🦘Teng-Fang – Master Student in NYCU

👋 Hi! I’m Hsiao, Teng-Fang (蕭登方)

I’ve been pursuing my PhD degree of Electrical Engineering at National Yang Ming Chiao Tung University since September 2026 🎓. Under the supervision of professor Shuai, Hong-Han.

My research focuses on Computer Vision and AIGC.
I previously worked on 2D generation and image editing, and I’m now exploring 3D and video generation 🧠🖼️🎥.

I’m the first author of publications at SIGGRAPH 2026, ICCV 2025, AAAI 2025, and WACV 2024,
and also co-author of papers accepted at ECCV 2026, ICIP 2025 (Oral), EMNLP 2025 (Findings) 📄✨.

I’m always open to academic discussions, collaborations, or research opportunities 🤝 — feel free to reach out!

VecSet-Edit: Unleashing Pre-trained LRM for Mesh Editing from Single Image
Teng-Fang Hsiao, Bo-Kai Ruan, Yu-Lun Liu, Hong-Han Shuai
Special Interest Group on Computer Graphics and Interactive Techniques Conference Papers (SIGGRAPH), 2026
Editing 3D Mesh with image-only instruction, without 3D annotation 🖼️🔥🐶
pdf / GitHub / Project page

TF-TI2I: Training-Free Text-and-Image-to-Image Generation via Multi-Modal Implicit-Context Learning in Text-to-Image Models
Teng-Fang Hsiao, Bo-Kai Ruan, Yi-Lun Wu, Tzu-Ling Lin, Hong-Han Shuai
International Conference on Computer Vision (ICCV), 2025
Augment your T2I models with arbitrary number of images as references in a Training-Free manner 🦖🖼️🔥
pdf / GitHub / Project page

FreeCond: Free Lunch in the Input Conditions of Text-Guided Inpainting
Teng-Fang Hsiao, Bo-Kai Ruan, Sung-Lin Tsai, Yi-Lun Wu, Hong-Han Shuai
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2026
Enhancing Inpainting Quality without additional computation 🖌️💪0️⃣
pdf / GitHub

Training-and-Prompt-Free General Painterly Harmonization via Zero-Shot Disentenglement on Style and Content References
Teng-Fang Hsiao, Bo-Kai Ruan, Hong-Han Shuai
Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2025
Harmonizing any copy and pasted objects in a Training-Free manner 🖼️👩🏻‍🎨🎨
pdf / GitHub

RADIANCE: Relative Adaptive Denoising with IP-Adapter for Novel Concept Enhancement
Zi-Xiang Ni, Bo-Lun Huang, Teng-Fang Hsiao, Bo-Kai Ruan, Hong-Han Shuai
European Conference on Computer Vision (ECCV), 2026
Enhance image generation with rare concepts in a Training-Free manner 🐶😸🐛
pdf /

Not All Thats Rare Is Lost: Causal Paths to Rare Concept Synthesis
Bo-Kai Ruan, Zi-Xiang Ni, Bo-Lun Huang, Teng-Fang Hsiao, Hong-Han Shuai
arXiv preprint, 2025/5
Rare Prompt T2I Generation 👽👾🤖
pdf /

Breaking the Reviewer: Assessing the Vulnerability of Large Language Models in Automated Peer Review Under Textual Adversarial Attacks
Tzu-Ling Lin, Wei-Chih Chen, Teng-Fang Hsiao, Hou-I Liu, Ya-Hsin Yeh, Yu Kai Chan, Wen-Sheng Lien, Po-Yen Kuo, Philip S Yu, Hong-Han Shuai
To be appear on EMNLP Findings, 2025
LLM Reviewers Are Not Robust against adversarial attacks 📜🤜🤖
pdf /

IterDiff: Training-Free Iterative Face Editing Via Efficient Clip-Guided Memory Bank
Chun-Yao Chiu, Feng-Kai Huang, Teng-Fang Hsiao, Hong-Han Shuai, Wen-Huang Cheng
IEEE International Conference on Image Processing (ICIP), 2025
Overcome Image Corruption during Iteratively Image Editing made by IP2P 🧠🏦🎨
pdf /

Natural light can also be dangerous: Traffic sign misinterpretation under adversarial natural light attacks
Teng-Fang Hsiao, Bo-Lun Huang, Zi-Xiang Ni, Yan-Ting Lin, Hong-Han Shuai, Yung-Hui Li, Wen-Huang Cheng
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2024
Real world physical attack on Autonomus Driving with Natural Light 💡🚗⚠️
pdf / GitHub