10 papers
Learning How the World Evolves: Extrapolative Video World Models via Latent Dynamics Reasoning
Haodong Li, Shaoteng Liu, Tianyu Wang +7
The world evolves following its dynamics, i.e., its laws of motion. However, leading video diffusion models largely fit the pixels without modeling how the pixels transit over time…
-Scene: Physically Grounded Image-to-3D Scene Reconstruction
Haodong Li, Lulu Shao, Haolin Lu +4
Reconstructing compositional 3D scenes from a single image is a fundamental challenge in 3D world modeling. Recent methods can recover high-fidelity, complete 3D objects and predic…
Lotus-2: Advancing Geometric Dense Prediction with Powerful Image Generative Model
Jing He, Haodong Li, Mingzhi Sheng +1
Recovering pixel-wise geometric properties from a single image is fundamentally ill-posed due to appearance ambiguity and non-injective mappings between 2D observations and 3D stru…
Rolling Sink: Bridging Limited-Horizon Training and Open-Ended Testing in Autoregressive Video Diffusion
Haodong Li, Shaoteng Liu, Zhe Lin +1
Recently, autoregressive (AR) video diffusion models have achieved remarkable performance. However, due to their limited training durations, a train-test gap emerges when testing a…
MPF-Net: Exposing High-Fidelity AI-Generated Video Forgeries via Hierarchical Manifold Deviation and Micro-Temporal Fluctuations
Xinan He, Kaiqing Lin, Yue Zhou +8
With the rapid advancement of video generation models such as Veo and Wan, the visual quality of synthetic content has reached a level where macro-level semantic errors and tempora…
TraceTrans: Translation and Spatial Tracing for Surgical Prediction
Xiyu Luo, Haodong Li, Xinxing Cheng +4
Image-to-image translation models have achieved notable success in converting images across visual domains and are increasingly used for medical tasks such as predicting post-opera…