Skip to content

DemosNAV·01Demos PapersNAV·02Papers BlogNAV·03Blog LLMNAV·04LLM HarnessNAV·05Harness AI CodingNAV·06AI Coding SkillsNAV·07Skills LeaderboardNAV·08Leaderboard ImageNAV·09Image Audio & VideoNAV·10Audio & Video 3DNAV·113D DesignNAV·12Design OfficeNAV·13Office AI GamesNAV·14AI Games Agent StudioNAV·15Agent Studio Gear StoreNAV·16Gear Store Agent ContentNAV·17Agent Content

robot-products,robotvideos,components,crowdfunding,opensource,world-models,industry,investment,physical-ai,applications,sota,discuss,about

[●●●]FETCHING

Editor's picksAll gear →AdAmazon

actuatorSO-101 follower arm kit (12V Feetech STS3215 servos)A common starter arm kit in the SO-100/SO-101 ecosystem — build it, then run the open-source imitation-learning demos.View on Amazon→ai-hardwareNVIDIA Jetson Orin Nano Super Developer KitA small robot brain for VLA and vision models: 67 TOPS at a ~15W envelope, runs ROS 2 and Isaac.View on Amazon→gpuGIGABYTE GeForce RTX 5080 GAMING OC 16GThe 16GB tier for running vision models locally and fine-tuning LoRA adapters — cheaper than hourly cloud for long experiments.View on Amazon→

As an Amazon Associate, we earn from qualifying purchases.

Agientry

AGI intelligence, footprints of progress · © 2026

RobotWorldRobotics and embodied AI

@McQueenFuFollow LinkedInFollowTags About DMCA391 papers73 articles72 open source

← 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.

GAM 3D Grounding Robot foundation models VLA Manipulation Robotics Embodied 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

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

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

@LeoKharon · 846 views · 2026-09-08

VLAWorld ModelsRobot Manipulation

NVIDIA Cosmos 3 Edge keeps robot policies onboard and fast

NVIDIA Cosmos 3 Edge keeps robot policies onboard and fast

@NVIDIARobotics · 764 views · 2026-09-02

Jetson AGX ThorThor T5000NVIDIA Cosmos 3 Edge

LeWAM: An End-to-End JEPA That Controls Real Robots

LeWAM: An End-to-End JEPA That Controls Real Robots

@Minghao__Fu · 97 views · 2026-10-09

World ModelsJEPAManipulation

Four Next-Gen Robot Hands Compared: Atlas, Dex5-S, Torso 3, Wuji Hand 2

Four Next-Gen Robot Hands Compared: Atlas, Dex5-S, Torso 3, Wuji Hand 2

@VaderResearch · 217 views · 2026-10-07

Dexterous HandRobot HandHumanoid

Proxy Policy Steering: Test-Time Robot Policy Adaptation

Proxy Policy Steering: Test-Time Robot Policy Adaptation

@LeoKharon · 547 views · 2026-09-26

Proxy Policy SteeringRobot Policy AdaptationDiffusion policies

Real-Time EXPO-FT: Reliable VLA Fine-Tuning

Real-Time EXPO-FT: Reliable VLA Fine-Tuning

@robotsdigest · 625 views · 2026-09-24

VLARobotic ManipulationReinforcement Learning