1 citations · 3 across the 13 of their papers we have counts for
14 papers
DiT as Real-Time Rerenderer: Streaming Video Stylization with Autoregressive Diffusion Transformer
Hengye Lyu, Zisu Li, Yue Hong +4
Recent advances in video generation models has significantly accelerated video generation and related downstream tasks. Among these, video stylization holds important research valu…
Efficient Matrix Implementation for Rotary Position Embedding
Chen Minqi, Zhongqi Yue, Shihao Zhang +5
Rotary Position Embedding (RoPE) has become a core component of modern Transformer architectures across language, vision, and 3D domains. However, existing implementations rely on…
Align is not Enough: Multimodal Universal Jailbreak Attack against Multimodal Large Language Models
Youze Wang, Wenbo Hu, Yinpeng Dong +3
Large Language Models (LLMs) have evolved into Multimodal Large Language Models (MLLMs), significantly enhancing their capabilities by integrating visual information and other type…
Aligned Contrastive Loss for Long-Tailed Recognition
Jiali Ma, Jiequan Cui, Maeno Kazuki +4
In this paper, we propose an Aligned Contrastive Learning (ACL) algorithm to address the long-tailed recognition problem. Our findings indicate that while multi-view training boost…
Learning to Animate Images from A Few Videos to Portray Delicate Human Actions
Haoxin Li, Yingchen Yu, Qilong Wu +3
Despite recent progress, video generative models still struggle to animate static images into videos that portray delicate human actions, particularly when handling uncommon or nov…
CARE Transformer: Mobile-Friendly Linear Visual Transformer via Decoupled Dual Interaction
Yuan Zhou, Qingshan Xu, Jiequan Cui +4
Recently, large efforts have been made to design efficient linear-complexity visual Transformers. However, current linear attention models are generally unsuitable to be deployed i…
Instruction Tuning-free Visual Token Complement for Multimodal LLMs
Dongsheng Wang, Jiequan Cui, Miaoge Li +3
As the open community of large language models (LLMs) matures, multimodal LLMs (MLLMs) have promised an elegant bridge between vision and language. However, current research is inh…
A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training
Kai Wang, Mingjia Shi, Yukun Zhou +6
Training diffusion models is always a computation-intensive task. In this paper, we introduce a novel speed-up method for diffusion model training, called, which is based on a clos…
Few-shot Learner Parameterization by Diffusion Time-steps
Zhongqi Yue, Pan Zhou, Richang Hong +2
Even when using large multi-modal foundation models, few-shot learning is still challenging -- if there is no proper inductive bias, it is nearly impossible to keep the nuanced cla…
Doubly Abductive Counterfactual Inference for Text-based Image Editing
Xue Song, Jiequan Cui, Hanwang Zhang +3
We study text-based image editing (TBIE) of a single image by counterfactual inference because it is an elegant formulation to precisely address the requirement: the edited image s…
Controllable Relation Disentanglement for Few-Shot Class-Incremental Learning
Yuan Zhou, Richang Hong, Yanrong Guo +3
In this paper, we propose to tackle Few-Shot Class-Incremental Learning (FSCIL) from a new perspective, i.e., relation disentanglement, which means enhancing FSCIL via disentanglin…
Exploring Diffusion Time-steps for Unsupervised Representation Learning
Zhongqi Yue, Jiankun Wang, Qianru Sun +3
Representation learning is all about discovering the hidden modular attributes that generate the data faithfully. We explore the potential of Denoising Diffusion Probabilistic Mode…
Consistent3D: Towards Consistent High-Fidelity Text-to-3D Generation with Deterministic Sampling Prior
Zike Wu, Pan Zhou, Xuanyu Yi +2
Score distillation sampling (SDS) and its variants have greatly boosted the development of text-to-3D generation, but are vulnerable to geometry collapse and poor textures yet. To…
Invariant Feature Regularization for Fair Face Recognition
Jiali Ma, Zhongqi Yue, Kagaya Tomoyuki +4
Fair face recognition is all about learning invariant feature that generalizes to unseen faces in any demographic group. Unfortunately, face datasets inevitably capture the imbalan…