Robot Learning Notes
Technical visual notes for papers and model architectures I want to remember quickly.
Papers from Physical Intelligence
π₀.₇: A Steerable Generalist Robotic Foundation Model with Emergent Capabilities
RL Token: Bootstrapping Online RL with Vision-Language-Action Models
MEM: Multi-Scale Embodied Memory for Vision Language Action Models
FAST: Frequency-space Action Sequence Tokenization
π₀.₅: A Vision-Language-Action Model with Open-World Generalization
π₀: A Vision-Language-Action Flow Model for General Robot Control
Foundation Policies
Others
Transformer Transformer: A Unified Model for Motion-Conditioned Robot Co-design
SAM 3: Segment Anything with Concepts
VLS: Steering Pretrained Robot Policies via Vision-Language Models
Action-to-Action Flow Matching
Robometer: Scaling General-Purpose Robotic Reward Models via Trajectory Comparisons
MolmoMotion: Forecasting Point Trajectories in 3D with Language Instruction
World Models
Hands
Agentic Robotics
ASPIRE: Agentic /Skills Discovery for Robotics
CaP-X: A Framework for Benchmarking and Improving Coding Agents for Robot Manipulation
Code as Policies: Language Model Programs for Embodied Control
ENPIRE: Agentic Robot Policy Self-Improvement in the Real World
FIND: Find Something You Can’t Do
RATs: Playful Agentic Robot Learning
RPG: Reconstruct, Practice, Go Real