance AI in Integrated Circuit Manufacturing
Yuting Hu, Lei Zhuang, Hua Xiang +2
As integrated circuit (IC) dimensions shrink below the lithographic wavelength, optical lithography faces growing challenges from diffraction and process variability. Model-based o…
Auto-Prompt Ensemble for LLM Judge
Jiajie Li, Huayi Zhang, Peng Lin +2
We present a novel framework that improves the reliability of LLM judges by selectively augmenting LLM with auxiliary evaluation dimensions. Existing LLM judges often miss crucial…
Rebuild AC Power Flow Models with Graph Attention Networks
Yuting Hu, Jinjun Xiong
A full power flow (PF) model is a complete representation of the physical power network. Traditional model-based methods rely on the full PF model to implement power flow analysis.…
LLaVA-Surg: Towards Multimodal Surgical Assistant via Structured Surgical Video Learning
Jiajie Li, Garrett Skinner, Gene Yang +4
Multimodal large language models (LLMs) have achieved notable success across various domains, while research in the medical field has largely focused on unimodal images. Meanwhile,…
xMLP: Revolutionizing Private Inference with Exclusive Square Activation
Jiajie Li, Jinjun Xiong
Private Inference (PI) enables deep neural networks (DNNs) to work on private data without leaking sensitive information by exploiting cryptographic primitives such as multi-party…
FL-NAS: Towards Fairness of NAS for Resource Constrained Devices via Large Language Models
Ruiyang Qin, Yuting Hu, Zheyu Yan +3
Neural Architecture Search (NAS) has become the de fecto tools in the industry in automating the design of deep neural networks for various applications, especially those driven by…