7 papers
Adaptive Look, Flexible Thought: Learning How and How Long to Think in Multimodal Reasoning
Quanlin Chen, Xiuwei Chen, Kun Xiang +5
The introduction of long chain-of-thought (CoT) reasoning and external tools has substantially improved the performance of multimodal large language models (MLLMs) on general and r…
VR-JEPA: Learning Contrastive-State Latent Guidance for Generation-based Video Reasoning
Zehua Ma, Kun Xiang, Yunshuang Nie +9
Reasoning through video generation offers a promising path toward visual intelligence by modeling latent visual states and their dynamics. However, current video generation models…
Beyond the Eye: Efficient Multimodal Reasoning via Self-Regulated Implicit Visual Tools
Xiuwei Chen, Quanlin Chen, Wentao Hu +8
Recent multimodal large language models (MLLMs) have made remarkable progress on fine-grained perception tasks under the "Thinking with Images" (TwI) paradigm by iteratively perfor…
AnyCrowd: Instance-Isolated Identity-Pose Binding for Arbitrary Multi-Character Animation
Zhenyu Xie, Ji Xia, Michael Kampffmeyer +9
Controllable character animation has advanced rapidly in recent years, yet multi-character animation remains underexplored. As the number of characters grows, multi-character refer…
SKeDA: A Generative Watermarking Framework for Text-to-video Diffusion Models
Yang Yang, Xinze Zou, Zehua Ma +2
The rise of text-to-video generation models has raised growing concerns over content authenticity, copyright protection, and malicious misuse. Watermarking serves as an effective m…
ERGO: Excess-Risk-Guided Optimization for High-Fidelity Monocular 3D Gaussian Splatting
Zehua Ma, Hanhui Li, Zhenyu Xie +4
Generating 3D content from a single image remains a fundamentally challenging and ill-posed problem due to the inherent absence of geometric and textural information in occluded re…
DreamVTON: Customizing 3D Virtual Try-on with Personalized Diffusion Models
Zhenyu Xie, Haoye Dong, Yufei Gao +2
Image-based 3D Virtual Try-ON (VTON) aims to sculpt the 3D human according to person and clothes images, which is data-efficient (i.e., getting rid of expensive 3D data) but challe…