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.

Introducing ACT-2 Preview The first robotics model to unify broad generalization with high reliability. A single fine-tuning example can teach Memo a new behavior that generalizes. Zero shot, real unseen homes, 99% success rate.

Tony Zhao

97,353 subscribers

279,647 Aufrufe • vor 17 Stunden •via X (Twitter)

Wissenschaft & Technologie Bildung Gaming

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Introducing RL-100: Performant Robotic Manipulation with Real-World Reinforcement Learning. 7 real robot tasks, 900/900 successes. Up to 250 consecutive trials in one task, running 2 hours nonstop without failure. High success rate against physical disturbances, zero-shot, and few-shot adaptation Our first step toward a deployable robot learning system.

Introducing RL-100: Performant Robotic Manipulation with Real-World Reinforcement Learning. 7 real robot tasks, 900/900 successes. Up to 250 consecutive trials in one task, running 2 hours nonstop without failure. High success rate against physical disturbances, zero-shot, and few-shot adaptation Our first step toward a deployable robot learning system.

Kun Lei

90,870 Aufrufe • vor 9 Monaten

In just ~3 months, as a solo founder with no prior robotics experience, General Trajectory trained a foundation model for dexterous manipulation that lets humanoid robots pick up unseen objects and perform real-world work. It generalizes to novel objects and scenes, including cases where prior SoTA models achieve 0% success. Congrats on the launch Joshua!

In just ~3 months, as a solo founder with no prior robotics experience, General Trajectory trained a foundation model for dexterous manipulation that lets humanoid robots pick up unseen objects and perform real-world work. It generalizes to novel objects and scenes, including cases where prior SoTA models achieve 0% success. Congrats on the launch Joshua!

Y Combinator

68,556 Aufrufe • vor 6 Monaten

Yesterday, we live demo-ed a “generalist” VLA for (I think) the first time ever to a broad audience Robotics: Science and Systems. Bring any object. Ask anything. New environment, new instructions, no fine-tuning. Just impeccable vibes! ✨

Yesterday, we live demo-ed a “generalist” VLA for (I think) the first time ever to a broad audience Robotics: Science and Systems. Bring any object. Ask anything. New environment, new instructions, no fine-tuning. Just impeccable vibes! ✨

Dhruv Shah

56,610 Aufrufe • vor 1 Jahr

today we're introducing lipsync-2, the world's first zero-shot lipsyncing model that preserves a speaker's unique style w/o additional training or fine-tuning lipsync-2 is a leap forward in realism, expressiveness, control, quality, and speed across live-action, animated, and AI-generated video lipsync-2 is rolling out in GA today 🧵

today we're introducing lipsync-2, the world's first zero-shot lipsyncing model that preserves a speaker's unique style w/o additional training or fine-tuning lipsync-2 is a leap forward in realism, expressiveness, control, quality, and speed across live-action, animated, and AI-generated video lipsync-2 is rolling out in GA today 🧵

sync. labs

89,616 Aufrufe • vor 1 Jahr

Super excited for the release of Robot Utility Models (RUMs)! RUMs is a simple method to build zero-shot robot policies that can solve useful tasks in completely new homes without any additional training often at 90%+ success rate. 🧵👇

Super excited for the release of Robot Utility Models (RUMs)! RUMs is a simple method to build zero-shot robot policies that can solve useful tasks in completely new homes without any additional training often at 90%+ success rate. 🧵👇

Lerrel Pinto

56,591 Aufrufe • vor 1 Jahr

Introducing Dynamism v1 (DYNA-1) by Dyna Robotics – the first robot foundation model built for round-the-clock, high-throughput dexterous autonomy. Here is a time-lapse video of our model autonomously folding 850+ napkins in a span of 24 hours with • 99.4% success rate — zero human intervention • 60% human throughput speed • 4.3/5 quality ratings (set by the client) A thread on our motivation, insights and results:

Introducing Dynamism v1 (DYNA-1) by Dyna Robotics – the first robot foundation model built for round-the-clock, high-throughput dexterous autonomy. Here is a time-lapse video of our model autonomously folding 850+ napkins in a span of 24 hours with • 99.4% success rate — zero human intervention • 60% human throughput speed • 4.3/5 quality ratings (set by the client) A thread on our motivation, insights and results:

Jason Ma

519,363 Aufrufe • vor 1 Jahr

Big News! Meta just released Segment Anything, a new AI model that can "cut out" any object, in any image/video, with a single click. The model is designed and trained to be promptable, so it can transfer zero-shot to new image distributions and tasks.

Big News! Meta just released Segment Anything, a new AI model that can "cut out" any object, in any image/video, with a single click. The model is designed and trained to be promptable, so it can transfer zero-shot to new image distributions and tasks.

Lior Alexander

290,190 Aufrufe • vor 3 Jahren

🚀🚀🚀 Ever wondered what it takes for robots to handle real-world household tasks? long-horizon execution, deformable object dexterity, and unseen object generalization — meet GR-3, ByteDance Seed’s new Vision-Language-Action (VLA) model! GR-3 is a generalizable Vision-Language-Action (VLA) model with strong capabilities in complex long-horizon tasks. It understands unseen abstract concepts, manipulates deformable objects robustly, and adapts to novel settings with minimal human data. ✨ Generalization: Generalizes well to unseen objects, environments, and even instructions with abstract concepts. ✨ Long-Horizon Manipulation: Completes long-horizon tasks with strong instruction-following capabilities. ✨ Deformable Object Manipulation: Manipulate deformable objects robustly. Project Page: Arxiv: #ByteDance #ByteDanceSeed #GR3 #VLA #Robotics #FoundationModels

🚀🚀🚀 Ever wondered what it takes for robots to handle real-world household tasks? long-horizon execution, deformable object dexterity, and unseen object generalization — meet GR-3, ByteDance Seed’s new Vision-Language-Action (VLA) model! GR-3 is a generalizable Vision-Language-Action (VLA) model with strong capabilities in complex long-horizon tasks. It understands unseen abstract concepts, manipulates deformable objects robustly, and adapts to novel settings with minimal human data. ✨ Generalization: Generalizes well to unseen objects, environments, and even instructions with abstract concepts. ✨ Long-Horizon Manipulation: Completes long-horizon tasks with strong instruction-following capabilities. ✨ Deformable Object Manipulation: Manipulate deformable objects robustly. Project Page: Arxiv: #ByteDance #ByteDanceSeed #GR3 #VLA #Robotics #FoundationModels

Xiao Ma

46,323 Aufrufe • vor 1 Jahr

A new milestone for real-time accurate 3D spatial computing! Introducing ⚡️Fast-FoundationStereo⚡️, a real-time zero-shot stereo depth estimation model that accelerates the original FoundationStereo by >10x with comparable quality. Details in threads 🧵 (1/N)

A new milestone for real-time accurate 3D spatial computing! Introducing ⚡️Fast-FoundationStereo⚡️, a real-time zero-shot stereo depth estimation model that accelerates the original FoundationStereo by >10x with comparable quality. Details in threads 🧵 (1/N)

Bowen Wen

77,058 Aufrufe • vor 7 Monaten

We are excited to announce CLIN 🤖: The first continually learning language agent that excels in both task adaptation and generalization to unseen tasks and environments in a pure zero-shot setup. Aristo Team at Ai2 Ai2 Website: Let's dive in 🧵 (1/n)

We are excited to announce CLIN 🤖: The first continually learning language agent that excels in both task adaptation and generalization to unseen tasks and environments in a pure zero-shot setup. Aristo Team at Ai2 Ai2 Website: Let's dive in 🧵 (1/n)

Bodhisattwa Majumder

35,052 Aufrufe • vor 2 Jahren

HRM-Text 101 is here. This tutorial takes you from zero to one: from setup to fine-tuning to evaluation. Download the base checkpoint. Fine-tune it on a real task. Evaluate the results. End to end, on a single GPU. Watch the tutorial and start building with HRM-Text.

HRM-Text 101 is here. This tutorial takes you from zero to one: from setup to fine-tuning to evaluation. Download the base checkpoint. Fine-tune it on a real task. Evaluate the results. End to end, on a single GPU. Watch the tutorial and start building with HRM-Text.

Sapient Intelligence

187,734 Aufrufe • vor 1 Monat

Generalist AI has just broken the "impossible triangle" of speed, reliability, and intelligence in robotics. They’ve pushed their embodied foundation model forward in a big way: GEN-1 hits “Mastery” on simple physical tasks,99% average success rate, and it can improvise when things go wrong. Smooth, natural, fast(factory owners must be very interested)👇 >Folding boxes: 200 runs at 99% success in ~12 seconds ( ~34s before) >Packing phones, folding T-shirts, servicing robot vacuums,hundreds of reps with almost zero failures > Intelligent improvisation, handling uncertain tasks >Needs only about 1 hour of robot-specific data per task This feels like a real step toward humanoid robots that are actually reliable enough for factories, warehouse or homes. Physical AGI is accelerating

Generalist AI has just broken the "impossible triangle" of speed, reliability, and intelligence in robotics. They’ve pushed their embodied foundation model forward in a big way: GEN-1 hits “Mastery” on simple physical tasks,99% average success rate, and it can improvise when things go wrong. Smooth, natural, fast(factory owners must be very interested)👇 >Folding boxes: 200 runs at 99% success in ~12 seconds ( ~34s before) >Packing phones, folding T-shirts, servicing robot vacuums,hundreds of reps with almost zero failures > Intelligent improvisation, handling uncertain tasks >Needs only about 1 hour of robot-specific data per task This feels like a real step toward humanoid robots that are actually reliable enough for factories, warehouse or homes. Physical AGI is accelerating

CyberRobo

25,519 Aufrufe • vor 3 Monaten

Ex-NVIDIA engineer who built Unsloth explained RL, kernels, reasoning, quantization, and agents in 2 hours 42 minutes - better than $5000 fine-tuning bootcamps. pick the base model -> write triton kernels for 2x faster fine-tune -> quantize to 4-bit -> run GRPO/DPO -> ship a reasoning model on your single GPU. That loop is why Unsloth is the default way to fine-tune Llama, Qwen, Gemma, and Phi on hardware you already own. Unsloth + Triton kernels + 4-bit quantization + GRPO/DPO + single-GPU fine-tuning - that's the stack. Watch and save it, then fine-tune your first model tonight.

Ex-NVIDIA engineer who built Unsloth explained RL, kernels, reasoning, quantization, and agents in 2 hours 42 minutes - better than $5000 fine-tuning bootcamps. pick the base model -> write triton kernels for 2x faster fine-tune -> quantize to 4-bit -> run GRPO/DPO -> ship a reasoning model on your single GPU. That loop is why Unsloth is the default way to fine-tune Llama, Qwen, Gemma, and Phi on hardware you already own. Unsloth + Triton kernels + 4-bit quantization + GRPO/DPO + single-GPU fine-tuning - that's the stack. Watch and save it, then fine-tune your first model tonight.

h100envy

486,016 Aufrufe • vor 7 Tagen

BIGAI’s Model-Enabled Embodied Robot Hits 99% Success in SMT Factories The Beijing Institute for General Artificial Intelligence (BIGAI) just deployed its first large-model-enabled Embodied AI Robot for SMT material picking, achieving unmanned, multi-machine collaborative operation in real factory environments. This system utilizes mobile visual servo grasping and a predefined model to deliver millimeter-level stable operations with a 99% success rate. Crucially, the robot integrates seamlessly with factory MES systems via full-link coordination and employs autonomous semantic path planning for high-precision navigation and industrial-grade stability.

BIGAI’s Model-Enabled Embodied Robot Hits 99% Success in SMT Factories The Beijing Institute for General Artificial Intelligence (BIGAI) just deployed its first large-model-enabled Embodied AI Robot for SMT material picking, achieving unmanned, multi-machine collaborative operation in real factory environments. This system utilizes mobile visual servo grasping and a predefined model to deliver millimeter-level stable operations with a 99% success rate. Crucially, the robot integrates seamlessly with factory MES systems via full-link coordination and employs autonomous semantic path planning for high-precision navigation and industrial-grade stability.

RoboHub🤖

27,794 Aufrufe • vor 9 Monaten

Personalized 3D Generative Avatars from a Single Portrait Contributions: 1. Generate a personalized 3D avatar from a reference portrait image with controllable facial attributes. 2. Create high-quality synthetic 2D video datasets with diverse attribute editing from a reference portrait image. 3. Use latent space regularization with face morphing supervision for a continuous and smooth latent space, enhancing the generative ability for unseen or interpolated attribute appearances. 4. Employ an efficient fine-tuning technique via Low-Rank Adaptation (LoRA) [26] to integrate any new facial attribute into the avatar model.

MrNeRF

20,507 Aufrufe • vor 1 Jahr

Introducing Lemon Slice Live: the first real-time audio-video AI model Anyone can video chat with any character by just uploading a single photo. Every pixel on the screen is rendered at 25fps in real-time by a transformer model. Here’s how we built it + a live demo! 👇

Introducing Lemon Slice Live: the first real-time audio-video AI model Anyone can video chat with any character by just uploading a single photo. Every pixel on the screen is rendered at 25fps in real-time by a transformer model. Here’s how we built it + a live demo! 👇

LemonSlice

171,007 Aufrufe • vor 1 Jahr

Robotics just hit a dexterity milestone 🤯! Sharpa Robotics demonstrated autonomous dual-hand apple peeling using its new MoDE-VLA system. Using human-like dexterous hands with tactile sensing, the robot can feel contact and adjust its grip while rotating and peeling the apple. While the system achieved 30% success, the 73% peel completion rate shows robots are starting to master the fine, contact-rich manipulation needed for real world tasks.

Robotics just hit a dexterity milestone 🤯! Sharpa Robotics demonstrated autonomous dual-hand apple peeling using its new MoDE-VLA system. Using human-like dexterous hands with tactile sensing, the robot can feel contact and adjust its grip while rotating and peeling the apple. While the system achieved 30% success, the 73% peel completion rate shows robots are starting to master the fine, contact-rich manipulation needed for real world tasks.

SciTech Era

39,156 Aufrufe • vor 4 Monaten

Microsoft's new Florence 2 is big for Computer Vision. It's a merge between Text and Vision. With a single prompt you can instruct the model to do CV tasks like captioning, object detection, grounding, and segmentation. The best part, it only uses a single backbone to handle everything. ▸ Excels in zero-shot performance ▸ Unified model for detection, captioning, etc. ▸ FLD-5B dataset: 5B+ annotations, 126M images ▸ New benchmarks (>5.5+) on COCO, ADE20K

Microsoft's new Florence 2 is big for Computer Vision. It's a merge between Text and Vision. With a single prompt you can instruct the model to do CV tasks like captioning, object detection, grounding, and segmentation. The best part, it only uses a single backbone to handle everything. ▸ Excels in zero-shot performance ▸ Unified model for detection, captioning, etc. ▸ FLD-5B dataset: 5B+ annotations, 126M images ▸ New benchmarks (>5.5+) on COCO, ADE20K

Lior Alexander

186,560 Aufrufe • vor 2 Jahren

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

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

The Humanoid Hub

35,204 Aufrufe • vor 5 Monaten