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。

Humanoids 🤖 will do anything humans can do. But are state-of-the-art algorithms up to the challenge? Introducing HumanoidBench, the first-of-its-kind simulated humanoid benchmark with 27 distinct whole-body tasks requiring intricate long-horizon planning and coordination. 🧵👇

Carlo Sferrazza

2,445 subscribers

117,104 次观看 • 2 年前 •via X (Twitter)

科学技术新闻政治教育

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Can MLLMs actually track what's happening in a video? Introducing VSTAT 🎯, our new benchmark for visual state tracking. The tasks are simple: count cups, read typed words, count page flips. Humans solve them easily. MLLMs don't. 🧵 [1/11]

Can MLLMs actually track what's happening in a video? Introducing VSTAT 🎯, our new benchmark for visual state tracking. The tasks are simple: count cups, read typed words, count page flips. Humans solve them easily. MLLMs don't. 🧵 [1/11]

Sihyun Yu

161,222 次观看 • 19 天前

Humanoid teleoperation is difficult to scale A new paper explores a more scalable data source: first-person videos of humans doing tasks with their bare hands. The human-humanoid behavior policy unifies the state-action space, enabling effective retargeting to robot actions.

Humanoid teleoperation is difficult to scale A new paper explores a more scalable data source: first-person videos of humans doing tasks with their bare hands. The human-humanoid behavior policy unifies the state-action space, enabling effective retargeting to robot actions.

The Humanoid Hub

21,660 次观看 • 1 年前

🤖💰Inspired by Elon Musk’s vision of 20 billion humanoid robots, we’re thrilled to announce the process of developing the world’s first anti-hacking, anti-explosion, and anti-malfunction safety system that will secure all types of humanoids. Private and business entities can now invest and be part of our revolutionary product. Details:

🤖💰Inspired by Elon Musk’s vision of 20 billion humanoid robots, we’re thrilled to announce the process of developing the world’s first anti-hacking, anti-explosion, and anti-malfunction safety system that will secure all types of humanoids. Private and business entities can now invest and be part of our revolutionary product. Details:

Terror Alarm

37,221 次观看 • 1 年前

$📢Announcing our 3D head avatar benchmark📢 Two tasks with hidden test sets: - Dynamic Novel View Synthesis on Heads - Monocular FLAME-driven Head Avatar Reconstruction Our goal is to make research on 3D head avatars more comparable and ultimately increase the realism of digital humans. The benchmark studies distinct phenomena of 3D head avatar creation, such as extreme facial expressions, slow motion captures of shaking long hair, or complicated light reflection and refraction patterns of glasses. The two benchmark tasks assess two core desiderata of 3D avatars: While the novel view synthesis challenge focuses on best possible rendering quality of complex moving scenes, the avatar animation challenge is concerned with how well a driving signal is translated into an avatar. Evaluations are light-weight and consist of diverse video recordings from the popular NeRSemble dataset with a hidden test set. Participation in the benchmark is therefore straight-forward and requires only 5 reconstructions per task. Leaderboard and benchmark submission: Benchmark data access and toolkit: Great work by Tobias Kirschstein Simon Giebenhain$

📢Announcing our 3D head avatar benchmark📢 Two tasks with hidden test sets: - Dynamic Novel View Synthesis on Heads - Monocular FLAME-driven Head Avatar Reconstruction Our goal is to make research on 3D head avatars more comparable and ultimately increase the realism of digital humans. The benchmark studies distinct phenomena of 3D head avatar creation, such as extreme facial expressions, slow motion captures of shaking long hair, or complicated light reflection and refraction patterns of glasses. The two benchmark tasks assess two core desiderata of 3D avatars: While the novel view synthesis challenge focuses on best possible rendering quality of complex moving scenes, the avatar animation challenge is concerned with how well a driving signal is translated into an avatar. Evaluations are light-weight and consist of diverse video recordings from the popular NeRSemble dataset with a hidden test set. Participation in the benchmark is therefore straight-forward and requires only 5 reconstructions per task. Leaderboard and benchmark submission: Benchmark data access and toolkit: Great work by Tobias Kirschstein Simon Giebenhain

Matthias Niessner

28,062 次观看 • 1 年前

Introducing benchmark tracking across all of arXiv With thousands of models and benchmarks out there, it's impossible to track what's actually state-of-the-art We now index results from millions of papers to surface which models are SOTA according to open source research!

Introducing benchmark tracking across all of arXiv With thousands of models and benchmarks out there, it's impossible to track what's actually state-of-the-art We now index results from millions of papers to surface which models are SOTA according to open source research!

alphaXiv

10,892 次观看 • 6 个月前

Introducing Bubble Up You can now submit Bubble Up tasks to probe the limits of current AI capabilities for your own tasks. Select unsatisfied results, click “Optimize Bubble”, and submit bubble up tasks — even without vibe coding anything yourself.

Introducing Bubble Up You can now submit Bubble Up tasks to probe the limits of current AI capabilities for your own tasks. Select unsatisfied results, click “Optimize Bubble”, and submit bubble up tasks — even without vibe coding anything yourself.

DAPPOS

21,479 次观看 • 2 个月前

This year, an important mission is to let simulated humanoids solve long-term manipulation tasks in challenging dynamic, cluttered environments. This is a simple demonstration achieved by TokenHSI (CVPR 2025). The humanoid here is controlled by a single, unified model.

This year, an important mission is to let simulated humanoids solve long-term manipulation tasks in challenging dynamic, cluttered environments. This is a simple demonstration achieved by TokenHSI (CVPR 2025). The humanoid here is controlled by a single, unified model.

Liang Pan

149,479 次观看 • 1 年前

In the future, it might just be humanoid robots doing the refueling!🤖⛽️ Sinopec plans to introduce humanoid robot workers across its gas stations. They will handle tasks like fueling, picking up items, restocking, and inspections,working alongside human staff, especially during peak holiday periods in China to ease service pressure. With more than 30,000 gas stations across the country (most of them equipped with convenience stores), this implies a deployment of at least 30,000 humanoid robots. The robot is a wheeled humanoid developed by Beijing-based company FIVEAGES.

In the future, it might just be humanoid robots doing the refueling!🤖⛽️ Sinopec plans to introduce humanoid robot workers across its gas stations. They will handle tasks like fueling, picking up items, restocking, and inspections,working alongside human staff, especially during peak holiday periods in China to ease service pressure. With more than 30,000 gas stations across the country (most of them equipped with convenience stores), this implies a deployment of at least 30,000 humanoid robots. The robot is a wheeled humanoid developed by Beijing-based company FIVEAGES.

CyberRobo

23,536 次观看 • 2 个月前

The feet and ankles are the base of athleticism If they’re fragile, the whole body suffers. If they’re strong, responsive, and durable… the whole body will thank you. What’re your favorite exercises to build up the feet and ankles? Let me know in the comments 👇

The feet and ankles are the base of athleticism If they’re fragile, the whole body suffers. If they’re strong, responsive, and durable… the whole body will thank you. What’re your favorite exercises to build up the feet and ankles? Let me know in the comments 👇

Brendan Thompson, PT, DPT

356,864 次观看 • 2 年前

Daniel Arsham Enters Otherside. Introducing the Daniel Arsham Voyager, a first-of-its-kind collaboration fusing fine art and digital identity. A collectible that evolves like the world of Otherside, limited to 300 editions. Coming soon.

Daniel Arsham Enters Otherside. Introducing the Daniel Arsham Voyager, a first-of-its-kind collaboration fusing fine art and digital identity. A collectible that evolves like the world of Otherside, limited to 300 editions. Coming soon.

Othersidemeta

603,077 次观看 • 8 个月前

gm! Burn the Boats is finally everywhere books with fiery covers are sold : ) It is a blueprint for the doers, hardwired to do hard things. For those who know we can achieve anything with the right mindset. Thousands of years of military history & reams of science prove humans perform better when we give ourselves no option but to win. BTB leaves you with a feeling that will remain long after you finish. Infinite possibility.

gm! Burn the Boats is finally everywhere books with fiery covers are sold : ) It is a blueprint for the doers, hardwired to do hard things. For those who know we can achieve anything with the right mindset. Thousands of years of military history & reams of science prove humans perform better when we give ourselves no option but to win. BTB leaves you with a feeling that will remain long after you finish. Infinite possibility.

Matt Higgins

318,922 次观看 • 3 年前

Introducing 2️⃣ new AI systems for robotics: 🤖 ALOHA Unleashed to perform two-armed manipulation tasks 🦾 DemoStart to control a multi-fingered robotic hand They learned to tackle a range of actions requiring dexterity. Here's how. 🧵

Introducing 2️⃣ new AI systems for robotics: 🤖 ALOHA Unleashed to perform two-armed manipulation tasks 🦾 DemoStart to control a multi-fingered robotic hand They learned to tackle a range of actions requiring dexterity. Here's how. 🧵

Google DeepMind

297,118 次观看 • 1 年前

When evaluated against the WebVoyager benchmark, which tests agent performance on end-to-end real world web tasks, Project Mariner achieved a state-of-the-art result of 83.5% working as a single agent setup.

When evaluated against the WebVoyager benchmark, which tests agent performance on end-to-end real world web tasks, Project Mariner achieved a state-of-the-art result of 83.5% working as a single agent setup.

Google DeepMind

23,958 次观看 • 1 年前

Would you? Could you? Challenge your balance and speed with the thrilling water stone run! These stones dip into the water if you linger too long, requiring quick reflexes and steady footing to make it across. A fun and exciting test of agility and balance-can you master the art of running on water stones? This looks fun, but things are never as easy as they look.

Would you? Could you? Challenge your balance and speed with the thrilling water stone run! These stones dip into the water if you linger too long, requiring quick reflexes and steady footing to make it across. A fun and exciting test of agility and balance-can you master the art of running on water stones? This looks fun, but things are never as easy as they look.

NancyH

4,934,707 次观看 • 3 个月前

"Anybody who tries to do anything BIG, will always be criticized... The people who do the most criticizing are the people who are completely incapable of doing anything."

"Anybody who tries to do anything BIG, will always be criticized... The people who do the most criticizing are the people who are completely incapable of doing anything."

KABUGO

15,275 次观看 • 2 个月前

Here's a fun one you can't do in the lab: diamond melting at thousands of degrees simulated with Orb. You can simulate anything you want with it here:

Here's a fun one you can't do in the lab: diamond melting at thousands of degrees simulated with Orb. You can simulate anything you want with it here:

Tim Duignan

31,130 次观看 • 1 年前

introducing the beehiiv Media Collective: a first-of-its-kind residency program built to support independent journalism 🗞 the lineup is already stacked, but we've opened up a few more spots... more below:

introducing the beehiiv Media Collective: a first-of-its-kind residency program built to support independent journalism 🗞 the lineup is already stacked, but we've opened up a few more spots... more below:

beehiiv 🐝

10,568 次观看 • 1 年前

Introducing: Pact Quests. Do tasks → earn points → climb tiers → get the airdrop. The fun side of DeFi is now live. Join the PACT Quests 👇

Introducing: Pact Quests. Do tasks → earn points → climb tiers → get the airdrop. The fun side of DeFi is now live. Join the PACT Quests 👇

Pact Swap Labs

1,179,782 次观看 • 8 个月前

We are finally releasing a new benchmark!! #RSS2023 Main highlights are: * For real-world * Reproducible (3D printing) * 9 furniture assembly long-horizon tasks * 200+ hrs of demonstrations This apparently is my 3rd furniture-related benchmark.🥹

We are finally releasing a new benchmark!! #RSS2023 Main highlights are: * For real-world * Reproducible (3D printing) * 9 furniture assembly long-horizon tasks * 200+ hrs of demonstrations This apparently is my 3rd furniture-related benchmark.🥹

Joseph Lim

26,922 次观看 • 3 年前