正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

VLA is dead? Zhi-Yi Ren, a Research Scientist at Physical Intelligence⁠ working on VLA pre-training, argues that VLA and World Models aren’t competing paths. His view: modeling the future can simply become part of the VLA stack and the two approaches may eventually converge.

Eren Chen

7,802 subscribers

72,925 次观看 • 16 天前 •via X (Twitter)

科学技术教育

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

3D-VLA A 3D Vision-Language-Action Generative World Model Recent vision-language-action (VLA) models rely on 2D inputs, lacking integration with the broader realm of the 3D physical world. Furthermore, they perform action prediction by learning a direct mapping from

3D-VLA A 3D Vision-Language-Action Generative World Model Recent vision-language-action (VLA) models rely on 2D inputs, lacking integration with the broader realm of the 3D physical world. Furthermore, they perform action prediction by learning a direct mapping from

AK

85,570 次观看 • 2 年前

VLA-JEPA just dropped in LeRobot 🤖 What makes this model special is that it does not just learn what action to take from a given observation, it also leverages a JEPA world model to learn action-relevant dynamics. During training, the VLA leverages V-JEPA2 by conditioning its predictor. This clever trick adds a world modeling objective to the training, which also allows pretraining on human videos. At inference, the world model is dropped entirely, keeping only a standard VLA architecture: Qwen backbone and action head. The demo here was only fine-tuned on 13 examples, showing great pretraining capability and running in real time on NVIDIA Robotics DGX Spark! VLA-JEPA is the first world model to be ported to LeRobot, and I feel like it won't be the last 🚀 Thomas Wolf clem 🤗

VLA-JEPA just dropped in LeRobot 🤖 What makes this model special is that it does not just learn what action to take from a given observation, it also leverages a JEPA world model to learn action-relevant dynamics. During training, the VLA leverages V-JEPA2 by conditioning its predictor. This clever trick adds a world modeling objective to the training, which also allows pretraining on human videos. At inference, the world model is dropped entirely, keeping only a standard VLA architecture: Qwen backbone and action head. The demo here was only fine-tuned on 13 examples, showing great pretraining capability and running in real time on NVIDIA Robotics DGX Spark! VLA-JEPA is the first world model to be ported to LeRobot, and I feel like it won't be the last 🚀 Thomas Wolf clem 🤗

LeRobot

320,289 次观看 • 2 个月前

The next evolution: VLA+ models Just yesterday Microsoft Research released Rho-alpha (ρα) – their first robotics model, built on the Phi family. While most Vision-Language-Action (VLA) models stop at vision and language, Rho-alpha adds: ▪️ Tactile sensing to feel objects during manipulation ▪️ Online learning that lets it improve from human corrections (via teleoperation, 3D mouse or other tools) in real-time even after deployment. Both these sides make adaptability central rather than incidental. Microsoft calls it a VLA+ model, positioning it as an extension beyond what current VLA systems support. ➡️ Today Rho-alpha can control dual-arm robot setups to perform tasks such as: • Manipulating the BusyBox following natural-language instructions • Plug insertion • Toolbox packing and object arrangement with bimanual coordination But to understand why this "plus" matters, we need to understand what came before. Here, we'll take you through the entire landscape of VLA models – Gemini Robotics, π0, SmolVLA, Helix, ACoT-VLA and others:

The next evolution: VLA+ models Just yesterday Microsoft Research released Rho-alpha (ρα) – their first robotics model, built on the Phi family. While most Vision-Language-Action (VLA) models stop at vision and language, Rho-alpha adds: ▪️ Tactile sensing to feel objects during manipulation ▪️ Online learning that lets it improve from human corrections (via teleoperation, 3D mouse or other tools) in real-time even after deployment. Both these sides make adaptability central rather than incidental. Microsoft calls it a VLA+ model, positioning it as an extension beyond what current VLA systems support. ➡️ Today Rho-alpha can control dual-arm robot setups to perform tasks such as: • Manipulating the BusyBox following natural-language instructions • Plug insertion • Toolbox packing and object arrangement with bimanual coordination But to understand why this "plus" matters, we need to understand what came before. Here, we'll take you through the entire landscape of VLA models – Gemini Robotics, π0, SmolVLA, Helix, ACoT-VLA and others:

Turing Post

62,362 次观看 • 7 个月前

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 次观看 • 1 个月前

Pi0 from Physical Intelligence is one of the best generalist Vision-Language-Action (VLA) models for robotics (and predecessor of Pi0.5). 🧵 Here's how it works + how you can fine-tune it on your own robot for a simple task:

Pi0 from Physical Intelligence is one of the best generalist Vision-Language-Action (VLA) models for robotics (and predecessor of Pi0.5). 🧵 Here's how it works + how you can fine-tune it on your own robot for a simple task:

Ilia

32,956 次观看 • 11 个月前

JARVIS-VLA just dropped on Hugging Face Post-Training Large-Scale Vision Language Models to Play Visual Games with Keyboards and Mouse obtain VLA models in Minecraft that can follow human instructions on over 1k different atomic tasks, including crafting, smelting, cooking, mining, and killing. experiments demonstrate that post-training on non-trajectory tasks leads to a significant 40% improvement over the best agent baseline on a diverse set of atomic tasks. Furthermore, demonstrate that approach surpasses traditional imitation learning-based policies in Minecraft, achieving state-of-the-art performance.

JARVIS-VLA just dropped on Hugging Face Post-Training Large-Scale Vision Language Models to Play Visual Games with Keyboards and Mouse obtain VLA models in Minecraft that can follow human instructions on over 1k different atomic tasks, including crafting, smelting, cooking, mining, and killing. experiments demonstrate that post-training on non-trajectory tasks leads to a significant 40% improvement over the best agent baseline on a diverse set of atomic tasks. Furthermore, demonstrate that approach surpasses traditional imitation learning-based policies in Minecraft, achieving state-of-the-art performance.

AK

60,243 次观看 • 1 年前

X-Humanoid unveiled TG-VLA, which it calls the world's first whole-body VLA framework for full-size humanoid robots. The goal: move humanoids past "mobile dual-arm systems" to human-like, whole-body coordinated operation. Built on three technologies: - HEX: an open-source full-size humanoid VLA that learns across embodiments and coordinates the whole body. Claimed SOTA on real-world whole-body manipulation - HAF-VLA: hierarchical action flow that decomposes whole-body motion into subtasks. Best or joint-best on 6 benchmarks - DSRL-DCT: online RL for high-DoF humanoids in a compressed latent space. 100% success on mobile manipulation HEX is open-source.

X-Humanoid unveiled TG-VLA, which it calls the world's first whole-body VLA framework for full-size humanoid robots. The goal: move humanoids past "mobile dual-arm systems" to human-like, whole-body coordinated operation. Built on three technologies: - HEX: an open-source full-size humanoid VLA that learns across embodiments and coordinates the whole body. Claimed SOTA on real-world whole-body manipulation - HAF-VLA: hierarchical action flow that decomposes whole-body motion into subtasks. Best or joint-best on 6 benchmarks - DSRL-DCT: online RL for high-DoF humanoids in a compressed latent space. 100% success on mobile manipulation HEX is open-source.

The Humanoid Hub

19,563 次观看 • 1 个月前

A 2-hour uncut video of X-VLA folding cloth at a 100% success rate. we provide the checkpoints, and you can easily fine-tune them on any dataset (any action dimension): enjoy!

A 2-hour uncut video of X-VLA folding cloth at a 100% success rate. we provide the checkpoints, and you can easily fine-tune them on any dataset (any action dimension): enjoy!

jade

32,518 次观看 • 8 个月前

>build a 1.5B VLA on top of MiniCPM-V 4.6 >compete with π0.5 and Qwen-VLA >use roughly half the visual-processing compute >remember previous steps without blowing up inference cost >pull the network plug >let the robot keep tracking — fully local, fully onboard >with CUDA Graph optimization and custom Triton fused kernels, MiniCPM-Robot inference throughput goes from 10 Hz → 33 Hz, and up to 36 Hz on the same NVIDIA H20 >release the models and framework as open source so why does robotics still rely on bigger models and the cloud? OpenBMB just dropped MiniCPM-Robot at WAIC two models + one inference framework 🧵

>build a 1.5B VLA on top of MiniCPM-V 4.6 >compete with π0.5 and Qwen-VLA >use roughly half the visual-processing compute >remember previous steps without blowing up inference cost >pull the network plug >let the robot keep tracking — fully local, fully onboard >with CUDA Graph optimization and custom Triton fused kernels, MiniCPM-Robot inference throughput goes from 10 Hz → 33 Hz, and up to 36 Hz on the same NVIDIA H20 >release the models and framework as open source so why does robotics still rely on bigger models and the cloud? OpenBMB just dropped MiniCPM-Robot at WAIC two models + one inference framework 🧵

arc.

48,279 次观看 • 1 个月前

Daksha is learning. Powered by Viveka Decision Core and an indigenous VLA architecture, Daksha observes, understands, and executes real-world tasks while improving with every interaction. Building the future of embodied AI and general-purpose humanoid robots i Hub robotics

Daksha is learning. Powered by Viveka Decision Core and an indigenous VLA architecture, Daksha observes, understands, and executes real-world tasks while improving with every interaction. Building the future of embodied AI and general-purpose humanoid robots i Hub robotics

Athil Krishna

34,320 次观看 • 2 个月前

Rollouts in the real world are slow and expensive. What if we could rollout trajectories entirely inside a world model (WM)? Introducing 🚀Ctrl-World🚀, a generative manipulation WM that can interact with advanced VLA policy in imagination. 🧵1/6

Rollouts in the real world are slow and expensive. What if we could rollout trajectories entirely inside a world model (WM)? Introducing 🚀Ctrl-World🚀, a generative manipulation WM that can interact with advanced VLA policy in imagination. 🧵1/6

Yanjiang Guo

95,748 次观看 • 10 个月前

LeRobot v0.6.0 is officially here: Imagine, Evaluate, Improve! 🤖🚀 We are closing the robot learning loop with massive upgrades for the open-source robotics community. From policies that imagine the future to a much leaner installation, here is what is new: - 🌍 World Models: VLA-JEPA, LingBot-VA, and FastWAM help your policies anticipate the future. - 👀 VLA Expansion: Welcome GR00T 1.7, MolmoAct2, EO-1, Multitask DiT, and EVO1. - 🏅 Reward Models API: Track success seamlessly with Robometer and TOPReward. - 🎯 Unified Evaluation: 6 new simulation benchmarks, all accessible via the lerobot-eval CLI. - ☁️ And more: lerobot-rollout CLI for DAgger corrections, HF Jobs cloud training, up to 2x faster data loading, GUI - LeLab, many docs improvements Ready to build the future of robotics? Dive into the full release notes here: clem 🤗 Thomas Wolf

LeRobot v0.6.0 is officially here: Imagine, Evaluate, Improve! 🤖🚀 We are closing the robot learning loop with massive upgrades for the open-source robotics community. From policies that imagine the future to a much leaner installation, here is what is new: - 🌍 World Models: VLA-JEPA, LingBot-VA, and FastWAM help your policies anticipate the future. - 👀 VLA Expansion: Welcome GR00T 1.7, MolmoAct2, EO-1, Multitask DiT, and EVO1. - 🏅 Reward Models API: Track success seamlessly with Robometer and TOPReward. - 🎯 Unified Evaluation: 6 new simulation benchmarks, all accessible via the lerobot-eval CLI. - ☁️ And more: lerobot-rollout CLI for DAgger corrections, HF Jobs cloud training, up to 2x faster data loading, GUI - LeLab, many docs improvements Ready to build the future of robotics? Dive into the full release notes here: clem 🤗 Thomas Wolf

LeRobot

55,284 次观看 • 1 个月前

By unifying prediction and control, NavWAM acts as a closed-loop policy out of the box. In evaluations, it outperforms planning-based world models without needing test-time action search, matches a much larger 7B VLA policy, and transfers successfully to real mobile robots.

By unifying prediction and control, NavWAM acts as a closed-loop policy out of the box. In evaluations, it outperforms planning-based world models without needing test-time action search, matches a much larger 7B VLA policy, and transfers successfully to real mobile robots.

Robots Digest 🤖

11,076 次观看 • 2 个月前

VLA policies learn generalist robot behaviors from massive teleoperation datasets, hoping that the right behavior emerges. But they rarely use perception during training or inference: powerful foundation models of 3D geometry, semantics, or human motion are ignored. TimSong, Long Le, and our GRASP Laboratory team introduce Omniguide, based on a simple idea: Instead of retraining policies, let perception guide action at inference time. We express diverse guidance sources as attractive and repulsive energy fields in 3D space and inject their gradients into the generative process of VLA policies. This lets perception modules steer actions without retraining the policy: A modular path toward composable robot intelligence. Project: Paper:

VLA policies learn generalist robot behaviors from massive teleoperation datasets, hoping that the right behavior emerges. But they rarely use perception during training or inference: powerful foundation models of 3D geometry, semantics, or human motion are ignored. TimSong, Long Le, and our GRASP Laboratory team introduce Omniguide, based on a simple idea: Instead of retraining policies, let perception guide action at inference time. We express diverse guidance sources as attractive and repulsive energy fields in 3D space and inject their gradients into the generative process of VLA policies. This lets perception modules steer actions without retraining the policy: A modular path toward composable robot intelligence. Project: Paper:

Kostas Daniilidis

47,642 次观看 • 5 个月前

Robotic insight 2: One undocumented feature of VLA models is that they can generalize pretty well from very little data, if you run them on good hardware. Here, with 35 demonstrations (5 mins in total), robot can pick up small pcb from any position and at any rotation angle.

Robotic insight 2: One undocumented feature of VLA models is that they can generalize pretty well from very little data, if you run them on good hardware. Here, with 35 demonstrations (5 mins in total), robot can pick up small pcb from any position and at any rotation angle.

Igor Kulakov (MicroFactory)

47,571 次观看 • 7 个月前

Robora x Lemorele We are excited to announce the integration of the Robora P300 (R) model. An exclusive model developed in partnership with Lemorele, features a custom Robora-exclusive SKU and hardware configuration designed to support high-performance, wireless video streaming for AI training and perception. We will integrate this specialized unit into our VLA Module. The Robora P300 (R) enables seamless, real-time capture of high-definition HDMI video from external cameras, allowing users to wirelessly feed visual data directly into the VLA training pipeline. This enhances capabilities such as multi-view learning, remote annotation, and real-world AI fine-tuning, all without requiring tethered camera setups. While the full Robora robotics platform is still in development, users will be able to use the Robora P300 (R) hardware with their existing iOS or Android devices, enabling them to begin collecting and streaming visual data for VLA from mobile platforms. As part of our commitment to the Robora community, we will be offering exclusive giveaways of the Robora P300 (R) hardware to token holders, giving early supporters the opportunity to contribute directly to Robora’s growing AI training ecosystem and to gain early access to the tools that power the future of robotics and intelligent vision.

Robora x Lemorele We are excited to announce the integration of the Robora P300 (R) model. An exclusive model developed in partnership with Lemorele, features a custom Robora-exclusive SKU and hardware configuration designed to support high-performance, wireless video streaming for AI training and perception. We will integrate this specialized unit into our VLA Module. The Robora P300 (R) enables seamless, real-time capture of high-definition HDMI video from external cameras, allowing users to wirelessly feed visual data directly into the VLA training pipeline. This enhances capabilities such as multi-view learning, remote annotation, and real-world AI fine-tuning, all without requiring tethered camera setups. While the full Robora robotics platform is still in development, users will be able to use the Robora P300 (R) hardware with their existing iOS or Android devices, enabling them to begin collecting and streaming visual data for VLA from mobile platforms. As part of our commitment to the Robora community, we will be offering exclusive giveaways of the Robora P300 (R) hardware to token holders, giving early supporters the opportunity to contribute directly to Robora’s growing AI training ecosystem and to gain early access to the tools that power the future of robotics and intelligent vision.

Robora

19,276 次观看 • 11 个月前

Scaling vision-language-action (VLA) models to high-DoF dexterous hands has long been a "holy grail" challenge due to the high-dimensional action space and data scarcity. As a wrap up of the year 2025, we are releasing GR-Dexter, a holistic hardware-model-data framework for generalist manipulation on a bimanual dexterous-hand robot. This is the first VLA system to achieve: ✅ High-DoF Control: Managing a 56-DoF bimanual system (21-DoF per hand). ✅ Long-Horizon Tasks with tool use: Vacuuming, bread serving with tongs, and table decluttering. ✅ Open-World Generalization: Robust performance with unseen objects and abstract instructions. Project page: ArXiv:

Scaling vision-language-action (VLA) models to high-DoF dexterous hands has long been a "holy grail" challenge due to the high-dimensional action space and data scarcity. As a wrap up of the year 2025, we are releasing GR-Dexter, a holistic hardware-model-data framework for generalist manipulation on a bimanual dexterous-hand robot. This is the first VLA system to achieve: ✅ High-DoF Control: Managing a 56-DoF bimanual system (21-DoF per hand). ✅ Long-Horizon Tasks with tool use: Vacuuming, bread serving with tongs, and table decluttering. ✅ Open-World Generalization: Robust performance with unseen objects and abstract instructions. Project page: ArXiv:

Xiao Ma

93,908 次观看 • 7 个月前

We just did World’s first on-stage autonomous demo of long-horizon dexterous VLA 🚨 No training. No setup. Performance out of the box. Live demo is hard and unpredictable, but we felt great about our model’s generalization, and it went pretty well! 💯 Zero-shot. 100% success.

We just did World’s first on-stage autonomous demo of long-horizon dexterous VLA 🚨 No training. No setup. Performance out of the box. Live demo is hard and unpredictable, but we felt great about our model’s generalization, and it went pretty well! 💯 Zero-shot. 100% success.

Jason Ma

63,752 次观看 • 11 个月前

XPeng's all-new generation humanoid robot, IRON, not only achieves an extreme level of anthropomorphism but also possesses a "brain" that can think like a human. This will be a significant competitor to $TSLA's Optimus v3 when both robots enter mass production in 2026. ✅ IRON is the humanoid robot with the highest computing power in the world, equipped with the second-generation VLA and 3 Turing AI chips, it builds a high-level combination of capabilities—VLT + VLA + VLM—for its "cerebrum" and "cerebellum." This allows it to achieve advanced intelligence like dialogue, walking, and interaction. ✅ It is the industry's first application of all-solid-state batteries, achieving extreme lightweighting, ultra-high energy density, and ultimate safety. ✅ XPeng also introduced robot active safety protection to maximize the safety of participants in the physical AI world, and expanded the "Fourth Law," ensuring privacy data never leaves the robot.

XPeng's all-new generation humanoid robot, IRON, not only achieves an extreme level of anthropomorphism but also possesses a "brain" that can think like a human. This will be a significant competitor to $TSLA's Optimus v3 when both robots enter mass production in 2026. ✅ IRON is the humanoid robot with the highest computing power in the world, equipped with the second-generation VLA and 3 Turing AI chips, it builds a high-level combination of capabilities—VLT + VLA + VLM—for its "cerebrum" and "cerebellum." This allows it to achieve advanced intelligence like dialogue, walking, and interaction. ✅ It is the industry's first application of all-solid-state batteries, achieving extreme lightweighting, ultra-high energy density, and ultimate safety. ✅ XPeng also introduced robot active safety protection to maximize the safety of participants in the physical AI world, and expanded the "Fourth Law," ensuring privacy data never leaves the robot.

Ming

63,141 次观看 • 9 个月前