ZPressor: Bottleneck-Aware Compression for Scalable Feed-Forward 3DGS

Weijie Wang, Donny Y. Chen, Zeyu Zhang, Duochao Shi, Akide Liu, Bohan Zhuang

Project Page

• In this work, we analyze feed-forward 3DGS frameworks through the lens of the Information Bottleneck principle and introduce ZPressor, a lightweight architecture-agnostic module that enables efficient compression of multi-view inputs into a compact latent state Z that retains essential scene information while discarding redundancy.

Revisiting Depth Representations for Feed-Forward 3D Gaussian Splatting

Duochao Shi†, Weijie Wang†, Donny Y. Chen, Zeyu Zhang, Jia-Wang Bian, Bohan Zhuang, Chunhua Shen († equal contribution)

Project Page

• We introduce PM-Loss, a novel regularization loss based on a pointmap predicted by a pre-trained transformer. It effectively enforces geometric smoothness, especially around object boundaries. With the improved depth map, our method significantly improves the feed-forward 3DGS across various architectures and scenes, delivering consistently better rendering results.

Advancing Multimodal Reasoning: From Optimized Cold Start to Staged Reinforcement Learning

Shuang Chen†, Yue Guo†, Zhaochen Su, Yafu Li, Yulun Wu, Jiacheng Chen, Jiayu Chen, Weijie Wang, Xiaoye Qu, Yu Cheng († equal contribution)

Project Page

• We introduce ReVisual-R1, achieving a new state-of-the-art among open-source 7B MLLMs on challenging benchmarks including MathVerse, MathVision, WeMath, LogicVista, DynaMath, and challenging AIME2024 and AIME2025.

SciKnowEval: Evaluating Multi-level Scientific Knowledge of Large Language Models

Kehua Feng†, Keyan Ding†, Weijie Wang†, Xiang Zhuang, Zeyuan Wang, Ming Qin, Yu Zhao, Jianhua Yao, Qiang Zhang, Huajun Chen († equal contribution)

Project Page

• This paper introduce the SciKnowEval benchmark, a novel framework that systematically evaluates LLMs across five progressive levels of scientific knowledge. Specifically, we take biology and chemistry as the two instances of SciKnowEval and construct a dataset encompassing 50K multi-level scientific problems and solutions.

WonderTurbo:Generating Interactive 3D World in 0.72 Seconds

Chaojun Ni†, Xiaofeng Wang†, Zheng Zhu†, Weijie Wang†, Haoyun Li, Guosheng Zhao, Jie Li, Wenkang Qin, Guan Huang, Wenjun Mei († equal contribution)

Project Page

• We introduce WonderTurbo, the first real-time interactive 3D scene generation framework capable of generating novel perspectives of 3D scenes within 0.72 seconds. Specifically, WonderTurbo accelerates both geometric and appearance modeling in 3D scene generation.

TransDiff: Diffusion-Based Method for Manipulating Transparent Objects Using a Single RGB-D Image

Haoxiao Wang†, Kaichen Zhou†, Binrui Gu, Zhiyuan Feng, Weijie Wang, Peilin Sun, Yicheng Xiao, Jianhua Zhang, Hao Dong († equal contribution)

Project Page

• We propose a single-view RGB-D-based depth completion framework, TransDiff, that leverages the Denoising Diffusion Probabilistic Models(DDPM) to achieve material-agnostic object grasping in desktop.

Street gaussians for modeling dynamic urban scenes

Yunzhi Yan, Haotong Lin, Chenxu Zhou, Weijie Wang, Haiyang Sun, Kun Zhan, Xianpeng Lang, Xiaowei Zhou, Sida Peng

Project Page

• This paper aims to tackle the problem of modeling dynamic urban street scenes from monocular videos. We introduce Street Gaussians, a new explicit scene representation that tackles some major limitations.