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。

"Fast Foundation Stereo: When Foundation Models Meet Efficient Stereo Matching" TL;DR: distills stereo foundation models into an efficient real-time stereo matching framework, preserving high accuracy while dramatically reducing inference cost.

Alexandre Morgand

2,292 subscribers

14,827 次观看 • 1 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

Why can't “world models” just be sim? A real-time real2sim demo in the upcoming “ManiDreams” Foundation Stereo + SAM2 + Newton = Generalizable 3D physics prediction in a fast (15FPS) and lightweight (3070) way. No data or object mesh needed

Why can't “world models” just be sim? A real-time real2sim demo in the upcoming “ManiDreams” Foundation Stereo + SAM2 + Newton = Generalizable 3D physics prediction in a fast (15FPS) and lightweight (3070) way. No data or object mesh needed

Vector Wang

30,474 次观看 • 5 个月前

60fps depth : ) these are pixels streamed over the air over wifi UDP, using fast foundation stereo i need to get end to end latency down to 20ms. inference is 10 right now. wonder if its possible (it is)

60fps depth : ) these are pixels streamed over the air over wifi UDP, using fast foundation stereo i need to get end to end latency down to 20ms. inference is 10 right now. wonder if its possible (it is)

kache

23,072 次观看 • 12 天前

MusicHiFi Fast High-Fidelity Stereo Vocoding Diffusion-based audio and music generation models commonly generate music by constructing an image representation of audio (e.g., a mel-spectrogram) and then converting it to audio using a phase reconstruction model or vocoder.

MusicHiFi Fast High-Fidelity Stereo Vocoding Diffusion-based audio and music generation models commonly generate music by constructing an image representation of audio (e.g., a mel-spectrogram) and then converting it to audio using a phase reconstruction model or vocoder.

AK

27,285 次观看 • 2 年前

Excited to introduce StereoPolicy, led by Evans Han. 📷📷🤖StereoPolicy is an effective way to add geometric cues to modern robot policy models while keeping the strengths of pretrained 2D encoders. ⁉️Why stereo for robot manipulation? Monocular RGB often lacks the depth cues needed for precise manipulation, while RGB-D and point clouds can be noisy or brittle, especially on reflective and transparent objects in real-world deployment. Instead of explicitly reconstructing disparity, depth, or point clouds, StereoPolicy directly fuses synchronized left/right RGB views to learn implicit stereo cues, avoiding extra reconstruction latency that can make real-time manipulation difficult. Project Page:

Excited to introduce StereoPolicy, led by Evans Han. 📷📷🤖StereoPolicy is an effective way to add geometric cues to modern robot policy models while keeping the strengths of pretrained 2D encoders. ⁉️Why stereo for robot manipulation? Monocular RGB often lacks the depth cues needed for precise manipulation, while RGB-D and point clouds can be noisy or brittle, especially on reflective and transparent objects in real-world deployment. Instead of explicitly reconstructing disparity, depth, or point clouds, StereoPolicy directly fuses synchronized left/right RGB views to learn implicit stereo cues, avoiding extra reconstruction latency that can make real-time manipulation difficult. Project Page:

Ruohan Zhang

851,247 次观看 • 3 个月前

Presto! Distilling Steps and Layers for Accelerating Music Generation Despite advances in diffusion-based text-to-music (TTM) methods, efficient, high-quality generation remains a challenge. We introduce Presto!, an approach to inference acceleration for score-based diffusion transformers via reducing both sampling steps and cost per step. To reduce steps, we develop a new score-based distribution matching distillation (DMD) method for the EDM-family of diffusion models, the first GAN-based distillation method for TTM. To reduce the cost per step, we develop a simple, but powerful improvement to a recent layer distillation method that improves learning via better preserving hidden state variance. Finally, we combine our step and layer distillation methods together for a dual-faceted approach. We evaluate our step and layer distillation methods independently and show each yield best-in-class performance. Our combined distillation method can generate high-quality outputs with improved diversity, accelerating our base model by 10-18x (230/435ms latency for 32 second mono/stereo 44.1kHz, 15x faster than comparable SOTA) -- the fastest high-quality TTM to our knowledge.

Presto! Distilling Steps and Layers for Accelerating Music Generation Despite advances in diffusion-based text-to-music (TTM) methods, efficient, high-quality generation remains a challenge. We introduce Presto!, an approach to inference acceleration for score-based diffusion transformers via reducing both sampling steps and cost per step. To reduce steps, we develop a new score-based distribution matching distillation (DMD) method for the EDM-family of diffusion models, the first GAN-based distillation method for TTM. To reduce the cost per step, we develop a simple, but powerful improvement to a recent layer distillation method that improves learning via better preserving hidden state variance. Finally, we combine our step and layer distillation methods together for a dual-faceted approach. We evaluate our step and layer distillation methods independently and show each yield best-in-class performance. Our combined distillation method can generate high-quality outputs with improved diversity, accelerating our base model by 10-18x (230/435ms latency for 32 second mono/stereo 44.1kHz, 15x faster than comparable SOTA) -- the fastest high-quality TTM to our knowledge.

AK

30,442 次观看 • 1 年前

Getting started with an ML project? Andrew Ng shares practical tips to set up a strong foundation—choosing a reasonable algorithm, running quick sanity checks, and focusing on data quality over chasing the latest models. These steps can save time, prevent errors, and make iteration more efficient. Streamline your workflow and build better ML systems in the Machine Learning in Production course:

Getting started with an ML project? Andrew Ng shares practical tips to set up a strong foundation—choosing a reasonable algorithm, running quick sanity checks, and focusing on data quality over chasing the latest models. These steps can save time, prevent errors, and make iteration more efficient. Streamline your workflow and build better ML systems in the Machine Learning in Production course:

DeepLearning.AI

11,307 次观看 • 1 年前

This seemingly obvious prediction didn't take long to become reality. MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors Contributions: • The first real-time SLAM system using the two-view 3D reconstruction prior MASt3R [20] as a foundation. • Efficient techniques for pointmap matching, tracking and local fusion, graph construction and loop closure, and second-order global optimization. • A state-of-the-art dense SLAM system capable of handling generic, time-varying camera models. Abstract: We present a real-time monocular dense SLAM system, designed from the ground up using MASt3R, a two-view 3D reconstruction and matching prior. Equipped with this strong prior, our system remains robust on in-the-wild video sequences, making no assumptions on a fixed or parametric camera model beyond a unique camera center. Key features include: - Efficient methods for pointmap matching, camera tracking, and local fusion - Graph construction and loop closure - Second-order global optimization With known calibration, a simple modification achieves state-of-the-art performance across various benchmarks. Altogether, we propose a plug-and-play monocular SLAM system capable of producing globally-consistent poses and dense geometry while operating at 15 FPS.

This seemingly obvious prediction didn't take long to become reality. MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors Contributions: • The first real-time SLAM system using the two-view 3D reconstruction prior MASt3R [20] as a foundation. • Efficient techniques for pointmap matching, tracking and local fusion, graph construction and loop closure, and second-order global optimization. • A state-of-the-art dense SLAM system capable of handling generic, time-varying camera models. Abstract: We present a real-time monocular dense SLAM system, designed from the ground up using MASt3R, a two-view 3D reconstruction and matching prior. Equipped with this strong prior, our system remains robust on in-the-wild video sequences, making no assumptions on a fixed or parametric camera model beyond a unique camera center. Key features include: - Efficient methods for pointmap matching, camera tracking, and local fusion - Graph construction and loop closure - Second-order global optimization With known calibration, a simple modification achieves state-of-the-art performance across various benchmarks. Altogether, we propose a plug-and-play monocular SLAM system capable of producing globally-consistent poses and dense geometry while operating at 15 FPS.

MrNeRF

29,974 次观看 • 1 年前

Current world models often separate spatial reasoning from temporal modeling, leading to consistency bottlenecks and scaling limits. We developed RAYNOVA, a 4D world foundation model, to address this by unifying space and time into a single representation via a pure auto-regressive framework. The result: Data-driven high-fidelity simulation data that scales across any vehicles, anywhere. Read the full technical breakdown:

Current world models often separate spatial reasoning from temporal modeling, leading to consistency bottlenecks and scaling limits. We developed RAYNOVA, a 4D world foundation model, to address this by unifying space and time into a single representation via a pure auto-regressive framework. The result: Data-driven high-fidelity simulation data that scales across any vehicles, anywhere. Read the full technical breakdown:

Applied Intuition

11,252 次观看 • 3 个月前

Today, we’re thrilled to unveil the Arcee.ai Foundation Models, a new family of GenAI models designed from the ground up for enterprise reality. The first release—AFM-4.5B—is a 4.5-billion-parameter frontier model that delivers excellent accuracy, strict compliance, and very high cost efficiency. In short: enterprise-grade intelligence that can run anywhere—on a smartphone, at the edge, or in the cloud. For a quick taste, you can test AFM-4.5B in our playground and on For a deeper dive into the model’s training pipeline and benchmarks, details are available in our technical blog post. ➡️ Arcee AI playground: ➡️ Together AI playground: ➡️ Launch blog post: ➡️ Technical blog post: PS: As we’ll now focus on our AFM foundation models, and because we love open-source, we're opening up access to our previously closed-source language models. Details in the tech blog post!

Today, we’re thrilled to unveil the Arcee.ai Foundation Models, a new family of GenAI models designed from the ground up for enterprise reality. The first release—AFM-4.5B—is a 4.5-billion-parameter frontier model that delivers excellent accuracy, strict compliance, and very high cost efficiency. In short: enterprise-grade intelligence that can run anywhere—on a smartphone, at the edge, or in the cloud. For a quick taste, you can test AFM-4.5B in our playground and on For a deeper dive into the model’s training pipeline and benchmarks, details are available in our technical blog post. ➡️ Arcee AI playground: ➡️ Together AI playground: ➡️ Launch blog post: ➡️ Technical blog post: PS: As we’ll now focus on our AFM foundation models, and because we love open-source, we're opening up access to our previously closed-source language models. Details in the tech blog post!

Arcee.ai

21,934 次观看 • 1 年前

STUDIO CHAIN Features: - High throughput and low latency with a focus on scalability for high demand products and enterprise apps - Efficient consensus mechanisms - Custom gas token - Redundancy, security, and resilience - Cross chain interoperability - Customizability for product needs - Fast data processing, enabling interactive products and real-time applications - Off-chain channels The Karrat Foundation is opening an opportunity for leaders in the space to collaborate with us and the Karrat community on building an exciting blockchain initiative. Bring your expertise to the table and be part of something transformative. $KARRAT Empowering gaming, AI and entertainment ecosystems.

STUDIO CHAIN Features: - High throughput and low latency with a focus on scalability for high demand products and enterprise apps - Efficient consensus mechanisms - Custom gas token - Redundancy, security, and resilience - Cross chain interoperability - Customizability for product needs - Fast data processing, enabling interactive products and real-time applications - Off-chain channels The Karrat Foundation is opening an opportunity for leaders in the space to collaborate with us and the Karrat community on building an exciting blockchain initiative. Bring your expertise to the table and be part of something transformative. $KARRAT Empowering gaming, AI and entertainment ecosystems.

Karrat

224,642 次观看 • 1 年前

New course: Efficient Inference with SGLang: Text and Image Generation, built in partnership with LMSys LMSYS Org and RadixArk RadixArk, and taught by Richard Chen Richard Chen, a Member of Technical Staff at RadixArk. Running LLMs in production is expensive, and much of that cost comes from redundant computation. This short course teaches you to eliminate that waste using SGLang, an open-source inference framework that caches computation already done and reuses it across future requests. When ten users share the same system prompt, SGLang processes it once, not ten times. The speedups compound quickly, especially when there's a lot of shared context across requests. Skills you'll gain: - Implement a KV cache from scratch to eliminate redundant computation within a single request - Scale caching across users and requests with RadixAttention, so shared context is only processed once - Accelerate image generation with diffusion models using SGLang's caching and multi-GPU parallelism Join and learn to make LLM inference faster and more cost-efficient at scale!

New course: Efficient Inference with SGLang: Text and Image Generation, built in partnership with LMSys LMSYS Org and RadixArk RadixArk, and taught by Richard Chen Richard Chen, a Member of Technical Staff at RadixArk. Running LLMs in production is expensive, and much of that cost comes from redundant computation. This short course teaches you to eliminate that waste using SGLang, an open-source inference framework that caches computation already done and reuses it across future requests. When ten users share the same system prompt, SGLang processes it once, not ten times. The speedups compound quickly, especially when there's a lot of shared context across requests. Skills you'll gain: - Implement a KV cache from scratch to eliminate redundant computation within a single request - Scale caching across users and requests with RadixAttention, so shared context is only processed once - Accelerate image generation with diffusion models using SGLang's caching and multi-GPU parallelism Join and learn to make LLM inference faster and more cost-efficient at scale!

Andrew Ng

102,403 次观看 • 5 个月前

Type “building” and the model finds the buildings. This is what deploying Google Earth AI imagery models in advanced spatial intelligence systems looks like in practice. Inside Vantor Sentry, Google Earth AI’s Open Vocabulary Detection (OVD) models allow analysts to identify objects in high-resolution satellite imagery simply by typing what they’re looking for. No pre-training. No custom labeling workflow. Combined with the quality and accuracy of Vantor’s spatial foundation—including the satellite imagery you see here—this provides sovereign operators with an unparalleled capability. Deployed inside a secure, air-gapped environment, this capability accelerates: 🔒 Persistent site monitoring 🔄 Change detection 🏗️ Infrastructure analysis 🗺️ Mission planning And because these models are integrated into Tensorglobe, they don’t operate in isolation. They can be fine-tuned locally using Vantor satellite imagery, third-party commercial data, sovereign sensor feeds, and customer-owned private archives. This is how foundation models become operational tools. Learn more:

Type “building” and the model finds the buildings. This is what deploying Google Earth AI imagery models in advanced spatial intelligence systems looks like in practice. Inside Vantor Sentry, Google Earth AI’s Open Vocabulary Detection (OVD) models allow analysts to identify objects in high-resolution satellite imagery simply by typing what they’re looking for. No pre-training. No custom labeling workflow. Combined with the quality and accuracy of Vantor’s spatial foundation—including the satellite imagery you see here—this provides sovereign operators with an unparalleled capability. Deployed inside a secure, air-gapped environment, this capability accelerates: 🔒 Persistent site monitoring 🔄 Change detection 🏗️ Infrastructure analysis 🗺️ Mission planning And because these models are integrated into Tensorglobe, they don’t operate in isolation. They can be fine-tuned locally using Vantor satellite imagery, third-party commercial data, sovereign sensor feeds, and customer-owned private archives. This is how foundation models become operational tools. Learn more:

Vantor

16,356 次观看 • 6 个月前

$Meet My AI Ears. A lot of folks ask me how I capture ASMR video and audio for training of AI? I always use Binaural 3D audio and have for decades in different forms. But how? A Brief History of Binaural Recording Binaural recording, the foundation of 3D audio, dates back to 1881 when French inventor Clément Ader created the first system using multiple telephone transmitters at the Paris Opera to transmit stereo sound to listeners, simulating spatial presence. By the 1920s, patents like W. Bartlett Jones’ 1927 filing advanced devices for capturing and reproducing “binaural” signals. The 1930s saw Alan Blumlein’s work on stereophonic sound, which he termed “binaural,” laying groundwork for modern stereo. Commercial milestones hit in the 1950s with binaural records from labels like Cook Laboratories and the first binaural reel-to-reel tapes. A resurgence came in the 1970s with Neumann’s KU-80 dummy head, the first commercial binaural system. Today, it’s integral to VR, ASMR, and immersive media. The Technology of Binaural 3D Audio At its core, binaural recording mimics human hearing by using two microphones placed in ear-shaped molds or a dummy head, separated like human ears (typically 14-18 cm apart). This captures spatial cues: interaural time differences (ITD) for sound arrival timing, interaural level differences (ILD) for volume variations, and head-related transfer functions (HRTF) that account for how the head, torso, and pinnae filter sounds. The result? A 3D soundscape that tricks the brain into perceiving direction, distance, and elevation when played back via headphones—no speakers needed for immersion. Advanced setups use omnidirectional capsules (e.g., DPA 4060) for high-fidelity capture, often in silicone ears to replicate natural diffraction. I use the 3DIO Microphones today but I would cover a dummy head in texture material and place two stereo (4 channels) microphones in each ear. I would then mix down the resulting signals into stereo. The 3DIO series features dual omnidirectional capsules in realistic silicone ear molds, spaced 14 cm apart for compact, accurate 3D capture based on over 13 years of research into human hearing. Models like the Free Space Pro II use premium DPA 4060 CORE capsules for ultra-low noise and high sensitivity, delivering stereo output ideal for immersive applications like game audio. Today just about any ASMR producer uses these. But I use them to capture, curate and archive sound and video we will lose or just about lost for AI training in a way no model or AI company is doing today. I am duplicating the human 3D binaural audio experience and memory. Below is a crude demonstration. If you can listen in headphones. Or turn your phone sideways to feel the audio space. I’ll have a far more professional demo soon to show the real power of 3D audio. (Oh that music is a MIDI player that uses disks to play).$

Meet My AI Ears. A lot of folks ask me how I capture ASMR video and audio for training of AI? I always use Binaural 3D audio and have for decades in different forms. But how? A Brief History of Binaural Recording Binaural recording, the foundation of 3D audio, dates back to 1881 when French inventor Clément Ader created the first system using multiple telephone transmitters at the Paris Opera to transmit stereo sound to listeners, simulating spatial presence. By the 1920s, patents like W. Bartlett Jones’ 1927 filing advanced devices for capturing and reproducing “binaural” signals. The 1930s saw Alan Blumlein’s work on stereophonic sound, which he termed “binaural,” laying groundwork for modern stereo. Commercial milestones hit in the 1950s with binaural records from labels like Cook Laboratories and the first binaural reel-to-reel tapes. A resurgence came in the 1970s with Neumann’s KU-80 dummy head, the first commercial binaural system. Today, it’s integral to VR, ASMR, and immersive media. The Technology of Binaural 3D Audio At its core, binaural recording mimics human hearing by using two microphones placed in ear-shaped molds or a dummy head, separated like human ears (typically 14-18 cm apart). This captures spatial cues: interaural time differences (ITD) for sound arrival timing, interaural level differences (ILD) for volume variations, and head-related transfer functions (HRTF) that account for how the head, torso, and pinnae filter sounds. The result? A 3D soundscape that tricks the brain into perceiving direction, distance, and elevation when played back via headphones—no speakers needed for immersion. Advanced setups use omnidirectional capsules (e.g., DPA 4060) for high-fidelity capture, often in silicone ears to replicate natural diffraction. I use the 3DIO Microphones today but I would cover a dummy head in texture material and place two stereo (4 channels) microphones in each ear. I would then mix down the resulting signals into stereo. The 3DIO series features dual omnidirectional capsules in realistic silicone ear molds, spaced 14 cm apart for compact, accurate 3D capture based on over 13 years of research into human hearing. Models like the Free Space Pro II use premium DPA 4060 CORE capsules for ultra-low noise and high sensitivity, delivering stereo output ideal for immersive applications like game audio. Today just about any ASMR producer uses these. But I use them to capture, curate and archive sound and video we will lose or just about lost for AI training in a way no model or AI company is doing today. I am duplicating the human 3D binaural audio experience and memory. Below is a crude demonstration. If you can listen in headphones. Or turn your phone sideways to feel the audio space. I’ll have a far more professional demo soon to show the real power of 3D audio. (Oh that music is a MIDI player that uses disks to play).

Brian Roemmele

30,800 次观看 • 8 个月前

🥳Excited to share our latest work: "Diff-A-Riff"! 🥁 A Latent Diffusion Model that generates instrumental accompaniments for any musical input, specifically tailored for music producers! It's faster, lighter, and produces superior audio quality. Control via text/audio references. 48kHz sample rate, (pseudo) stereo, ~3Gb memory, takes 6 seconds to generate 90 seconds of music. Trained on a single GPU. 📜 🎶 🎸 "Diff-A-Riff" adapts to any musical input, following the artist's unique style. 🎛️ Optional controls via text prompts, audio references, interpolation slider, pseudo-stereo width and loop intensity. 🎚️ It produces state-of-the-art audio quality indistinguishable from real data by human raters and operates at unprecedented speed. 🧠 "Diff-A-Riff" is smaller and more efficient than previous models thanks to its Consistency Autoencoder, making it accessible and practical for various applications. Big shoutout to my outer space colleagues: Javier Nistal, the Machine in "machine learning" 🚄, Marco Pasini, the neural net whisperer 🤫, Cyran Aouameur, the troubleshootah 🛠️, Maarten Grachten, aka MaartenGPT 🤖. #Teamwork #AI #MusicTech #Innovation Javier Nistal Marco Pasini Cyran Aouameur SonyCSL(Paris)_Music Team

🥳Excited to share our latest work: "Diff-A-Riff"! 🥁 A Latent Diffusion Model that generates instrumental accompaniments for any musical input, specifically tailored for music producers! It's faster, lighter, and produces superior audio quality. Control via text/audio references. 48kHz sample rate, (pseudo) stereo, ~3Gb memory, takes 6 seconds to generate 90 seconds of music. Trained on a single GPU. 📜 🎶 🎸 "Diff-A-Riff" adapts to any musical input, following the artist's unique style. 🎛️ Optional controls via text prompts, audio references, interpolation slider, pseudo-stereo width and loop intensity. 🎚️ It produces state-of-the-art audio quality indistinguishable from real data by human raters and operates at unprecedented speed. 🧠 "Diff-A-Riff" is smaller and more efficient than previous models thanks to its Consistency Autoencoder, making it accessible and practical for various applications. Big shoutout to my outer space colleagues: Javier Nistal, the Machine in "machine learning" 🚄, Marco Pasini, the neural net whisperer 🤫, Cyran Aouameur, the troubleshootah 🛠️, Maarten Grachten, aka MaartenGPT 🤖. #Teamwork #AI #MusicTech #Innovation Javier Nistal Marco Pasini Cyran Aouameur SonyCSL(Paris)_Music Team

Stefan Lattner

17,710 次观看 • 2 年前

🚨 BREAKING: Big news in the computer vision world! 🎥 Luxonis | Robotic Vision just dropped its new OAK 4 line, and it’s a big upgrade for edge computer vision. Instead of being “just a stereo camera,” OAK 4 is a fully standalone vision computer with 52 TOPS of on-device AI. Models run locally, depth is computed locally, and no external PC or cloud pipeline is required. This is why robotics teams love it: lower latency, lower cost, fewer failure points in the field. The hardware is built for the real-world. IP67, shock-resistant, wide-FOV RGB + stereo pair, IR projection, IMU, audio, and a patent-pending calibration system that keeps depth accurate even when conditions change. But the real move is the platform. With Luxonis Hub, you can deploy models, grab telemetry, push OTA updates, or collect data when performance drifts, all from a unified interface. It turns a single device into an end-to-end edge CV system. Most customers today in robotics are groups who just want something that works: AMRs, bin-picking systems, trailer-loading robots, and ag-tech. 🤖 And they all say the same thing, the appeal isn’t raw TOPS, it’s the all-in-one simplicity that lets them scale without building custom infrastructure. Feels like the direction edge vision has been waiting for: rugged hardware + high-throughput on-device compute + a real management layer. A next step toward “plug-and-deploy” perception for robots. 🔗 Find out more here: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

🚨 BREAKING: Big news in the computer vision world! 🎥 Luxonis | Robotic Vision just dropped its new OAK 4 line, and it’s a big upgrade for edge computer vision. Instead of being “just a stereo camera,” OAK 4 is a fully standalone vision computer with 52 TOPS of on-device AI. Models run locally, depth is computed locally, and no external PC or cloud pipeline is required. This is why robotics teams love it: lower latency, lower cost, fewer failure points in the field. The hardware is built for the real-world. IP67, shock-resistant, wide-FOV RGB + stereo pair, IR projection, IMU, audio, and a patent-pending calibration system that keeps depth accurate even when conditions change. But the real move is the platform. With Luxonis Hub, you can deploy models, grab telemetry, push OTA updates, or collect data when performance drifts, all from a unified interface. It turns a single device into an end-to-end edge CV system. Most customers today in robotics are groups who just want something that works: AMRs, bin-picking systems, trailer-loading robots, and ag-tech. 🤖 And they all say the same thing, the appeal isn’t raw TOPS, it’s the all-in-one simplicity that lets them scale without building custom infrastructure. Feels like the direction edge vision has been waiting for: rugged hardware + high-throughput on-device compute + a real management layer. A next step toward “plug-and-deploy” perception for robots. 🔗 Find out more here: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

41,955 次观看 • 9 个月前

Been looking into RICE AI ( ◉ - ◉ ) lately, and it’s one of the few projects actually tackling a real challenge in robotics and AGI: the lack of high-quality training data. Robots can’t get truly intelligent without it. They building a decentralized way to collect and share robotics data, using a DePIN network to train physical AI foundation models. The project was even hand-picked by CZ as a winner of the Dubai BNB Chain Demo Day, and it’s backed by Floki while also being part of the NVIDIA Inception Program. They also launched FLOKI Minibot M1 - a small AI companion that doubles as a data node. Every interaction with it feeds the RICE AI Foundry, the first decentralized platform for Robotics Foundation Models, and contributors earn $RICE tokens in return. And it’s working: – 800 minibots sold in 24h – 33,000% oversubscribed Binance IDO – 500+ robots already deployed worldwide Feels like a project with real long-term potential. Worth keeping an eye on. RICE AI ( ◉ - ◉ )

Been looking into RICE AI ( ◉ - ◉ ) lately, and it’s one of the few projects actually tackling a real challenge in robotics and AGI: the lack of high-quality training data. Robots can’t get truly intelligent without it. They building a decentralized way to collect and share robotics data, using a DePIN network to train physical AI foundation models. The project was even hand-picked by CZ as a winner of the Dubai BNB Chain Demo Day, and it’s backed by Floki while also being part of the NVIDIA Inception Program. They also launched FLOKI Minibot M1 - a small AI companion that doubles as a data node. Every interaction with it feeds the RICE AI Foundry, the first decentralized platform for Robotics Foundation Models, and contributors earn $RICE tokens in return. And it’s working: – 800 minibots sold in 24h – 33,000% oversubscribed Binance IDO – 500+ robots already deployed worldwide Feels like a project with real long-term potential. Worth keeping an eye on. RICE AI ( ◉ - ◉ )

Christiaan

12,696 次观看 • 1 年前

Meet LongCat-Video-Avatar 1.5🐱—our upgraded, open-source digital human framework. Built for real production, not just short demos. What's New: 🔹 Upgraded Audio Encoder: Replaces Wav2Vec2 with Whisper-Large, yielding significantly smoother and more natural lip dynamics. 🔹 Production-Ready Stability: Achieves accurate lip-synchronization, full-body temporal stability, and robust long-video generation with strict identity consistency. 🔹 Stylized Domain Generalization: Robustly generalizes to anime, animals, and complex real-world conditions such as multi-person interactions and object handling. 🔹 Efficient 8-Step Inference: Advanced step distillation accelerates inference to 8 NFE, balancing cost-effective serving with exceptional visual fidelity. 📊 LongCat-Video-Avatar 1.5 performs strongly in realism, naturalness, and stability, outperforming leading open-source models and closed systems. 🐱 Avatar 1.5 framework is now open source: 🔗 Weights & Code: 🔗 HuggingFace: 🔗 Tech Report: 🔗 Project Page:

Meituan LongCat

31,437 次观看 • 3 个月前

$BREAKING: SambaNova Announces First Close of $1 Billion Series E at $11B Valuation Led by General Atlantic, with participation from Seligman Ventures, T. Rowe Price, & Capital Group SambaNova CEO Rodrigo Liang (Rodrigo Liang) says AI is entering a new era of "premium inference" "The world of inference is running into an economics problem." Enter: new SambaNova "SM50" "A cloud-scale RDU that allows us to deliver premium inference at significantly higher performance than you can get with GPUs, at a fraction of the cost & a fraction of the power." Why does that matter? "When you're running faster with the high-accuracy models, you can charge more at a lower cost, allowing our service providers to generate more margin." Liang says the shift is just beginning: "The world's moving into inference." And after today's funding announcement: "We're using this capital to accelerate our supply chain and make sure we can deliver the racks to customers worldwide." Full interview from Paris coming soon.$

BREAKING: SambaNova Announces First Close of $1 Billion Series E at $11B Valuation Led by General Atlantic, with participation from Seligman Ventures, T. Rowe Price, & Capital Group SambaNova CEO Rodrigo Liang (Rodrigo Liang) says AI is entering a new era of "premium inference" "The world of inference is running into an economics problem." Enter: new SambaNova "SM50" "A cloud-scale RDU that allows us to deliver premium inference at significantly higher performance than you can get with GPUs, at a fraction of the cost & a fraction of the power." Why does that matter? "When you're running faster with the high-accuracy models, you can charge more at a lower cost, allowing our service providers to generate more margin." Liang says the shift is just beginning: "The world's moving into inference." And after today's funding announcement: "We're using this capital to accelerate our supply chain and make sure we can deliver the racks to customers worldwide." Full interview from Paris coming soon.

Molly O’Shea

14,162 次观看 • 2 个月前

Foundation models are enough to solve robotics! Unfortunately, this is not true. We keep hearing that Vision-Language-Action (VLA) models struggle because of the gap between static training and the dynamic real world. A German startup (Sereact) just released a solution that bridges this gap perfectly. They are introducing a new paradigm called Interactive RL Policy Patching. It's a distributed framework that allows robots to self-learn from human corrections without needing full retraining. When a robot fails, a human operator provides a brief "patch" or demonstration. The system then uses online off-policy reinforcement learning to update the behavior instantly. This is powered by a massive foundation model trained on hundreds of millions of interactions from over 100 deployed robot stations. The best part is the distributed parameter synchronization... When one robot learns a fix, the update is published fleet-wide... meaning the entire swarm gets smarter from a single human intervention. They are already proving this on complex manipulation tasks like shoe unboxing and screw sorting, drastically reducing the data needed to handle edge cases. Real-world environments are unforgiving, and I love seeing systems that can actually adapt on the fly! 📍 More info:

Foundation models are enough to solve robotics! Unfortunately, this is not true. We keep hearing that Vision-Language-Action (VLA) models struggle because of the gap between static training and the dynamic real world. A German startup (Sereact) just released a solution that bridges this gap perfectly. They are introducing a new paradigm called Interactive RL Policy Patching. It's a distributed framework that allows robots to self-learn from human corrections without needing full retraining. When a robot fails, a human operator provides a brief "patch" or demonstration. The system then uses online off-policy reinforcement learning to update the behavior instantly. This is powered by a massive foundation model trained on hundreds of millions of interactions from over 100 deployed robot stations. The best part is the distributed parameter synchronization... When one robot learns a fix, the update is published fleet-wide... meaning the entire swarm gets smarter from a single human intervention. They are already proving this on complex manipulation tasks like shoe unboxing and screw sorting, drastically reducing the data needed to handle edge cases. Real-world environments are unforgiving, and I love seeing systems that can actually adapt on the fly! 📍 More info:

Ilir Aliu

18,210 次观看 • 7 个月前

I used NotebookLM to study Google new breakthrough with TurboQuant and used Video overview to study the subject, best learning tool in the world at the moment. TurboQuant: Redefining AI Efficiency with Extreme Compression Google Research has introduced TurboQuant, a suite of advanced algorithms designed to dramatically compress the data used by large language models and search engines. By utilizing specialized techniques like PolarQuant and Quantized Johnson-Lindenstrauss, the system transforms complex information into a compact "shorthand" that requires significantly less memory. This innovation specifically addresses the key-value cache bottleneck, allowing AI models to process massive amounts of text faster without losing accuracy. Testing demonstrates that these methods can shrink data size by six times while actually increasing operational speed on high-end hardware. Ultimately, these theoretical advancements enable more efficient semantic search and high-performance AI applications at a global scale.

I used NotebookLM to study Google new breakthrough with TurboQuant and used Video overview to study the subject, best learning tool in the world at the moment. TurboQuant: Redefining AI Efficiency with Extreme Compression Google Research has introduced TurboQuant, a suite of advanced algorithms designed to dramatically compress the data used by large language models and search engines. By utilizing specialized techniques like PolarQuant and Quantized Johnson-Lindenstrauss, the system transforms complex information into a compact "shorthand" that requires significantly less memory. This innovation specifically addresses the key-value cache bottleneck, allowing AI models to process massive amounts of text faster without losing accuracy. Testing demonstrates that these methods can shrink data size by six times while actually increasing operational speed on high-end hardware. Ultimately, these theoretical advancements enable more efficient semantic search and high-performance AI applications at a global scale.

Emily

14,648 次观看 • 5 个月前