activity
20242026
collaborators

8 papers

cs.CV2026

DiffRGD: An Inference-Time Diffusion Guidance Through Riemannian Gradient Descent

Jia-Wei Liao, Li-Xuan Peng, Mei-Heng Yueh +3

Recently, diffusion models have been widely adopted in generative modeling and have served as foundational models for many image generation tasks. To control the generation without…

cs.CV2026

An Improved Variational Method for Image Denoising

Jing-En Huang, Jia-Wei Liao, Ku-Te Lin +2

The total variation (TV) method is an image denoising technique that aims to reduce noise by minimizing the total variation of the image, which measures the variation in pixel inte…

cs.CV2026

COT-FM: Cluster-wise Optimal Transport Flow Matching

Chiensheng Chiang, Kuan-Hsun Tu, Jia-Wei Liao +2

We introduce COT-FM, a general framework that reshapes the probability path in Flow Matching (FM) to achieve faster and more reliable generation. FM models often produce curved tra…

cs.CV2025

M-ErasureBench: A Comprehensive Multimodal Evaluation Benchmark for Concept Erasure in Diffusion Models

Ju-Hsuan Weng, Jia-Wei Liao, Cheng-Fu Chou +1

Text-to-image diffusion models may generate harmful or copyrighted content, motivating research on concept erasure. However, existing approaches primarily focus on erasing concepts…

cs.CV2025

BEVANet: Bilateral Efficient Visual Attention Network for Real-Time Semantic Segmentation

Ping-Mao Huang, I-Tien Chao, Ping-Chia Huang +2

Real-time semantic segmentation presents the dual challenge of designing efficient architectures that capture large receptive fields for semantic understanding while also refining…

cs.CV2025

DiffQRCoder: Diffusion-based Aesthetic QR Code Generation with Scanning Robustness Guided Iterative Refinement

Jia-Wei Liao, Winston Wang, Tzu-Sian Wang +4

With the success of Diffusion Models for image generation, the technologies also have revolutionized the aesthetic Quick Response (QR) code generation. Despite significant improvem…