8 papers
Sub-JEPA: Subspace Gaussian Regularization for Stable End-to-End World Models
Kai Zhao, Dongliang Nie, Yuchen Lin +4
Joint-Embedding Predictive Architectures (JEPAs) provide a simpleframework for learning world models by predicting future latent representations.However, JEPA training is subject t…
Diff4Splat: Controllable 4D Scene Generation with Latent Dynamic Reconstruction Models
Panwang Pan, Chenguo Lin, Jingjing Zhao +8
We introduce Diff4Splat, a feed-forward method that synthesizes controllable and explicit 4D scenes from a single image. Our approach unifies the generative priors of video diffusi…
Learning to Select Visual In-Context Demonstrations
Eugene Lee, Yu-Chi Lin, Jiajie Diao
Multimodal Large Language Models (MLLMs) adapt to visual tasks via in-context learning (ICL), which relies heavily on demonstration quality. The dominant demonstration selection st…
MoVieS: Motion-Aware 4D Dynamic View Synthesis in One Second
Chenguo Lin, Yuchen Lin, Panwang Pan +5
We present MoVieS, a Motion-aware View Synthesis model that reconstructs 4D dynamic scenes from monocular videos in one second. It represents dynamic 3D scenes with pixel-aligned G…
ID-Crafter: VLM-Grounded Online RL for Compositional Multi-Subject Video Generation
Panwang Pan, Jingjing Zhao, Yuchen Lin +5
Significant progress has been achieved in high-fidelity video synthesis, yet current paradigms often fall short in effectively integrating identity information from multiple subjec…
InstructLayout: Instruction-Driven 2D and 3D Layout Synthesis with Semantic Graph Prior
Chenguo Lin, Yuchen Lin, Panwang Pan +2
Comprehending natural language instructions is a charming property for both 2D and 3D layout synthesis systems. Existing methods implicitly model object joint distributions and exp…