Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

How robust can model predictive control be if we can solve each trajectory optimization to global optimality? On the contact-rich push-T problem, we show that model-based global optimization is so robust that it never fails, even if the model is not even correct! We achieve global optimality via sparse... show more

Heng Yang

5,037 subscribers

28,745 Aufrufe • vor 1 Jahr •via X (Twitter)

Wissenschaft & Technologie Nachrichten & Politik Bildung

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Malaria is a complex & unforgiving disease, but one that we can end if we work together. Fredros Okumu & JenHatmaker discuss the global impacts of malaria and how we can advance progress against it on this episode of “Make Me Care About…”

Malaria is a complex & unforgiving disease, but one that we can end if we work together. Fredros Okumu & JenHatmaker discuss the global impacts of malaria and how we can advance progress against it on this episode of “Make Me Care About…”

Gates Foundation

496,733 Aufrufe • vor 3 Jahren

#Habs Mike Matheson on officiating "That is a good question, and we are wondering ourselves. But it is out of our control, so it is not something to worry about. We need to keep playing and keep focusing on the things we can control." #GoHabsGo #NHL #Hockey

#Habs Mike Matheson on officiating "That is a good question, and we are wondering ourselves. But it is out of our control, so it is not something to worry about. We need to keep playing and keep focusing on the things we can control." #GoHabsGo #NHL #Hockey

Chris G

20,359 Aufrufe • vor 4 Monaten

We are releasing the fastest TTS model as open source! One of the biggest problems we encountered while optimizing TTS models is optimization itself. Since it is LLM-based, even optimizing with VLLM and SgLang libraries is not enough. Additionally, I made the outputs much better with special optimizations for training. The voices you are listening to are results obtained from only 20% of the model training. We trained these outputs on 8xB200 in 24 hours. Even though the dataset includes some low-quality data, the model's output is much better. We will release the code as open source tomorrow. Data: Emilia-3m Model: EchoDit (custom) Codec: DacVae Opt: Flash-attn + CacheDit

We are releasing the fastest TTS model as open source! One of the biggest problems we encountered while optimizing TTS models is optimization itself. Since it is LLM-based, even optimizing with VLLM and SgLang libraries is not enough. Additionally, I made the outputs much better with special optimizations for training. The voices you are listening to are results obtained from only 20% of the model training. We trained these outputs on 8xB200 in 24 hours. Even though the dataset includes some low-quality data, the model's output is much better. We will release the code as open source tomorrow. Data: Emilia-3m Model: EchoDit (custom) Codec: DacVae Opt: Flash-attn + CacheDit

Kadir Nar

32,232 Aufrufe • vor 1 Monat

Odyssey-3 is live. One world model trained on visual data that can drive cars, fly drones, control robots, and even play video games. The basic premise is that it's better to train a single model across different systems instead of a new model for each system. It's sort of like how a gamer can use their skills in CounterStrike to play Call of Duty or GTA 5.

Odyssey-3 is live. One world model trained on visual data that can drive cars, fly drones, control robots, and even play video games. The basic premise is that it's better to train a single model across different systems instead of a new model for each system. It's sort of like how a gamer can use their skills in CounterStrike to play Call of Duty or GTA 5.

Ian Miles

24,978 Aufrufe • vor 3 Tagen

ICML 2026: Latent Reasoning in TRMs is Secretly a Policy Improvement Operator Why does recursive reasoning, especially latent reasoning, actually work? The theory is still young, and even mechanistic explanations are limited. We close part of this gap by showing that latent reasoning is secretly doing policy improvement. Each recursion pushes the model steadily toward the target. Based on this view, we propose an algorithm that boosts learning and inference efficiency by up to 18x.

ICML 2026: Latent Reasoning in TRMs is Secretly a Policy Improvement Operator Why does recursive reasoning, especially latent reasoning, actually work? The theory is still young, and even mechanistic explanations are limited. We close part of this gap by showing that latent reasoning is secretly doing policy improvement. Each recursion pushes the model steadily toward the target. Based on this view, we propose an algorithm that boosts learning and inference efficiency by up to 18x.

Arip

24,987 Aufrufe • vor 3 Monaten

HyENA is now live and it is here to redefine Perpetuals trading from the ground up. Brought to you by Based, powered by , and built entirely on Hyperliquid HIP-3. HyENA introduces a new standard for on-chain trading: an internet trading engine with native yield. With HyENA, you can trade any asset on earth 24/7, all while your collateral continues to work for you in the background. No idle capital. No stale liquidity. Just a seamless, hyper-efficient trading experience. HyENA is not just an upgrade. We are presenting a new model for how global markets can operate. Hyperliquid

HyENA is now live and it is here to redefine Perpetuals trading from the ground up. Brought to you by Based, powered by , and built entirely on Hyperliquid HIP-3. HyENA introduces a new standard for on-chain trading: an internet trading engine with native yield. With HyENA, you can trade any asset on earth 24/7, all while your collateral continues to work for you in the background. No idle capital. No stale liquidity. Just a seamless, hyper-efficient trading experience. HyENA is not just an upgrade. We are presenting a new model for how global markets can operate. Hyperliquid

Based

34,109 Aufrufe • vor 9 Monaten

Model-Free Reinforcement Learning (MFRL) has been alluring, especially with supercharged compute with physics on GPU. However, the methods use 0-th order gradients, and are often not the best optimizers. Can we do better than PPO in continuous control for robotics? Turns out yes! 🥳 tl;dr: Faster, better RL than PPO in continuous control 💪 The answer lies in using more information from the simulation. We are juicing the simulation on GPU as it is, why not use it for gradients as well? This has been a driving question in a series of our works. We first studied this problem in ICLR 2022 paper on Short Horizon Actor Critic Naive gradient based methods are stuck in local minima and have exploding/vanishing gradients. SHAC solved this problem truncated rollouts and model based value estimation, where the model is Differentiable Sim. This boosted sample efficiency and wall-clock time immensely especially in high dimensional systems such as humanoids Yet, given enough compute PPO often caught up. Our follow up paper on on Adaptive Horizon Actor Critic at ICML 2024 discovers the cause and provides a fix. However, we find that even when given ground-truth dynamics, not all gradients are useful due to sample error. 1st-Order Model-Based Reinforcement Learning methods employing differentiable simulation provide gradients with reduced variance but are susceptible to bias in scenarios involving stiff dynamics, such as physical contact. We find that back-propagating through contact and long trajectories drastically reduces gradient accuracy. Using this insight, we propose AHAC to dynamically adapt its roll-out horizon to avoid differentiating through stiff contact. AHAC is a first-order model-based RL algorithm that learns high-dimensional tasks in minutes (wall clock) and outperforms PPO by 40%, even in the limit of data provided to PPO. This work is led by Ignat Georgiev alongside Krishnan Srinivasan, Jie Xu, Eric Heiden and ample assistance from warp team at NVIDIA Robotics (Miles Macklin)

Model-Free Reinforcement Learning (MFRL) has been alluring, especially with supercharged compute with physics on GPU. However, the methods use 0-th order gradients, and are often not the best optimizers. Can we do better than PPO in continuous control for robotics? Turns out yes! 🥳 tl;dr: Faster, better RL than PPO in continuous control 💪 The answer lies in using more information from the simulation. We are juicing the simulation on GPU as it is, why not use it for gradients as well? This has been a driving question in a series of our works. We first studied this problem in ICLR 2022 paper on Short Horizon Actor Critic Naive gradient based methods are stuck in local minima and have exploding/vanishing gradients. SHAC solved this problem truncated rollouts and model based value estimation, where the model is Differentiable Sim. This boosted sample efficiency and wall-clock time immensely especially in high dimensional systems such as humanoids Yet, given enough compute PPO often caught up. Our follow up paper on on Adaptive Horizon Actor Critic at ICML 2024 discovers the cause and provides a fix. However, we find that even when given ground-truth dynamics, not all gradients are useful due to sample error. 1st-Order Model-Based Reinforcement Learning methods employing differentiable simulation provide gradients with reduced variance but are susceptible to bias in scenarios involving stiff dynamics, such as physical contact. We find that back-propagating through contact and long trajectories drastically reduces gradient accuracy. Using this insight, we propose AHAC to dynamically adapt its roll-out horizon to avoid differentiating through stiff contact. AHAC is a first-order model-based RL algorithm that learns high-dimensional tasks in minutes (wall clock) and outperforms PPO by 40%, even in the limit of data provided to PPO. This work is led by Ignat Georgiev alongside Krishnan Srinivasan, Jie Xu, Eric Heiden and ample assistance from warp team at NVIDIA Robotics (Miles Macklin)

Animesh Garg

52,308 Aufrufe • vor 2 Jahren

AI has had exactly two scaling axes that worked so far, and the second one is starting to look finite too the first one was pretraining: with scaling parameters and data, we got world knowledge (i.e. ChatGPT had read enough to know things), but it started saturating a while ago the second one was RL, and people had been doing RL the whole time before that: RLHF is RL but it never scaled far because it was trying to control the exact output, which tokens come out, how the text reads, but you can only push that so far before you’re just polishing RLVR dropped that constraint: giving the model a task, then checking whether the final answer is right, and ignoring everything in between -- so the model does whatever it wants in the middle and only the endpoint gets graded, and that’s much closer to actual RL and it’s what bought us planning and reasoning (arguably, tool use sits around 2.5 on this list -- while useful, it's not a different kind of thing) so one axis gave knowledge, the other gave reasoning, and both of them are one model working alone the next axis is how many models you can get working on the same problem, which is a different kind of axis than the previous two we know that multi-agent RL has always been the harder problem: I spent years in that literature and the gap between single-agent and multi-agent is definitely not incremental -- it’s a whole different class of difficulty! which is also why the derivatives are steep at the start, nobody has picked the easy wins yet... and the thing that gates this multi-agent coordination is communication: models can only coordinate as well as they can exchange information, and right now they do that by writing sentences to each other imagine what could we possibly achieve if we properly open that third axis development by letting models to exchange information in their native "language" without loosing any computational data that they produce during inference

AI has had exactly two scaling axes that worked so far, and the second one is starting to look finite too the first one was pretraining: with scaling parameters and data, we got world knowledge (i.e. ChatGPT had read enough to know things), but it started saturating a while ago the second one was RL, and people had been doing RL the whole time before that: RLHF is RL but it never scaled far because it was trying to control the exact output, which tokens come out, how the text reads, but you can only push that so far before you’re just polishing RLVR dropped that constraint: giving the model a task, then checking whether the final answer is right, and ignoring everything in between -- so the model does whatever it wants in the middle and only the endpoint gets graded, and that’s much closer to actual RL and it’s what bought us planning and reasoning (arguably, tool use sits around 2.5 on this list -- while useful, it's not a different kind of thing) so one axis gave knowledge, the other gave reasoning, and both of them are one model working alone the next axis is how many models you can get working on the same problem, which is a different kind of axis than the previous two we know that multi-agent RL has always been the harder problem: I spent years in that literature and the gap between single-agent and multi-agent is definitely not incremental -- it’s a whole different class of difficulty! which is also why the derivatives are steep at the start, nobody has picked the easy wins yet... and the thing that gates this multi-agent coordination is communication: models can only coordinate as well as they can exchange information, and right now they do that by writing sentences to each other imagine what could we possibly achieve if we properly open that third axis development by letting models to exchange information in their native "language" without loosing any computational data that they produce during inference

Sasha Malysheva

14,445 Aufrufe • vor 1 Monat

Each of these homes were built in a factory in 2 hours, and assembled on-site in 3 hours. This is the type of innovation Canada is embracing in order to build the homes we need, faster. Canadian industry and Canadian workers have the creativity and ambition required to meet this moment. By working together, we can, and we will, solve the housing crisis.

Each of these homes were built in a factory in 2 hours, and assembled on-site in 3 hours. This is the type of innovation Canada is embracing in order to build the homes we need, faster. Canadian industry and Canadian workers have the creativity and ambition required to meet this moment. By working together, we can, and we will, solve the housing crisis.

Sean Fraser

347,145 Aufrufe • vor 2 Jahren

Qualia has been selected for the Google DeepMind Robotics Program. We train embodied models that put a robot on a real manual task and make it work, on the floor, not in a demo. Foundation models and reasoning are where robotics is heading, and doing that work alongside DeepMind, who are pushing this frontier, is exactly where we want to be. If you are a company looking to see how a new generation of robots can help your manual tasks, contact us at hello@qualiastudios.dev More soon

Qualia has been selected for the Google DeepMind Robotics Program. We train embodied models that put a robot on a real manual task and make it work, on the floor, not in a demo. Foundation models and reasoning are where robotics is heading, and doing that work alongside DeepMind, who are pushing this frontier, is exactly where we want to be. If you are a company looking to see how a new generation of robots can help your manual tasks, contact us at [email protected] More soon

Qualia

87,991 Aufrufe • vor 3 Monaten

Excited to introduce Diffusion Augmented Agents (DAAGs)✨. We give an agent control of a diffusion model, so it can create its own *synthetic experience*.🪄 The result is a lifelong agent that can learn new reward detectors and policies, much more efficiently. Here's how. 👇

Excited to introduce Diffusion Augmented Agents (DAAGs)✨. We give an agent control of a diffusion model, so it can create its own synthetic experience.🪄 The result is a lifelong agent that can learn new reward detectors and policies, much more efficiently. Here's how. 👇

Norman Di Palo

12,931 Aufrufe • vor 2 Jahren

boochan comes in pair, pls do not separate 🍊 if we went in together and met at the training center, it’d be so amazing 🐰 you’d be able to rely on each other a lot! 🍊 we wouldnt really be able to live together at the training center even if we entered at the same time, but if we meet there, we’d have a really deep bond

boochan comes in pair, pls do not separate 🍊 if we went in together and met at the training center, it’d be so amazing 🐰 you’d be able to rely on each other a lot! 🍊 we wouldnt really be able to live together at the training center even if we entered at the same time, but if we meet there, we’d have a really deep bond

🐻

31,494 Aufrufe • vor 21 Tagen

I’m honored to share that I have been appointed the first Global Ambassador for WR Chess This new chapter will take me across continents, promoting chess and impacting lives on a global stage from Africa, Asia, Latin America tour to a world record event in Peru in June. The CEO of WR Chess Wadim Rosenstein has quietly supported the African chess community for four years. Together I believe we can achieve so much more for the chess world. We agreed to meet in Paris and travel to Prague for the chess festival. And for hours, we spoke about a global vision and a legacy for chess development and industrialization across Africa and beyond. One important thing Wadim and I share in common is we both came from nothing but chess opened doors we never imagined. Now we want to extend this to the world. I am proud to join the WR Chess family. Even more excited for what we will build together. It is possible to do great things from a small place.

I’m honored to share that I have been appointed the first Global Ambassador for WR Chess This new chapter will take me across continents, promoting chess and impacting lives on a global stage from Africa, Asia, Latin America tour to a world record event in Peru in June. The CEO of WR Chess Wadim Rosenstein has quietly supported the African chess community for four years. Together I believe we can achieve so much more for the chess world. We agreed to meet in Paris and travel to Prague for the chess festival. And for hours, we spoke about a global vision and a legacy for chess development and industrialization across Africa and beyond. One important thing Wadim and I share in common is we both came from nothing but chess opened doors we never imagined. Now we want to extend this to the world. I am proud to join the WR Chess family. Even more excited for what we will build together. It is possible to do great things from a small place.

Tunde Onakoya

149,653 Aufrufe • vor 6 Monaten

World Models are the path for some AI Models in the future. But how can we efficiently train these models to not only see the world the way humans do but to see the world in a new and unique way. By visualizing, what is normally sequenced audio patterns, we can derive much more insights. Here we see Paganini in a visual form that can than be described and transcribed into a World Model. We can observe connections in a manner that may not have been clear prior to the digitalization of music and sound in this way. The company with the most valuable potential in building a World Model is Tesla. Not that this type of visualization is being used, but that the mechanisms are in place, and the technology is in place for the company to thrive in this new form of AI.

World Models are the path for some AI Models in the future. But how can we efficiently train these models to not only see the world the way humans do but to see the world in a new and unique way. By visualizing, what is normally sequenced audio patterns, we can derive much more insights. Here we see Paganini in a visual form that can than be described and transcribed into a World Model. We can observe connections in a manner that may not have been clear prior to the digitalization of music and sound in this way. The company with the most valuable potential in building a World Model is Tesla. Not that this type of visualization is being used, but that the mechanisms are in place, and the technology is in place for the company to thrive in this new form of AI.

Brian Roemmele

57,454 Aufrufe • vor 10 Monaten

RAOUL PAL: BITCOIN IS DEEPLY DISCOUNTED Raoul Pal says based on global liquidity and how Nasdaq has tracked, #Bitcoin should be closer to $160,000 right now. That gap, in his view, is the liquidity discount $BTC is trading at. He calls this a technical year -- not a demand problem, but a timing one. According to the model, the finish should’ve been much stronger. If liquidity keeps doing what it’s been doing, that gap doesn’t stay open forever.

RAOUL PAL: BITCOIN IS DEEPLY DISCOUNTED Raoul Pal says based on global liquidity and how Nasdaq has tracked, #Bitcoin should be closer to $160,000 right now. That gap, in his view, is the liquidity discount $BTC is trading at. He calls this a technical year -- not a demand problem, but a timing one. According to the model, the finish should’ve been much stronger. If liquidity keeps doing what it’s been doing, that gap doesn’t stay open forever.

CryptosRus

111,244 Aufrufe • vor 7 Monaten

my favorite of the new LTX 2.3 LoRAs ✨ Remember when a year ago we need a full on model like VACE to do that? and now an IC LoRA is even better

my favorite of the new LTX 2.3 LoRAs ✨ Remember when a year ago we need a full on model like VACE to do that? and now an IC LoRA is even better

Linoy Tsaban

12,814 Aufrufe • vor 3 Monaten

[ ANNOUNCEMENT FOR THE RORIIPUPPER ARKNIGHTS X PERSONA 3 R COLLAB GLOBAL GIVEAWAY ] Scarf and I are months ahead of schedule, but that's because we want the event to be special and fun. Here is a preview of a prototype of the site that we will be using for the Arknights x Persona3R giveaway that we are going to hold. The instructions for how to join the giveaway are not final and may be changed later as we may add more things to give away and better requirements to prevent cheaters as much as we can. Here is also a preview of the raffle/roulette animation that will decide the winners for the giveaway. I know we're six months early, however we're just so hyped and we have a lot of ideas art and animation wise for it. For now, this is what we can show y'all.

[ ANNOUNCEMENT FOR THE RORIIPUPPER ARKNIGHTS X PERSONA 3 R COLLAB GLOBAL GIVEAWAY ] Scarf and I are months ahead of schedule, but that's because we want the event to be special and fun. Here is a preview of a prototype of the site that we will be using for the Arknights x Persona3R giveaway that we are going to hold. The instructions for how to join the giveaway are not final and may be changed later as we may add more things to give away and better requirements to prevent cheaters as much as we can. Here is also a preview of the raffle/roulette animation that will decide the winners for the giveaway. I know we're six months early, however we're just so hyped and we have a lot of ideas art and animation wise for it. For now, this is what we can show y'all.

Roriipupper腰王

54,284 Aufrufe • vor 19 Tagen

We should nuke the filibuster to pass the SAVE America Act. If we don’t have the votes to nuke the filibuster, we should put the SAVE America Act on the floor and debate it until it passes, requiring filibustering senators to speak and making clear that if they stop speaking, we can “call the question” and pass it with a simple majority. If for some reason we can’t do that—and to be clear, there’s no legitimate reason why we can’t—then we should use budget reconciliation to pass it. But not passing the SAVE America Act is not an option. Neither is taking a lengthy recess without doing any of the above.

We should nuke the filibuster to pass the SAVE America Act. If we don’t have the votes to nuke the filibuster, we should put the SAVE America Act on the floor and debate it until it passes, requiring filibustering senators to speak and making clear that if they stop speaking, we can “call the question” and pass it with a simple majority. If for some reason we can’t do that—and to be clear, there’s no legitimate reason why we can’t—then we should use budget reconciliation to pass it. But not passing the SAVE America Act is not an option. Neither is taking a lengthy recess without doing any of the above.

Mike Lee

166,213 Aufrufe • vor 1 Monat

Ever watch an agent solve a problem with 100% confidence and get it completely wrong? You can fix it… if you catch it. But then you need to watch every… single… run. New paper: We show that a meta-agent can do this for you, so your agents get ~2x more done on their own. 🧵

Ever watch an agent solve a problem with 100% confidence and get it completely wrong? You can fix it… if you catch it. But then you need to watch every… single… run. New paper: We show that a meta-agent can do this for you, so your agents get ~2x more done on their own. 🧵

Weiyan Shi

63,646 Aufrufe • vor 2 Monaten

There is only one reason to share truth. And no it has nothing to do with money- and everything to do about helping God move. Peace is the prize- a better world for everyone is the prize. We make SACRIFICES for things we want most in this world. Christ made the ultimate sacrifice If He can do that for us FREE of charge- we owe it to each other to work TOGETHER to make the world a better place- despite the toll and sacrifice. A level playing field- where we can all work hard and do our best to succeed- that is the payout. A better world for all We’re not here for just ourselves- otherwise the second commandment wouldn’t be like the first- love your neighbor as yourself. This world gets better the sooner we all wake up. Information is free- we collect and share it for free in hopes that it keeps spreading. Only working TOGETHER can we win. We are meant to move these messages for God so that humanity can wake up- this plan is designed that way- working together The Lord is ONE. We are bound as a family by Our Father in Heaven. We are apart of Him and He is apart of all of us. We are billions of little pieces of the Lords gift of life. We’ve been separated and pushed apart because it makes us weak. We were designed to be powerful by the love we draw from Creator and push through creation. We are ONE with Our Holy Father 🙏💗 Be EXCELLENT to each other frens

There is only one reason to share truth. And no it has nothing to do with money- and everything to do about helping God move. Peace is the prize- a better world for everyone is the prize. We make SACRIFICES for things we want most in this world. Christ made the ultimate sacrifice If He can do that for us FREE of charge- we owe it to each other to work TOGETHER to make the world a better place- despite the toll and sacrifice. A level playing field- where we can all work hard and do our best to succeed- that is the payout. A better world for all We’re not here for just ourselves- otherwise the second commandment wouldn’t be like the first- love your neighbor as yourself. This world gets better the sooner we all wake up. Information is free- we collect and share it for free in hopes that it keeps spreading. Only working TOGETHER can we win. We are meant to move these messages for God so that humanity can wake up- this plan is designed that way- working together The Lord is ONE. We are bound as a family by Our Father in Heaven. We are apart of Him and He is apart of all of us. We are billions of little pieces of the Lords gift of life. We’ve been separated and pushed apart because it makes us weak. We were designed to be powerful by the love we draw from Creator and push through creation. We are ONE with Our Holy Father 🙏💗 Be EXCELLENT to each other frens

🐸🐸🐸 🇺🇸

23,726 Aufrufe • vor 2 Jahren