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。

Catching a flying ball is hard. What if with a flat plate? 🏓 Our work at RSS’26 shows it’s possible through Zero-Shot Sim2Real With Domain-Randomized Instance Set (DRIS), we catches different kinds of balls without any real-world fine-tuning 🔗

Vector Wang

2,229 subscribers

68,730 次观看 • 3 个月前 •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

🤖What if a robot could perform a new task just from a natural language command, with zero demonstrations? Our new work, NovaFlow, makes it possible! We use pre-trained video generative model to create a video of the task, then translate it into a plan for real-world robot execution. 1/6 #Robotics #AI #ZeroShot #Manipulation

🤖What if a robot could perform a new task just from a natural language command, with zero demonstrations? Our new work, NovaFlow, makes it possible! We use pre-trained video generative model to create a video of the task, then translate it into a plan for real-world robot execution. 1/6 #Robotics #AI #ZeroShot #Manipulation

Hongyu Li

105,669 次观看 • 10 个月前

Spatial understanding is important to moving around in complex environments and is a huge part of the challenge of generalizing to new scenes. Most world models, however, largely ignore this spatial dimension, focusing on 2D images. Not PointWorld, though. PointWorld is a 3D world model trained from real and simulated data which can perform a wide variety of manipulation tasks on a real robot, including grasping or handling articulated objects, all without any additional fine tuning. Wenlong Huang joins us to tell us more about what makes this work and how it’s different from other world models. Watch Episode #83 of RoboPapers, with Chris Paxton and Jiafei Duan, to learn more!

Spatial understanding is important to moving around in complex environments and is a huge part of the challenge of generalizing to new scenes. Most world models, however, largely ignore this spatial dimension, focusing on 2D images. Not PointWorld, though. PointWorld is a 3D world model trained from real and simulated data which can perform a wide variety of manipulation tasks on a real robot, including grasping or handling articulated objects, all without any additional fine tuning. Wenlong Huang joins us to tell us more about what makes this work and how it’s different from other world models. Watch Episode #83 of RoboPapers, with Chris Paxton and Jiafei Duan, to learn more!

RoboPapers

16,197 次观看 • 2 个月前

It's no secret that Michael Bay likes to shoot his films with as much practical effects as possible. In #Transformers (2007) there is a shot where Optimus Prime and Megatron crash through a building, this shot was done practically using a miniature at 1/4 scale by ILM. Doing this shot practically allowed them to get the randomness of the destruction without having to do expensive simulations. The CG robots were then added into the shot to merge the photographic plate with the CG elements. When doing live-action films, it is always a good idea to shoot physically as much as possible. This provides the VFX artists with real world reference to ground their work in and allows them to compliment the shot with CG elements. One of the reasons the original Transformers trilogy looks so good is because of the incredible blend of practical and digital effects. It is difficult to watch the film and spot what is real and what is CG. ILM VFX Supervisor Scott Farrar talks through how this scene was pulled off:

It's no secret that Michael Bay likes to shoot his films with as much practical effects as possible. In #Transformers (2007) there is a shot where Optimus Prime and Megatron crash through a building, this shot was done practically using a miniature at 1/4 scale by ILM. Doing this shot practically allowed them to get the randomness of the destruction without having to do expensive simulations. The CG robots were then added into the shot to merge the photographic plate with the CG elements. When doing live-action films, it is always a good idea to shoot physically as much as possible. This provides the VFX artists with real world reference to ground their work in and allows them to compliment the shot with CG elements. One of the reasons the original Transformers trilogy looks so good is because of the incredible blend of practical and digital effects. It is difficult to watch the film and spot what is real and what is CG. ILM VFX Supervisor Scott Farrar talks through how this scene was pulled off:

Rassoul Edji

513,295 次观看 • 1 年前

This work is not about a new technique. GMT (General Motion Tracking) shows good engineering practices that you can actually train a single unified whole-body control policy for all agile motion, and it works in the real world, directly with sim2real without adaptation. This is different from many existing works that trains/adapts one individual policy for each specific motion. Instead of just showing the beautiful motions/dances, this is actually practical. Because now you can convert all types of commands into real actions in real time without tuning anything. Visit to check out how we handle the following challenges: ✅ Partial Observability. ✅ Hardware Limitations. ✅ Unbalanced Data Distribution. ✅ Model Expressiveness. Work led by Zixuan Chen Mazeyu Ji

This work is not about a new technique. GMT (General Motion Tracking) shows good engineering practices that you can actually train a single unified whole-body control policy for all agile motion, and it works in the real world, directly with sim2real without adaptation. This is different from many existing works that trains/adapts one individual policy for each specific motion. Instead of just showing the beautiful motions/dances, this is actually practical. Because now you can convert all types of commands into real actions in real time without tuning anything. Visit to check out how we handle the following challenges: ✅ Partial Observability. ✅ Hardware Limitations. ✅ Unbalanced Data Distribution. ✅ Model Expressiveness. Work led by Zixuan Chen Mazeyu Ji

Xiaolong Wang

83,261 次观看 • 1 年前

Trained a humanoid entirely in a 3D scan of the office. Zero real-world fine-tuning. It just walked in and worked. RL needs hundreds of thousands of attempts, and real robots can't afford to crash. A misjudged gap or a glass door collision breaks hardware and costs hours resetting. So you train in a sim. But sim policies usually train on randomized, untextured geometry; depth is easy to fake. The robot learns structure, not the real world: no materials, no lighting, no idea what anything actually is. RGB cameras carry all of that but training RGB policies in generic fake worlds won’t generalize to the real world. Niantic Spatial 🌎 Scaniverse reconstructs your scan of the real deployment site. One 360° camera walkthrough → photorealistic 3D Gaussian splat at metric scale → collision mesh pulled from the same reconstruction, so vision and physics match exactly. Drops straight into NVIDIA Isaac Sim/Lab, no manual conversion. Flexion simulation-first approach then seamlessly enables the training of RGB-only nav policies inside that reconstruction. With added domain randomization + large image encoders for robustness, this deploys straight to hardware. No real-world fine-tuning. Deployment: months of on-site adaptation → days. Tune into the NVIDIA livestream on 12 August to hear how these companies are closing the sim2real gap: NVIDIA Robotics ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Trained a humanoid entirely in a 3D scan of the office. Zero real-world fine-tuning. It just walked in and worked. RL needs hundreds of thousands of attempts, and real robots can't afford to crash. A misjudged gap or a glass door collision breaks hardware and costs hours resetting. So you train in a sim. But sim policies usually train on randomized, untextured geometry; depth is easy to fake. The robot learns structure, not the real world: no materials, no lighting, no idea what anything actually is. RGB cameras carry all of that but training RGB policies in generic fake worlds won’t generalize to the real world. Niantic Spatial 🌎 Scaniverse reconstructs your scan of the real deployment site. One 360° camera walkthrough → photorealistic 3D Gaussian splat at metric scale → collision mesh pulled from the same reconstruction, so vision and physics match exactly. Drops straight into NVIDIA Isaac Sim/Lab, no manual conversion. Flexion simulation-first approach then seamlessly enables the training of RGB-only nav policies inside that reconstruction. With added domain randomization + large image encoders for robustness, this deploys straight to hardware. No real-world fine-tuning. Deployment: months of on-site adaptation → days. Tune into the NVIDIA livestream on 12 August to hear how these companies are closing the sim2real gap: NVIDIA Robotics ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

118,434 次观看 • 13 天前

Please stop using AI on tannies pics. They keep voicing out their discomfort about it. 🐰: But we should really tone down using AI. I mean what I’m saying is, if AI is used in a way that helps a lot of people, like supporting certain jobs or meaningful work, then I think that’s really great. 🐰: But honestly, people are making all kinds of things with AI now… it’s getting hard to even tell what’s real and what’s AI anymore. 🐰: At that point, how is it any different from deepfakes? I think we shouldn’t overuse AI like this.

Please stop using AI on tannies pics. They keep voicing out their discomfort about it. 🐰: But we should really tone down using AI. I mean what I’m saying is, if AI is used in a way that helps a lot of people, like supporting certain jobs or meaningful work, then I think that’s really great. 🐰: But honestly, people are making all kinds of things with AI now… it’s getting hard to even tell what’s real and what’s AI anymore. 🐰: At that point, how is it any different from deepfakes? I think we shouldn’t overuse AI like this.

vjk ☆

263,681 次观看 • 4 个月前

#Saints HC Kellen Moore on catching rookies up to speed at minicamp: "These guys have been through a lot these last few months, and a lot of it isn't necessarily football work ... We want these guys to get acclimated as quickly as possible with the vets, so our approach is give them as much information as we can."

#Saints HC Kellen Moore on catching rookies up to speed at minicamp: "These guys have been through a lot these last few months, and a lot of it isn't necessarily football work ... We want these guys to get acclimated as quickly as possible with the vets, so our approach is give them as much information as we can."

NOF

22,393 次观看 • 3 个月前

Aryna Sabalenka says she’s looking forward to battling the power of Elena Rybakina “Is she one of the few players who hits the ball as hard as you?” Aryna: “I think her shots are heavy, deep, flat balls that are not easy to work with. We have great history. She’s an incredible player. We had a lot of great battles.. a lot of finals we played. If it’s gonna be her, I’m looking forward to battling this power.” (via Australian Open Press)

Aryna Sabalenka says she’s looking forward to battling the power of Elena Rybakina “Is she one of the few players who hits the ball as hard as you?” Aryna: “I think her shots are heavy, deep, flat balls that are not easy to work with. We have great history. She’s an incredible player. We had a lot of great battles.. a lot of finals we played. If it’s gonna be her, I’m looking forward to battling this power.” (via Australian Open Press)

The Tennis Letter

150,195 次观看 • 6 个月前

So we did a bunch of projects with real world reinforcement learning - but it was often too inefficient to be practical to train tabula rasa. This suggests we need better priors, but acquiring these from on-robot data can often be expensive as well. In our recent work, we show that despite being fundamentally inaccurate, simulation can guide provide a cheap way to guide real-world RL finetuning to be super efficient! We propose Simulation-Guided Fine-Tuning (SGFT) - a simple paradigm for sim2real finetuning that uses simulation to provide reward shaping that accelerates real world RL finetuning *beyond* just providing an initialization. TLDR: Use value functions from sim to shape rewards for real-world RL, see large sample efficiency improvements 🧵(1/6)

So we did a bunch of projects with real world reinforcement learning - but it was often too inefficient to be practical to train tabula rasa. This suggests we need better priors, but acquiring these from on-robot data can often be expensive as well. In our recent work, we show that despite being fundamentally inaccurate, simulation can guide provide a cheap way to guide real-world RL finetuning to be super efficient! We propose Simulation-Guided Fine-Tuning (SGFT) - a simple paradigm for sim2real finetuning that uses simulation to provide reward shaping that accelerates real world RL finetuning beyond just providing an initialization. TLDR: Use value functions from sim to shape rewards for real-world RL, see large sample efficiency improvements 🧵(1/6)

Abhishek Gupta

13,637 次观看 • 1 年前

Arena reached a $100M annual revenue run rate just 8 months after launching our evaluation product. We started as a research project at UC Berkeley with a simple mission: measure AI progress through real-world use. As AI shifts from chatbots to agents taking on longer, higher-stakes work, the problem matters more than ever. Today, Arena measures real-world AI utility with a community of tens of millions. With Agent Arena, we’re evaluating long-running agents on complex, real-world tasks - how they use tools, adapt to feedback, recover from errors, and accomplish goals set by humans. We are excited to keep deepening our work in agentic evaluations. Here’s Anastasios Nikolas Angelopoulos on what this milestone means and where we go from here:

Arena reached a $100M annual revenue run rate just 8 months after launching our evaluation product. We started as a research project at UC Berkeley with a simple mission: measure AI progress through real-world use. As AI shifts from chatbots to agents taking on longer, higher-stakes work, the problem matters more than ever. Today, Arena measures real-world AI utility with a community of tens of millions. With Agent Arena, we’re evaluating long-running agents on complex, real-world tasks - how they use tools, adapt to feedback, recover from errors, and accomplish goals set by humans. We are excited to keep deepening our work in agentic evaluations. Here’s Anastasios Nikolas Angelopoulos on what this milestone means and where we go from here:

Arena.ai

211,004 次观看 • 1 个月前

The Human in HR is everything. We loved being at CIPM Abuja last month, reimagining the world of work and connecting with HR professionals to hear why they do what they do. This video is a highlight of the energy and insight from the conference through our lens. It was a big reminder of the mission we serve at PaidHR. 💙

The Human in HR is everything. We loved being at CIPM Abuja last month, reimagining the world of work and connecting with HR professionals to hear why they do what they do. This video is a highlight of the energy and insight from the conference through our lens. It was a big reminder of the mission we serve at PaidHR. 💙

PaidHR

11,504 次观看 • 9 个月前

A good description of our True Realm. We live on a vast, stationary flat plane, not a spinning ball in space. At the center is the North Pole, with continents spreading outward. The outer edge is surrounded by an impassable Antarctic ice wall that contains the oceans. Above us is the firmament....a rotating dome with the Sun, Moon, and stars circling overhead, creating day and night. There is no outer space or globe Earth as we are now seeing through the BS coming from Artemis and NASA . We inhabit a beautiful, enclosed, purposeful creation on solid, level ground under a close sky. This is our real world.

A good description of our True Realm. We live on a vast, stationary flat plane, not a spinning ball in space. At the center is the North Pole, with continents spreading outward. The outer edge is surrounded by an impassable Antarctic ice wall that contains the oceans. Above us is the firmament....a rotating dome with the Sun, Moon, and stars circling overhead, creating day and night. There is no outer space or globe Earth as we are now seeing through the BS coming from Artemis and NASA . We inhabit a beautiful, enclosed, purposeful creation on solid, level ground under a close sky. This is our real world.

DeepWebSlinger

21,021 次观看 • 4 个月前

Today we’re announcing Ontology 1, our newest AI model. Perhaps surprisingly, it’s at least 2.7x more accurate than the world’s best ecommerce search engines, and handles queries that have never been possible before. We keep reaching for the edge of what it can do. We haven’t found it yet. Not only that, but it learns on its own with no retraining or fine-tuning. And it’s hallucination-free. It’s a successor architecture for search. Learn how we built it at and check out the benchmarks at Try it at

Today we’re announcing Ontology 1, our newest AI model. Perhaps surprisingly, it’s at least 2.7x more accurate than the world’s best ecommerce search engines, and handles queries that have never been possible before. We keep reaching for the edge of what it can do. We haven’t found it yet. Not only that, but it learns on its own with no retraining or fine-tuning. And it’s hallucination-free. It’s a successor architecture for search. Learn how we built it at and check out the benchmarks at Try it at

Onton

324,061 次观看 • 25 天前

Our sky is a giant clock, lit by two identically-sized luminaries (Sun and Moon), that act as local spotlights with limited light throw (thus creating the day/night cycle). The reason why the controllers of our world feed you the "spinning ball flying through space" fantasy is because once you understand what you're actually looking at...it becomes abundantly clear that we live inside an intelligently-designed realm, built by a masterful Creator.

Our sky is a giant clock, lit by two identically-sized luminaries (Sun and Moon), that act as local spotlights with limited light throw (thus creating the day/night cycle). The reason why the controllers of our world feed you the "spinning ball flying through space" fantasy is because once you understand what you're actually looking at...it becomes abundantly clear that we live inside an intelligently-designed realm, built by a masterful Creator.

Ben Wehrman

137,425 次观看 • 3 个月前

What if you got the same AI functionalities of Notion without compromising on the optionality and price? We’ve been working hard on creating this through a mix of usage based pricing and CLI tools that work directly within our harness. This way you get the optionality to spend credits on more domain specific requests while we help create the infrastructure that are deterministic in your workflows. with Sarah Sachs on Latent.Space

What if you got the same AI functionalities of Notion without compromising on the optionality and price? We’ve been working hard on creating this through a mix of usage based pricing and CLI tools that work directly within our harness. This way you get the optionality to spend credits on more domain specific requests while we help create the infrastructure that are deterministic in your workflows. with Sarah Sachs on Latent.Space

Notion Developers

23,234 次观看 • 3 个月前

🤙 Just JGGL It — True Stories | Episode 1 🤙 © "There's a massive amount of digital noise out there. It's incredibly hard for real people to break through." Meet Sergey — lead of sound production at JGGL, with 26+ years in the industry, including work with Sabaton and The Offspring. 🚀 This is Episode 1 of our behind-the-scenes series — a look at the people building JGGL.

🤙 Just JGGL It — True Stories | Episode 1 🤙 © "There's a massive amount of digital noise out there. It's incredibly hard for real people to break through." Meet Sergey — lead of sound production at JGGL, with 26+ years in the industry, including work with Sabaton and The Offspring. 🚀 This is Episode 1 of our behind-the-scenes series — a look at the people building JGGL.

JGGL

11,641 次观看 • 1 个月前

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.

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 次观看 • 1 年前

Patriots—please pause for a minute. My team and I worked very hard on this. What you’re about to watch is the most powerful, inspiring snapshot of what we accomplished this past year. In a world drowned in noise and distraction, this is a reminder of what’s possible when people take a stand. If you care about our country and this movement, it would mean the world to me if you would watch our Year in Review. We’ve endured relentless adversity to fight for our culture, our values, and YOU. This video reflects that perseverance—and the work we’re committed to continuing. This is for all of you. We hope you’ll stand with us in 2026.

Patriots—please pause for a minute. My team and I worked very hard on this. What you’re about to watch is the most powerful, inspiring snapshot of what we accomplished this past year. In a world drowned in noise and distraction, this is a reminder of what’s possible when people take a stand. If you care about our country and this movement, it would mean the world to me if you would watch our Year in Review. We’ve endured relentless adversity to fight for our culture, our values, and YOU. This video reflects that perseverance—and the work we’re committed to continuing. This is for all of you. We hope you’ll stand with us in 2026.

Brandon Straka #WalkAway

97,163 次观看 • 7 个月前

At Tata Motors, we believe quality, accuracy, and safety are inseparable pillars of excellence. Powered by cutting-edge technology and robotics working in harmony with human ingenuity, we’ve set Zero Errors as the gold standard for precision. This isn’t just a goal — it’s our philosophy, shaping every step of our journey. Watch the film to discover how Zero Errors is our chosen way of life, challenging us to continually innovate and redefine what’s possible. #MissionZero #TataMotors #ConnectingAspirations

At Tata Motors, we believe quality, accuracy, and safety are inseparable pillars of excellence. Powered by cutting-edge technology and robotics working in harmony with human ingenuity, we’ve set Zero Errors as the gold standard for precision. This isn’t just a goal — it’s our philosophy, shaping every step of our journey. Watch the film to discover how Zero Errors is our chosen way of life, challenging us to continually innovate and redefine what’s possible. #MissionZero #TataMotors #ConnectingAspirations

Tata Motors

12,595 次观看 • 1 年前