Skip to content
RobotWorld
← Tags

#Foundation Models (34)

WaterfallPagination
Natura-1: Nature Will 50B-Parameter Foundation Model for Robot Intelligence
0:15

Natura-1: Nature Will 50B-Parameter Foundation Model for Robot Intelligence

@johnkoetsier · 94 views · 2026-10-13
Foundation ModelsDexterous ManipulationHumanoid
Natura-1: A 50B MoE Foundation Model for General Dexterous Manipulation
3:12

Natura-1: A 50B MoE Foundation Model for General Dexterous Manipulation

@naturewill · 162 views · 2026-10-13
Foundation ModelsDexterous ManipulationVLA
WR1.0: Beyond Locomotion, Toward Whole-Body Intelligence
4:22

WR1.0: Beyond Locomotion, Toward Whole-Body Intelligence

@westlake_robot · 209 views · 2026-10-09
HumanoidWhole-Body ControlMobile Manipulation
Delta Intelligence unveils Delta-0: a humanoid foundation model for whole-body loco-manipulation across 69 DoFs
4:34

Delta Intelligence unveils Delta-0: a humanoid foundation model for whole-body loco-manipulation across 69 DoFs

@HumanoidRTech · 1.2k views · 2026-09-28
HumanoidMobile ManipulationWhole-Body Control
Delta-0 Makes a Unitree G1 Play Music, Then Do Household Chores
4:15

Delta-0 Makes a Unitree G1 Play Music, Then Do Household Chores

@CyberRobooo · 633 views · 2026-09-28
HumanoidUnitreeUnitree G1
Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models

Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models

Embodied-R1.5 unifies spatial cognition & reasoning, planning & correction, and embodied pointing & location within a single 8B Qwen3-VL backbone, trained on a 15B-token corpus built by three automated pipelines plus a multi-task balanced RL recipe. A Planner-Grounder-Corrector closed loop lets one model drive the full autonomy stack, completing 10-step long-horizon real-robot tasks like making milk tea with autonomous error recovery; Embodied-R1.5-VLA reaches 92.4% on SimplerEnv Google Robot without large-scale action pretraining, beating pi0.5 by 20+ points. SOTA on 16 of 24 embodied benchmarks; weights, data, code and the EmbodiedEvalKit are fully open-sourced.

Yuan, Yifu, Huang, Yaoting, Yao, Xianze · 577 views · Jun 9, 2026
Embodied AIVLAFoundation ModelsJun 9, 2026
Light-O1: Two Humanoids in One Continuous Household Run
6:12

Light-O1: Two Humanoids in One Continuous Household Run

@HumanoidRTech · 815 views · 2026-09-25
Light-O1Light OriginsWhole-Body Control
Sam Altman on AI Scale, Utilities, and One-Person Labs
26:31

Sam Altman on AI Scale, Utilities, and One-Person Labs

@maarcoofdezz · 676 views · 2026-09-24
OpenAISam AltmanFoundation Models
Gen-HumanEgo: Open-Source Egocentric Human Data for Robot Learning
4:14

Gen-HumanEgo: Open-Source Egocentric Human Data for Robot Learning

@GenrobotAI · 966 views · 2026-09-23
Egocentric VisionRobot LearningOpen Source
FLUX 3 Action: Open-Weights 7B World Action Model
0:05

FLUX 3 Action: Open-Weights 7B World Action Model

@HuggingPapers · 758 views · 2026-09-23
World-action modelsVLARobot Learning
Light-O1: A Humanoid Foundation Model Pretrained on Human Video
2:23

Light-O1: A Humanoid Foundation Model Pretrained on Human Video

@heetezition · 536 views · 2026-09-22
HumanoidFoundation ModelsAction Tokens
Helix 2.5 Recap: Scaling Human Data to Zero-Shot Generalization
0:09

Helix 2.5 Recap: Scaling Human Data to Zero-Shot Generalization

@CyberRobooo · 646 views · 2026-09-18
HumanoidFoundation ModelsData Scaling
Liber-0: Turning Human Experience into Robot Behavior
1:06

Liber-0: Turning Human Experience into Robot Behavior

@liberai_robot · 1.6k views · 2026-09-17
Dexterous ManipulationRobot LearningFoundation Models
Figure Helix 2.5: Zero-Shot Chores in 30 Unseen Homes
1:35

Figure Helix 2.5: Zero-Shot Chores in 30 Unseen Homes

@TheHumanoidHub · 1.4k views · 2026-09-17
HumanoidVLAFoundation Models
X-WBC: A Cross-Embodiment Foundation Model for Humanoid Whole-Body Control
0:30

X-WBC: A Cross-Embodiment Foundation Model for Humanoid Whole-Body Control

@vigram_void · 708 views · 2026-09-16
HumanoidWhole-Body ControlCross-Embodiment
Odyssey-3: A Foundation World Model for Physical Agents
1:37

Odyssey-3: A Foundation World Model for Physical Agents

@odysseyml · 1.2k views · 2026-09-15
World ModelsFoundation ModelsPhysical AI
FTP-1: A Generalist Foundation Tactile Policy
0:51

FTP-1: A Generalist Foundation Tactile Policy

@LeoKharon · 860 views · 2026-09-14
Tactile SensingFoundation ModelsRobot Manipulation
Unitree opens UnifoLM-WLA-1.0
2:49

Unitree opens UnifoLM-WLA-1.0

@UnitreeRobotics · 672 views · 2026-09-10
HumanoidVLAUnitree
Unitree UnifoLM-X2-1.0: Real-Time World-Model-Driven Humanoid Combat
0:38

Unitree UnifoLM-X2-1.0: Real-Time World-Model-Driven Humanoid Combat

@UnitreeRobotics · 647 views · 2026-09-07
UnitreeUnifoLMWorld Models
N0-Foundation: A Tactile-Enabled Foundation for Embodied Manipulation
1:21

N0-Foundation: A Tactile-Enabled Foundation for Embodied Manipulation

@robotsdigest · 840 views · 2026-09-01
NeoDataNeoteAITEAI
LightNav-0: Light Origins Unveils a Generalist Navigation Brain for Robots
0:18

LightNav-0: Light Origins Unveils a Generalist Navigation Brain for Robots

@LightOrigins_ · 602 views · 2026-08-26
LightNav-0Light OriginsRobot navigation
World Action Models (WAMs): Unifying VLA and World Models

World Action Models (WAMs): Unifying VLA and World Models

Introduces World Action Models (WAMs) to unify predictive state modeling with action generation, addressing VLA limitations. Proposes taxonomy and analyzes data ecosystem.

Siyin Wang, Junhao Shi, Zhaoyang Fu · 605 views · May 12, 2026
Embodied AIVLAWorld ModelsMay 12, 2026
G0.5: One Autoregressive Stream for Robot Reasoning and Action

G0.5: One Autoregressive Stream for Robot Reasoning and Action

G0.5 is a pretrained autoregressive VLA in which a single transformer decoder emits reasoning and action tokens under one objective. A cross-embodiment action tokenizer, a native chain-of-thought stream, and a visual memory module make this tractable at foundation-model scale, letting the pretrained VLM capabilities carry over to physical behavior. It surpasses pi-0.5 and GR00T-N1.7 across 7 regimes including real-world R1 robot fine-tuning, BEHAVIOR Challenge, DROID zero-shot transfer, LIBERO, RoboTwin 2.0 and SimplerEnv.

Yicheng Liu, Zibin Dong, Baijun Ye · 707 views · Aug 12, 2026
VLAGalaxeaFoundation ModelsAug 12, 2026
BeingBeyond: Beijing embodied-AI startup building a pure robot brain
2:34

BeingBeyond: Beijing embodied-AI startup building a pure robot brain

@ErenChenAI · 427 views · 2026-08-08
BeingBeyondEmbodied AIFoundation Models

As an Amazon Associate, we earn from qualifying purchases.