activity
20242026
collaborators

18 papers

cs.CV2026

Chat-Scene++: Exploiting Context-Rich Object Identification for 3D LLM

Haifeng Huang, Yilun Chen, Zehan Wang +2

Recent advancements in multi-modal large language models (MLLMs) have shown strong potential for 3D scene understanding. However, existing methods struggle with fine-grained object…

cs.CV2026

ImVideoEdit: Image-learning Video Editing via 2D Spatial Difference Attention Blocks

Jiayang Xu, Fan Zhuo, Majun Zhang +6

Current video editing models often rely on expensive paired video data, which limits their practical scalability. In essence, most video editing tasks can be formulated as a decoup…

cs.CV2026

Orient Anything V2: Unifying Orientation and Rotation Understanding

Zehan Wang, Ziang Zhang, Jiayang Xu +5

This work presents Orient Anything V2, an enhanced foundation model for unified understanding of object 3D orientation and rotation from single or paired images. Building upon Orie…

cs.CV2025

DSI-Bench: A Benchmark for Dynamic Spatial Intelligence

Ziang Zhang, Zehan Wang, Guanghao Zhang +5

Reasoning about dynamic spatial relationships is essential, as both observers and objects often move simultaneously. Although vision-language models (VLMs) and visual expertise mod…

cs.LG2025

APO: Enhancing Reasoning Ability of MLLMs via Asymmetric Policy Optimization

Minjie Hong, Zirun Guo, Yan Xia +4

Multimodal Large Language Models (MLLMs) are powerful at integrating diverse data, but they often struggle with complex reasoning. While Reinforcement learning (RL) can boost reaso…

cs.CV2025

GenSpace: Benchmarking Spatially-Aware Image Generation

Zehan Wang, Jiayang Xu, Ziang Zhang +4

Humans can intuitively compose and arrange scenes in the 3D space for photography. However, can advanced AI image generators plan scenes with similar 3D spatial awareness when crea…