← authors · overview

• CAS-ViT: Convolutional Additive Self-attention Vision Transformers for Efficient Mobile Applications
  2024 · 20 citations
• Towards Task-Oriented Flying: Framework, Infrastructure, and Principles
  2025 · 2 citations
• TapSampling: Inference-Time Sampling with a Task-Progress-Understanding Verifier for Robotic Manipulation
  2026
• Small Generalizable Prompt Predictive Models Can Steer Efficient RL Post-Training of Large Reasoning Models
  2026
• Hierarchical and Holistic Open-Vocabulary Functional 3D Scene Graphs for Indoor Spaces
  2026
• Adaptive Neighborhood-Constrained Q Learning for Offline Reinforcement Learning
  2025
• Unsupervised Data Generation for Offline Reinforcement Learning: A Perspective from Model
  2025
• Towards Task-Oriented Flying: Framework, Infrastructure, and Principles
  2025
• Can We Achieve Efficient Diffusion without Self-Attention? Distilling Self-Attention into Convolutions
  2025
• DeepIM: Deep Iterative Matching for 6D Pose Estimation
  2018
• Occlusion-Aware Self-Supervised Monocular 6D Object Pose Estimation
  2022
• Multi-Camera Collaborative Depth Prediction via Consistent Structure Estimation
  2022
• Stimulate the Potential of Robots via Competition
  2024
• RaSim: A Range-aware High-fidelity RGB-D Data Simulation Pipeline for Real-world Applications
  2024