Guanqi Zhan

Physis-Lang: Self-Evolving Language as a Physical Representation for Video World Model

Liming Lu†, Xianzheng Ma†, Wenkun He†, Guanqi Zhan†*, Yilin Zhao, Junyu Chen, Mengyao Xu, Jiaojiao Fan, Wenhang Ge, Yuchao Gu, Yunze Liu, Boyi Li, Zhen Dong, Victor Prisacariu, Ming-Yu Liu, Song Han, Han Cai*

† Equal contribution · * Corresponding author

Improving the physics of generated videos through self-evolving language. A shared physical representation connects data curation, training, and generation; PhysCapBench measures caption quality and guides iterative refinement.

EGM: Efficient Visual Grounding Language Models

Guanqi Zhan*, Changye Li*, Zhijian Liu, Yao Lu, Yi Wu, Song Han, Ligeng Zhu

Efficient spatial reasoning with small vision-language models. Curated reasoning data, supervised fine-tuning, and reinforcement learning improve visual and amodal grounding.

Inferring Dynamic Physical Properties from Video Foundation Models

Guanqi Zhan*, Xianzheng Ma*, Weidi Xie, Andrew Zisserman

Do video foundation models learn the physics behind motion? Probing generative and self-supervised representations for elasticity, viscosity, and friction, with PhysVid evaluating transfer from simulated to real-world videos.

Grounded 3D-Aware Spatial Vision-Language Modeling

An-Chieh Cheng, Yang Fu, Yatai Ji, Ligeng Zhu, Guanqi Zhan, Zhuoyang Zhang, Zhaojing Yang, Song Han, Yao Lu, Pavlo Molchanov, Vidya Nariyambut Murali, Jan Kautz, Xiaolong Wang, Hongxu Yin, Sifei Liu

Connecting visual evidence to metric 3D space. Grounded visual chain-of-thought and monocular 3D grounding help vision-language models reason about object locations, distances, and spatial relationships.

TARGO and TARGO-Net: Benchmarking Target-driven Object Grasping under Occlusions

Yan Xia*, Ran Ding*, Ziyuan Qin*, Guanqi Zhan, Kaichen Zhou, Long Yang, Hao Dong, Daniel Cremers

Grasping a chosen object in a partially observed world. An occlusion-aware benchmark and a target–scene model combine shape completion with clutter context for robust target-driven robotic grasping.

ELIP: Enhanced Visual-Language Foundation Models for Image Retrieval

Guanqi Zhan*, Yuanpei Liu*, Kai Han, Weidi Xie, Andrew Zisserman

Adapting frozen vision-language foundation models efficiently. Text-conditioned visual prompts, hard-sample mining, and curated training data align visual representations with language queries and improve retrieval generalization.

A General Protocol to Probe Large Vision Models for 3D Physical Understanding

Guanqi Zhan, Chuanxia Zheng, Weidi Xie, Andrew Zisserman

What physical knowledge emerges from large-scale pretraining? A common protocol probes generative and discriminative models for geometry, materials, support, lighting, occlusion, and depth, connecting learned representations to 3D physical understanding.

Amodal Ground Truth and Completion in the Wild

Guanqi Zhan, Chuanxia Zheng, Weidi Xie, Andrew Zisserman

Inferring complete objects beyond what is visible. Pretrained Stable Diffusion features support amodal segmentation, while a 3D-driven data pipeline creates real-image ground truth for evaluating completion with MP3D-Amodal.

InstructNav: Zero-shot System for Generic Instruction Navigation in Unexplored Environment

Yuxing Long*, Wenzhe Cai*, Hongcheng Wang, Guanqi Zhan, Hao Dong

From language and visual observations to embodied decisions. Dynamic Chain-of-Navigation and multi-sourced value maps guide robots through unexplored environments under diverse instructions, without navigation-specific training.

Broadcasting Support Relations Recursively from Local Dynamics for Object Retrieval in Clutters

Yitong Li*, Ruihai Wu*, Haoran Lu, Chuanruo Ning, Yan Shen, Guanqi Zhan, Hao Dong

Reasoning about physical dependencies before acting. Local dynamics propagate through a support graph to infer which objects support others and plan step-by-step object retrieval in cluttered real-world scenes.

Learning Environment-Aware Affordance for 3D Articulated Object Manipulation under Occlusions

Ruihai Wu*, Kai Cheng*, Yan Shen, Chuanruo Ning, Guanqi Zhan, Hao Dong

Learning where a robot can act under occlusion. Environment-aware affordances incorporate surrounding objects and robot constraints, using contrastive learning to connect 3D observations with feasible articulated-object manipulation.

Score-PA: Score-based 3D Part Assembly

Junfeng Cheng, Mingdong Wu, Ruiyuan Zhang, Guanqi Zhan, Chao Wu, Hao Dong

Generating coherent 3D structures from unassembled parts. Score-based modeling captures diverse plausible assemblies, with a fast predictor–corrector sampler for efficient generation of part configurations.

A Tri-Layer Plugin to Improve Occluded Detection

Guanqi Zhan, Weidi Xie, Andrew Zisserman

Understanding the scene structure behind occlusion. Joint reasoning over an object, its occluder, and its occludee improves detection and segmentation of partially hidden objects.

Generative 3D Part Assembly via Dynamic Graph Learning

Jialei Huang*, Guanqi Zhan*, Qingnan Fan, Kaichun Mo, Lin Shao, Baoquan Chen, Leonidas Guibas, Hao Dong

From a set of parts to a coherent 3D object. Dynamic graph reasoning learns relationships between parts and iteratively refines their poses, generating plausible assemblies without semantic part labels.

DLGAN: Disentangling Label-Specific Fine-Grained Features for Image Manipulation

Guanqi Zhan*, Yihao Zhao*, Bingchan Zhao, Haoqi Yuan, Baoquan Chen, Hao Dong

Controllable generation through disentangled representations. Separating label-specific and label-independent features enables discrete attributes and reference images to guide fine-grained manipulation and cross-domain interpolation.