14 papers
RIDGE: Re-Noising with Internal Dynamic Guidance for Image Editing
Ruiliang Gong, Zhen Wang, Yanghao Wang +1
Inversion-free flow-based image editing avoids latent inversion, but still requires a target-side state at every editing step. The widely used equal-displacement construction keeps…
h-Flow: Flexible Flow-based Image Editing via Doob's h-Transform
Zehui Guo, Zhen Wang, Junwei Shu +3
Editing images with pre-trained text-to-image flow models typically requires carefully balancing target alignment with the desired prompt and source consistency with the original i…
Robustifying Vision-Language Models via Test-Time Prompt Adaptation
Xingyu Zhu, Huanshen Wu, Shuo Wang +4
Pre-trained Vision-Language Models (VLMs) such as CLIP achieve strong zero-shot generalization, but their performance degrades sharply under adversarial perturbations. Existing tes…
LISA: Likelihood Score Alignment for Visual-condition Controllable Generation
Yanghao Wang, Hongxu Chen, Jiazhen Liu +4
The prevalent dual-branch paradigm, i.e., training a side network to encode visual conditions and fusing its intermediate-layer features to a frozen pretrained main network, has sh…
Physics-Informed Video Generation via Mixture-of-Experts Latent Alignment
Cong Wang, Hanxin Zhu, Jiayi Luo +6
Large-scale video generation models have made remarkable progress in semantic consistency and visual quality, producing videos that are increasingly coherent and visually convincin…
SwiftI2V: Efficient High-Resolution Image-to-Video Generation via Conditional Segment-wise Generation
YaoYang Liu, Yuechen Zhang, Wenbo Li +3
High-resolution image-to-video (I2V) generation aims to synthesize realistic temporal dynamics while preserving fine-grained appearance details of the input image. At 2K resolution…
RealCam: Real-Time Novel-View Video Generation with Interactive Camera Control
Youcan Xu, Jiaxin Shi, Zhen Wang +5
Camera-controlled video-to-video (V2V) generation enables dynamic viewpoint synthesis from monocular footage, holding immense potential for interactive filmmaking and live broadcas…
Direct Product Flow Matching: Decoupling Radial and Angular Dynamics for Few-Shot Adaptation
Hongxu Chen, Yanghao Wang, Bowei Zhu +6
Recent flow matching (FM) methods improve the few-shot adaptation of vision-language models, by modeling cross-modal alignment as a continuous multi-step flow. In this paper, we ar…
Adaptive Weighted h-Transform Sampling for Coarse-Guided Visual Generation
Yanghao Wang, Ziqi Jiang, Zhen Wang +1
Coarse-guided visual generation, which synthesizes fine visual samples from degraded or low-fidelity coarse references, is essential for various real-world applications. While trai…
FlowMotion: Training-Free Flow Guidance for Video Motion Transfer
Zhen Wang, Youcan Xu, Jun Xiao +1
Video motion transfer aims to generate a target video that inherits motion patterns from a source video while rendering new scenes. Existing training-free approaches focus on const…
Bi-Anchor Interpolation Solver for Accelerating Generative Modeling
Hongxu Chen, Hongxiang Li, Zhen Wang +1
Flow Matching (FM) models have emerged as a leading paradigm for high-fidelity synthesis. However, their reliance on iterative Ordinary Differential Equation (ODE) solving creates…
Zero-Residual Concept Erasure via Progressive Alignment in Text-to-Image Model
Hongxu Chen, Zhen Wang, Taoran Mei +4
Concept Erasure, which aims to prevent pretrained text-to-image models from generating content associated with semantic-harmful concepts (i.e., target concepts), is getting increas…
IterIS: Iterative Inference-Solving Alignment for LoRA Merging
Hongxu Chen, Runshi Li, Bowei Zhu +2
Low-rank adaptations (LoRA) are widely used to fine-tune large models across various domains for specific downstream tasks. While task-specific LoRAs are often available, concerns…
CLIPDrag: Combining Text-based and Drag-based Instructions for Image Editing
Ziqi Jiang, Zhen Wang, Long Chen
Precise and flexible image editing remains a fundamental challenge in computer vision. Based on the modified areas, most editing methods can be divided into two main types: global…