Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

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...

animesh_garg's profile picture

Animesh Garg

33,626 subscribers

26,218 Aufrufe • vor 1 Jahr •via X (Twitter)

Wissenschaft & TechnologieBildung#NeurIPS2024
LIVE

Anya Rossi• Live Now

Private livecam show

10 Kommentare

Profilbild von Animesh Garg
Animesh Gargvor 1 Jahr

also a shout out to @LerrelPinto and team for their work on BAKU which is concurrent and equally impressive in terms of thinning the chaff in BC architectures. This is important and their ideas are also very timely. It is exciting to see the field simplify architectures and also simpler latent variable transformer architectures becoming very competitive at multimodal action space modeling.

Profilbild von Animesh Garg
Animesh Gargvor 1 Jahr

Also shout out to @zsoltkira @AlexToshev and team for another learned action tokenizer “…show that a learned tokenization allows for sufficient modeling precision, yielding the best performance on downstream tasks. For discrete actions, we demonstrate that semantically aligning these actions with the native output token space of the MLLM leads to the strongest performance. We arrive at these lessons via a thorough study of seven action space adapters…” Learned action tokenization, combined with simplified transformer architectures is scaling very well I’m so glad to see more activity on this question and that too from my next-door neighbor @zsoltkira

Profilbild von Dr. Angelica Lim @petitegeek.bsky.social
Dr. Angelica Lim @petitegeek.bsky.socialvor 1 Jahr

100% agree! Tokenizing motion as a language also helps for translating language to motion (IROS 2022) We also have relevant work in BC with action tokens coming up at IROS 2024

Profilbild von Animesh Garg
Animesh Gargvor 1 Jahr

thanks for sharing. we will look at it and definitely cite it in the camera ready.

Profilbild von Kaustubh Sridhar
Kaustubh Sridharvor 1 Jahr

Hi @animesh_garg @MeteAtharva , this is a really interesting paper! Just wanted to share our ICLR 24 paper, MCNN which also previously improved over diffusion policy and other BC baselines. Thanks

Profilbild von Ge Yang
Ge Yangvor 1 Jahr

This is really good!

Profilbild von You Jiacheng
You Jiachengvor 1 Jahr

I feel the effectiveness attribution of the causal tokenizer design might be wrong. Since the AR transformer generates the tokens auto-regressively (and causally), it's natural to use a causal tokenizer -- otherwise there is a mismatch.

Profilbild von wildiris
wildirisvor 1 Jahr

This is fantastic. It's exactly what I'm working on in hardware.

Profilbild von Animesh Garg
Animesh Gargvor 1 Jahr

Great to hear that would love to know more how to do that in hardware

Profilbild von Anonymous Deep Learning
Anonymous Deep Learningvor 1 Jahr

Cool but is it really necessary to reduce motion information to a much lower bandwidth information such as language? For humans language is easy to understand but robots can understand trajectories in coordinates. So isn’t language a shortcut here?

Ähnliche Videos

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.
0:48

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 Aufrufe • vor 3 Jahren

Milestone! We (robotic arms for gadgets assembly) finished the first commercial order, which brought the first revenue. Here are some learnings from this: The customer was a smart toy manufacturer. The task was to add a heatsink to Raspberry Pi. We received parts from them and returned the assembled modules back. Currently, it's done by teleoperation. Later it will be done by a remote employee via the Internet. Then it will be automated action by action, reducing the operator's time on this and making the task profitable. ps. If you have an assembly task that we can do for you asynchronically - leave a comment below. Learning 1. It's possible! This task which is usually done by the human arm with 5 fingers can be done with a two-finger gripper with the addition of a couple of simple tooling. The task was not simplified. We peeled off thin films from stickers, unpacked paper boxes, moved PCB boards full of components, etc. And no unsolvable problems have been encountered yet. Challenges: 1) The paper box shifted during the opening Solved with the plastic walls that you can lean against 2) Heat pad, stuck to the gripper instead of heat sync. Can be solved by gripper with a pump, but this time solved with the patience of the operator 3) The film on the pad is very thin. Turned out that sub-millimeter arm precision is enough to peel it off with just a regular gripper. 4) The working area has not enough space. You'll only know this by doing real tasks in bulk. This could be solved by an extra pair of long arms, but in this case, solved with the patience of the operator. I think that in the end, we will have 5-10 types of universal tooling and 5-10 types of grippers to solve almost all the problems in such assembly tasks. Learning 2. It's slow. It took 5 times more time, than doing it with human hands. But the good news is there's a lot of room for improvement. We now have specific “time for task” metrics, which we will decrease with iterations. The main reasons for slowness: 1) To rotate the gripper to a steep angle you are forced to control one robot arm with two hands instead of using both arms. We can fix this by just making more room for rotations. 2) Grabbing PCB board with two arms is hard. A slight difference in rotation can break the board, and it's hard to control these angles visually. To solve this, the best way is to use force feedback so you can feel the pressure applied to the item. 3) Accuracy and steadiness is still can be improved We will try a metal version and double the motors to do this. 4) It is physically difficult for the human hands to move with such precision To solve this, we will add a pad for the hands like in surgical robots Learning 3. It's a good business model The "Factory in the cloud" is a good business model for this stage. You send us parts and we send back assembled modules. Currently, it's more convenient than sending a robot to your place, as we can iterate/fix the robot quickly and utilize it 100% of the time. When we polish the set-up over time - we can send robots to your place. So if we can assemble something for you in the USA with Chinese prices by using modern automation - leave a comment below.
0:48

Milestone! We (robotic arms for gadgets assembly) finished the first commercial order, which brought the first revenue. Here are some learnings from this: The customer was a smart toy manufacturer. The task was to add a heatsink to Raspberry Pi. We received parts from them and returned the assembled modules back. Currently, it's done by teleoperation. Later it will be done by a remote employee via the Internet. Then it will be automated action by action, reducing the operator's time on this and making the task profitable. ps. If you have an assembly task that we can do for you asynchronically - leave a comment below. Learning 1. It's possible! This task which is usually done by the human arm with 5 fingers can be done with a two-finger gripper with the addition of a couple of simple tooling. The task was not simplified. We peeled off thin films from stickers, unpacked paper boxes, moved PCB boards full of components, etc. And no unsolvable problems have been encountered yet. Challenges: 1) The paper box shifted during the opening Solved with the plastic walls that you can lean against 2) Heat pad, stuck to the gripper instead of heat sync. Can be solved by gripper with a pump, but this time solved with the patience of the operator 3) The film on the pad is very thin. Turned out that sub-millimeter arm precision is enough to peel it off with just a regular gripper. 4) The working area has not enough space. You'll only know this by doing real tasks in bulk. This could be solved by an extra pair of long arms, but in this case, solved with the patience of the operator. I think that in the end, we will have 5-10 types of universal tooling and 5-10 types of grippers to solve almost all the problems in such assembly tasks. Learning 2. It's slow. It took 5 times more time, than doing it with human hands. But the good news is there's a lot of room for improvement. We now have specific “time for task” metrics, which we will decrease with iterations. The main reasons for slowness: 1) To rotate the gripper to a steep angle you are forced to control one robot arm with two hands instead of using both arms. We can fix this by just making more room for rotations. 2) Grabbing PCB board with two arms is hard. A slight difference in rotation can break the board, and it's hard to control these angles visually. To solve this, the best way is to use force feedback so you can feel the pressure applied to the item. 3) Accuracy and steadiness is still can be improved We will try a metal version and double the motors to do this. 4) It is physically difficult for the human hands to move with such precision To solve this, we will add a pad for the hands like in surgical robots Learning 3. It's a good business model The "Factory in the cloud" is a good business model for this stage. You send us parts and we send back assembled modules. Currently, it's more convenient than sending a robot to your place, as we can iterate/fix the robot quickly and utilize it 100% of the time. When we polish the set-up over time - we can send robots to your place. So if we can assemble something for you in the USA with Chinese prices by using modern automation - leave a comment below.

Igor Kulakov

37,266 Aufrufe • vor 1 Jahr

We are back. After one year of quiet building. Introducing GENE-26.5, our first robotic brain that takes a major step toward human-level capability. For years, robotics has struggled to learn from the world’s largest and valuable data source: Humans. Solving it means rethinking the whole stack from the ground up: - A robotics-native foundation model. - A 1:1 human-like robotic hand. - A noninvasive data collection glove for motion, force, and touch. - A simulator that turns weeks of experiments into minutes. GENE-26.5 is trained across language, vision, proprioception, tactile, and action. We designed a set of tasks to test how far we can go with this new paradigm. Fully autonomous, 1x speed, one model, same weights. (Enjoy with sound on) We are approaching the endgame for robotics. And this is just a beginning.
3:05

We are back. After one year of quiet building. Introducing GENE-26.5, our first robotic brain that takes a major step toward human-level capability. For years, robotics has struggled to learn from the world’s largest and valuable data source: Humans. Solving it means rethinking the whole stack from the ground up: - A robotics-native foundation model. - A 1:1 human-like robotic hand. - A noninvasive data collection glove for motion, force, and touch. - A simulator that turns weeks of experiments into minutes. GENE-26.5 is trained across language, vision, proprioception, tactile, and action. We designed a set of tasks to test how far we can go with this new paradigm. Fully autonomous, 1x speed, one model, same weights. (Enjoy with sound on) We are approaching the endgame for robotics. And this is just a beginning.

Genesis AI

2,732,380 Aufrufe • vor 3 Monaten

The holy grail of robotics is to be able to perform previously-unseen, out-of-distribution manipulation tasks “zero shot” in a new environment. NovaFlow proposes an approach which (1) generates a video, (2) computes predicted flow — how points move through the scene — and (3) uses this flow as an objective to generate a motion. Using this procedure, NovaFlow generates motions in unseen scenes, for unseen tasks, and can transfer across embodiments. To learn more, we are joined by Hongyu Li and Jiahui Fu from RAI. Watch Episode #63 of RoboPapers with Chris Paxton and Michael Cho - Rbt/Acc now to learn more!
1:08:49

The holy grail of robotics is to be able to perform previously-unseen, out-of-distribution manipulation tasks “zero shot” in a new environment. NovaFlow proposes an approach which (1) generates a video, (2) computes predicted flow — how points move through the scene — and (3) uses this flow as an objective to generate a motion. Using this procedure, NovaFlow generates motions in unseen scenes, for unseen tasks, and can transfer across embodiments. To learn more, we are joined by Hongyu Li and Jiahui Fu from RAI. Watch Episode #63 of RoboPapers with Chris Paxton and Michael Cho - Rbt/Acc now to learn more!

RoboPapers

21,434 Aufrufe • vor 6 Monaten

The robot is learning several novel tasks instantly, after just ONE demonstration each... Instant Policy makes it possible: no extra training, no weight updates, just pure in-context learning. It just got accepted at ICLR 2025, and it’s changing how robots learn. With just a single demo, a robot can pick up a new task and start performing it right away. Why this is a big deal: ✅ Learns tasks instantly with just one or a few demonstrations ✅ Improves over time as more demonstrations are given ✅ Uses simulation-based training with “pseudo-demonstrations” for scalability ✅ Can transfer skills across different robots and even follow language-defined tasks It brings in-context learning to robotics, opening up new possibilities for flexible, real-world automation. You can try it yourself: code and weights are available at • • • • Thank you to Edward Johns, Director of the Robot Learning Lab at Imperial College for sharing their work! 🙏
0:50

The robot is learning several novel tasks instantly, after just ONE demonstration each... Instant Policy makes it possible: no extra training, no weight updates, just pure in-context learning. It just got accepted at ICLR 2025, and it’s changing how robots learn. With just a single demo, a robot can pick up a new task and start performing it right away. Why this is a big deal: ✅ Learns tasks instantly with just one or a few demonstrations ✅ Improves over time as more demonstrations are given ✅ Uses simulation-based training with “pseudo-demonstrations” for scalability ✅ Can transfer skills across different robots and even follow language-defined tasks It brings in-context learning to robotics, opening up new possibilities for flexible, real-world automation. You can try it yourself: code and weights are available at • • • • Thank you to Edward Johns, Director of the Robot Learning Lab at Imperial College for sharing their work! 🙏

Ilir Aliu

46,285 Aufrufe • vor 1 Jahr

Excited to finally share Generative Value Learning (GVL), my Google DeepMind project on extracting universal value functions from long-context VLMs via in-context learning! We discovered a simple method to generate zero-shot and few-shot values for 300+ robot tasks and 50+ datasets using SOTA VLMs like Gemini (Try out the demo on our website on your robot video today!) I worked a lot on leveraging foundation models as guidance for robots in my PhD, and to me, this result forges a new frontier in how we can use foundation models for robot learning, given its broad applicability independent of embodiment and task types. Quite excited about how we can build on this work as a community!
0:32

Excited to finally share Generative Value Learning (GVL), my Google DeepMind project on extracting universal value functions from long-context VLMs via in-context learning! We discovered a simple method to generate zero-shot and few-shot values for 300+ robot tasks and 50+ datasets using SOTA VLMs like Gemini (Try out the demo on our website on your robot video today!) I worked a lot on leveraging foundation models as guidance for robots in my PhD, and to me, this result forges a new frontier in how we can use foundation models for robot learning, given its broad applicability independent of embodiment and task types. Quite excited about how we can build on this work as a community!

Jason Ma

98,090 Aufrufe • vor 1 Jahr

Modern AI is confined to the digital world. At Skild AI, we are building towards AGI for the real world, unconstrained by robot type or task — a single, omni-bodied brain. Today, we are sharing our journey, starting with early milestones, with more to come in the weeks ahead. Our Mission: Artificial General Intelligence grounded in the physical world. We believe AGI that can truly understand and reason in the real world can only be built through grounding in the physical world. Our Vision: Any robot, Any task, One brain. We tackle robotics in its full generality – building a continually improving, omni-bodied brain that can control any hardware for any task. Who are we? A passionate group of scientists & engineers driven by our shared vision. We have been researching AI and robotics for more than a decade. Our team includes pioneers of self-supervised learning, curiosity-driven exploration, end-to-end sim2real for visual locomotion, dexterous manipulation, learning from human videos, robot parkour, and many more. Many of these works have won awards at top-tier AI and Robotics conferences. Our team has also built production-ready systems at Anduril, Tesla, Nvidia, Meta, Kitty Hawk, Google, Everyday Robotics, and Amazon. Join us in our mission to build the robot brains of tomorrow.
2:48

Modern AI is confined to the digital world. At Skild AI, we are building towards AGI for the real world, unconstrained by robot type or task — a single, omni-bodied brain. Today, we are sharing our journey, starting with early milestones, with more to come in the weeks ahead. Our Mission: Artificial General Intelligence grounded in the physical world. We believe AGI that can truly understand and reason in the real world can only be built through grounding in the physical world. Our Vision: Any robot, Any task, One brain. We tackle robotics in its full generality – building a continually improving, omni-bodied brain that can control any hardware for any task. Who are we? A passionate group of scientists & engineers driven by our shared vision. We have been researching AI and robotics for more than a decade. Our team includes pioneers of self-supervised learning, curiosity-driven exploration, end-to-end sim2real for visual locomotion, dexterous manipulation, learning from human videos, robot parkour, and many more. Many of these works have won awards at top-tier AI and Robotics conferences. Our team has also built production-ready systems at Anduril, Tesla, Nvidia, Meta, Kitty Hawk, Google, Everyday Robotics, and Amazon. Join us in our mission to build the robot brains of tomorrow.

Skild AI

383,840 Aufrufe • vor 1 Jahr

How do you give a humanoid the general motion capability? Not just single motions, but all motion? Introducing SONIC, our new work on supersizing motion tracking for natural humanoid control. We argue that motion tracking is the scalable foundation task for humanoids. So we "supersized" it: 9k+ GPU hours and 100M+ motion frames. But tracking alone is not enough; we show how to make a useful control system out of it: - Universal Kinematic Planner: Enables game-like gamepad control and high-level teleoperation, just like controlling a character in a game. - VR Full-Body Teleop: Direct, real-time whole-body control by a human wearing a VR headset. - VR Keypoint Teleop: Control the upper body (hands/head) while our planner handles robust locomotion automatically. - VLA Integration: We connect this motion tracker to autonomous Visual-Language-Action (VLA) models for autonomous task execution! We use a Universal Token Space to UNIFY this command space, turning our robust tracker into a general-purpose, programmable humanoid brain. This is the generalist "System 1" for humanoids. 🚀 Project: #Humanoids #Robotics #AI #FoundationModels #NVIDIAResearch 🧠🔥
1:32

How do you give a humanoid the general motion capability? Not just single motions, but all motion? Introducing SONIC, our new work on supersizing motion tracking for natural humanoid control. We argue that motion tracking is the scalable foundation task for humanoids. So we "supersized" it: 9k+ GPU hours and 100M+ motion frames. But tracking alone is not enough; we show how to make a useful control system out of it: - Universal Kinematic Planner: Enables game-like gamepad control and high-level teleoperation, just like controlling a character in a game. - VR Full-Body Teleop: Direct, real-time whole-body control by a human wearing a VR headset. - VR Keypoint Teleop: Control the upper body (hands/head) while our planner handles robust locomotion automatically. - VLA Integration: We connect this motion tracker to autonomous Visual-Language-Action (VLA) models for autonomous task execution! We use a Universal Token Space to UNIFY this command space, turning our robust tracker into a general-purpose, programmable humanoid brain. This is the generalist "System 1" for humanoids. 🚀 Project: #Humanoids #Robotics #AI #FoundationModels #NVIDIAResearch 🧠🔥

Zhengyi “Zen” Luo

62,399 Aufrufe • vor 9 Monaten

3D-LLM: Injecting the 3D World into Large Language Models paper page: Large language models (LLMs) and Vision-Language Models (VLMs) have been proven to excel at multiple tasks, such as commonsense reasoning. Powerful as these models can be, they are not grounded in the 3D physical world, which involves richer concepts such as spatial relationships, affordances, physics, layout, and so on. In this work, we propose to inject the 3D world into large language models and introduce a whole new family of 3D-LLMs. Specifically, 3D-LLMs can take 3D point clouds and their features as input and perform a diverse set of 3D-related tasks, including captioning, dense captioning, 3D question answering, task decomposition, 3D grounding, 3D-assisted dialog, navigation, and so on. Using three types of prompting mechanisms that we design, we are able to collect over 300k 3D-language data covering these tasks. To efficiently train 3D-LLMs, we first utilize a 3D feature extractor that obtains 3D features from rendered multi- view images. Then, we use 2D VLMs as our backbones to train our 3D-LLMs. By introducing a 3D localization mechanism, 3D-LLMs can better capture 3D spatial information. Experiments on ScanQA show that our model outperforms state-of-the-art baselines by a large margin (e.g., the BLEU-1 score surpasses state-of-the-art score by 9%). Furthermore, experiments on our held-in datasets for 3D captioning, task composition, and 3D-assisted dialogue show that our model outperforms 2D VLMs. Qualitative examples also show that our model could perform more tasks beyond the scope of existing LLMs and VLMs.
0:50

3D-LLM: Injecting the 3D World into Large Language Models paper page: Large language models (LLMs) and Vision-Language Models (VLMs) have been proven to excel at multiple tasks, such as commonsense reasoning. Powerful as these models can be, they are not grounded in the 3D physical world, which involves richer concepts such as spatial relationships, affordances, physics, layout, and so on. In this work, we propose to inject the 3D world into large language models and introduce a whole new family of 3D-LLMs. Specifically, 3D-LLMs can take 3D point clouds and their features as input and perform a diverse set of 3D-related tasks, including captioning, dense captioning, 3D question answering, task decomposition, 3D grounding, 3D-assisted dialog, navigation, and so on. Using three types of prompting mechanisms that we design, we are able to collect over 300k 3D-language data covering these tasks. To efficiently train 3D-LLMs, we first utilize a 3D feature extractor that obtains 3D features from rendered multi- view images. Then, we use 2D VLMs as our backbones to train our 3D-LLMs. By introducing a 3D localization mechanism, 3D-LLMs can better capture 3D spatial information. Experiments on ScanQA show that our model outperforms state-of-the-art baselines by a large margin (e.g., the BLEU-1 score surpasses state-of-the-art score by 9%). Furthermore, experiments on our held-in datasets for 3D captioning, task composition, and 3D-assisted dialogue show that our model outperforms 2D VLMs. Qualitative examples also show that our model could perform more tasks beyond the scope of existing LLMs and VLMs.

AK

249,798 Aufrufe • vor 3 Jahren

Introducing EdgeBench, a benchmark designed to study how agents learn from environments over at least 12~72-hour runs. We find that performance follows a log-sigmoid function of environment interaction time with high precision. EdgeBench is built with three ingredients: - 🌍 Real & Diverse: 134 real-world tasks across 6 task categories, spanning scientific problems, professional knowledge work, software engineering, optimization, formal math, and games. - ⏳ Ultra-Long-Horizon: Each task supports 12–72 hours of agent work. Recorded human effort averages 57.2 hours. - 🔁 Informative Feedback: Agents receive real-world feedback for continuous improvement. After 38,000 hours of agent runs on EdgeBench, a scaling law for learning from environments emerges: - 📈 As agents interact with task environments over time, their aggregate performance is precisely fit by a log-sigmoid function. - 🧠 This phenomenon can be explained by an elegant theory of graph exploration. We are releasing an initial 51 of the 134 tasks, together with the full evaluation framework, to help advance long-horizon agent research. Check our blog & paper for more findings! Blog Paper GitHub Dataset Details below 👇🧵
0:52

Introducing EdgeBench, a benchmark designed to study how agents learn from environments over at least 12~72-hour runs. We find that performance follows a log-sigmoid function of environment interaction time with high precision. EdgeBench is built with three ingredients: - 🌍 Real & Diverse: 134 real-world tasks across 6 task categories, spanning scientific problems, professional knowledge work, software engineering, optimization, formal math, and games. - ⏳ Ultra-Long-Horizon: Each task supports 12–72 hours of agent work. Recorded human effort averages 57.2 hours. - 🔁 Informative Feedback: Agents receive real-world feedback for continuous improvement. After 38,000 hours of agent runs on EdgeBench, a scaling law for learning from environments emerges: - 📈 As agents interact with task environments over time, their aggregate performance is precisely fit by a log-sigmoid function. - 🧠 This phenomenon can be explained by an elegant theory of graph exploration. We are releasing an initial 51 of the 134 tasks, together with the full evaluation framework, to help advance long-horizon agent research. Check our blog & paper for more findings! Blog Paper GitHub Dataset Details below 👇🧵

Deyao Zhu

361,860 Aufrufe • vor 1 Monat

Creator of C#, Anders Hejlsberg(Anders Hejlsberg), on the design goals that shaped the language and why standardisation was a goal from the beginning: “The overarching thing was this power and productivity of C++ with the ease of use of Visual Basic. We knew we wanted to build an object oriented language. We wanted managed code or byte code so we could target different runtime environments. We wanted garbage collection and exception handling, but also things like a unified object system where, and that's true in C#, anything can be assigned to an object. If it's a value type, we box it. And it's a self-describing object. So, reflection: you can ask an object, ‘what are you’? And you can get all of the facts about it at runtime, and you can dynamically manipulate it in ways that just don't exist in a lot of other environments. We wanted a language that made this new model of properties, methods and events first class because that was how components were built as opposed to just sort of functions and procedures and even objects. And we wanted to create a language that was standardised. We wanted to give this language to a standardisation committee and try to level the playing field there. And all of those things were sort of like what was rolled up in C#”
1:43

Creator of C#, Anders Hejlsberg(Anders Hejlsberg), on the design goals that shaped the language and why standardisation was a goal from the beginning: “The overarching thing was this power and productivity of C++ with the ease of use of Visual Basic. We knew we wanted to build an object oriented language. We wanted managed code or byte code so we could target different runtime environments. We wanted garbage collection and exception handling, but also things like a unified object system where, and that's true in C#, anything can be assigned to an object. If it's a value type, we box it. And it's a self-describing object. So, reflection: you can ask an object, ‘what are you’? And you can get all of the facts about it at runtime, and you can dynamically manipulate it in ways that just don't exist in a lot of other environments. We wanted a language that made this new model of properties, methods and events first class because that was how components were built as opposed to just sort of functions and procedures and even objects. And we wanted to create a language that was standardised. We wanted to give this language to a standardisation committee and try to level the playing field there. And all of those things were sort of like what was rolled up in C#”

The Pragmatic Engineer

18,332 Aufrufe • vor 3 Monaten

Introducing VL-JEPA: Vision-Language Joint Embedding Predictive Architecture for streaming, live action recognition, retrieval, VQA, and classification tasks with better performance and higher efficiency than large VLMs. • VL-JEPA is the first non-generative model that can perform general-domain vision-language tasks in real-time, built on a joint embedding predictive architecture. • We demonstrate in controlled experiments that VL-JEPA, trained with latent space embedding prediction, outperforms VLMs that rely on data space token prediction. • We show that VL-JEPA delivers significant efficiency gains over VLMs for online video streaming applications, thanks to its non-autoregressive design and native support for selective decoding. • We highlight that our VL-JEPA model, with an unified model architecture, can effectively handle a wide range of classification, retrieval, and VQA tasks at the same time. by Delong Chen (陈德龙) Mustafa Shukor Théo Moutakanni Willy Jade Lei Yu Tejaswi Kasarla Allen Bolourchi Yann LeCun Pascale Fung
1:51

Introducing VL-JEPA: Vision-Language Joint Embedding Predictive Architecture for streaming, live action recognition, retrieval, VQA, and classification tasks with better performance and higher efficiency than large VLMs. • VL-JEPA is the first non-generative model that can perform general-domain vision-language tasks in real-time, built on a joint embedding predictive architecture. • We demonstrate in controlled experiments that VL-JEPA, trained with latent space embedding prediction, outperforms VLMs that rely on data space token prediction. • We show that VL-JEPA delivers significant efficiency gains over VLMs for online video streaming applications, thanks to its non-autoregressive design and native support for selective decoding. • We highlight that our VL-JEPA model, with an unified model architecture, can effectively handle a wide range of classification, retrieval, and VQA tasks at the same time. by Delong Chen (陈德龙) Mustafa Shukor Théo Moutakanni Willy Jade Lei Yu Tejaswi Kasarla Allen Bolourchi Yann LeCun Pascale Fung

Pascale Fung

90,144 Aufrufe • vor 8 Monaten

Multi-Track Timeline Control for Text-Driven 3D Human Motion Generation paper page: Recent advances in generative modeling have led to promising progress on synthesizing 3D human motion from text, with methods that can generate character animations from short prompts and specified durations. However, using a single text prompt as input lacks the fine-grained control needed by animators, such as composing multiple actions and defining precise durations for parts of the motion. To address this, we introduce the new problem of timeline control for text-driven motion synthesis, which provides an intuitive, yet fine-grained, input interface for users. Instead of a single prompt, users can specify a multi-track timeline of multiple prompts organized in temporal intervals that may overlap. This enables specifying the exact timings of each action and composing multiple actions in sequence or at overlapping intervals. To generate composite animations from a multi-track timeline, we propose a new test-time denoising method. This method can be integrated with any pre-trained motion diffusion model to synthesize realistic motions that accurately reflect the timeline. At every step of denoising, our method processes each timeline interval (text prompt) individually, subsequently aggregating the predictions with consideration for the specific body parts engaged in each action. Experimental comparisons and ablations validate that our method produces realistic motions that respect the semantics and timing of given text prompts.
0:21

Multi-Track Timeline Control for Text-Driven 3D Human Motion Generation paper page: Recent advances in generative modeling have led to promising progress on synthesizing 3D human motion from text, with methods that can generate character animations from short prompts and specified durations. However, using a single text prompt as input lacks the fine-grained control needed by animators, such as composing multiple actions and defining precise durations for parts of the motion. To address this, we introduce the new problem of timeline control for text-driven motion synthesis, which provides an intuitive, yet fine-grained, input interface for users. Instead of a single prompt, users can specify a multi-track timeline of multiple prompts organized in temporal intervals that may overlap. This enables specifying the exact timings of each action and composing multiple actions in sequence or at overlapping intervals. To generate composite animations from a multi-track timeline, we propose a new test-time denoising method. This method can be integrated with any pre-trained motion diffusion model to synthesize realistic motions that accurately reflect the timeline. At every step of denoising, our method processes each timeline interval (text prompt) individually, subsequently aggregating the predictions with consideration for the specific body parts engaged in each action. Experimental comparisons and ablations validate that our method produces realistic motions that respect the semantics and timing of given text prompts.

AK

126,612 Aufrufe • vor 2 Jahren

Synchronize Dual Hands for Physics-Based Dexterous Guitar Playing discuss: We present a novel approach to synthesize dexterous motions for physically simulated hands in tasks that require coordination between the control of two hands with high temporal precision. Instead of directly learning a joint policy to control two hands, our approach performs bimanual control through cooperative learning where each hand is treated as an individual agent. The individual policies for each hand are first trained separately, and then synchronized through latent space manipulation in a centralized environment to serve as a joint policy for two-hand control. By doing so, we avoid directly performing policy learning in the joint state-action space of two hands with higher dimensions, greatly improving the overall training efficiency. We demonstrate the effectiveness of our proposed approach in the challenging guitar-playing task. The virtual guitarist trained by our approach can synthesize motions from unstructured reference data of general guitar-playing practice motions, and accurately play diverse rhythms with complex chord pressing and string picking patterns based on the input guitar tabs that do not exist in the references. Along with this paper, we provide the motion capture data that we collected as the reference for policy training.
6:21

Synchronize Dual Hands for Physics-Based Dexterous Guitar Playing discuss: We present a novel approach to synthesize dexterous motions for physically simulated hands in tasks that require coordination between the control of two hands with high temporal precision. Instead of directly learning a joint policy to control two hands, our approach performs bimanual control through cooperative learning where each hand is treated as an individual agent. The individual policies for each hand are first trained separately, and then synchronized through latent space manipulation in a centralized environment to serve as a joint policy for two-hand control. By doing so, we avoid directly performing policy learning in the joint state-action space of two hands with higher dimensions, greatly improving the overall training efficiency. We demonstrate the effectiveness of our proposed approach in the challenging guitar-playing task. The virtual guitarist trained by our approach can synthesize motions from unstructured reference data of general guitar-playing practice motions, and accurately play diverse rhythms with complex chord pressing and string picking patterns based on the input guitar tabs that do not exist in the references. Along with this paper, we provide the motion capture data that we collected as the reference for policy training.

AK

26,855 Aufrufe • vor 1 Jahr

Today we are excited to open up Neuracore to the academic community! Neuracore is a new data foundation built to accelerate robot learning by removing one of the field’s biggest bottlenecks: capturing and working with high-fidelity multimodal robotics data. For the first time, researchers can store, view, and work with robotics data in a cloud-native system built specifically for large-scale learning, and we are making this core platform completely free for academia. The platform lets teams capture every sensor at its native rate, store and visualize data without loss, and then train and deploy models locally using our open-source code (Link in the comments). We are rolling out access to select academic institutions first. Anyone with an academic email can sign up, and if your institution is not part of the initial rollout, you will be able to join the waitlist directly. Beyond providing this infrastructure, we see an opportunity to build a global community where engineers and researchers can share, collaborate, and advance the frontier of robot learning together. Supported by our recent $3M pre-seed round led by Earlybird VC, we are excited to take this mission even further. Our long-term goal is for Neuracore to become the natural home for cutting-edge robot learning algorithms and real-world robotics experimentation, helping accelerate the next wave of Physical AI.
1:00

Today we are excited to open up Neuracore to the academic community! Neuracore is a new data foundation built to accelerate robot learning by removing one of the field’s biggest bottlenecks: capturing and working with high-fidelity multimodal robotics data. For the first time, researchers can store, view, and work with robotics data in a cloud-native system built specifically for large-scale learning, and we are making this core platform completely free for academia. The platform lets teams capture every sensor at its native rate, store and visualize data without loss, and then train and deploy models locally using our open-source code (Link in the comments). We are rolling out access to select academic institutions first. Anyone with an academic email can sign up, and if your institution is not part of the initial rollout, you will be able to join the waitlist directly. Beyond providing this infrastructure, we see an opportunity to build a global community where engineers and researchers can share, collaborate, and advance the frontier of robot learning together. Supported by our recent $3M pre-seed round led by Earlybird VC, we are excited to take this mission even further. Our long-term goal is for Neuracore to become the natural home for cutting-edge robot learning algorithms and real-world robotics experimentation, helping accelerate the next wave of Physical AI.

Neuracore

40,796 Aufrufe • vor 9 Monaten

COACHES — STOP SCROLLING 🚨🚨 This post is worth reading (and re-reading). 📌 Pep Guardiola on what still keeps him motivated, obsessed, and excited to come in every single day — now and in the future 👇 “There’s one thing I’ve always done as a manager. Watch our last game. Spend 2–3 hours. Watch frame-by-frame, clip-by-clip, action-by-action. Every action from the opponents and ourselves. To see what we can improve. And I see ‘oh, there is a pattern we have to improve’. That makes me wake up in the morning: ‘Okay, this is what we have to work on so the team will be better.’I have to visualise the team will be better. ‘When we do that, we will be more solid, more consistent, create more chances, concede less, win more games.’In terms of football, we can do better. The moment I feel it’s done — I can’t squeeze more out of the players, I don’t visualize I can do better — I’ll go home.” This is the mindset. 👉 Curiosity. 👉 Relentless reflection. 👉 The belief that there is always another level.
1:11

COACHES — STOP SCROLLING 🚨🚨 This post is worth reading (and re-reading). 📌 Pep Guardiola on what still keeps him motivated, obsessed, and excited to come in every single day — now and in the future 👇 “There’s one thing I’ve always done as a manager. Watch our last game. Spend 2–3 hours. Watch frame-by-frame, clip-by-clip, action-by-action. Every action from the opponents and ourselves. To see what we can improve. And I see ‘oh, there is a pattern we have to improve’. That makes me wake up in the morning: ‘Okay, this is what we have to work on so the team will be better.’I have to visualise the team will be better. ‘When we do that, we will be more solid, more consistent, create more chances, concede less, win more games.’In terms of football, we can do better. The moment I feel it’s done — I can’t squeeze more out of the players, I don’t visualize I can do better — I’ll go home.” This is the mindset. 👉 Curiosity. 👉 Relentless reflection. 👉 The belief that there is always another level.

Keepitonthedeck

37,049 Aufrufe • vor 8 Monaten

For the first time in human history, we are teaching a Foundation Model to master the diverse tasks of medicinal chemists, biologists, and computational scientists all in one place. In our latest collaboration with Liquid AI, we are moving away from fragmented, specialized tools toward a single, super-intelligent model. What surprised me most? This model isn't just performing at reasonable levels—it has started outperforming specialist models across physics-based tasks, imaging, and longitudinal data. Why this changes everything: -Synergy over Specialization: Fine-tuning on specific tasks has unlocked unexpected capabilities in synergetic areas, opening a new frontier in multimodal AI research. -Zero-Shot Potential: We are building a model that can perform out-of-scope tasks, moving us closer to an "AI deity" for drug discovery. -Quality First: The goal isn't just to bypass regulations to save time; it’s about using these synergies to develop better, more effective drugs. We are no longer just looking at linear regression or simple text; we are looking at the future of how humanity fights disease. #LiquidAI #InsilicoMedicine #GenerativeAI #DrugDiscovery #DeepTech #BiotechInnovation
1:53

For the first time in human history, we are teaching a Foundation Model to master the diverse tasks of medicinal chemists, biologists, and computational scientists all in one place. In our latest collaboration with Liquid AI, we are moving away from fragmented, specialized tools toward a single, super-intelligent model. What surprised me most? This model isn't just performing at reasonable levels—it has started outperforming specialist models across physics-based tasks, imaging, and longitudinal data. Why this changes everything: -Synergy over Specialization: Fine-tuning on specific tasks has unlocked unexpected capabilities in synergetic areas, opening a new frontier in multimodal AI research. -Zero-Shot Potential: We are building a model that can perform out-of-scope tasks, moving us closer to an "AI deity" for drug discovery. -Quality First: The goal isn't just to bypass regulations to save time; it’s about using these synergies to develop better, more effective drugs. We are no longer just looking at linear regression or simple text; we are looking at the future of how humanity fights disease. #LiquidAI #InsilicoMedicine #GenerativeAI #DrugDiscovery #DeepTech #BiotechInnovation

Alex Zhavoronkov, PhD (aka Aleksandrs Zavoronkovs)

10,544 Aufrufe • vor 4 Monaten

For decades, we’ve dreamed of robots that can seamlessly step into our world and lend a hand. Today, we take a major stride toward making that dream a reality: Introducing Gemini Robotics 2 from Google DeepMind, the intelligence layer powering the next generation of truly adaptable robots. This major advance unlocks intelligent whole-body control, advanced dexterity, and even multi-robot collaboration 🤯. Ok but... how does a robot actually "think"? Real-world tasks take time and planning. To manage that complexity, our new embodied reasoning model, Gemini Robotics ER 2, acts as the robot’s high-level brain, enhancing the robot’s capabilities to: — Observe the environment — Reason about the actions needed to complete the task — Coordinate with the vision-language-action model to carry out actions — Track progress until the job is done This setup allows robots to execute complex multi-step workflows, self-correct if a step fails, and adapt to completely novel situations. Learn more about Gemini Robotics ER 2 (and our two other brand new models) here:
2:16

For decades, we’ve dreamed of robots that can seamlessly step into our world and lend a hand. Today, we take a major stride toward making that dream a reality: Introducing Gemini Robotics 2 from Google DeepMind, the intelligence layer powering the next generation of truly adaptable robots. This major advance unlocks intelligent whole-body control, advanced dexterity, and even multi-robot collaboration 🤯. Ok but... how does a robot actually "think"? Real-world tasks take time and planning. To manage that complexity, our new embodied reasoning model, Gemini Robotics ER 2, acts as the robot’s high-level brain, enhancing the robot’s capabilities to: — Observe the environment — Reason about the actions needed to complete the task — Coordinate with the vision-language-action model to carry out actions — Track progress until the job is done This setup allows robots to execute complex multi-step workflows, self-correct if a step fails, and adapt to completely novel situations. Learn more about Gemini Robotics ER 2 (and our two other brand new models) here:

Google AI

701,925 Aufrufe • vor 28 Tagen

Chinese robotics company Astribot released their latest World-Action Model (WAM), Lumo-2. Technical breakdown: - based on a frozen 🥶 Qwen-3.5 4B VLM - trained in 3 progressive stages: 1. Action is aligned with latent world dynamics (an abstract representation of action). Real-world actions are anchored to physical constraints, while the latent space is guided to focus on motion-relevant changes. This bidirectional relationship makes the model physically grounded -> critical for a world model. 2. Action is aligned with vision and language. Reusing the vision backbone and action encoder from the frozen VLM, the authors add a custom vocabulary (for new actions), a semantic module, an action decoder, and an action projector. This aligns the (new) action representations with the (existing) vision-language semantic space. Most importantly: it builds a direct mapping from natural-language instructions to motor execution. 3. End-to-end training on language, video, and robot data. Only the new modules (everything outside the frozen backbone) are trained end-to-end across temporal reasoning, physical understanding, long-horizon, and dexterous manipulation. At the end of the day, Lumo-2 is not the best on benchmarks, but that's not the point. What's genuinely new: - a way to combine latent world modeling and action generation through progressive alignment - a physically-grounded latent dynamics space - it lifts performance on unseen objects using un-annotated human egocentric video + Vision Pro captures, no special transfer algorithm needed Why it matters: - the whole model is thin trainable adapters (semantic module, action decoder/projector) on a frozen 4B backbone (cheap) - that scale is suited for real-time embedded inference (~2.71× decode speedup, no accuracy loss) - its real moat is long-horizon execution, where the added temporal memory pays off far more than on any other task As a result, this robot can now make your latte (5x sped up video):
0:39

Chinese robotics company Astribot released their latest World-Action Model (WAM), Lumo-2. Technical breakdown: - based on a frozen 🥶 Qwen-3.5 4B VLM - trained in 3 progressive stages: 1. Action is aligned with latent world dynamics (an abstract representation of action). Real-world actions are anchored to physical constraints, while the latent space is guided to focus on motion-relevant changes. This bidirectional relationship makes the model physically grounded -> critical for a world model. 2. Action is aligned with vision and language. Reusing the vision backbone and action encoder from the frozen VLM, the authors add a custom vocabulary (for new actions), a semantic module, an action decoder, and an action projector. This aligns the (new) action representations with the (existing) vision-language semantic space. Most importantly: it builds a direct mapping from natural-language instructions to motor execution. 3. End-to-end training on language, video, and robot data. Only the new modules (everything outside the frozen backbone) are trained end-to-end across temporal reasoning, physical understanding, long-horizon, and dexterous manipulation. At the end of the day, Lumo-2 is not the best on benchmarks, but that's not the point. What's genuinely new: - a way to combine latent world modeling and action generation through progressive alignment - a physically-grounded latent dynamics space - it lifts performance on unseen objects using un-annotated human egocentric video + Vision Pro captures, no special transfer algorithm needed Why it matters: - the whole model is thin trainable adapters (semantic module, action decoder/projector) on a frozen 4B backbone (cheap) - that scale is suited for real-time embedded inference (~2.71× decode speedup, no accuracy loss) - its real moat is long-horizon execution, where the added temporal memory pays off far more than on any other task As a result, this robot can now make your latte (5x sped up video):

Léo

32,296 Aufrufe • vor 1 Monat

The DeepSeek-R1 paper is a gem! Highly encourage everyone to read it. It's clear that LLM reasoning capabilities can be learned in different ways. RL, if applied correctly and at scale, can lead to some really powerful and interesting scaling and emergent properties. There is more to RL than meets the eye! Here is my breakdown of the paper along with a few tests: The multi-state training might not make sense initially but they provide clues on optimizations that we can continue to tap into. Data quality is still very important for enhancing the usability of the LLM. Unlike other reasoning LLMs, DeepSeek-R1's training recipe and weights are open so we can build on top of it. This opens up exciting research opportunities. About the attached clip: the previous preview model wasn't able to solve this task. DeepSeek-R1 can solve this and many other tasks that o1 can solve. It's a very good model for coding and math.
1:57

The DeepSeek-R1 paper is a gem! Highly encourage everyone to read it. It's clear that LLM reasoning capabilities can be learned in different ways. RL, if applied correctly and at scale, can lead to some really powerful and interesting scaling and emergent properties. There is more to RL than meets the eye! Here is my breakdown of the paper along with a few tests: The multi-state training might not make sense initially but they provide clues on optimizations that we can continue to tap into. Data quality is still very important for enhancing the usability of the LLM. Unlike other reasoning LLMs, DeepSeek-R1's training recipe and weights are open so we can build on top of it. This opens up exciting research opportunities. About the attached clip: the previous preview model wasn't able to solve this task. DeepSeek-R1 can solve this and many other tasks that o1 can solve. It's a very good model for coding and math.

elvis

140,692 Aufrufe • vor 1 Jahr