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。

Compared to conventional VLAs, S1 is a step-change improvement. For known tasks, S1 can match the performance of language-prompted VLAs. For novel tasks, S1 exponentially outperforms any existing language-prompted VLAs as we scale the pre-training. We believe this is a promising direction towards establishing scaling laws for robotics.

Skild AI

20,197 subscribers

301,156 次观看 • 2 天前 •via X (Twitter)

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

Language following is a tough problem for VLAs: while these models can follow complex language, in practice getting datasets that enable language following is hard. We developed a method to counterfactually and automatically label data to improve language following! 🧵👇

Language following is a tough problem for VLAs: while these models can follow complex language, in practice getting datasets that enable language following is hard. We developed a method to counterfactually and automatically label data to improve language following! 🧵👇

Sergey Levine

44,236 次观看 • 1 年前

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

22,424 次观看 • 1 年前

MotionGPT: Human Motion as a Foreign Language paper page: Though the advancement of pre-trained large language models unfolds, the exploration of building a unified model for language and other multi-modal data, such as motion, remains challenging and untouched so far. Fortunately, human motion displays a semantic coupling akin to human language, often perceived as a form of body language. By fusing language data with large-scale motion models, motion-language pre-training that can enhance the performance of motion-related tasks becomes feasible. Driven by this insight, we propose MotionGPT, a unified, versatile, and user-friendly motion-language model to handle multiple motion-relevant tasks. Specifically, we employ the discrete vector quantization for human motion and transfer 3D motion into motion tokens, similar to the generation process of word tokens. Building upon this "motion vocabulary", we perform language modeling on both motion and text in a unified manner, treating human motion as a specific language. Moreover, inspired by prompt learning, we pre-train MotionGPT with a mixture of motion-language data and fine-tune it on prompt-based question-and-answer tasks. Extensive experiments demonstrate that MotionGPT achieves state-of-the-art performances on multiple motion tasks including text-driven motion generation, motion captioning, motion prediction, and motion in-between.

MotionGPT: Human Motion as a Foreign Language paper page: Though the advancement of pre-trained large language models unfolds, the exploration of building a unified model for language and other multi-modal data, such as motion, remains challenging and untouched so far. Fortunately, human motion displays a semantic coupling akin to human language, often perceived as a form of body language. By fusing language data with large-scale motion models, motion-language pre-training that can enhance the performance of motion-related tasks becomes feasible. Driven by this insight, we propose MotionGPT, a unified, versatile, and user-friendly motion-language model to handle multiple motion-relevant tasks. Specifically, we employ the discrete vector quantization for human motion and transfer 3D motion into motion tokens, similar to the generation process of word tokens. Building upon this "motion vocabulary", we perform language modeling on both motion and text in a unified manner, treating human motion as a specific language. Moreover, inspired by prompt learning, we pre-train MotionGPT with a mixture of motion-language data and fine-tune it on prompt-based question-and-answer tasks. Extensive experiments demonstrate that MotionGPT achieves state-of-the-art performances on multiple motion tasks including text-driven motion generation, motion captioning, motion prediction, and motion in-between.

AK

125,353 次观看 • 3 年前

We discovered an emergent property of VLAs like π0/π0.5/π0.6: as we scale up pre-training, the model learns to align human videos and robot data! This gives us a simple way to leverage human videos. Once π0.5 knows how to control robots, it can naturally learn from human video.

We discovered an emergent property of VLAs like π0/π0.5/π0.6: as we scale up pre-training, the model learns to align human videos and robot data! This gives us a simple way to leverage human videos. Once π0.5 knows how to control robots, it can naturally learn from human video.

Physical Intelligence

1,185,399 次观看 • 8 个月前

We promised and now we have delivered. The S1 X is the EV scooter for every Indian. 🛵🇮🇳 It's everything you love about the S1 but in a more affordable package starting from INR 69,999 - Ab chaabi ke saath 🔑 Can't wait for you all to experience the all new S1 X! Deliveries start next week!

We promised and now we have delivered. The S1 X is the EV scooter for every Indian. 🛵🇮🇳 It's everything you love about the S1 but in a more affordable package starting from INR 69,999 - Ab chaabi ke saath 🔑 Can't wait for you all to experience the all new S1 X! Deliveries start next week!

Bhavish Aggarwal

69,536 次观看 • 2 年前

Not the flashiest demos, but what’s under the hood represents a foundational shift for general-purpose robotics. World models are the next-gen foundation of Physical AI, not the VLM backbones found in typical VLAs. DreamZero is a 14B-parameter World Action Model (WAM) by NVIDIA that treats robotics as a joint video-and-action prediction task. Unlike traditional Vision-Language-Action (VLA) models that map images directly to motor commands, DreamZero leverages a pretrained video diffusion backbone to predict future world states and actions simultaneously. - achieves 2× better zero-shot generalization to unseen tasks and environments compared to state-of-the-art VLAs. - learns effectively from heterogeneous, non-repetitive data (500 hours), breaking the need for thousands of repeated demonstrations. - adapts to new robot embodiments with just 30 minutes of play data. - enables 7Hz closed-loop control via system optimizations and "DreamZero-Flash," making high-capacity diffusion models viable for real-time use.

Not the flashiest demos, but what’s under the hood represents a foundational shift for general-purpose robotics. World models are the next-gen foundation of Physical AI, not the VLM backbones found in typical VLAs. DreamZero is a 14B-parameter World Action Model (WAM) by NVIDIA that treats robotics as a joint video-and-action prediction task. Unlike traditional Vision-Language-Action (VLA) models that map images directly to motor commands, DreamZero leverages a pretrained video diffusion backbone to predict future world states and actions simultaneously. - achieves 2× better zero-shot generalization to unseen tasks and environments compared to state-of-the-art VLAs. - learns effectively from heterogeneous, non-repetitive data (500 hours), breaking the need for thousands of repeated demonstrations. - adapts to new robot embodiments with just 30 minutes of play data. - enables 7Hz closed-loop control via system optimizations and "DreamZero-Flash," making high-capacity diffusion models viable for real-time use.

The Humanoid Hub

35,204 次观看 • 6 个月前

Can vision-language-action (VLA) models generalize to diverse OOD tasks and align with customized objectives? 🤔 🚀 We introduce GRAPE, a plug-and-play algorithm to generalize robot policies via preference alignment. GRAPE unfolds three benefits to boost the generalizability of VLAs: 👉1. GRAPE aligns VLAs on a trajectory level and endows the model with the ability for global decision-making, instead of merely cloning behavior; 👉2. GRAPE implicitly models reward from both successful and failed trials to boost generalizability to diverse tasks; 👉3. GRAPE adopts a scalable preference synthesis algorithm to rank trajectories with preferences that align with arbitrary objectives. Our experiments on a diverse array of real-world and simulated robotic tasks reveal: 1⃣GRAPE enhances the performance of state-of-the-art VLA models, increasing success rates on in-domain and unseen manipulation tasks by 51.79% and 60.36%; 2⃣GRAPE is versatile to be aligned with diverse objectives and reduce collision rates by 44.31% or rollout length by 11.15% when aligning towards safer or more efficient manipulation policy, respectively. Check out our full project for more details: 🔥 Paper: 🔥 Project: 🔥 Code:

Can vision-language-action (VLA) models generalize to diverse OOD tasks and align with customized objectives? 🤔 🚀 We introduce GRAPE, a plug-and-play algorithm to generalize robot policies via preference alignment. GRAPE unfolds three benefits to boost the generalizability of VLAs: 👉1. GRAPE aligns VLAs on a trajectory level and endows the model with the ability for global decision-making, instead of merely cloning behavior; 👉2. GRAPE implicitly models reward from both successful and failed trials to boost generalizability to diverse tasks; 👉3. GRAPE adopts a scalable preference synthesis algorithm to rank trajectories with preferences that align with arbitrary objectives. Our experiments on a diverse array of real-world and simulated robotic tasks reveal: 1⃣GRAPE enhances the performance of state-of-the-art VLA models, increasing success rates on in-domain and unseen manipulation tasks by 51.79% and 60.36%; 2⃣GRAPE is versatile to be aligned with diverse objectives and reduce collision rates by 44.31% or rollout length by 11.15% when aligning towards safer or more efficient manipulation policy, respectively. Check out our full project for more details: 🔥 Paper: 🔥 Project: 🔥 Code:

Huaxiu Yao

20,071 次观看 • 1 年前

🦾 The Ukrainian Armed Forces use a home-made unmanned ground vehicle SkyLab UA Sirko-S1. The Sirko-S1 is designed to perform a variety of tasks. 🔸Capable of transporting up to 200 kg of cargo over a distance of 2.5 km, it facilitates the delivery of ammunition, provisions and medicines to the front line. In addition, they can be used to evacuate the wounded from the battlefield. 🔸Sirko-S1 is equipped with a thermal imaging camera, a laser rangefinder and a standard camera, which together provide reconnaissance of positions. 🔸The flexibility of the platform is further increased by the ability to quickly add compatible modules. 🔸Encrypted communication for control and video transmission 🔸Four-wheel electric drive with energy regeneration modes. 🔸 Sirko-S1 is currently in mass production.

🦾 The Ukrainian Armed Forces use a home-made unmanned ground vehicle SkyLab UA Sirko-S1. The Sirko-S1 is designed to perform a variety of tasks. 🔸Capable of transporting up to 200 kg of cargo over a distance of 2.5 km, it facilitates the delivery of ammunition, provisions and medicines to the front line. In addition, they can be used to evacuate the wounded from the battlefield. 🔸Sirko-S1 is equipped with a thermal imaging camera, a laser rangefinder and a standard camera, which together provide reconnaissance of positions. 🔸The flexibility of the platform is further increased by the ability to quickly add compatible modules. 🔸Encrypted communication for control and video transmission 🔸Four-wheel electric drive with energy regeneration modes. 🔸 Sirko-S1 is currently in mass production.

MAKS 25 🇺🇦👀

40,586 次观看 • 7 个月前

Google presents AudioPaLM: A Large Language Model That Can Speak and Listen paper page: introduce AudioPaLM, a large language model for speech understanding and generation. AudioPaLM fuses text-based and speech-based language models, PaLM-2 [Anil et al., 2023] and AudioLM [Borsos et al., 2022], into a unified multimodal architecture that can process and generate text and speech with applications including speech recognition and speech-to-speech translation. AudioPaLM inherits the capability to preserve paralinguistic information such as speaker identity and intonation from AudioLM and the linguistic knowledge present only in text large language models such as PaLM-2. We demonstrate that initializing AudioPaLM with the weights of a text-only large language model improves speech processing, successfully leveraging the larger quantity of text training data used in pretraining to assist with the speech tasks. The resulting model significantly outperforms existing systems for speech translation tasks and has the ability to perform zero-shot speech-to-text translation for many languages for which input/target language combinations were not seen in training. AudioPaLM also demonstrates features of audio language models, such as transferring a voice across languages based on a short spoken prompt.

Google presents AudioPaLM: A Large Language Model That Can Speak and Listen paper page: introduce AudioPaLM, a large language model for speech understanding and generation. AudioPaLM fuses text-based and speech-based language models, PaLM-2 [Anil et al., 2023] and AudioLM [Borsos et al., 2022], into a unified multimodal architecture that can process and generate text and speech with applications including speech recognition and speech-to-speech translation. AudioPaLM inherits the capability to preserve paralinguistic information such as speaker identity and intonation from AudioLM and the linguistic knowledge present only in text large language models such as PaLM-2. We demonstrate that initializing AudioPaLM with the weights of a text-only large language model improves speech processing, successfully leveraging the larger quantity of text training data used in pretraining to assist with the speech tasks. The resulting model significantly outperforms existing systems for speech translation tasks and has the ability to perform zero-shot speech-to-text translation for many languages for which input/target language combinations were not seen in training. AudioPaLM also demonstrates features of audio language models, such as transferring a voice across languages based on a short spoken prompt.

AK

290,517 次观看 • 3 年前

Every wondered if we can model motion as a language? can we tokenize this new language? is it useful? Turns out tremendously! 🚀 In out latest #NeurIPS2024 paper on QueST: Self-Supervised Skill Abstractions for Learning Continuous Control, we find that action tokenization matters a lot! We can learn skill encodings by representing temporal action abstractions with a discrete codebook. This enables 2 things 1. Better Behaviour Cloning: we can better assimilate multi-task data (>9%) over best paper. This is currently best in class BC method! 2. generalization of this language to represent new tasks in 5-shot transfer to longer horizon tasks! Check out the thread by Atharva Mete for more details. And check out more details at: Joint work with Atharva Mete Albert Wilcox Haotian Xue Yongxin Chen Georgia Tech School of Interactive Computing Machine Learning at Georgia Tech Robotics@GT NVIDIA Robotics

Every wondered if we can model motion as a language? can we tokenize this new language? is it useful? Turns out tremendously! 🚀 In out latest #NeurIPS2024 paper on QueST: Self-Supervised Skill Abstractions for Learning Continuous Control, we find that action tokenization matters a lot! We can learn skill encodings by representing temporal action abstractions with a discrete codebook. This enables 2 things 1. Better Behaviour Cloning: we can better assimilate multi-task data (>9%) over best paper. This is currently best in class BC method! 2. generalization of this language to represent new tasks in 5-shot transfer to longer horizon tasks! Check out the thread by Atharva Mete for more details. And check out more details at: Joint work with Atharva Mete Albert Wilcox Haotian Xue Yongxin Chen Georgia Tech School of Interactive Computing Machine Learning at Georgia Tech Robotics@GT NVIDIA Robotics

Animesh Garg

26,218 次观看 • 1 年前

"This city is not only a major infrastructure facility, but overall, Krasnoarmeysk is a good base for solving all SMO tasks. From here, the Russian army can easily move in any direction that the General Staff deems most promising," Putin said.

"This city is not only a major infrastructure facility, but overall, Krasnoarmeysk is a good base for solving all SMO tasks. From here, the Russian army can easily move in any direction that the General Staff deems most promising," Putin said.

Victor vicktop55 commentary

16,813 次观看 • 8 个月前

This week’s Paper Club is all about robotics. Every year for the last decade, someone has promised that the era of robotics is just around the corner. But we’re still waiting. So we gathered a bunch of the top researchers working in AI and robotics to present the latest findings on where we are and what comes next. Thanks to the following presenters: 0:00 – Francois Chaubard: Ten years of “next year, robotics is solved” 7:59 – Marcel Torné: MEM - Multi-Scale Embodied Memory for Vision Language Action Models ( 20:21 – Milan Ganai: Self-Supervised Bootstrapping of Action-Predictive Embodied Reasoning ( 33:42 – Tyler Lum: SimToolReal - An Object-Centric Policy for Zero-Shot Dexterous Tool Manipulation ( 51:21 – Nikolaus West: Why the next great robotics companies will start with teleoperation 1:08:30 – Bill & Guanming Wang (YC P26): World action models and what comes after VLAs

This week’s Paper Club is all about robotics. Every year for the last decade, someone has promised that the era of robotics is just around the corner. But we’re still waiting. So we gathered a bunch of the top researchers working in AI and robotics to present the latest findings on where we are and what comes next. Thanks to the following presenters: 0:00 – Francois Chaubard: Ten years of “next year, robotics is solved” 7:59 – Marcel Torné: MEM - Multi-Scale Embodied Memory for Vision Language Action Models ( 20:21 – Milan Ganai: Self-Supervised Bootstrapping of Action-Predictive Embodied Reasoning ( 33:42 – Tyler Lum: SimToolReal - An Object-Centric Policy for Zero-Shot Dexterous Tool Manipulation ( 51:21 – Nikolaus West: Why the next great robotics companies will start with teleoperation 1:08:30 – Bill & Guanming Wang (YC P26): World action models and what comes after VLAs

Y Combinator

148,571 次观看 • 19 天前

We just brought flow maps to language modeling for one-step sequence generation 💥 Discrete diffusion is not necessary -- continuous flows over one-hot encodings achieve SoTA performance and ≥8.3× faster generation 🔥 We believe this is a major step forward for discrete generative modeling and language modeling alike. 🚀 Full thread from first author Chanhyuk Lee:

We just brought flow maps to language modeling for one-step sequence generation 💥 Discrete diffusion is not necessary -- continuous flows over one-hot encodings achieve SoTA performance and ≥8.3× faster generation 🔥 We believe this is a major step forward for discrete generative modeling and language modeling alike. 🚀 Full thread from first author Chanhyuk Lee:

Nicholas Boffi

44,416 次观看 • 6 个月前

Pretraining is essential for good performance on a wide variety of robotics tasks, and so most vision-language-action models build off of a vision language model (VLM) trained on a wide variety of image-language data. But how does the choice of VLM translate to downstream robotics performance? Jianke Zhang and @GYanjiang join us to talk about this key part of the robot policy, looking at a wide variety of different VLMs and how they perform. Interestingly, they see that performance on auxiliary tasks like quesiton answering did not lead to downstream improvements in control. To learn more, watch episode 65 of RoboPapers now, with Chris Paxton and Jiafei Duan!

Pretraining is essential for good performance on a wide variety of robotics tasks, and so most vision-language-action models build off of a vision language model (VLM) trained on a wide variety of image-language data. But how does the choice of VLM translate to downstream robotics performance? Jianke Zhang and @GYanjiang join us to talk about this key part of the robot policy, looking at a wide variety of different VLMs and how they perform. Interestingly, they see that performance on auxiliary tasks like quesiton answering did not lead to downstream improvements in control. To learn more, watch episode 65 of RoboPapers now, with Chris Paxton and Jiafei Duan!

RoboPapers

23,905 次观看 • 5 个月前

A majority of Californians believe the state is heading in the wrong direction—we need CHANGE! This state’s leadership has failed its people and it’s time for a new direction. Change is coming to California! ☀️

A majority of Californians believe the state is heading in the wrong direction—we need CHANGE! This state’s leadership has failed its people and it’s time for a new direction. Change is coming to California! ☀️

Steve Hilton

41,187 次观看 • 2 个月前

Excited to release PostTrainBench v1.0! This benchmark evaluates the ability of frontier AI agents to post-train language models in a simplified setting. We believe this is a first step toward tracking progress in recursive self-improvement 🧵:

Excited to release PostTrainBench v1.0! This benchmark evaluates the ability of frontier AI agents to post-train language models in a simplified setting. We believe this is a first step toward tracking progress in recursive self-improvement 🧵:

Karina

194,228 次观看 • 5 个月前

Still following your human intuition to mix corpora from different sources for language model pre-training 🧠? Everyone says that data mixture has a big impact on model performance, but how - and why🕵️? Did you know that web corpora are actually highly impactful for downstream tasks 🏆? Let's check out our preprint "RegMix: Data Mixture as Regression for Language Model Pre-training" 📄 🔬In this paper, we've proposed an automatic data mixture method RegMix that achieves a 6.3% improvement over human selection on the widely used HellaSwag benchmark - and it only needs a 2% extra training FLOPs! 📈 Details in the thread 🧵

Still following your human intuition to mix corpora from different sources for language model pre-training 🧠? Everyone says that data mixture has a big impact on model performance, but how - and why🕵️? Did you know that web corpora are actually highly impactful for downstream tasks 🏆? Let's check out our preprint "RegMix: Data Mixture as Regression for Language Model Pre-training" 📄 🔬In this paper, we've proposed an automatic data mixture method RegMix that achieves a 6.3% improvement over human selection on the widely used HellaSwag benchmark - and it only needs a 2% extra training FLOPs! 📈 Details in the thread 🧵

Qian Liu

54,961 次观看 • 2 年前

Humanoids need a single, generalist control policy for all of their physical tasks, not a new one for every new chore or demo. A policy for walking can't dance. A policy for dancing can't support mowing the lawn. We need to scale up humanoid control for diverse behaviors, just like we did with language and video models. Watch this humanoid, supported by a single control policy, to start its day, mow the lawn, jog, dance, and even hold the elevator for a colleague. This is the "System 1" for humanoids—a robust, natural humanoid controller that will support general-purpose autonomy. Project Page: #Robotics #AI #NVIDIA #SONIC #FoundationModel 🤖🔥

Humanoids need a single, generalist control policy for all of their physical tasks, not a new one for every new chore or demo. A policy for walking can't dance. A policy for dancing can't support mowing the lawn. We need to scale up humanoid control for diverse behaviors, just like we did with language and video models. Watch this humanoid, supported by a single control policy, to start its day, mow the lawn, jog, dance, and even hold the elevator for a colleague. This is the "System 1" for humanoids—a robust, natural humanoid controller that will support general-purpose autonomy. Project Page: #Robotics #AI #NVIDIA #SONIC #FoundationModel 🤖🔥

Zhengyi “Zen” Luo

15,948 次观看 • 9 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