Ziwei Wang

26

Papers

17

Total Citations

Papers (26)

ThinkBot: Embodied Instruction Following with Thought Chain Reasoning

Text-guided Sparse Voxel Pruning for Efficient 3D Visual Grounding

MoManipVLA: Transferring Vision-language-action Models for General Mobile Manipulation

EfficientLLaVA: Generalizable Auto-Pruning for Large Vision-language Models

UniGoal: Towards Universal Zero-shot Goal-oriented Navigation

IGL-Nav: Incremental 3D Gaussian Localization for Image-goal Navigation

AnyBimanual: Transferring Unimanual Policy for General Bimanual Manipulation

GWM: Towards Scalable Gaussian World Models for Robotic Manipulation

Learning Visual Hierarchies in Hyperbolic Space for Image Retrieval

LowRankOcc: Tensor Decomposition and Low-Rank Recovery for Vision-based 3D Semantic Occupancy Prediction

Memory-based Adapters for Online 3D Scene Perception

Towards Accurate Post-training Quantization for Diffusion Models

Learning Deep Binary Descriptor With Multi-Quantization

GraphBit: Bitwise Interaction Mining via Deep Reinforcement Learning

Learning Channel-Wise Interactions for Binary Convolutional Neural Networks

Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration

BiDet: An Efficient Binarized Object Detector

Shapley-NAS: Discovering Operation Contribution for Neural Architecture Search

Binarizing Sparse Convolutional Networks for Efficient Point Cloud Analysis

Instance Similarity Learning for Unsupervised Feature Representation

An Asynchronous Kalman Filter for Hybrid Event Cameras

Generalizable Mixed-Precision Quantization via Attribution Rank Preservation

Deep Hashing with Active Pairwise Supervision

Shap-CAM: Visual Explanations for Convolutional Neural Networks Based on Shapley Value

MP-GUI: Modality Perception with MLLMs for GUI Understanding

MCUFormer: Deploying Vision Tranformers on Microcontrollers with Limited Memory