1 citations · 1 across the 10 of their papers we have counts for
11 papers
Your Data Manifold is Secretly a Reward Model: Shell-LCC for Text-to-Video Generation
Shihao Zhang, Yunzhi Li, Yuguang Yan +4
Recent text-to-video (T2V) diffusion models rely heavily on auxiliary reward signals (e.g., via reward models or DPO) to align generated content with human aesthetics and improve r…
MoCapAnything V2: End-to-End Motion Capture for Arbitrary Skeletons
Kehong Gong, Zhengyu Wen, Dao Thien Phong +10
Recent methods for arbitrary-skeleton motion capture from monocular video follow a factorized pipeline, where a Video-to-Pose network predicts joint positions and an analytical inv…
SpriteHand: Real-Time Versatile Hand-Object Interaction with Autoregressive Video Generation
Zisu Li, Hengye Lyu, Jiaxin Shi +4
Modeling and synthesizing complex hand-object interactions remains a significant challenge, even for state-of-the-art physics engines. Conventional simulation-based approaches rely…
Generative Augmented Reality: Paradigms, Technologies, and Future Applications
Chen Liang, Jiawen Zheng, Yufeng Zeng +7
This paper introduces Generative Augmented Reality (GAR) as a next-generation paradigm that reframes augmentation as a process of world re-synthesis rather than world composition b…
Reasoning Physical Video Generation with Diffusion Timestep Tokens via Reinforcement Learning
Wang Lin, Liyu Jia, Wentao Hu +6
Despite recent progress in video generation, producing videos that adhere to physical laws remains a significant challenge. Traditional diffusion-based methods struggle to extrapol…
Generalized Visual Relation Detection with Diffusion Models
Kaifeng Gao, Siqi Chen, Hanwang Zhang +3
Visual relation detection (VRD) aims to identify relationships (or interactions) between object pairs in an image. Although recent VRD models have achieved impressive performance,…
Seeing World Dynamics in a Nutshell
Qiuhong Shen, Xuanyu Yi, Mingbao Lin +3
We consider the problem of efficiently representing casually captured monocular videos in a spatially- and temporally-coherent manner. While existing approaches predominantly rely…
LoRA of Change: Learning to Generate LoRA for the Editing Instruction from A Single Before-After Image Pair
Xue Song, Jiequan Cui, Hanwang Zhang +4
In this paper, we propose the LoRA of Change (LoC) framework for image editing with visual instructions, i.e., before-after image pairs. Compared to the ambiguities, insufficient s…
Ca2-VDM: Efficient Autoregressive Video Diffusion Model with Causal Generation and Cache Sharing
Kaifeng Gao, Jiaxin Shi, Hanwang Zhang +3
With the advance of diffusion models, today's video generation has achieved impressive quality. To extend the generation length and facilitate real-world applications, a majority o…
ViD-GPT: Introducing GPT-style Autoregressive Generation in Video Diffusion Models
Kaifeng Gao, Jiaxin Shi, Hanwang Zhang +2
With the advance of diffusion models, today's video generation has achieved impressive quality. But generating temporal consistent long videos is still challenging. A majority of v…
Non-confusing Generation of Customized Concepts in Diffusion Models
Wang Lin, Jingyuan Chen, Jiaxin Shi +8
We tackle the common challenge of inter-concept visual confusion in compositional concept generation using text-guided diffusion models (TGDMs). It becomes even more pronounced in…