Shows / Embodied AI 101
Embodied AI 101
Embodied AI 101 tracks the latest research at the intersection of AI and physical intelligence. Robotics, manipulation, world models, and the path from digital intelligence to embodied agents — each episode breaks down recent papers and advances in the field. We examine the methodology, real-world implications, and path to deployment. Covering robot learning, perception, control, and the fundamental challenge of grounding intelligence in the physical world. New episodes daily.
Episodes
- Embodied AI 101
Humanoid Scooter Control: Does Sim-to-Real Reinforcement Learning Work?
Can reinforcement learning trained in simulation let a humanoid control a real scooter? This episode examines what the reported transfer demonstrates, how the…
- Embodied AI 101
ENPIRE: Can Coding Agents Improve Real-World Robot Manipulation?
Can coding agents improve real-world robot manipulation without a researcher rewriting every experiment? This episode explains what ENPIRE automates, what…
- Embodied AI 101
GAS-Robo: Can Grid Actions Improve LLM-Driven Manipulation?
Can a grid-action interface make language models better robotic manipulation planners, rather than just better selectors of predefined skills? This episode…
- Embodied AI 101
Four Keypoints, One Careful Pour: Connecting Language to Precise Robot Motion
Bridging VLM and KMP: Enabling Fine-Grained Robotic Manipulation via Semantic Keypoints Representation
- Embodied AI 101
PEAfowl: Helping Two Arms Agree on What They See
PEAfowl: Perception-Enhanced Multi-View Vision-Language-Action for Bimanual Manipulation
- Embodied AI 101
MotorMind: Giving a Frozen VLM the Controls
MotorMind leverages a frozen VLM with mid-level prospective actions and asynchronous feedback to control robots zero-shot on manipulation tasks, requiring no…
- Embodied AI 101
MAPF-World: Why a Little Foresight Can Beat a Bigger Policy
MAPF-World: Action World Model for Multi-Agent Path Finding
- Embodied AI 101
Digit Leaves the Lab: The Real Lesson of 500 Demonstrations
An end-to-end policy trained on ~500 teleoperation demonstrations combined with a sim-based whole-body controller achieves 80–90% success on unseen, chaotic…
- Embodied AI 101
VLS: Steering Frozen Robot Policies Without Retraining
VLS steers frozen diffusion and flow-matching robot policies using vision-language models to handle out-of-distribution changes such as novel obstacles and…
- Embodied AI 101
CAST: Making Language Matter to Robot Policies
CAST: Counterfactual Labels Improve Instruction Following in Vision-Language-Action Models In this episode of Embodied AI 101, we explore "CAST: Making…
- Embodied AI 101
When the Command Disappears: What Counts as Robot Intelligence?
Robot Independent Intelligence: When Language Vanishes in Vision-Language-Action Models In this episode of Embodied AI 101, we explore "When the Command…
- Embodied AI 101
Fast Plans Are Not Enough: Does the Robot Actually Use Its Plan?
Introduces a hierarchical VLA architecture that better bridges high-level language planning and low-level robot execution, reducing the gap between what a…
- Embodied AI 101
Atlas's New Hands: Built to Learn, Not Just to Look Human
Atlas is upgraded with 13 DoF dexterous hands featuring tactile sensing, direct drive actuation, and sim-to-real RL training, designed for real tool use and…
- Embodied AI 101
Astra Gets a Body: What Zero-Shot Humanoid Control Actually Transfers
Astra demonstrates zero-shot open-ended pick-and-place on a physical humanoid robot, bridging simulation tooling directly to real-world execution without…
- Embodied AI 101
Physical Coding: Robots That Check Their Work—and Keep the Fixes
A new paper introduces self-evolving coding agents for robotics that represent task state and execution as code, enabling robots to verify, recover from…
- Embodied AI 101
SpatialClaw: Give the VLM a Geometry Notebook
SpatialClaw is an NVIDIA spatial reasoning agent that uses Python-based code generation to perform 3D spatial reasoning, achieving +13.6 average improvement…
- Embodied AI 101
Real-Time EXPO-FT: Slow VLA, Fast Corrections, Better Control
Async RL fine-tuning via EXPO-FT enables π0.5 to handle highly dynamic manipulation tasks such as ball balancing and striking in real time. The approach…
- Embodied AI 101
Aether: From Plausible Futures to Feasible Robot Plans
Aether's unified world model jointly learns environment dynamics and long-term physical state evolution under physical constraints, enabling robots to plan…
- Embodied AI 101
ARLI: Fixing the Missing State in Asynchronous Robot RL
Proposes a framework that restores the Markov property for RL fine-tuning of VLAs despite asynchronous inference delays, enabling effective RL training on…
- Embodied AI 101
Flex-π: Teach Geometry, Choose How Much to Imagine
A 6B-parameter world-action model that jointly predicts 3D pointmaps and DINO features alongside RGB frames, improving demonstration efficiency…
- Embodied AI 101
SkipVLA: Let the Planner Move, Let the VLA Manipulate
SkipVLA proposes a hybrid architecture combining a classical planner with a Vision-Language-Action model for manipulation tasks, achieving 2.5x faster…
- Embodied AI 101
ForeDrive: A World Model Is Only Useful If It Changes the Plan
ForeDrive introduces a planning-relevant latent world model that guides autonomous driving through foresight, enabling the agent to anticipate future states…
- Embodied AI 101
DO AS I DO: Making Human Video Executable
A new algorithm reconstructs and retargets monocular RGB (or synthetically generated) videos to high-DoF robot hands, enabling scalable dexterous manipulation…
- Embodied AI 101
GAM: Ground the Target Before You Learn the Action
GAM is a robot foundation model that conditions action chunk prediction on 3D grounded inputs — including language, 3D point clouds, and bounding boxes —…
- Embodied AI 101
Tune Slowly, Control Quickly: Learning a Better Robot Navigation Stack
Autonomous navigation in complex, unstructured environments poses a significant challenge, with traditional planners lacking adaptability and end-to-end…
- Embodied AI 101
THAW-VLA: World-Model Features Without World-Model Latency
This work distills frozen world-model representations into compact VLAs via a single feature-alignment loss at training time, with the teacher cached once and…
- Embodied AI 101
Joga: Why a Soccer Humanoid Needs to Control Its Gaze
Joga demonstrates agile humanoid soccer on a Unitree G1 using an actuated neck and residual models to close the sim-to-real gap for both perception and…
- Embodied AI 101
AthenaZero: Why Dynamic Manipulation Starts With Lower Inertia
AthenaZero is a bimanual manipulator designed to minimize inertia without compromising control authority. By using quasidirect drive actuation and transmission…
- Embodied AI 101
FROA-Drive and the Hard Part of Targeted Policy Repair
Vision–Language–Action (VLA) models have shown strong potential for end-to-end autonomous driving, yet their post-training commonly relies on expensive…
- Embodied AI 101
Teach the Robot Where to Act—Then Make It Fast
We present a framework for assistive robot manipulation that addresses two fundamental challenges: efficient adaptation of large-scale models for scene…
- Embodied AI 101
HEAR: The Sound Your Robot Missed Between Actions
Humans and animals use sound as a crucial cue for interacting with the physical world, as acoustic events can reveal contact, completion, hidden contents, or…
- Embodied AI 101
VS-Splat: Learning Where 3D Detail Belongs
A new feed-forward Gaussian Splatting method that selectively processes voxels for efficient 3D scene reconstruction, targeting real-time perception stacks for…
- Embodied AI 101
Spatial Search Comes to Quest — Beyond Pretty Gaussian Splats
Adapts a training-free Spatial Search prototype to Meta Quest's spatial data pipeline, enabling natural-language search over Gaussian Splatting and mesh scenes…
- Embodied AI 101
Occamy-1.0: Teaching a 35B Agent to Finish the Job
Introduces a 35B cost-efficient model positioned at the Pareto frontier for collaborative long-horizon agent tasks, achieving performance competitive with…
- Embodied AI 101
Helix 2.5: The House Changed. The Policy Didn't.
Figure's Helix 2.5 humanoid robot enters 30 unseen Bay Area rental homes with no additional training and performs useful whole-body tasks for 4+ hours…
- Embodied AI 101
The Hard Part Was the Stack: PI's Robot Goes to Work
Physical Intelligence's mobile π robot runs fully autonomous for hours in a real production environment stacking boxes at Dandelion Chocolate, exposing…
- Embodied AI 101
ZDTaichu5.0-9B: Better Spatial Reasoning, an Unfinished Edge Story
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…
- Embodied AI 101
Light-Loco-Parkour: Learning the Skill Is Only Half the Problem
Light-Loco-Parkour presents a multi-skill distillation approach for learning perceptive whole-body parkour and locomotion skills deployable on real robots…
- Embodied AI 101
OM-1: Human Skills, Many Bodies
OM-1 is a robot foundation model trained exclusively on human manipulation data (no teleoperation or robot demonstrations) that achieves near human-level…
- Embodied AI 101
Show-Harness Gives VLMs a Robot Keyboard
Uses discrete semantic actions paired with embodiment-specific interpreters to turn any pretrained VLM into a robot controller without a dedicated policy…
- Embodied AI 101
BridgeVLA++: Keep the Geometry, Give the Robot a Memory
Renders point clouds as three orthographic 2D views fed into a pretrained PaliGemma VLM, predicting heatmaps to recover 6-DoF actions with temporal/spatial…
- Embodied AI 101
The Sim-to-Real Gap Inside the Gearbox
Reinforcement learning (RL) has become a powerful tool for quadrupedal locomotion, and a sim-to-real approach is widely adopted to avoid hardware damage during…
- Embodied AI 101
A Stable Grasp Isn't Enough: Giving 6-DoF Grasping a Purpose
Robotic grasping in cluttered scenes is dominated by methods that optimise either stability or a predefined task category, leaving a gap between 'can this…
- Embodied AI 101
HiDream-O1-Embodied: A World Model Must Earn Its Actions
HiDream-O1-Embodied is a unified native architecture that ingests text, images, and video and directly outputs physical actions, positioning itself as a step…
- Embodied AI 101
Axis's Real2Sim2Real Bet: Make the Data Prove Itself
Axis introduced a Real2Sim2Real pipeline that converts real objects and scenes into high-fidelity physics-accurate simulations and validates learned policies…
- Embodied AI 101
A Rubik's Cube, Two Robot Hands, and One Category Error
GPT-6 Astra is demonstrated solving a Rubik's Cube using dexterous robot hands in a real physical setup, showcasing a significant leap in…
- Embodied AI 101
UnifoLM: Predict the Interaction, Not the Whole World
Unitree's UnifoLM is a 6B-parameter world model trained on 2,500 hours of real robot data that predicts only dynamic pixels and optical flow rather than full…
- Embodied AI 101
Stop Making the Video Model Remember the World
A new world model architecture that decouples world-state evolution from rendering: an agent writes executable rules, a persistent engine tracks entities, and…
- Embodied AI 101
Atlas Turns Phone Scans Into Robot Worlds—But Not Yet Into Physics
Atlas is a unified spatial intelligence model that reconstructs real scenes from 2–3 images, generates 1440p video along camera paths, and supports real-to-sim…
- Embodied AI 101
W²G-Net: Carrying Instance Identity from Shiny Scrap to the Gripper
Purpose This study aims to develop a robust vision-guided framework for instance-level recognition and grasp-based classification of metal waste in dense…
- Embodied AI 101
When Avoidance Is Not Enough: T-CARE Gives UAV Swarms a Right-of-Way
Multi-agent UAV navigation in cluttered environments is challenged by deadlock, starvation-like persistent yielding, oscillation, and unsafe congestion…
- Embodied AI 101
Teaching Robots What "Better" Means
A method for preference-based learning applied to dexterous robotic manipulation, enabling robots to learn from human preferences in freeform settings…
- Embodied AI 101
TANGO: Stop Treating a Humanoid Like a Disk on the Floor
TANGO directly predicts 29-DoF joint actions from RGB observations for zero-shot real-world humanoid navigation, enabling coordinated arms, torso, and gait…
- Embodied AI 101
Stop Teaching the VLA Your Camera: Robot-Centric Pointmaps as an Action-Aligned Visual Interface
Vision-language-action (VLA) models predict robot actions from visual observations and language instructions. These actions are defined in the robot's own 3D…
- Embodied AI 101
One Policy, Many Bodies: Qwen-VLA's Bid to Unify Embodied AI
Embodied intelligence is often studied through specialized models for individual tasks such as manipulation or navigation, resulting in fragmented capabilities…
- Embodied AI 101
When the Simulator Lies About Friction: Physics as a Transfer Prior for Touch
Physics-Regularized Learning for Robust Sim-to-Real Tactile Friction Estimation In this episode of Embodied AI 101, we explore "When the Simulator Lies About…
- Embodied AI 101
Seeing Around Corners, Acting at the Edge: REACT as a VLA Safety Co-Pilot
Edge-based multimodal sensor data fusion with Vision-Language-Action (VLA) model for real-time autonomous vehicle accident avoidance In this episode of…
- Embodied AI 101
RoboTok: Turning the Internet Into a Motion Search Engine for Dexterous Robots
RoboTok retrieves human hand-pose trajectories from internet videos to automatically generate scalable robot training data for dexterous manipulation tasks…
- Embodied AI 101
VLAct: The VLA Backbone Is Not Just Plumbing
VLAct proposes a representation-centric continued pre-training approach for Vision-Language-Action models that converts limited robot data into transferable…
- Embodied AI 101
Two Models, One Gradient: Making World-Model RL Work for Contact-Rich Robots
Breaks intractable full world-model RL into a heavy global trajectory model combined with a lightweight latent local dynamics approximator, enabling scalable…