1

MeMo: Meaningful, Modular Controllers via Noise Injection
arXiv
QueST: Self-Supervised Skill Abstractions for Learning Continuous Control
arXiv Website
Avoid Everything: Model-Free Collision Avoidance with Expert-Guided Fine-Tuning
DextrAH-G: Pixels-to-Action Dexterous Arm-Hand Grasping with Geometric Fabrics
arXiv Website
DiffusionSeeder: Seeding Motion Optimization with Diffusion for Rapid Motion Planning
Discovering Robotic Interaction Modes with Discrete Representation Learning
Website
Gentle Manipulation of Tree Branches: A Contact-Aware Policy Learning Approach
Website
Manipulate-Anything: Automating Real-World Robots using Vision-Language Models
NOD-TAMP: Generalizable Long-Horizon Planning with Neural Object Descriptors
arXiv Website
RoboPoint: A Vision-Language Model for Spatial Affordance Prediction for Robotics
Paper Website