Skip to content
  • Categories
  • Recent
  • Tags
  • Popular
  • Users
Menu
  1. Home
  2. AI & Software
  3. Embodied Foundation Models

Embodied Foundation Models

Scheduled Pinned Locked Moved AI & Software
embodiedfoundation modelsrobotics
19 Posts 1 Posters 270 Views 1 Watching
  • Oldest to Newest
  • Newest to Oldest
  • Most Votes
Reply
  • Reply as topic
Log in to reply
This topic has been deleted. Only users with topic management privileges can see it.
  • montezM Offline
    montezM Offline
    montez
    wrote on last edited by montez
    #5

    NVIDIA Cosmos Reason 2

    Hugging Face: https://huggingface.co/nvidia/Cosmos-Reason2-8B, https://huggingface.co/nvidia/Cosmos-Reason2-2B, https://huggingface.co/nvidia/Cosmos-Reason2-32B
    Website: https://build.nvidia.com/nvidia/cosmos-reason2-8b
    Docs: https://huggingface.co/blog/nvidia/nvidia-cosmos-reason-2-brings-advanced-reasoning

    Developer: NVIDIA
    Released: January 2026
    Variants: 2B, 8B, 32B
    Parameters: 8.77B (8B tier)
    Architecture: Qwen3-VL fine-tune post-trained for physical-AI reasoning
    License: NVIDIA Open Model License Agreement
    Modalities: Image/video + text in / spatio-temporal reasoning, trajectory, point, and bounding-box predictions out
    Runs on: NVIDIA GPU
    Formats: safetensors, 4 shards (8B tier)
    On disk: 17.53GB (8B tier)

    1 Reply Last reply
    0
    • montezM Offline
      montezM Offline
      montez
      wrote on last edited by montez
      #6

      Unitree UnifoLM-VLA-0

      Hugging Face: https://huggingface.co/unitreerobotics/Unifolm-VLM-Base, https://huggingface.co/unitreerobotics/Unifolm-VLA-Base, https://huggingface.co/unitreerobotics/Unifolm-VLA-Libero
      GitHub: https://github.com/unitreerobotics/unifolm-vla
      Website: https://unigen-x.github.io/unifolm-vla.github.io

      Developer: Unitree Robotics
      Released: January 2026
      Variants: VLM-Base, VLA-Base, VLA-LIBERO
      Architecture: Qwen2.5-VL-7B backbone with a diffusion-transformer flow-matching action head; continued pretraining fuses 2D/3D spatial understanding with action-chunking prediction and forward/inverse dynamics constraints
      Modalities: Multi-view RGB + robot state + language instruction in / continuous manipulation actions out
      Formats: PyTorch checkpoint
      On disk: VLA-Base 18.98GB

      1 Reply Last reply
      0
      • montezM Offline
        montezM Offline
        montez
        wrote on last edited by montez
        #7

        Alibaba DAMO RynnBrain 1.1

        Hugging Face: https://huggingface.co/Alibaba-DAMO-Academy/RynnBrain1.1-2B, https://huggingface.co/Alibaba-DAMO-Academy/RynnBrain1.1-9B, https://huggingface.co/Alibaba-DAMO-Academy/RynnBrain1.1-122B-A10B
        GitHub: https://github.com/alibaba-damo-academy/RynnBrain
        Technical report: https://arxiv.org/abs/2602.14979

        Developer: Alibaba DAMO Academy
        Released: July 2026
        Variants: 2B, 9B, 122B-A10B
        Parameters: 9.41B (9B checkpoint)
        Architecture: Decoder-only vision-language transformer (dense 2B/9B, sparse-MoE 122B-A10B) on a Qwen3.5 base
        License: Apache License 2.0
        Modalities: Image/video + language in / spatial/3D grounding, contact-point and affordance predictions, task planning out
        Formats: safetensors
        On disk: 18.82GB (9B checkpoint)

        1 Reply Last reply
        0
        • montezM Offline
          montezM Offline
          montez
          wrote last edited by
          #8

          Black Forest Labs FLUX 3 Action

          Hugging Face: https://huggingface.co/black-forest-labs/flux-3-action-base, https://huggingface.co/black-forest-labs/flux-3-action-droid, https://huggingface.co/black-forest-labs/flux-3-action-so101
          GitHub: https://github.com/black-forest-labs/flux-action
          Website: https://bfl.ai/models/flux-3-action
          Docs: https://docs.bfl.ai/flux_3/flux3_action_overview

          Developer: Black Forest Labs
          Released: September 2026
          Variants: Base / DROID / SO-101
          Parameters: 7B
          Architecture: Diffusion-transformer world action model derived from the multimodal FLUX 3 backbone, with joint future-video and action prediction
          License: FLUX Kommunity License v1.0
          Modalities: Text + Multi-view RGB + Robot state in / Video + Action out
          Runs on: NVIDIA GPU (Linux), about 32GB VRAM for BF16 or 24GB with FP8r and text-encoder offload
          Formats: safetensors, LeRobot and FLUX Action inference

          1 Reply Last reply
          0
          • montezM Offline
            montezM Offline
            montez
            wrote last edited by
            #9

            OpenWAM-alpha

            Hugging Face: https://huggingface.co/OpenWAM/OpenWAM-Alpha-Pretrain-Foundation-Model, https://huggingface.co/collections/OpenWAM/openwam-alpha
            GitHub: https://github.com/OpenWAM-Official/OpenWAM
            Website: https://openwam-official.github.io/
            Technical report: https://arxiv.org/abs/2609.07398

            Developer: OpenWAM-Official
            Released: September 2026
            Variants: Pretrain-Foundation-Model / Sim fine-tunes (LIBERO, RoboTwin, RoboCasa365, RoboCasa-GR1, RoboDojo, EBench, VLABench) / Real fine-tunes (Dexterous-Hand-Wuji, RoboDojo-ARX-X5, RoboDojo-Piper, RoboDojo-Piper-X, Single-Arm-Franka)
            Parameters: Video DiT 5B / ActionDiT 1B
            Architecture: Dual-system world-action model: a pretrained Wan2.2-TI2V-5B video DiT and a dedicated ActionDiT coupled through joint self-attention with a mutual attention mask, on a frozen Wan2.2-VAE
            License: Apache-2.0
            Modalities: Multi-view RGB + language instruction + proprioceptive state in / future video + action chunk out (80-D unified action space)
            Runs on: NVIDIA datacenter GPUs, 8 x 80 GB recommended for training (CUDA 12.8); no inference requirement published
            Formats: safetensors
            On disk: Pretrain-Foundation-Model 24.81GB

            1 Reply Last reply
            0
            • montezM Offline
              montezM Offline
              montez
              wrote last edited by
              #10

              OLA Dimensions UniWAM

              Hugging Face: https://huggingface.co/chenpyyy/UniWAM-base, https://huggingface.co/collections/chenpyyy/uniwam
              GitHub: https://github.com/UniWAM/UniWAM
              Website: https://uniwam.github.io
              Technical report: https://arxiv.org/abs/2610.02054

              Developer: OLA Dimensions, HKUST(GZ)
              Released: October 2026
              Variants: UniWAM-base / UniWAM-robotwin-clean / UniWAM-libero / UniWAM-libero-plus
              Parameters: 8B
              Architecture: Mixture-of-Transformers, three experts: a Qwen3-VL-2B-Instruct physical reasoner, a Wan2.2-TI2V-5B world generator, a flow-matching action predictor; joint multimodal attention
              License: Apache-2.0
              Modalities: Camera images + proprioceptive state + language instruction in / physical language + future video + action chunk out
              Runs on: NVIDIA datacenter GPUs, post-training published on 8 x H100; no inference requirement published
              Formats: PyTorch (DeepSpeed checkpoint)
              On disk: UniWAM-base 16.05GB

              1 Reply Last reply
              0
              • montezM Offline
                montezM Offline
                montez
                wrote last edited by
                #11

                InternRobotics InternW0-Delta

                Hugging Face: https://huggingface.co/InternRobotics/InternW0-Delta-Base, https://huggingface.co/InternRobotics/InternW0-Delta-Libero, https://huggingface.co/InternRobotics/InternW0-Delta-RoboTwin, https://huggingface.co/InternRobotics/InternW0-Delta-RoboDojo
                GitHub: https://github.com/InternRobotics/InternW0-Delta
                Website: https://internrobotics.github.io/InternW0-Delta/
                Technical report: https://arxiv.org/abs/2609.31394

                Developer: Shanghai AI Laboratory (InternRobotics)
                Released: September 2026
                Variants: Base / Libero / RoboTwin / RoboDojo
                Architecture: World-action model: a pretrained Wan2.2-TI2V-5B video expert and an ActionDiT action expert coupled through 30 directed Mixture-of-Transformers blocks, with a frozen RynnBrain1.1-2B VLM conditioning the action expert and training-only 4D distillation
                License: MIT
                Modalities: Multi-view RGB + language instruction + proprioceptive state in / action chunk out (canonical 80-D action space)
                Runs on: NVIDIA GPU (Linux, CUDA); no inference requirement published
                Formats: PyTorch (.pt)
                On disk: 12.42GB per checkpoint (Base pretrain.pt)

                1 Reply Last reply
                0
                • montezM Offline
                  montezM Offline
                  montez
                  wrote last edited by
                  #12

                  Alibaba DAMO RynnValue

                  Hugging Face: https://huggingface.co/Alibaba-DAMO-Academy/RynnValue-8B-Quantile, https://huggingface.co/Alibaba-DAMO-Academy/RynnValue-4B-Quantile, https://huggingface.co/Alibaba-DAMO-Academy/RynnValue-8B, https://huggingface.co/Alibaba-DAMO-Academy/RynnValue-4B
                  GitHub: https://github.com/alibaba-damo-academy/RynnValue
                  Website: https://alibaba-damo-academy.github.io/RynnValue.github.io/
                  Technical report: https://arxiv.org/abs/2608.09853

                  Developer: Alibaba DAMO Academy
                  Released: August 2026
                  Variants: RynnValue-4B, RynnValue-8B, RynnValue-4B-Quantile, RynnValue-8B-Quantile
                  Parameters: 5.14B (4B checkpoints), 9.57B (8B checkpoints)
                  Architecture: RynnBrain backbone on the Qwen3-VL architecture; absolute and relative distributional value heads (fixed-bin or 256-bin quantile) plus a language head; predicts remaining time to task completion per frame
                  License: Apache License 2.0
                  Modalities: Image/video + language in / per-frame remaining-time value in seconds, video analysis text out
                  Runs on: Desktop GPU, single GPU with 24GB+ memory for the 8B model in bf16
                  Formats: safetensors
                  On disk: 10.29GB (4B checkpoints), 19.15GB (8B checkpoints)

                  1 Reply Last reply
                  0
                  • montezM Offline
                    montezM Offline
                    montez
                    wrote last edited by
                    #13

                    Alibaba DAMO RynnWorld-Latent

                    Hugging Face: https://huggingface.co/Alibaba-DAMO-Academy/RynnWorld-Latent
                    GitHub: https://github.com/alibaba-damo-academy/RynnWorld-Latent
                    Website: https://alibaba-damo-academy.github.io/RynnWorld-Latent.github.io/

                    Developer: Alibaba DAMO Academy
                    Released: October 2026
                    Parameters: 3.46B
                    Architecture: Full fine-tune of NVIDIA Cosmos3-Edge (Mixture-of-Transformers, Nemotron-2B backbone, SigLIP2 vision tower) into a latent-action-conditioned video world model; rectified-flow video generation on a frozen Wan2.2 VAE; 608-dimension RynnLAM latent actions shared by human and robot video
                    Modalities: First-frame image + Latent action sequence in / Video out
                    Formats: safetensors
                    On disk: 20.75GB safetensors (4 shards, BF16 weights plus F32 EMA copy)

                    1 Reply Last reply
                    0
                    • montezM Offline
                      montezM Offline
                      montez
                      wrote last edited by
                      #14

                      Xiaomi Robotics Xiaomi-Robotics-U0

                      Hugging Face: https://huggingface.co/XiaomiRobotics/Xiaomi-Robotics-U0, https://huggingface.co/XiaomiRobotics/Xiaomi-Robotics-U0-FlashAR, https://huggingface.co/XiaomiRobotics/Xiaomi-Robotics-U0-4B, https://huggingface.co/XiaomiRobotics/Xiaomi-Robotics-U0-Sequence, https://huggingface.co/XiaomiRobotics/Xiaomi-Robotics-U0-4B-Sequence
                      GitHub: https://github.com/XiaomiRobotics/Xiaomi-Robotics-U0
                      Website: http://robotics.xiaomi.com/xiaomi-robotics-u0.html
                      Technical report: https://arxiv.org/abs/2607.11643

                      Developer: Xiaomi Robotics
                      Released: July 2026
                      Variants: U0, U0-FlashAR, U0-4B, U0-Sequence, U0-4B-Sequence
                      Parameters: 34B (U0, U0-Sequence), 4B (U0-4B, U0-4B-Sequence)
                      Architecture: Autoregressive transformer initialized from EMU3.5; shared discrete visual tokenizer, single next-token objective across text and image sequences; FlashAR decodes visual tokens in anti-diagonal groups; Sequence checkpoints interleave subtask text and observations
                      License: Apache-2.0
                      Modalities: Text + Image + Video
                      Runs on: U0-4B variants: Desktop GPU / U0, U0-Sequence, U0-FlashAR: Datacenter GPU, vendor benchmark on one NVIDIA H20
                      Formats: safetensors
                      On disk: 68.21GB (U0, U0-Sequence), 75.02GB (U0-FlashAR), 10.16GB (U0-4B, U0-4B-Sequence)

                      1 Reply Last reply
                      0
                      • montezM Offline
                        montezM Offline
                        montez
                        wrote last edited by
                        #15

                        TeleAI SMART-VLA

                        Hugging Face: https://huggingface.co/TeleEmbodied/SMART-VLA
                        GitHub: https://github.com/TeleHuman/PRTS
                        Website: https://teamillusion-smart.github.io/
                        Technical report: https://arxiv.org/abs/2610.07652

                        Developer: TeleAI (China Telecom)
                        Released: October 2026
                        Parameters: 4.44B
                        Architecture: PRTS-architecture VLA on a Qwen3-VL-4B-Instruct backbone with a flow-matching DiT action head, pretrained on synthetic articulated-object manipulation data
                        License: MIT
                        Modalities: Camera images + language instruction in / 50-step action chunk (up to 32 action dimensions) out
                        Formats: safetensors (BF16, 2 shards)
                        On disk: 9.67GB (two safetensors shards)

                        1 Reply Last reply
                        0
                        • montezM Offline
                          montezM Offline
                          montez
                          wrote last edited by
                          #16

                          Microsoft Rho

                          Hugging Face: https://huggingface.co/microsoft/rho-base, https://huggingface.co/collections/microsoft/rho
                          GitHub: https://github.com/microsoft/rhobotics
                          Website: https://microsoft.github.io/rhobotics/
                          Technical report: https://arxiv.org/abs/2609.38164

                          Developer: Microsoft Research
                          Released: September 2026
                          Variants: rho-base / rho-yam-box / rho-ur-ai-trainer / rho-fr3-duo / rho-libero / rho-roboeval
                          Parameters: 5B (Phi-Phy VLM 4.68B / flow-matching action expert 542M)
                          Architecture: Vision-language-action model: a physically grounded Phi-family VLM (Phi-Phy) with a 12-block flow-matching action expert that cross-attends to a VLM decoder layer, midtrained per embodiment
                          License: MIT
                          Modalities: Multi-camera images + language instruction + robot state in / action chunk out (up to 50 steps in pretraining)
                          Runs on: NVIDIA GPU (Linux, CUDA; FlashAttention 2 by default); no VRAM requirement published
                          Formats: safetensors (BF16, 3 shards)
                          On disk: rho-base 10.50GB

                          1 Reply Last reply
                          0
                          • montezM Offline
                            montezM Offline
                            montez
                            wrote last edited by
                            #17

                            Meta FAIR RoboJEPA

                            GitHub: https://github.com/facebookresearch/robo_jepa
                            Website: https://robojepa.github.io
                            Technical report: https://arxiv.org/abs/2610.10515

                            Developer: Meta FAIR
                            Released: October 2026
                            Variants: 22M / 50M / 100M / 300M / 1B / 2B / 4B / 8B / 8B DROID 720p (3 views)
                            Parameters: 22M to 8B predictors on a frozen V-JEPA 2.1 ViT-G/384 encoder
                            Architecture: Action-conditioned JEPA latent world model: a transformer predictor over frozen V-JEPA 2.1 features, with latent CEM/MPC planning toward a goal image and an optional diffusion video decoder
                            License: CC BY-NC-SA 4.0
                            Modalities: Camera video + action sequence in / predicted future latent states out (optional decoded video); no action head, actions come from latent MPC planning
                            Runs on: NVIDIA GPU (CUDA 12.6), one GPU per model size for evaluation; no VRAM requirement published
                            Formats: PyTorch (.pth.tar) from dl.fbaipublicfiles.com
                            On disk: 8B 29.99GB, 1B 4.07GB, 300M 1.24GB (300k-step checkpoints), plus V-JEPA 2.1 ViT-G/384 encoder 30.24GB

                            1 Reply Last reply
                            0
                            • montezM Offline
                              montezM Offline
                              montez
                              wrote last edited by
                              #18

                              DeepCybo PhysBrain 1.5

                              Hugging Face: https://huggingface.co/DeepCybo/PhysBrain1.5-8B, https://huggingface.co/DeepCybo/PhysBrain1.5-2B
                              GitHub: https://github.com/DeepCybo-PhysAI/PhysBrain-1.5
                              Website: https://deepcybo-physai.github.io/PhysBrain-1.5/
                              Technical report: https://arxiv.org/abs/2609.14973

                              Developer: DeepCybo, Zhongguancun Academy, Zhongguancun Institute of Artificial Intelligence
                              Released: September 2026
                              Variants: 2B, 8B
                              Parameters: 2.16B (2B checkpoint), 8.90B (8B checkpoint)
                              Context: 262,144 tokens
                              Architecture: Qwen3-VL backbone extended with action and visual-state tokens; one shared autoregressive transformer, single next-token objective, no task-specific heads; ActionPiece action tokens with one action codebook across robot setups
                              Modalities: Text + Image + Video + Action history in / Text + Spatial grounding + Action chunk + Future-state image, depth map, robot mask out
                              Runs on: 2B: Laptop, Desktop GPU / 8B: Desktop GPU
                              Formats: safetensors
                              On disk: 4.32GB (2B checkpoint), 17.81GB (8B checkpoint)

                              1 Reply Last reply
                              0
                              • montezM Offline
                                montezM Offline
                                montez
                                wrote last edited by
                                #19

                                Metacognition NavGPT3

                                Hugging Face: https://huggingface.co/Metacognition-AI/NavGPT3-8B, https://huggingface.co/Metacognition-AI/NavGPT3-4B
                                GitHub: https://github.com/metacognitionai/NavGPT-3
                                Website: https://metacognitionai.github.io/NavGPT3/
                                Technical report: https://arxiv.org/abs/2610.10787

                                Developer: Metacognition
                                Released: October 2026
                                Variants: 4B, 8B
                                Parameters: 4.44B (4B checkpoint), 8.77B (8B checkpoint)
                                Architecture: Qwen3-VL fine-tune with a two-layer MLP action head on the last prompt token’s hidden state; one 3,072-token visual budget shared across a four-view, up to 16-step image history
                                License: GNU Affero General Public License v3.0
                                Modalities: Text + Four-view RGB image history in / 8 waypoints (x, y, theta) out
                                Runs on: NVIDIA GPU (Linux)
                                Formats: safetensors
                                On disk: 9.66GB (4B checkpoint), 17.54GB (8B checkpoint)

                                1 Reply Last reply
                                0
                                ↳

                                OBJECTS Forum

                                Join the conversation

                                Create an account to return to your place in the thread, follow new replies, bookmark useful posts, and upvote contributions you value.

                                Have something to add? Your perspective can make this thread better.

                                Register Login
                                Reply
                                • Reply as topic
                                Log in to reply
                                • Oldest to Newest
                                • Newest to Oldest
                                • Most Votes

                                • Login
                                • Don't have an account? Register
                                • Login or register to search.
                                • First post
                                  Last post
                                • 0
                                  • Categories
                                  • Recent
                                  • Tags
                                  • Popular
                                  • Users