Manipulation

• Datasets: InternData-A1, InternData-M1, RoboInter
• Models: InternVLA-A1, InternVLA-M1, X-VLA, VLAC, Seer
• Algorithms: RoboSplat, Robo3R, UltraDexGrasp, DexImit
• Benchmarks: GenManip

Navigation

• Datasets: InternData-N1
• Models: InternVLA-N1, StreamVLN, NavDP, LoGoPlanner
• Benchmarks: VLN-PE, VL-LN Bench

Perception

• Datasets: EmbodiedScan/MMScan
• Models: 🏆PointLLM (Best Paper Candidate at ECCV 2024), LLaVA-3D
• Benchmarks: MMSI-Bench, MMSI-Video-Bench, OST-Bench

Humanoid

• Datasets: MotionMillion
• WBC Controllers: HIMLoco, 🏆HoST (Best Systems Paper Finalist at RSS 2025), HugWBC, XHugWBC, AdaMimic
• Perceptive Controllers: Perceptive Internal Model, BeamDojo, Gallant, Humanoid Goalkeeper
• HSI Controllers: UniHSI, TokenHSI, PhysHSI
• Behavior Foundation Models: UniTracker, BFM, HumanX
• TeleOp System: HOMIE

AIGC

• Datasets: OmniWorld, InternScenes
• Models: Aether, Pi3, AnySplat, PLANNING
• Text2Scenes: MeshCoder, MesaTask