64 citations · 268 across the 26 of their papers we have counts for
26 papers
StateAct: Program State, before Pixels, for Long-Horizon Computer-Use Agents
Yan Yang, Xiangru Jian, Ziyang Luo +7
Computer-use agents are usually improved by strengthening perception: better models for reading a screenshot and choosing where to click. Yet a screenshot is only a lossy rendering…
DiG: Scalable and Efficient Diffusion Models with Gated Linear Attention
Lianghui Zhu, Zilong Huang, Bencheng Liao +4
Diffusion models with large-scale pre-training have achieved significant success in the field of visual content generation, particularly exemplified by Diffusion Transformers (DiT)…
ClassDiffusion: More Aligned Personalization Tuning with Explicit Class Guidance
Jiannan Huang, Jun Hao Liew, Hanshu Yan +4
Recent text-to-image customization works have proven successful in generating images of given concepts by fine-tuning diffusion models on a few examples. However, tuning-based meth…
LightningDrag: Lightning Fast and Accurate Drag-based Image Editing Emerging from Videos
Yujun Shi, Jun Hao Liew, Hanshu Yan +2
Accuracy and speed are critical in image editing tasks. Pan et al. introduced a drag-based image editing framework that achieves pixel-level control using Generative Adversarial Ne…
PeRFlow: Piecewise Rectified Flow as Universal Plug-and-Play Accelerator
Hanshu Yan, Xingchao Liu, Jiachun Pan +3
We present Piecewise Rectified Flow (PeRFlow), a flow-based method for accelerating diffusion models. PeRFlow divides the sampling process of generative flows into several time win…
MagicVideo-V2: Multi-Stage High-Aesthetic Video Generation
Weimin Wang, Jiawei Liu, Zhijie Lin +9
The growing demand for high-fidelity video generation from textual descriptions has catalyzed significant research in this field. In this work, we introduce MagicVideo-V2 that inte…
Towards Accurate Guided Diffusion Sampling through Symplectic Adjoint Method
Jiachun Pan, Hanshu Yan, Jun Hao Liew +2
Training-free guided sampling in diffusion models leverages off-the-shelf pre-trained networks, such as an aesthetic evaluation model, to guide the generation process. Current trai…
MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model
Zhongcong Xu, Jianfeng Zhang, Jun Hao Liew +5
This paper studies the human image animation task, which aims to generate a video of a certain reference identity following a particular motion sequence. Existing animation works t…
MagicProp: Diffusion-based Video Editing via Motion-aware Appearance Propagation
Hanshu Yan, Jun Hao Liew, Long Mai +2
This paper addresses the issue of modifying the visual appearance of videos while preserving their motion. A novel framework, named MagicProp, is proposed, which disentangles the v…
MagicEdit: High-Fidelity and Temporally Coherent Video Editing
Jun Hao Liew, Hanshu Yan, Jianfeng Zhang +2
In this report, we present MagicEdit, a surprisingly simple yet effective solution to the text-guided video editing task. We found that high-fidelity and temporally coherent video-…
MagicAvatar: Multimodal Avatar Generation and Animation
Jianfeng Zhang, Hanshu Yan, Zhongcong Xu +2
This report presents MagicAvatar, a framework for multimodal video generation and animation of human avatars. Unlike most existing methods that generate avatar-centric videos direc…
AdjointDPM: Adjoint Sensitivity Method for Gradient Backpropagation of Diffusion Probabilistic Models
Jiachun Pan, Jun Hao Liew, Vincent Y. F. Tan +2
Existing customization methods require access to multiple reference examples to align pre-trained diffusion probabilistic models (DPMs) with user-provided concepts. This paper aims…
DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editing
Yujun Shi, Chuhui Xue, Jun Hao Liew +5
Accurate and controllable image editing is a challenging task that has attracted significant attention recently. Notably, DragGAN is an interactive point-based image editing framew…
Towards Enhancing Time Series Contrastive Learning: A Dynamic Bad Pair Mining Approach
Xiang Lan, Hanshu Yan, Shenda Hong +1
Not all positive pairs are beneficial to time series contrastive learning. In this paper, we study two types of bad positive pairs that can impair the quality of time series repres…
Towards Adversarial Robustness of Deep Vision Algorithms
Hanshu Yan
Deep learning methods have achieved great success in solving computer vision tasks, and they have been widely utilized in artificially intelligent systems for image processing, ana…
MagicVideo: Efficient Video Generation With Latent Diffusion Models
Daquan Zhou, Weimin Wang, Hanshu Yan +3
We present an efficient text-to-video generation framework based on latent diffusion models, termed MagicVideo. MagicVideo can generate smooth video clips that are concordant with…
MagicMix: Semantic Mixing with Diffusion Models
Jun Hao Liew, Hanshu Yan, Daquan Zhou +1
Have you ever imagined what a corgi-alike coffee machine or a tiger-alike rabbit would look like? In this work, we attempt to answer these questions by exploring a new task called…
Towards Adversarially Robust Deep Image Denoising
Hanshu Yan, Jingfeng Zhang, Jiashi Feng +2
This work systematically investigates the adversarial robustness of deep image denoisers (DIDs), i.e, how well DIDs can recover the ground truth from noisy observations degraded by…
Efficient Sharpness-aware Minimization for Improved Training of Neural Networks
Jiawei Du, Hanshu Yan, Jiashi Feng +4
Overparametrized Deep Neural Networks (DNNs) often achieve astounding performances, but may potentially result in severe generalization error. Recently, the relation between the sh…
Information-Theoretic Characterization of the Generalization Error for Iterative Semi-Supervised Learning
Haiyun He, Hanshu Yan, Vincent Y. F. Tan
Using information-theoretic principles, we consider the generalization error (gen-error) of iterative semi-supervised learning (SSL) algorithms that iteratively generate pseudo-lab…
Recovering the Unbiased Scene Graphs from the Biased Ones
Meng-Jiun Chiou, Henghui Ding, Hanshu Yan +3
Given input images, scene graph generation (SGG) aims to produce comprehensive, graphical representations describing visual relationships among salient objects. Recently, more effo…
CIFS: Improving Adversarial Robustness of CNNs via Channel-wise Importance-based Feature Selection
Hanshu Yan, Jingfeng Zhang, Gang Niu +3
We investigate the adversarial robustness of CNNs from the perspective of channel-wise activations. By comparing \textit{non-robust} (normally trained) and \textit{robustified} (ad…
RAIN: A Simple Approach for Robust and Accurate Image Classification Networks
Jiawei Du, Hanshu Yan, Vincent Y. F. Tan +3
It has been shown that the majority of existing adversarial defense methods achieve robustness at the cost of sacrificing prediction accuracy. The undesirable severe drop in accura…
Adversarial Domain Adaptation with Prototype-Based Normalized Output Conditioner
Dapeng Hu, Jian Liang, Qibin Hou +2
In this work, we attempt to address unsupervised domain adaptation by devising simple and compact conditional domain adversarial training methods. We first revisit the simple conca…