EmbodiedSWE: Coding Agents for Long Horizon Dexterous Robotics
MemBodied: Recurrent Associative Memory for Vision-Language-Action Models
RoboFollow: Unveiling the Instruction Following Mirage in Embodied Agents
Think Like a World Model, Act Like a VLA: Distilling World-Model Representations into Compact Robot Policies
X-Planner: Event-Structured Task Planning for Embodied Intelligence
Grounded Action Model: 3D Grounding as a Foundation for Robotics
HuRo: Robotizing Human Videos for Scalable VLA Pretraining
GeoAAC: Geometry-Based Adaptive Action Chunking from Denoising Trajectories in VLA Policies
1
rMuscle: Robotic Muscle Memory for Efficient Vision-Language-Action Model Inference
1
TANGO: Humanoid Navigation in Cluttered Environments with a Whole-Body Vision-Language-Action Model
1
ShieldVLA: Feasibility-Aware Safety Alignment for Vision-Language-Action Models
SimpleMemVLA: A Simple but Effective Native-Video Memory for Vision-Language-Action Models
Scaling Automatic Research Agents via World Models
1