Skip to content
RobotWorld
← Back to Videos

GAM: 3D Grounding as a Robot Foundation

Loading video
Loading video

GAM uses pretrained 3D grounding to turn language, point, and box prompts into object-centric representations, improving manipulation robustness when scenes and targets move.

GAM3D GroundingRobot foundation modelsVLAManipulationRoboticsEmbodied AI
Category: arm
Author: @DJiafei
Date: 2026-09-22T00:00:00
Duration: 40.0s
Source: https://x.com/DJiafei/status/2102403075529146383
Reference: https://arxiv.org/abs/2609.23863

Related Videos

AlphaNIST: Chaining Ten Robotic Assemblies from Sparse Rewards
0:10

AlphaNIST: Chaining Ten Robotic Assemblies from Sparse Rewards

@mateoguaman · 113 views · 2026-10-13
AlphaNISTReinforcement LearningRobotic Assembly
Flex-pi: A Multi-Stream World-Action Model with Compute Flexibility
0:43

Flex-pi: A Multi-Stream World-Action Model with Compute Flexibility

@LeoKharon · 881 views · 2026-09-08
VLAWorld ModelsRobot Manipulation
NVIDIA Cosmos 3 Edge keeps robot policies onboard and fast
0:28

NVIDIA Cosmos 3 Edge keeps robot policies onboard and fast

@NVIDIARobotics · 796 views · 2026-09-02
Jetson AGX ThorThor T5000NVIDIA Cosmos 3 Edge
ACCRUE: Continual Off-Policy RL for Robot Foundation Models
1:00

ACCRUE: Continual Off-Policy RL for Robot Foundation Models

@cykim1006 · 34 views · 2026-10-14
Reinforcement LearningContinual learningRobot foundation models
AlphaNIST: Binary Reward Plus Control Cost Hits 98.2% Sim Success
1:33

AlphaNIST: Binary Reward Plus Control Cost Hits 98.2% Sim Success

@octi_zhang · 94 views · 2026-10-13
Robotic ArmManipulationReinforcement Learning
AlphaNIST: One Policy From Scratch Solves All 20 NIST Assembly Tasks
0:07

AlphaNIST: One Policy From Scratch Solves All 20 NIST Assembly Tasks

@patrickhyin · 53 views · 2026-10-13
Robotic ArmManipulationReinforcement Learning

As an Amazon Associate, we earn from qualifying purchases.