activity
20172026
most citedRole-Wise Data Augmentation for Knowledge Distillation

18 citations · 76 across the 54 of their papers we have counts for

collaborators
Showing cs.CVShow all

68 papers · 1 filter

cs.CV2026

ZipTok3D: High-Fidelity 3D Tokenization with Compact Token Prefixes

Mingda Lin, Weijie Wang, Zeyu Zhang +7

Compact token sequences are essential for efficient 3D generation. However, existing 3D tokenizers typically organize latent representations either over spatial regions or as fixed…

cs.CV2026

Block3D: Efficient Text-to-3D Generation via Block-Wise Diffusion

Bowen Cui, Weijie Wang, Zeyu Zhang +7

While text-to-3D generation has advanced rapidly, achieving high geometric fidelity at low inference cost remains challenging. Existing text-to-3D methods either decode discrete sh…

cs.CV2026

WorldOlympiad: Can Your World Model Survive a Triathlon?

Yuke Zhao, Wangbo Zhao, Weijie Wang +8

We introduce WorldOlympiad, a benchmark for diagnosing video-based world models across physical faithfulness, geometric consistency, and interaction fidelity. While existing benchm…

cs.CV2026

Towards Error-Free Long Video Generation

Shuning Chang, Weihua Chen, Jiasheng Tang +8

Recent advances in video generation have made minute-level synthesis possible; however, generating long videos remains challenging due to error accumulation, attribute drift, and t…

cs.CV2026

Flash-GRPO: Efficient Alignment for Video Diffusion via One-Step Policy Optimization

Xiaoxuan He, Siming Fu, Zeyue Xue +9

Group Relative Policy Optimization has emerged as essential for aligning video diffusion models with human preferences, but faces a critical computational bottleneck: training a 14…

cs.CV2026

Latent Spatial Memory for Video World Models

Weijie Wang, Haoyu Zhao, Yifan Yang +7

Video world models that maintain 3D spatial consistency across generated frames typically rely on explicit point cloud memory constructed in RGB space. This design is both computat…