HeyJaredEmbodied AI 101
Stay in the loop on research in AI and physical intelligence.
- Indexed episodes, last 90 days
- 184
- Latest publication
- Sep 16, 2026
- Audience
- Checking…
- Earliest in this view
- Jul 5, 2026
Latest episodes
The Hard Part Was the Stack: PI's Robot Goes to Work (opens the original)
Read excerpt
Physical Intelligence's mobile π robot runs fully autonomous for hours in a real production environment stacking boxes at Dandelion Chocolate, exposing generalization and reliability gaps between lab demos and production utility. Represents a significant milestone in deploying robot foundation models in unstructured real-world settings.
ZDTaichu5.0-9B: Better Spatial Reasoning, an Unfinished Edge Story (opens the original)
Read excerpt
ZDTaichu5.0-9B is a 9B edge-deployable multimodal model built on a Qwen3.5 backbone with C-RADIOv4 vision encoder that leads open sub-10B VLMs on spatial-reasoning benchmarks including ViewSpatial and MMSI-Bench, while supporting embodied AI and tool-use agent tasks. Its strong spatial reasoning performance at edge scale makes it particularly relevant for on-device robot perception.
Light-Loco-Parkour: Learning the Skill Is Only Half the Problem (opens the original)
Read excerpt
Light-Loco-Parkour presents a multi-skill distillation approach for learning perceptive whole-body parkour and locomotion skills deployable on real robots, enabling versatile agile movement across diverse terrains. The method advances embodied locomotion by combining perception and whole-body control into a unified distilled policy.
OM-1: Human Skills, Many Bodies (opens the original)
Read excerpt
OM-1 is a robot foundation model trained exclusively on human manipulation data (no teleoperation or robot demonstrations) that achieves near human-level dexterity and zero-shot generalization across tabletop arms, industrial arms, and humanoids, including multi-robot collaboration. Its ability to transfer from human video data alone to diverse robot morphologies marks a notable step toward scalable robot learning.
Show-Harness Gives VLMs a Robot Keyboard (opens the original)
Read excerpt
Uses discrete semantic actions paired with embodiment-specific interpreters to turn any pretrained VLM into a robot controller without a dedicated policy network or additional pretraining. Demonstrates strong zero-shot generalization across diverse tasks and environments.
Publishing over time
Last 90 days. Choose a month to open its work.
Recurring subjects
Named in the text we hold. One piece can cover several.
Audience
No verified audience measurement yet.
About this data
Counts cover the work we have indexed. Tone needs enough text and a confident classification. Excerpts and episode notes are not full articles or transcripts.
Identity or attribution wrong? Suggest a correction.