Zhongyuan Wang

14

Papers

196

Total Citations

Papers (14)

RoboBrain: A Unified Brain Model for Robotic Manipulation from Abstract to Concrete

Learning Multi-Dimensional Human Preference for Text-to-Image Generation

Code-Style In-Context Learning for Knowledge-Based Question Answering

Lift3D Policy: Lifting 2D Foundation Models for Robust 3D Robotic Manipulation

Cross-Modal Stealth: A Coarse-to-Fine Attack Framework for RGB-T Tracker

FriendsQA: A New Large-Scale Deep Video Understanding Dataset with Fine-grained Topic Categorization for Story Videos

Multi-Shape Matching with Cycle Consistency Basis via Functional Maps

Link-based Contrastive Learning for One-Shot Unsupervised Domain Adaptation

OODML: Whole Slide Image Classification Meets Online Pseudo-Supervision and Dynamic Mutual Learning

Code-as-Monitor: Constraint-aware Visual Programming for Reactive and Proactive Robotic Failure Detection

SpFormer: Spatio-Temporal Modeling for Scanpaths with Transformer

ProJudge: A Multi-Modal Multi-Discipline Benchmark and Instruction-Tuning Dataset for MLLM-based Process Judges

Rethinking the Adversarial Robustness of Multi-Exit Neural Networks in an Attack-Defense Game

Stacking Brick by Brick: Aligned Feature Isolation for Incremental Face Forgery Detection