11 papers
Learning Representations to Guide Pixel Diffusion Transformers
Zihao Pan, Mengting Chen, Cheng Shi +6
Visual representations are largely developed for understanding, yet what makes them useful for generation remains unclear. We study this question in pixel diffusion transformers an…
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…
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…
Where and How to Prune: An Empirical Study of Visual Token Pruning for GUI Agent Navigation
Daiqiang Li, Zihao Pan, Zeyu Zhang +8
In recent years, GUI agents have demonstrated strong potential in navigation tasks. However, preserving complete historical screenshots introduces substantial computational overhea…
Think with 3D: Geometric Imagination Grounded Spatial Reasoning from Limited Views
Zhangquan Chen, Manyuan Zhang, Xinlei Yu +8
Though recent advances in vision-language models (VLMs) have achieved remarkable progress across a wide range of multimodal tasks, understanding 3D spatial relationships from limit…
X2Edit: Revisiting Arbitrary-Instruction Image Editing through Self-Constructed Data and Task-Aware Representation Learning
Jian Ma, Xujie Zhu, Zihao Pan +4
Existing open-source datasets for arbitrary-instruction image editing remain suboptimal, while a plug-and-play editing module compatible with community-prevalent generative models…
Detail++: Training-Free Detail Enhancer for T2I Diffusion Models
Lifeng Chen, Jiner Wang, Zihao Pan +3
Recent advances in text-to-image (T2I) generation have led to impressive visual results. However, these models still face significant challenges when handling complex prompt, parti…
Training-Free Watermarking for Autoregressive Image Generation
Yu Tong, Zihao Pan, Shuai Yang +1
Invisible image watermarking can protect image ownership and prevent malicious misuse of visual generative models. However, existing generative watermarking methods are mainly desi…
GRE Suite: Geo-localization Inference via Fine-Tuned Vision-Language Models and Enhanced Reasoning Chains
Chun Wang, Xiaojun Ye, Xiaoran Pan +3
Recent advances in Visual Language Models (VLMs) have demonstrated exceptional performance in visual reasoning tasks. However, geo-localization presents unique challenges, requirin…
Blind Spot Navigation: Evolutionary Discovery of Sensitive Semantic Concepts for LVLMs
Zihao Pan, Yu Tong, Weibin Wu +6
Adversarial attacks aim to generate malicious inputs that mislead deep models, but beyond causing model failure, they cannot provide certain interpretable information such as ``\te…
SCA: Improve Semantic Consistent in Unrestricted Adversarial Attacks via DDPM Inversion
Zihao Pan, Lifeng Chen, Weibin Wu +2
Systems based on deep neural networks are vulnerable to adversarial attacks. Unrestricted adversarial attacks typically manipulate the semantic content of an image (e.g., color or…