All Episodes
Embodied AI 101 — 401 episodes · page 3 of 5
SKooP: Symmetric Koopman Predictions for Legged Robot Reinforcement Learning
RobotTT: A Tactile Transformer for Dexterous Manipulation
TAC-LOCO: Unified Whole-Body Control for Contact-Aware Locomotion and Manipulation
TACTIC: Contact-Centric Control for Whole-Arm Manipulation
SIEVE: Structure-Aware Data Selection for Imitation Learning with VLAs
DexMachina: RL for Long-Horizon Bimanual Dexterous Policies
Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation
RoboTTT: Test-Time Training for Visuomotor Policies
HY-Embodied-VLM-1.0: Efficient Physical-World Agents
Learning Unified Force and Position Control for Legged Loco-Manipulation
HapticVLA: Extending Vision-Language-Action Models to Contact-Rich Tasks Without Touch Sensors
AnoleVLA: Lightweight VLA with Deep State Space Models for Mobile Manipulation
ABot-N1: Visual Language Navigation Foundation Model
ABot-AgentOS: A General-Purpose Robotic Agent Operating System
Trust Region Policy Distillation (TOP-D)
HANDOFF: Humanoid Agentic Task-Space Whole-Body Control via Distilled Complementary Teachers
EVA-Client: A Unified Framework for Real-Robot Policy Iteration
UniVR-34B: A Vision-Only Foundation Model for Physical Tasks
CLAP: Converting Vision-Language Models into Vision-Language-Action Models via Language-Prompted Actions
InternVLA-A1.5: Unifying Understanding, Latent Foresight, and Action
MotionWAM: Towards Foundation World Action Models for Real-Time Humanoid Loco-Manipulation
On-Device Diffusion Transformer Policy for Efficient Robot Manipulation
Robotic World Model: Neural Dynamics for Locomotion
LingBot-Vision: Self-Supervised ViT with Masked Boundary Modeling
LaMem-VLA: Latent-Memory-Native VLA Framework
LingBot-VA 2.0: Native Video-Action Foundation Model for Robot Control
GigaWorld-1: Large-Scale World Model for Robot Policy Evaluation
Learning Unified Force and Position Control for Legged Loco-Manipulation
Robix: Unified Vision-Language Model for Robotic Reasoning and Planning
EmbodiedOneVision (EO-1): A Unified Decoder-Only Transformer for General Robot Control
mimic-video: Video-Action Models for Robot Learning
Lowering the Barrier: The GEM Open-Source Arm
RynnWorld-4D: A 4D Embodied World Model for Bimanual Robot Control
RynnWorld-Teleop: Digital Teleoperation via World Model Rendering
VLA-Corrector: Adaptive Action Horizons through Latent Visual Monitoring
Scenes as Objects, Not Primitives: Instance-Structured 3D Tokenization
Current as Touch: Proprioceptive Contact Feedback for Compliant Dexterous Manipulation
DART: One-Shot VLA Policy Adaptation via Weight-Space Arithmetic
Does VLA Even Know the Basics? Act2Answer Benchmark
Contact-Grounded Policy: Dexterous Visuotactile Policy with Generative Contact Grounding
Freeform Preference Learning (FPL) for Robotic Manipulation
Orca: The World is in Your Mind
Qwen-RobotNav: A Scalable Unified Navigation Model for Agentic Robotics
Scaling Robot Skills from Cheap Human Videos
ABC: An Open Behavior Cloning Stack for Bimanual Manipulation
Qwen-RobotManip: Alignment Unlocks Scale for Robotic Manipulation Foundation Models
ASPIRE: Automated Skill Discovery for Robotics
SERF: 4D Latent Mapping for Long-Horizon Mobile Manipulation
ViserDex: Visual Sim-to-Real for Robust Dexterous In-Hand Reorientation
DexSkin: A High-Coverage, Conformable "Electronic Skin" for Robot Fingers
EBench: A Diagnostic Benchmark for Generalist Manipulation Policies
VITRA: A Foundation for Dexterous VLA via Human Video Pretraining
DexWM: A Dexterous Manipulation World Model from Human Videos
PoLAR: Factorizing Extent and Mode in Latent Actions for Robot Policy Learning
Continual Robot Policy Learning via Variational Neural Dynamics
PhysisForcing: Physics-Reinforced World Models for Robotic Manipulation
Translation as a Bridging Action
Play2Perfect: Dexterous Play Pretraining for Precise Assembly
Dexora: Open-Source VLA for High-DoF Bimanual Dexterity
WorldVLA: Towards Autoregressive Action World Model
HumDex: Humanoid Dexterous Manipulation Made Easy
ForceBand: Learning Forceful Manipulation with sEMG
In-Context World Modeling for Robotic Control
WOLF-VLA: Vision-Language-Action for Humanoid Walking
Motion-Focused Latent Action for Cross-Embodiment VLA from Human Videos
ManiFlow: Manipulation via Rectified Flow
RL-100: Toward Highly Reliable Real-World Robot Reinforcement Learning
Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation
Bi-HIL: Bilateral Control-Based Multimodal Hierarchical Imitation Learning for Long-Horizon Contact-Rich Manipulation
From Passive Observer to Active Critic: Reinforcement Learning Elicits Process Reasoning for Robotic Manipulation
ROVE: Unlocking Human Interventions for Humanoid Manipulation via Reinforcement Learning
ConstrainedMimic: Safe Humanoid Robot Motion Tracking
REAL: Robust Extreme Agility via Spatio-Temporal Policy Learning and Physics-Guided Filtering
HiFlow: Tokenization-Free Scale-Wise Autoregressive Policy Learning via Flow Matching
Reactive Diffusion Policy: Slow-Fast Visual-Tactile Learning for Contact-Rich Manipulation
SARM2 + SPIRAL: Multi-Task Reward Models and RL Refinement for Long-Horizon Dexterous Manipulation
Co-VLA: Coordination-Aware Structured Action Modeling for Dual-Arm VLA Systems
ThinkingVLA: Interleaved Vision and Language Reasoning for Robotic Manipulation
Playful Agentic Robot Learning
Learning Unified Force and Position Control for Legged Loco-Manipulation
Robots that Collaborate: Sequential Asymmetric Imitation for Learning Coupled Robot Policies
AstraBrain-WBC 0.5: A Humanoid Robot Cerebellum Foundation Model
SRL: Combining SLIP Model and Reinforcement Learning for Agile Robotic Jumping
DataClaw0: Agentic Tailoring for Raw Multimodal Streams
ACE-Ego-0: Unifying Egocentric Human and Robotic Data for VLA Pretraining
VERA: Video-to-Action World Model Policy
GEN-1: Scaled Dexterous Manipulation Foundation Model
Efficient Hybrid SE(3)-Equivariant Visuomotor Flow Policy via Spherical Harmonics for Robot Manipulation
Cortical Policy: A Dual-Stream View Transformer for Robotic Manipulation
VisualClaw: A Self-Evolving Wearable Vision Agent
Kairos: A Native World Model Stack for Physical AI
DragMesh-2: A Contact-Driven Framework for Dexterous Hand–Object Interaction
Guava: A Universal Harness for Robot Manipulation
Geometric Action Model for Robot Policies
ENPIRE: Physical AutoResearch with a Fleet of 8 Robots
MolmoAct2: An Open Foundation Model for Real-World Robotics
Hy-Embodied-0.5-VLA: A Massive Bimanual Teleoperation Dataset for Vision-Language-Action
Q-Guided Flow: Test-Time Gradient Guidance of Flow Policies
Flow Reversal Steering: Guiding Diffusion-Based Robot Policies with High-Level Reasoning
Test-Time Compute Scaling for Robot Policies (DIRECT)