Author

Yongjun Xu

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Sep 2026

SceneScaffold: Active Scene-State Construction for Unified 3D Scene Understanding

Recent 3D large multimodal models (3D-LMMs) rely on a visual bottleneck to compress complex 3D scene evidence into a limited number of visual tokens compatible with large language models (LLMs). Current visual bottlenecks, however, often passively compress heterogeneous 3D evidence into a homogeneous object-centric tok...

Xiang-Qi Li, Li-Bo Huang, Jia-Rui Zhao et al. · 0 citations

Aug 2026

S $^{2}$ Q-VDiT$^+$: Accurate Quantized Video Diffusion Transformer with Multi-Resolution Sampling and Structural Distillation.

Large-scale video diffusion models (V-DMs) have achieved remarkable text-to-video generation quality, yet their massive computational complexity makes deployment costly. Post-Training Quantization (PTQ) offers an appealing route to accelerate inference without retraining, but existing diffusion PTQ methods remain fragi...

Wei-Lun Feng, Chuan-Guang Yang, Haotong Qin et al. · IEEE Transactions on Pattern... · 3 citations