181 published models
All models, A–Z.
A complete server-rendered directory of the current public Catalog. Use the main models page when you need search, filters, and comparisons.
A
6 recordsABot-M0
AMAP CV Lab · 2026
Official model catalog record.
ABot-M0.5
AMAP CV Lab · 2026
Official model catalog record.
ACE-Brain-0.5
ACE-Robotics · 2026
Official model catalog record.
ACT
ALOHA / LeRobot ecosystem · 2023-04-23
Action Chunking with Transformers predicts short action sequences for efficient imitation learning in manipulation tasks.
Act Aloha Sim Insertion Human
lerobot · 2025-01-29
Action Chunking Transformer Policy (as per Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware) trained for the AlohaInsertion environment from gym-aloha.
Act Aloha Sim Transfer Cube Human
lerobot · 2024-05-05
Action Chunking Transformer Policy (as per Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware) trained for the AlohaTransferCube environment from gym-aloha.
B
5 recordsBeing-H0
PKU · 2025
Official model catalog record.
Being-H0.5
BeingBeyond · 2026
Official model catalog record.
Being-H0.5 Base
lerobot · 2026-07-28
This is a deterministic LeRobot-format conversion of BeingBeyond/Being-H05-2B. It contains the policy configuration, serialized preprocessor and postprocessor pipelines, tokenizer, conversion report, and safetensors weights.
Being-H0.5 RoboCasa
lerobot · 2026-07-28
This is a deterministic LeRobot-format conversion of BeingBeyond/Being-H05-2B_robocasa. It contains the policy configuration, serialized preprocessor and postprocessor pipelines, tokenizer, conversion report, and safetensors weights.
Being-H0.7
BeingBeyond · 2026
Official model catalog record.
C
2 recordsD
8 recordsDiffusion Policy
Columbia / Toyota Research Institute / collaborators · 2023-03-07
Visuomotor policy approach that represents robot behavior as a conditional denoising diffusion process.
Diffusion Pusht
lerobot · 2024-05-05
Diffusion Policy (as per Diffusion Policy: Visuomotor Policy Learning via Action Diffusion) trained for the PushT environment from gym-pusht.
Diffusion Pusht Keypoints
lerobot · 2024-07-05
Diffusion Policy (as per Diffusion Policy: Visuomotor Policy Learning via Action Diffusion) trained for the PushT environment from gym-pusht with keypoint-only observations.
DM0
Dexmal · 2026
Dexbotic: Open-Source Vision-Language-Action Toolbox
DreamVLA
SJTU · 2025
Official model catalog record.
DreamZero
NVIDIA · 2026
Official model catalog record.
DreamZero / World Action Models
Research · 2026
World-action model framing where future visual states and actions are predicted in an aligned policy model.
Dyna-2
Dyna Robotics · 2026-08-10
Dyna-2 is Dyna Robotics' world-action model, pre-trained on more than one million hours of egocentric human video and evaluated on held-out human and robot data.
E
8 recordsEgoScale
NVIDIA · 2026
Official model catalog record.
EgoVLA
UC San Diego · 2025
Official model catalog record.
EO-1
IPEC / EO-Robotics · 2025-08-28
A unified embodied model using interleaved vision-text-action pretraining for perception, reasoning, planning, and continuous robot control.
EO-1-3B
IPEC-COMMUNITY · 2025-08-28
Official model catalog record.
Eo1 Base
lerobot · 2026-08-05
This is a lossless key-layout conversion of IPEC-COMMUNITY/EO-1-3B at revision fe0a015d9349bdf886d898809213b3574eedf1f9 for LeRobot's native eo1 policy implementation.
Eo1 Qwen2 5 Vl
IPEC-COMMUNITY · 2025-09-18
A pre-initialized vision-language-action model based on Qwen2.5-VL-3B-Instruct, specifically designed for recent Lerobot PR: https://github.com/huggingface/lerobot/pull/1971
Eo1 Qwen25 Vl Bridge
IPEC-COMMUNITY · 2025-12-02
We introduce EO-1 model, an open-source unified embodied foundation model comprising 3B parameters, trained on the carefully curated interleaved embodied dataset EO-Data1.5M, Web Multimodal Data, and Robot Control Data (AgiBotWorld, Open X-Embodiment, RoboMIND, SO100-Community, etc.). The EO-1 model adopt a single unified decoder-only transformer that…
Eo1 Qwen25 Vl Fractal
IPEC-COMMUNITY · 2025-12-02
We introduce EO-1 model, an open-source unified embodied foundation model comprising 3B parameters, trained on the carefully curated interleaved embodied dataset EO-Data1.5M, Web Multimodal Data, and Robot Control Data (AgiBotWorld, Open X-Embodiment, RoboMIND, SO100-Community, etc.). The EO-1 model adopt a single unified decoder-only transformer that…
F
3 recordsFast Action Tokenizer
lerobot · 2026-02-14
This is the official repo for the FAST action tokenizer.
FastWAM Base
lerobot · 2026-06-18
This policy has been trained and pushed to the Hub using LeRobot.
Folding Latest
lerobot · 2026-04-03
π₀.₅ is a Vision-Language-Action model with open-world generalization, from Physical Intelligence. The LeRobot implementation is adapted from their open source OpenPI repository.
G
17 recordsGalaxea G0
OpenGalaxea · 2025-09-09
A dual-system VLM plus VLA model for planning and fine-grained control on long-horizon mobile-manipulation tasks.
GalaxeaVLA(G0)
Galaxea · 2025
Official model catalog record.
Gemini Robotics
Google DeepMind · 2025-03-25
Embodied reasoning and action model family that brings Gemini capabilities into robotics through vision, language, and physical action.
Gemini Robotics 1.5
Google DeepMind · 2025
An agentic robotics model combining advanced multimodal reasoning with vision-language-action control for multi-step physical tasks.
GEN-1.5
Generalist AI · 2026-08-19
GEN-1.5 is Generalist AI's embodied foundation model for learning robot skills in context from short demonstrations, using video, sensor, language, and proprioceptive inputs to produce action trajectories.
Genie 2
Google DeepMind · 2024
Large-scale foundation world model for generating action-controllable interactive environments from visual prompts.
GigaWorld-Policy
GigaAI · 2026
GigaWorld-Policy: An Efficient Action-Centered World–Action Model
GigaWorld-Policy-0.5
GigaAI · 2026
Official model catalog record.
GO-1
Shanghai AI Lab & AgiBot · 2025
Official model catalog record.
GR-2
ByteDance · 2024
Official model catalog record.
GR-3
ByteDance Seed · 2025
Official model catalog record.
GR00T 1.7
NVIDIA · 2026-02-25
NVIDIA's current open humanoid VLA release within an end-to-end Isaac workflow for teleoperation, training, evaluation, and deployment.
GR00T N1
NVIDIA · 2025-03-18
Open foundation model for generalist humanoid robots, focused on whole-body and manipulation behavior from multimodal robot data.
GR00T N1.5
NVIDIA · 2025
Official model catalog record.
GR00T N1.6
NVIDIA · 2025
NVIDIA Isaac GR00T N1.7 - A Foundation Model for Generalist Robots.
GR00T N1.7
NVIDIA · 2026
Official model catalog record.
GR00T-N1.7-3B
nvidia · 2026-02-25
Official model catalog record.
H
7 recordsH-RDT
THU · 2025
Official model catalog record.
Helix 02
Figure · 2026
A hierarchical whole-body VLA for continuous humanoid locomotion, manipulation, balance, tactile feedback, and long-horizon autonomy.
HumanScale
PKU · 2026
Official model catalog record.
Hy VLA RoboTwin
lerobot · 2026-07-28
Byte-identical tensor conversion of tencent/Hy-Embodied-0.5-VLA-RoboTwin at revision bd7bba6f5934ad62293a2a34f74760c6a3ef2ff8.
Hy VLA Umi
lerobot · 2026-07-28
Byte-identical tensor conversion of tencent/Hy-Embodied-0.5-VLA-UMI at revision 3f53d1f8d2bc587c523cfdc9f1041ceee42c2524.
Hy-Embodied-0.5-VLA
Tencent Robotics X · 2026
From Vision-Language-Action Models to a Real-World Robot Learning Stack
HybridVLA
PKU · 2025
Official model catalog record.
I
4 recordsiFlyBot-VLA
iFLYTEK & LindenBot · 2025
Official model catalog record.
InternVLA-A1
Shanghai AI Lab · 2026
InternVLA-A1: Unifying Understanding, Generation, and Action for Robotic Manipulation
InternVLA-A1.5
Shanghai AI Lab · 2026
Official model catalog record.
InternVLA-M1
Shanghai AI Lab · 2025
Official model catalog record.
J
1 recordK
1 recordL
41 recordsLaST-HD
PKU · 2026
Official model catalog record.
LaST0
PKU · 2026
Official model catalog record.
LDA-1B
PKU · 2026
[RSS 2026] LDA-1B: Scaling Latent Dynamics Action Model via Universal Embodied Data Ingestion
LingBot Depth
Robbyant · 2026-01-25
Masked Depth Modeling for Spatial Perception
LingBot Depth
robbyant · 2026-01-26
LingBot-Depth transforms incomplete and noisy depth sensor data into high-quality, metric-accurate 3D measurements. By jointly aligning RGB appearance and depth geometry in a unified latent space, our model serves as a powerful spatial perception foundation for robot learning and 3D vision applications.
LingBot Depth Postrain Dc Vitl14
robbyant · 2026-01-26
LingBot-Depth-DC is a post-trained variant of LingBot-Depth, specifically optimized for sparse depth completion tasks. This model excels at recovering dense depth maps from highly sparse inputs such as SfM/SLAM point clouds.
LingBot Depth Pretrain Vitl 14
robbyant · 2026-01-26
LingBot-Depth transforms incomplete and noisy depth sensor data into high-quality, metric-accurate 3D measurements. This is the general-purpose pretrained model for depth refinement tasks.
LingBot Depth Pretrain Vitl 14 v0.5
robbyant · 2026-02-14
LingBot-Depth transforms incomplete and noisy depth sensor data into high-quality, metric-accurate 3D measurements. This is the general-purpose pretrained model for depth refinement tasks.
LingBot Map
Robbyant · 2026-04-15
A feed-forward 3D foundation model for reconstructing scenes from streaming data
LingBot VA
Robbyant · 2026-01-29
[RSS 2026] Causal video-action world model for generalist robot control
LingBot VA Base
lerobot · 2026-06-05
This policy has been trained and pushed to the Hub using LeRobot.
LingBot VA LIBERO Long
lerobot · 2026-06-05
This policy has been trained and pushed to the Hub using LeRobot.
LingBot VA Posttrain LIBERO Long
robbyant · 2026-04-24
LingBot-VA is an autoregressive diffusion framework that learns frame prediction and policy execution simultaneously, introduced in the paper Causal World Modeling for Robot Control.
LingBot VA Posttrain RoboTwin
robbyant · 2026-01-29
LingBot-VA is an autoregressive diffusion framework that learns frame prediction and policy execution simultaneously, introduced in the paper Causal World Modeling for Robot Control.
LingBot VA RoboTwin
lerobot · 2026-06-05
This policy has been trained and pushed to the Hub using LeRobot.
LingBot Video Dense 1.3B
robbyant · 2026-07-08
Official model catalog record.
LingBot Vision
Robbyant · 2026-07-06
Self-supervised learning for spatial perception
LingBot Vision Vit Base
robbyant · 2026-07-06
LingBot-Vision is a family of self-supervised Vision Transformer backbones for dense spatial perception. The models are pretrained with masked boundary modeling, a boundary-centric objective that encourages spatially structured patch features while retaining strong semantic representations.
LingBot Vision Vit Giant
robbyant · 2026-07-06
LingBot-Vision is a family of self-supervised Vision Transformer backbones for dense spatial perception. The models are pretrained with masked boundary modeling, a boundary-centric objective that encourages spatially structured patch features while retaining strong semantic representations.
LingBot Vision Vit Large
robbyant · 2026-07-06
LingBot-Vision is a family of self-supervised Vision Transformer backbones for dense spatial perception. The models are pretrained with masked boundary modeling, a boundary-centric objective that encourages spatially structured patch features while retaining strong semantic representations.
LingBot Vision Vit Small
robbyant · 2026-07-06
LingBot-Vision is a family of self-supervised Vision Transformer backbones for dense spatial perception. The models are pretrained with masked boundary modeling, a boundary-centric objective that encourages spatially structured patch features while retaining strong semantic representations.
LingBot VLA
Robbyant · 2026-01-26
A Pragmatic VLA Foundation Model
LingBot VLA 4B
robbyant · 2026-01-26
Official model catalog record.
LingBot VLA 4B Depth
robbyant · 2026-01-26
Official model catalog record.
LingBot VLA 4B Posttrain RoboTwin
robbyant · 2026-03-09
Official model catalog record.
LingBot VLA v2 Base
lerobot · 2026-10-07
Pre-trained base checkpoint, the starting point for fine-tuning on a new robot.
LingBot VLA v2 RoboTwin
lerobot · 2026-10-07
Checkpoint fine-tuned by the authors on RoboTwin 2.0 (checkpoints/globalstep50000).
LingBot World
Robbyant · 2026-01-28
Advancing Open-source World Models
LingBot World Base Act Preview
robbyant · 2026-02-28
We are excited to introduce LingBot-World, an open-sourced world simulator stemming from video generation. Positioned as a top-tier world model, LingBot-World offers the following features. - High-Fidelity & Diverse Environments: It maintains high fidelity and robust dynamics in a broad spectrum of environments, including realism, scientific contexts,…
LingBot World Base Cam
robbyant · 2026-01-26
We are excited to introduce LingBot-World, an open-sourced world simulator stemming from video generation. Positioned as a top-tier world model, LingBot-World offers the following features. - High-Fidelity & Diverse Environments: It maintains high fidelity and robust dynamics in a broad spectrum of environments, including realism, scientific contexts,…
LingBot World Fast
robbyant · 2026-04-01
We are excited to introduce LingBot-World, an open-sourced world simulator stemming from video generation. Positioned as a top-tier world model, LingBot-World offers the following features. - High-Fidelity & Diverse Environments: It maintains high fidelity and robust dynamics in a broad spectrum of environments, including realism, scientific contexts,…
LingBot World Fast Diffusers
robbyant · 2026-05-29
We are excited to introduce LingBot-World, an open-sourced world simulator stemming from video generation. Positioned as a top-tier world model, LingBot-World offers the following features. - High-Fidelity & Diverse Environments: It maintains high fidelity and robust dynamics in a broad spectrum of environments, including realism, scientific contexts,…
LingBot World v2
Robbyant · 2026-07-08
Infinite Worlds with Versatile Interactions
LingBot World v2 1.3B Causal Fast
robbyant · 2026-09-04
We present LingBot-World 2.0 (also known as LingBot-World-Infinity), an advanced iteration of LingBot-World featuring four distinct upgrades. - Unbounded Interaction Horizon: Our model achieves an unbounded interaction horizon while maintaining consistent output quality, benefiting from a carefully crafted causal pretraining paradigm. - Rapid Response Time:…
LingBot World v2 14B Bid
robbyant · 2026-09-04
We present LingBot-World 2.0 (also known as LingBot-World-Infinity), an advanced iteration of LingBot-World featuring four distinct upgrades. - Unbounded Interaction Horizon: Our model achieves an unbounded interaction horizon while maintaining consistent output quality, benefiting from a carefully crafted causal pretraining paradigm. - Rapid Response Time:…
LingBot World v2 14B Causal Fast
robbyant · 2026-07-08
We present LingBot-World 2.0 (also known as LingBot-World-Infinity), an advanced iteration of LingBot-World featuring four distinct upgrades. - Unbounded Interaction Horizon: Our model achieves an unbounded interaction horizon while maintaining consistent output quality, benefiting from a carefully crafted causal pretraining paradigm. - Rapid Response Time:…
LingBot World v2 14B Causal Fast Diffusers
robbyant · 2026-07-08
We present LingBot-World 2.0 (also known as LingBot-World-Infinity), an advanced iteration of LingBot-World featuring four distinct upgrades. - Unbounded Interaction Horizon: Our model achieves an unbounded interaction horizon while maintaining consistent output quality, benefiting from a carefully crafted causal pretraining paradigm. - Rapid Response Time:…
LingBot World v2 14B Causal Pretrain
robbyant · 2026-09-04
We present LingBot-World 2.0 (also known as LingBot-World-Infinity), an advanced iteration of LingBot-World featuring four distinct upgrades. - Unbounded Interaction Horizon: Our model achieves an unbounded interaction horizon while maintaining consistent output quality, benefiting from a carefully crafted causal pretraining paradigm. - Rapid Response Time:…
LingBot-VLA 2.0
Robbyant · 2026-07-07
A whole-body VLA release focused on broader cross-embodiment transfer, mobile manipulation, and predictive dynamics supervision.
LingbotVA 2.0
Ant Group · 2026
Official model catalog record.
Looped World Models
Facemind / research · 2026-06-16
World-model architecture using looped transformer refinement over latent states for iterative environment understanding.
M
6 recordsMETIS
PKU · 2025
Official model catalog record.
MolmoAct
AI2 & UW · 2025
Official Repository for MolmoAct
MolmoAct2
UW & AI2 · 2026
Official Repository for MolmoAct2
MolmoB0T
AI2 · 2026
Official model catalog record.
MotuBrain
Shengshu · 2026
Official model catalog record.
Motus
THU · 2025
Official model catalog record.
N
1 recordO
6 recordsOA-WAM
Research · 2026-05-07
Object-addressable world-action model that decomposes scenes into robot and object slots while jointly predicting future world state and actions.
Octo
Octo Model Team · 2024-05-20
Open-source generalist robot policy pretrained on Open X-Embodiment trajectories and designed for fine-tuning to new robots and tasks.
OM-1
Reward AI · 2026-09-14
OM-1 (Omnibody Model 1) is Reward AI's general-purpose robot policy learned only from human demonstrations captured with the wearable Omnibody Hand, with no teleoperation or on-robot data, and deployed across robot arms and humanoids at human speed.
OpenVLA
openvla · 2024-06-13
OpenVLA: An open-source vision-language-action model for robotic manipulation.
OpenVLA 7B
openvla · 2024-06-10
OpenVLA 7B (openvla-7b) is an open vision-language-action model trained on 970K robot manipulation episodes from the Open X-Embodiment dataset. The model takes language instructions and camera images as input and generates robot actions. It supports controlling multiple robots out-of-the-box, and can be quickly adapted for new robot domains via…
OpenVLA-OFT
OpenVLA collaboration · 2025-02-28
An optimized OpenVLA fine-tuning recipe with continuous action chunks, multi-image input, and faster high-frequency control.
P
2 recordsQ
2 recordsR
10 recordsRDT-1B
Robotics Diffusion Transformer research · 2024-10-10
Diffusion foundation model for bimanual manipulation that uses large-scale robot data to generate action trajectories.
RDT2
THU · 2026
Official model catalog record.
ReconVLA
HKUST · 2025
Official model catalog record.
ResNet-10
lerobot · 2026-04-20
It's done in context of porting HIL-SERL paper code (https://hil-serl.github.io/) to Lerobot (https://github.com/Lerobot/lerobot). The HF doesn't have ResNet-10 model, which could be pretty usefult for robotics tasks because of it's small size. This model is converted from JAX to PyTorch, and the weights are preserved. ## Model Description
RoboCat
Google DeepMind · 2023-06-20
Self-improving generalist robotic agent that collects new demonstrations to improve its own manipulation capabilities.
Robometer-4B
lerobot · 2026-05-21
Robometer is a zero-shot general-purpose robotic reward model built on a fine-tuned Qwen3-VL backbone with progress, preference, and success heads. Given a video and a task description it outputs a per-frame progress signal in [0, 1] and a per-frame success probability — suitable for offline reward labelling and for low-frequency reward signals during RL…
RT-1
Google Robotics · 2022-12-13
Robotics Transformer policy trained on large-scale real-world robot demonstrations for language-conditioned manipulation.
RT-2
Google DeepMind · 2023-07-28
Vision-language-action model that transfers web-scale vision-language knowledge into robotic control.
RT-X
Open X-Embodiment collaboration · 2023-10-13
Cross-embodiment RT model family trained from the Open X-Embodiment mixture to study transfer across robots and tasks.
RynnVLA-001
DAMO · 2025
[ICRA 2026] RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulation
S
16 recordsS1
Skild AI · 2026-08-18
S1 is Skild AI's robotic foundation model for in-context execution from a single video demonstration, including source-reported unseen and long-horizon tasks without post-training.
SayCan
Google Research / Everyday Robots · 2022-04-04
Language-grounded robotics approach that combines language-model planning with affordance scores from robot skills.
SmolVLA
Hugging Face LeRobot · 2025-06-03
Compact open vision-language-action policy designed for practical robot fine-tuning and deployment through the LeRobot ecosystem.
SmolVLA Base
lerobot · 2025-06-01
SmolVLA is a compact, efficient Vision-Language-Action (VLA) model designed for affordable robotics, trainable on a single GPU and deployable on consumer hardware, while matching the performance of much larger VLAs through community-driven data.
SmolVLA LIBERO
lerobot · 2026-03-24
This policy has been trained and pushed to the Hub using LeRobot. See the full documentation at LeRobot Docs.
SmolVLA LIBERO Plus
lerobot · 2026-03-13
This policy has been trained and pushed to the Hub using LeRobot. See the full documentation at LeRobot Docs.
SmolVLA Metaworld
lerobot · 2026-04-08
This policy has been trained and pushed to the Hub using LeRobot. See the full documentation at LeRobot Docs.
SmolVLA RoboCasa
lerobot · 2026-04-16
This policy has been trained and pushed to the Hub using LeRobot. See the full documentation at LeRobot Docs.
SmolVLA Robocerebra
lerobot · 2026-04-16
This policy has been trained and pushed to the Hub using LeRobot. See the full documentation at LeRobot Docs.
SmolVLA RoboMME
lerobot · 2026-04-11
This policy has been trained and pushed to the Hub using LeRobot. See the full documentation at LeRobot Docs.
SmolVLA RoboTwin
lerobot · 2026-04-11
This policy has been trained and pushed to the Hub using LeRobot. See the full documentation at LeRobot Docs.
SmolVLA Vlabench
lerobot · 2026-04-21
This policy has been trained and pushed to the Hub using LeRobot. See the full documentation at LeRobot Docs.
So101 Tabletop Isaac
lerobot · 2026-10-15
A LeRobot EnvHub environment built natively in NVIDIA Isaac Sim 6.2: an SO-101 arm in the turquoise of the LeRobot kits, four painted wooden 3 cm cubes and a green open box on a table in a simple room, simulated by PhysX and rendered with RTX.
So101 Tabletop Mujoco
lerobot · 2026-10-15
A LeRobot EnvHub environment: an SO-101 arm in the turquoise of the LeRobot kits, four painted wooden 3 cm cubes (red, green, blue, yellow) and a green open box on a table in a simple room, simulated with MuJoCo. Each reset places the cubes, the box and the front camera with seeded offsets.
SpatialVLA
Shanghai AI Laboratory / collaborators · 2025-01-27
A spatially enhanced 4B VLA pretrained on 1.1 million real-robot episodes with explicit geometry-aware representations.
starVLA
starVLA · 2025-10-09
StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing
U
5 recordsUniDex
THU · 2026
Official model catalog record.
UniSim
UC Berkeley / research · 2023-10-09
Interactive real-world simulator research that models how visual scenes change under actions and interaction.
UniVLA
HKU · 2025
[RSS 2025] Learning to Act Anywhere with Task-centric Latent Actions
UP-VLA
THU · 2025
Official PyTorch implementation for ICML 2025 paper: UP-VLA.
UWM
University of Washington · 2025
Official model catalog record.
V
6 recordsVideoVLA
XJTU · 2025
Official model catalog record.
VITRA
THU · 2025
Official model catalog record.
VLA-JEPA-LIBERO
lerobot · 2026-05-28
This policy has been trained and pushed to the Hub using LeRobot.
VLA-JEPA-Pretrain
lerobot · 2026-05-28
This policy has been trained and pushed to the Hub using LeRobot.
VLA-JEPA-SimplerEnv
lerobot · 2026-05-28
This policy has been trained and pushed to the Hub using LeRobot.
Vqbet Pusht
lerobot · 2024-07-03
VQ-BeT (as per Behavior Generation with Latent Actions) trained for the PushT environment from gym-pusht.
W
3 recordsWall X
X-Square-Robot · 2025-09-04
Building General-Purpose Robots Based on Embodied Foundation Model
WALL-OSS 0.5
X Square Robot · 2026-05-29
An open 4B VLA pretrained across more than 20 embodiments, with physical-hardware evaluation of pretrained robotic capability.
Wall-WM
X Square Robot · 2026
Building General-Purpose Robots Based on Embodied Foundation Model
X
10 recordsX-VLA
2toinf · 2025-09-25
[ICLR 2026] The offical Implementation of "Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model"
X-VLA AgiBot World
lerobot · 2025-11-19
X-VLA is a Vision-Language-Action foundation model that uses soft prompts to handle cross-embodiment and cross-domain robot control within a unified Transformer architecture.
X-VLA Base
lerobot · 2025-11-19
Official model catalog record.
X-VLA Folding
lerobot · 2025-11-19
X-VLA is a Vision-Language-Action foundation model that uses soft prompts to handle cross-embodiment and cross-domain robot control within a unified Transformer architecture.
X-VLA Google Robot
lerobot · 2025-11-19
X-VLA is a Vision-Language-Action foundation model that uses soft prompts to handle cross-embodiment and cross-domain robot control within a unified Transformer architecture.
X-VLA LIBERO
lerobot · 2025-12-02
X-VLA is a Vision-Language-Action foundation model that uses soft prompts to handle cross-embodiment and cross-domain robot control within a unified Transformer architecture.
X-VLA Widowx
lerobot · 2025-11-19
X-VLA is a Vision-Language-Action foundation model that uses soft prompts to handle cross-embodiment and cross-domain robot control within a unified Transformer architecture.
Xiaomi-Robotics-0
Xiaomi · 2026
Official model catalog record.
Xiaomi-Robotics-1
Xiaomi · 2026
Official model catalog record.
Xiaomi-Robotics-U0
Xiaomi Robotics · 2026
Official model catalog record.
#
11 recordsπ0
Physical Intelligence · 2024
Official model catalog record.
π0 Base
lerobot · 2025-09-09
Official model catalog record.
π0 LIBERO Base
lerobot · 2025-09-09
Official model catalog record.
π0 Old
lerobot · 2025-02-03
This repository contains the model described in π_0: A Vision-Language-Action Flow Model for General Robot Control.
π0-FAST Base
lerobot · 2026-01-09
Official model catalog record.
π0.5
Physical Intelligence · 2025
A VLA model designed for open-world generalization by combining heterogeneous robot data, semantic subtask prediction, and high-level knowledge transfer.
π0.5 Base
lerobot · 2025-09-09
Official model catalog record.
π0.5 LIBERO Base
lerobot · 2025-09-09
Official model catalog record.
π0.5 v2 Base
lerobot · 2026-07-28
Official model catalog record.
π0.5 v2 RoboCasa
lerobot · 2026-07-01
Official model catalog record.
π0.7
Physical Intelligence · 2026
Official model catalog record.