GitHub

Decomp-Parsing-Service is a Python module that transforms abstract static analysis results into intermediate representations that can be used to suggest a decomposition of a ...

The Parsing Service interacts with the static analysis tools that generate abstract representations in the form of TypeData, methodData and invocationData. This service transforms these results into ...
GitHub

DAPS: Improving Diffusion Inverse Problem Solving with Decoupled Noise Annealing (CVPR 2025 Oral)

We propose a new method called Decoupled Annealing Posterior Sampling (DAPS) that relies on a novel noise annealing process to solve posterior sampling with diffusion prior. Specifically, we decouple ...
IEEE

Non-Uniform-Sampling-Enhanced LSTM-FCN Hybrid Network for Inverse Design of Optically Transparent Ultra-Wideband AFSR

Abstract: A new modeling framework integrating Ramer-Douglas-Peucker (RDP) non-uniform sampling (NUS) with a Long Short-Term Memory (LSTM)-Fully Connected Network (FCN) hybrid neural network (LFN) is ...
IEEE

Parallel Trajectory Constraint Sampling for Solving Universal Medical Inverse Problems

Abstract: Inverse problems in medical imaging, such as undersampled magnetic resonance imaging (MRI) and sparse-view computed tomography (CT) reconstruction, are essential yet challenging tasks for ...