Tianyi Wei
13 papers · 2021–2026 · 6 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
π£ Hot Topic Early Bird π Conference Polyglot Β· Silver π Academic Marathon Β· Sprint π Interdisciplinary Bridge Β· Silver πΊοΈ Taxonomy Completionist (30)
π§¬
Topic Evolution
π
Century Club Β· Bronze
π₯
Unstoppable Β· Bronze
ποΈ
Keyword Collector
(67)
Top co-authors
Research topics
Deep Learning
(10)
Computer Vision
(9)
Processing
(7)
Models
(6)
Machine Learning
(5)
Artificial Intelligence
(4)
Architectures
(4)
Core AI
(4)
Core Methods
(4)
Generation
(4)
Learning Types Β· Deep Learning
(4)
Analysis
(3)
Application Areas
(2)
Learning Types Β· Machine Learning
(2)
Security & Privacy
(1)
Keywords
image editing
(5)
diffusion model
(3)
image generation
(3)
hair editing
(2)
image synthesis
(2)
feature blending
(1)
feature embedding
(1)
attention mechanism
(1)
fine-grained classification
(1)
deepfake detection
(1)
instruction following
(1)
face recognition
(1)
generative model
(1)
edge detection
(1)
adversarial attack
(1)
image inpainting
(1)
text-to-image generation
(1)
cross-modal learning
(1)
convolutional neural network
(1)
anomaly detection
(1)
Papers
EARG-Net: Edge-Aware Reconstruction-Guided Network for Image Manipulation Detection and Localization
AAAI 2026
Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers
CVPR 2026
Trait Activation in Silicon: A Situation-Aware Framework for Psychologically Grounded Role-Playing
ACL 2026
FreeFlux: Understanding and Exploiting Layer-Specific Roles in RoPE-Based MMDiT for Versatile Image Editing
ICCV 2025
Scale Your Instructions: Enhance the Instruction-Following Fidelity of Unified Image Generation Model by Self-Adaptive Attention Scaling
ICCV 2025
A Geometric Distortion Immunized Deep Watermarking Framework with Robustness Generalizability
ECCV 2024
AquaLoRA: Toward White-box Protection for Customized Stable Diffusion Models via Watermark LoRA
ICML 2024
FaceRSA: RSA-Aware Facial Identity Cryptography Framework
AAAI 2024
SimAC: A Simple Anti-Customization Method for Protecting Face Privacy against Text-to-Image Synthesis of Diffusion Models
CVPR 2024
HairCLIPv2: Unifying Hair Editing via Proxy Feature Blending
ICCV 2023
HairCLIP: Design Your Hair by Text and Reference Image
CVPR 2022
Improved Image Matting via Real-Time User Clicks and Uncertainty Estimation
CVPR 2021
Multi-Attentional Deepfake Detection
CVPR 2021