Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

What if robots could think longer on harder problems without saying a single word?🤔 We introduce RD-VLA (Recurrent-Depth VLA): a latent, iterative reasoning architecture for robot control. ❌No Chain-of-Thought tokens. ❌No extra memory overhead. ✅Just reasoning—directly in latent space. 🧠🤖 Project page: 👇🧵

Jiafei Duan

6,680 subscribers

13,949 views • 9 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Chain-of-thought reasoning is a powerful tool to enable language models to work through complex problems. Can we use this with robots? With embodied chain-of-thought, vision-language-action (VLA) models can think through perception and planning! A 🧵👇

Chain-of-thought reasoning is a powerful tool to enable language models to work through complex problems. Can we use this with robots? With embodied chain-of-thought, vision-language-action (VLA) models can think through perception and planning! A 🧵👇

Sergey Levine

30,485 views • 2 years ago

🤔 Can we train one VLA policy to control multi-robot teams without any explicit communication? ✨ Introducing CHORUS: a single policy for decentralized, multi-embodiment collaboration 🧵⬇️

🤔 Can we train one VLA policy to control multi-robot teams without any explicit communication? ✨ Introducing CHORUS: a single policy for decentralized, multi-embodiment collaboration 🧵⬇️

Ria Doshi

63,172 views • 5 months ago

Gemini Robotics 1.5 features a separate reasoning engine (ER), but its VLA model is also capable of thinking due to interleaved reasoning tokens. The VLA is able to independently operate long autonomous sequences (15+ minutes) without aid from the ER/VLM.

Gemini Robotics 1.5 features a separate reasoning engine (ER), but its VLA model is also capable of thinking due to interleaved reasoning tokens. The VLA is able to independently operate long autonomous sequences (15+ minutes) without aid from the ER/VLM.

The Humanoid Hub

34,214 views • 1 year ago

Machine Mental Imagery Empower Multimodal Reasoning with Latent Visual Tokens

Machine Mental Imagery Empower Multimodal Reasoning with Latent Visual Tokens

AK

43,552 views • 1 year ago

We introduce W.A.L.T, a diffusion model for photorealistic video generation. Our model is a transformer trained on image and video generation in a shared latent space. 🧵👇

We introduce W.A.L.T, a diffusion model for photorealistic video generation. Our model is a transformer trained on image and video generation in a shared latent space. 🧵👇

Agrim Gupta

431,392 views • 2 years ago

🤖 New paper: MobileVLA-R1 A unified VLA system that brings real reasoning + continuous control to quadruped robots. CoT dataset, 2-stage training, real-world deployment. 📄paper & code & demo:

🤖 New paper: MobileVLA-R1 A unified VLA system that brings real reasoning + continuous control to quadruped robots. CoT dataset, 2-stage training, real-world deployment. 📄paper & code & demo:

Hao Tang (hiring postdocs)

27,306 views • 11 months ago

Hear me out JEV architecture but internal layers loop twice to simulate latent reasoning

Hear me out JEV architecture but internal layers loop twice to simulate latent reasoning

AVB

19,249 views • 1 month ago

Qwen-VLA feels like one of the first real robotics foundation models. A single system trained across robot manipulation, navigation, egocentric human video, simulation, and vision-language reasoning instead of isolated robot policies.

Qwen-VLA feels like one of the first real robotics foundation models. A single system trained across robot manipulation, navigation, egocentric human video, simulation, and vision-language reasoning instead of isolated robot policies.

Robots Digest 🤖

14,722 views • 5 months ago

X-Humanoid just dropped TG-VLA — the first full-size, whole-body VLA framework for humanoids. 🤖 Most VLA demos today still look arm-centric: see, plan, reach, grasp. The legs are mostly there to carry the arms. TG-VLA pushes action into the whole body: → HEX: task context & cross-embodiment learning → HAF-VLA: high-DoF motion → structured action flows → DSRL-DCT: online RL through a compressed latent space The real shift isn't a smarter hand — it's locomotion, torso control, balance, and manipulation inside one control loop. That's the move: from mobile dual-arm machines to full-body agents.

X-Humanoid just dropped TG-VLA — the first full-size, whole-body VLA framework for humanoids. 🤖 Most VLA demos today still look arm-centric: see, plan, reach, grasp. The legs are mostly there to carry the arms. TG-VLA pushes action into the whole body: → HEX: task context & cross-embodiment learning → HAF-VLA: high-DoF motion → structured action flows → DSRL-DCT: online RL through a compressed latent space The real shift isn't a smarter hand — it's locomotion, torso control, balance, and manipulation inside one control loop. That's the move: from mobile dual-arm machines to full-body agents.

RoboHub🤖

42,219 views • 4 months ago

What if we met… in latent space 😳 play !

What if we met… in latent space 😳 play !

Joel Simon

30,995 views • 2 years ago

Ever wondered what robots 🤖 could achieve if they could not just see – but also feel and hear? Introducing FuSe: a recipe for finetuning large vision-language-action (VLA) models with heterogeneous sensory data, such as vision, touch, sound, and more. Details in the thread 👇

Ever wondered what robots 🤖 could achieve if they could not just see – but also feel and hear? Introducing FuSe: a recipe for finetuning large vision-language-action (VLA) models with heterogeneous sensory data, such as vision, touch, sound, and more. Details in the thread 👇

Carlo Sferrazza

46,111 views • 1 year ago

Introducing Flow Reasoning Models. We developed a recurrent flow-based architecture to efficiently solve structured reasoning problems (e.g., Sudoku). FRMs apply continuous flows to discrete data and recurrently refine their past mistakes through self-conditioning.

Introducing Flow Reasoning Models. We developed a recurrent flow-based architecture to efficiently solve structured reasoning problems (e.g., Sudoku). FRMs apply continuous flows to discrete data and recurrently refine their past mistakes through self-conditioning.

Alec Helbling

132,502 views • 2 months ago

Embodied chain of thought (ECoT) is a powerful tool to get VLAs to think through problems, but why does it work? In our new work, we analyze various lightweight ECoT-like strategies, including co-training, to see what is the "minimal" amount of reasoning that can boost VLAs 🧵👇

Embodied chain of thought (ECoT) is a powerful tool to get VLAs to think through problems, but why does it work? In our new work, we analyze various lightweight ECoT-like strategies, including co-training, to see what is the "minimal" amount of reasoning that can boost VLAs 🧵👇

Sergey Levine

22,463 views • 1 year ago

A new paradigm for robot learning that unifies latent world modeling and action generation. Astribot has introduced Lumo-2, a latent world-action model for robot control. - Validated on a real robot through 20+ intricate chores, extending beyond simple benchmark testing. - A 3-stage recipe that progressively aligns actions with world dynamics, then vision, then language - Action quality depends on the geometry of the latent space, not just reconstruction accuracy - BAR (block-wise decoding) speeds up inference by 2.71x compared to standard autoregressive decoding - Shows cross-embodiment transfer without specialized transfer learning Results: - Beats π0.5 and Fast-WAM in temporal reasoning, physical understanding, long-horizon, and dexterous manipulation - Lumo-2's VLM consistently outperforms Qwen-3.5 4B on embodied benchmarks

A new paradigm for robot learning that unifies latent world modeling and action generation. Astribot has introduced Lumo-2, a latent world-action model for robot control. - Validated on a real robot through 20+ intricate chores, extending beyond simple benchmark testing. - A 3-stage recipe that progressively aligns actions with world dynamics, then vision, then language - Action quality depends on the geometry of the latent space, not just reconstruction accuracy - BAR (block-wise decoding) speeds up inference by 2.71x compared to standard autoregressive decoding - Shows cross-embodiment transfer without specialized transfer learning Results: - Beats π0.5 and Fast-WAM in temporal reasoning, physical understanding, long-horizon, and dexterous manipulation - Lumo-2's VLM consistently outperforms Qwen-3.5 4B on embodied benchmarks

The Humanoid Hub

20,623 views • 4 months ago

🕹️We are excited to introduce "ChronoEdit: Towards Temporal Reasoning for Image Editing and World Simulation" ChronoEdit reframes image editing as a video generation task to encourage temporal consistency. It leverages a temporal reasoning stage that denoises with “video reasoning tokens” to "reason" on physically plausible edits. See the attached video for results. Project Page: Arxiv: Code and model are coming.

🕹️We are excited to introduce "ChronoEdit: Towards Temporal Reasoning for Image Editing and World Simulation" ChronoEdit reframes image editing as a video generation task to encourage temporal consistency. It leverages a temporal reasoning stage that denoises with “video reasoning tokens” to "reason" on physically plausible edits. See the attached video for results. Project Page: Arxiv: Code and model are coming.

Huan Ling

37,080 views • 1 year ago

Meet VLA-JEPA, the first world model policy in LeRobot 🌍 Most VLAs just learn observation → action. VLA-JEPA also learns action-relevant dynamics: during training, a JEPA world model has to predict upcoming frames in latent space from the model's own actions. Then, at inference, the world model disappears entirely, leaving a standard, fast VLA: Qwen backbone, action head, nothing extra. In our demo it was fine-tuned on just 13 examples and ran in real time on an NVIDIA DGX Spark. On a consumer RTX 3080, it hits 10Hz using under 6GB of VRAM. World-model supervision during training, zero extra cost at inference. That's the whole trick.

Meet VLA-JEPA, the first world model policy in LeRobot 🌍 Most VLAs just learn observation → action. VLA-JEPA also learns action-relevant dynamics: during training, a JEPA world model has to predict upcoming frames in latent space from the model's own actions. Then, at inference, the world model disappears entirely, leaving a standard, fast VLA: Qwen backbone, action head, nothing extra. In our demo it was fine-tuned on just 13 examples and ran in real time on an NVIDIA DGX Spark. On a consumer RTX 3080, it hits 10Hz using under 6GB of VRAM. World-model supervision during training, zero extra cost at inference. That's the whole trick.

LeRobot

42,389 views • 4 months ago

Announcing a new Memory system for robots on Dimensional Robots in production generate thousands of hours of video, lidar, odometry, far too large to fit into your Agent context SpatialMemory2 builds a multimodal data store in latent space for your Agents Fully open source

Announcing a new Memory system for robots on Dimensional Robots in production generate thousands of hours of video, lidar, odometry, far too large to fit into your Agent context SpatialMemory2 builds a multimodal data store in latent space for your Agents Fully open source

stash

228,826 views • 6 months ago

UK-based startup 'Humanoid' announced KinetIQ, an AI framework with a Vision-Language-Action (VLA) model at its core. It uses a four-layer architecture: fleet orchestration, task decomposition, VLA, and RL for whole-body control. It works on both bipedal and wheeled robots.

UK-based startup 'Humanoid' announced KinetIQ, an AI framework with a Vision-Language-Action (VLA) model at its core. It uses a four-layer architecture: fleet orchestration, task decomposition, VLA, and RL for whole-body control. It works on both bipedal and wheeled robots.

The Humanoid Hub

22,035 views • 9 months ago

🤖✨ What if models that take action in the physical world could think through your instructions? Meet MolmoAct, our new fully open Action Reasoning Model (ARM) that does just that. 🧵

🤖✨ What if models that take action in the physical world could think through your instructions? Meet MolmoAct, our new fully open Action Reasoning Model (ARM) that does just that. 🧵

Ai2

181,208 views • 1 year ago