Tianyi Wei

Orcid: 0000-0002-7976-8439

According to our database1, Tianyi Wei authored at least 40 papers between 2016 and 2026.

Collaborative distances:

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

On csauthors.net:

Bibliography

2026
Unifying Multi-Modal Hair Editing via Proxy Feature Blending.
IEEE Trans. Pattern Anal. Mach. Intell., June, 2026

StructDiff: A Structure-Preserving and Spatially Controllable Diffusion Model for Single-Image Generation.
CoRR, April, 2026

From Sparse to Dense: Multi-View GRPO for Flow Models via Augmented Condition Space.
CoRR, March, 2026

Hand2World: Autoregressive Egocentric Interaction Generation via Free-Space Hand Gestures.
CoRR, February, 2026

Rethinking Multi-Condition DiTs: Eliminating Redundant Attention via Position-Alignment and Keyword-Scoping.
CoRR, February, 2026

PnP-U3D: Plug-and-Play 3D Framework Bridging Autoregression and Diffusion for Unified Understanding and Generation.
CoRR, February, 2026

PI-Light: Physics-Inspired Diffusion for Full-Image Relighting.
CoRR, January, 2026

UniForensics: Face Forgery Detection via General Facial Representation.
IEEE Trans. Dependable Secur. Comput., 2026

EARG-Net: Edge-Aware Reconstruction-Guided Network for Image Manipulation Detection and Localization.
Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

2025
Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers.
CoRR, December, 2025

BokehDepth: Enhancing Monocular Depth Estimation through Bokeh Generation.
CoRR, December, 2025

Dense Semantic Matching with VGGT Prior.
CoRR, September, 2025

Token Buncher: Shielding LLMs from Harmful Reinforcement Learning Fine-Tuning.
CoRR, August, 2025

WordCraft: Interactive Artistic Typography with Attention Awareness and Noise Blending.
CoRR, July, 2025

Antiano: A Series of Attacks Exploiting Vulnerabilities in Deep Face Anonymization Algorithms.
IEEE Trans. Inf. Forensics Secur., 2025

Bokeh Diffusion: Defocus Blur Control in Text-to-Image Diffusion Models.
Proceedings of the SIGGRAPH Asia 2025 Conference Papers, 2025

MentalChat16K: A Benchmark Dataset for Conversational Mental Health Assistance.
Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining, V.2, 2025

Scale Your Instructions: Enhance the Instruction-Following Fidelity of Unified Image Generation Model by Self-Adaptive Attention Scaling.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2025

FreeFlux: Understanding and Exploiting Layer-Specific Roles in RoPE-Based MMDiT for Versatile Image Editing.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2025

2024
Deep Image Matting With Sparse User Interactions.
IEEE Trans. Pattern Anal. Mach. Intell., February, 2024

Enhancing MMDiT-Based Text-to-Image Models for Similar Subject Generation.
CoRR, 2024

PRCpy: A Python Package for Processing of Physical Reservoir Computing.
CoRR, 2024

Clustering Alzheimer's Disease Subtypes via Similarity Learning and Graph Diffusion.
CoRR, 2024

Establishing Rigorous and Cost-effective Clinical Trials for Artificial Intelligence Models.
CoRR, 2024

AI.vs.Clinician: Unveiling Intricate Interactions Between AI and Clinicians through an Open-Access Database.
CoRR, 2024

Rank-based No-reference Quality Assessment for Face Swapping.
CoRR, 2024

AquaLoRA: Toward White-box Protection for Customized Stable Diffusion Models via Watermark LoRA.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

A Geometric Distortion Immunized Deep Watermarking Framework with Robustness Generalizability.
Proceedings of the Computer Vision - ECCV 2024, 2024

SimAC: A Simple Anti-Customization Method for Protecting Face Privacy Against Text-to-Image Synthesis of Diffusion Models.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

FaceRSA: RSA-Aware Facial Identity Cryptography Framework.
Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

2023
SimAC: A Simple Anti-Customization Method against Text-to-Image Synthesis of Diffusion Models.
CoRR, 2023

HairCLIPv2: Unifying Hair Editing via Proxy Feature Blending.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

2022
E2Style: Improve the Efficiency and Effectiveness of StyleGAN Inversion.
IEEE Trans. Image Process., 2022

HairCLIP: Design Your Hair by Text and Reference Image.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

2021
A Simple Baseline for StyleGAN Inversion.
CoRR, 2021

Multi-Attentional Deepfake Detection.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021

Improved Image Matting via Real-Time User Clicks and Uncertainty Estimation.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021

2017
Distributed Multi-Representative Re-Fusion Approach for Heterogeneous Sensing Data Collection.
ACM Trans. Embed. Comput. Syst., 2017

2016
Fast Program Codes Dissemination for Smart Wireless Software Defined Networks.
Sci. Program., 2016

Random Secure Comparator Selection Based Privacy-Preserving MAX/MIN Query Processing in Two-Tiered Sensor Networks.
J. Sensors, 2016


  Loading...