Wei Liang

19

Papers

150

Total Citations

Papers (19)

Move as You Say Interact as You Can: Language-guided Human Motion Generation with Scene Affordance

Language-driven All-in-one Adverse Weather Removal

Move to Understand a 3D Scene: Bridging Visual Grounding and Exploration for Efficient and Versatile Embodied Navigation

FloNa: Floor Plan Guided Embodied Visual Navigation

Prompt-guided Precise Audio Editing with Diffusion Models

Structured Scene Memory for Vision-Language Navigation

Counterfactual Cycle-Consistent Learning for Instruction Following and Generation in Vision-Language Navigation

Discovering the Real Association: Multimodal Causal Reasoning in Video Question Answering

Diffusion-Based Generation, Optimization, and Planning in 3D Scenes

Transferring Objects: Joint Inference of Container and Human Pose

DREAMWALKER: Mental Planning for Continuous Vision-Language Navigation

Active Visual Information Gathering for Vision-Language Navigation

METASCENES: Towards Automated Replica Creation for Real-world 3D Scans

LiteAT: A Data-Lightweight and User-Adaptive VR Telepresence System for Remote Education

From Notation to Gesture: Virtual Conductor Gesture Generation in VR via Structured Score Semantics

HUMANISE: Language-conditioned Human Motion Generation in 3D Scenes

Towards Versatile Embodied Navigation

Active Reasoning in an Open-World Environment

Interactive Visual Reasoning under Uncertainty