activity
20242026
collaborators

11 papers

cs.CV2026

MoWorld: A Flash World Model

Team Moxin, Deyi Ji, Tianrun Chen +37

The future of World Models depends not only on scaling model capability, but also on scaling practicality and inference efficiency. High-frame-rate inference enables responsive per…

cs.CV2026

Mean Flow Distillation: Robust and Stable Distillation for Flow Matching Models

An Zhao, Shengyuan Zhang, Zhongjian Sun +5

Flow Matching models have demonstrated strong performance across a wide range of generative tasks. However, their reliance on ODE-based iterative sampling incurs substantial comput…

cs.CV2026

4DVGGT-D: 4D Visual Geometry Transformer with Improved Dynamic Depth Estimation

Ying Zang, Xuanyi Liu, Yidong Han +9

Reconstructing dynamic 4D scenes from monocular videos is a fundamental yet challenging task. While recent 3D foundation models provide strong geometric priors, their performance s…

cs.CV2026

StreamCacheVGGT: Streaming Visual Geometry Transformers with Robust Scoring and Hybrid Cache Compression

Xuanyi Liu, Chunan Yu, Deyi Ji +6

Reconstructing dense 3D geometry from continuous video streams requires stable inference under a constant memory budget. Existing frameworks primarily rely on a ``pure evict…

cs.CV2026

Robust 4D Visual Geometry Transformer with Uncertainty-Aware Priors

Ying Zang, Yidong Han, Chaotao Ding +8

Reconstructing dynamic 4D scenes is an important yet challenging task. While 3D foundation models like VGGT excel in static settings, they often struggle with dynamic sequences whe…

cs.CV2026

Beyond Binary Preference: Aligning Diffusion Models to Fine-grained Criteria by Decoupling Attributes

Chenye Meng, Zejian Li, Zhongni Liu +9

Post-training alignment of diffusion models relies on simplified signals, such as scalar rewards or binary preferences. This limits alignment with complex human expertise, which is…