activity
20242026
collaborators

7 papers

cs.CV2026

What Matters for Diffusion-Friendly Latent Manifold? Prior-Aligned Autoencoders for Latent Diffusion

Zhengrong Yue, Taihang Hu, Mengting Chen +8

Tokenizers are a crucial component of latent diffusion models, as they define the latent space in which diffusion models operate. However, existing tokenizers are primarily designe…

cs.CV2026

Continuous-Time Distribution Matching for Few-Step Diffusion Distillation

Tao Liu, Hao Yan, Mengting Chen +8

Step distillation has become a leading technique for accelerating diffusion models, among which Distribution Matching Distillation (DMD) and Consistency Distillation are two repres…

cs.CV2025

Meta-Unlearning on Diffusion Models: Preventing Relearning Unlearned Concepts

Hongcheng Gao, Tianyu Pang, Chao Du +3

With the rapid progress of diffusion-based content generation, significant efforts are being made to unlearn harmful or copyrighted concepts from pretrained diffusion models (DMs)…

cs.CV2025

Anchor Token Matching: Implicit Structure Locking for Training-free AR Image Editing

Taihang Hu, Linxuan Li, Kai Wang +3

Text-to-image generation has seen groundbreaking advancements with diffusion models, enabling high-fidelity synthesis and precise image editing through cross-attention manipulation…

cs.CV2024

StyleDiffusion: Prompt-Embedding Inversion for Text-Based Editing

Senmao Li, Joost van de Weijer, Taihang Hu +5

A significant research effort is focused on exploiting the amazing capacities of pretrained diffusion models for the editing of images.They either finetune the model, or invert the…

cs.CV2024

Token Merging for Training-Free Semantic Binding in Text-to-Image Synthesis

Taihang Hu, Linxuan Li, Joost van de Weijer +6

Although text-to-image (T2I) models exhibit remarkable generation capabilities, they frequently fail to accurately bind semantically related objects or attributes in the input prom…