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.

Today we open-source LingBot-Video — the first MoE-based video foundation model built for embodied intelligence. 🔹30B params, only 3B active at inference. 🔹Augmented with 70K hours of embodied data on top of large-scale internet video pretraining. 🔹Already outperforming Wan2.6, Seedance 1.5 Pro, and Cosmos3 Super on RBench. 🧵👇

Robbyant

1,871 subscribers

462,747 Aufrufe • vor 4 Stunden •via X (Twitter)

Wissenschaft & Technologie Bildung

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

We're releasing HY-Embodied-0.5, a family of foundation models for real-world embodied agents. The 2B model is now open source. It strengthens spatial-temporal perception and embodied reasoning for prediction, interaction, and planning. 🤖 The suite includes: 🔹 2B for edge deployment 🔹 32B for complex reasoning Key innovations: 🔹 Mixture-of-Transformers (MoT) architecture for modality-specific computation 🔹 Latent tokens for improved perceptual representation 🔹 Self-evolving post-training 🔹 On-policy distillation from large to small models Across 22 benchmarks, the 2B model outperforms similarly sized SOTA systems on 16 tasks. The 32B model approaches frontier-level performance. 🔗 GitHub: 🤗 Hugging Face:

We're releasing HY-Embodied-0.5, a family of foundation models for real-world embodied agents. The 2B model is now open source. It strengthens spatial-temporal perception and embodied reasoning for prediction, interaction, and planning. 🤖 The suite includes: 🔹 2B for edge deployment 🔹 32B for complex reasoning Key innovations: 🔹 Mixture-of-Transformers (MoT) architecture for modality-specific computation 🔹 Latent tokens for improved perceptual representation 🔹 Self-evolving post-training 🔹 On-policy distillation from large to small models Across 22 benchmarks, the 2B model outperforms similarly sized SOTA systems on 16 tasks. The 32B model approaches frontier-level performance. 🔗 GitHub: 🤗 Hugging Face:

Tencent Hy

34,317 Aufrufe • vor 2 Monaten

Marey Realism 1.5 by Moonvalley is now live in ComfyUI API nodes! First video model trained only on 100% licensed 1080P footages — pro quality, production-ready, and commercially safe. Now available: 🔹 Text-to-Video 🔹 Image-to-Video 🕙 Pose and Motion Transfer nodes coming soon 🧵👇

Marey Realism 1.5 by Moonvalley is now live in ComfyUI API nodes! First video model trained only on 100% licensed 1080P footages — pro quality, production-ready, and commercially safe. Now available: 🔹 Text-to-Video 🔹 Image-to-Video 🕙 Pose and Motion Transfer nodes coming soon 🧵👇

ComfyUI

14,606 Aufrufe • vor 1 Jahr

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

30,603 Aufrufe • vor 1 Monat

Cinder City looks like a sci-fi version of The Division 👀 🔹Narrative-driven 3rd person shooter 🔹Play as super soldiers fighting mutated creatures and criminals 🔹Based in a dystopian 21st century Seoul 🔹Massive open world 🔹Large-scale multiplayer co-op 🔹Major emphasis on multiplayer team systems and PvE content 🔹Designed to reward strong coordination and teamwork 🔹Features a persistent open-world that actively expands and changes

Cinder City looks like a sci-fi version of The Division 👀 🔹Narrative-driven 3rd person shooter 🔹Play as super soldiers fighting mutated creatures and criminals 🔹Based in a dystopian 21st century Seoul 🔹Massive open world 🔹Large-scale multiplayer co-op 🔹Major emphasis on multiplayer team systems and PvE content 🔹Designed to reward strong coordination and teamwork 🔹Features a persistent open-world that actively expands and changes

Game Hunter

242,241 Aufrufe • vor 6 Tagen

Very excited to share our first public release after I joined Robbyant! We present Lingbot-Depth 👀 — a state-of-the-art depth foundation model trained with RGB-D MAE on millions of real & simulated RGBD pairs. 🔹 Camera depths as natural masks for RGB-D MAE modeling 🔹 Large-scale real + sim RGBD data curation pipeline What surprised us most: ✨ Significant improvement on transparent, reflective surfaces, and thin structures — traditionally the hardest cases for depth models. 👇These are some of hard causal-capture images we tested on. The results are pretty good! #DepthEstimation #FoundationModels #EmbodiedAI #3DVision #Robotics #RobbyAnt

Very excited to share our first public release after I joined Robbyant! We present Lingbot-Depth 👀 — a state-of-the-art depth foundation model trained with RGB-D MAE on millions of real & simulated RGBD pairs. 🔹 Camera depths as natural masks for RGB-D MAE modeling 🔹 Large-scale real + sim RGBD data curation pipeline What surprised us most: ✨ Significant improvement on transparent, reflective surfaces, and thin structures — traditionally the hardest cases for depth models. 👇These are some of hard causal-capture images we tested on. The results are pretty good! #DepthEstimation #FoundationModels #EmbodiedAI #3DVision #Robotics #RobbyAnt

Yinghao Xu

22,574 Aufrufe • vor 5 Monaten

Alabama RB Shaun Alexander was the first player on the cover of both NCAA & Madden NFL video games 🔹NFL MVP (2005); 2× All-Pro 🔹NFL 2000s All-Decade Team 🔹Seahawks Top 50 players 🔹All-American; SEC Player of the Year 🔹9,453 rushing yards & 100 TD 🔹14 kids

Alabama RB Shaun Alexander was the first player on the cover of both NCAA & Madden NFL video games 🔹NFL MVP (2005); 2× All-Pro 🔹NFL 2000s All-Decade Team 🔹Seahawks Top 50 players 🔹All-American; SEC Player of the Year 🔹9,453 rushing yards & 100 TD 🔹14 kids

Clint Goss

22,019 Aufrufe • vor 1 Monat

The protagonist of this ecosystem is not a person. It’s an agent: 🔹 Trained on crypto discourse 🔹 Emotionally modeled through art 🔹 Cognitively embodied via infra Meet: AIHybets #AIAgent #DecentralizedAI

The protagonist of this ecosystem is not a person. It’s an agent: 🔹 Trained on crypto discourse 🔹 Emotionally modeled through art 🔹 Cognitively embodied via infra Meet: AIHybets #AIAgent #DecentralizedAI

AI Hybrid Beasts

10,460 Aufrufe • vor 1 Jahr

🤖 LingBot-VLA 2.0 is now open-source — our next-gen embodied foundation model. 🔷 60,000 hours of high-quality pretraining data — combining curated robotic demonstrations and egocentric human operation videos 🔷 20 robot configurations across 17 brands — Astribot, Leju, Unitree, Franka, Fourier, Realman, and more 🔷 Whole-body DoF: heads, waists, dexterous hands, and mobile bases — enabling far more complex task scenarios 🔷 Inference under 130ms on RTX 4090 — developer events launching soon #EmbodiedAI #Robotics #OpenSource #VLA

🤖 LingBot-VLA 2.0 is now open-source — our next-gen embodied foundation model. 🔷 60,000 hours of high-quality pretraining data — combining curated robotic demonstrations and egocentric human operation videos 🔷 20 robot configurations across 17 brands — Astribot, Leju, Unitree, Franka, Fourier, Realman, and more 🔷 Whole-body DoF: heads, waists, dexterous hands, and mobile bases — enabling far more complex task scenarios 🔷 Inference under 130ms on RTX 4090 — developer events launching soon #EmbodiedAI #Robotics #OpenSource #VLA

Robbyant

673,098 Aufrufe • vor 1 Tag

🚀 Exciting update for LTX-Video: now with a commercial license, improved quality, and enhanced controllability using keyframes & video extension! 🔹 Commercial license 🔹 Better motion consistency 🔹 Multiple keyframes support 🔹 Forward/backward video extension 🔹 Higher resolutions & improved fine-details 🔹 Auto prompt understanding 🔹 New web app in LTX-Studio 🎬 🧵👇

🚀 Exciting update for LTX-Video: now with a commercial license, improved quality, and enhanced controllability using keyframes & video extension! 🔹 Commercial license 🔹 Better motion consistency 🔹 Multiple keyframes support 🔹 Forward/backward video extension 🔹 Higher resolutions & improved fine-details 🔹 Auto prompt understanding 🔹 New web app in LTX-Studio 🎬 🧵👇

Yoav HaCohen

28,979 Aufrufe • vor 1 Jahr

🔥 Very excited to share that we’re releasing LingBot-World 🌍 Robbyant — an open-source frontier world model! We’re pushing the limits of: 🔹 High-Fidelity Simulation & Precise Control 🔹 Long-Horizon Consistency & Memory 🔹 Modeling Physical & Game Worlds The most surprising part? The emergence of sophisticated behaviors that go beyond simple video generation. 👇I’m obsessed with this dragon demo 🐉. It can rollout for 1 min while maintaining crisp visual dynamics and consistent memory!

🔥 Very excited to share that we’re releasing LingBot-World 🌍 Robbyant — an open-source frontier world model! We’re pushing the limits of: 🔹 High-Fidelity Simulation & Precise Control 🔹 Long-Horizon Consistency & Memory 🔹 Modeling Physical & Game Worlds The most surprising part? The emergence of sophisticated behaviors that go beyond simple video generation. 👇I’m obsessed with this dragon demo 🐉. It can rollout for 1 min while maintaining crisp visual dynamics and consistent memory!

Yinghao Xu

41,426 Aufrufe • vor 5 Monaten

The first truly open-source audio-video model. LTX-2 is a DiT-based foundation model with all core video generation capabilities in one unified model. Designed to run locally on consumer GPUs. - text-to-video - image-to-video - and video-to-video modes 100% open-source.

The first truly open-source audio-video model. LTX-2 is a DiT-based foundation model with all core video generation capabilities in one unified model. Designed to run locally on consumer GPUs. - text-to-video - image-to-video - and video-to-video modes 100% open-source.

Akshay 🚀

66,042 Aufrufe • vor 6 Monaten

Sundar Pichai (Sundar Pichai), Google CEO, on: 🔹Race to AGI 🔹Agents 🔹AI & Information Diet 🔹Open Source 🔹Cybersecurity 🔹US vs China Intro AI agents replacing parts of the internet AI agents deciding our information diet Will agents kill the “raw internet”? AI cyberattacks and Google’s defense strategy Should dangerous cyber AI models be held back? The threshold for releasing powerful AI Why Google hasn't open-sourced a large model The broken business model with open-source AI American companies using Chinese AI The risk of building on China’s AI ecosystem Why Google cares so much about cheap, fast AI models Sundar on self-improving AI and the race to AGI Google’s compute situation Google has more AI demand than compute Google’s biggest compute bottleneck

Sundar Pichai (Sundar Pichai), Google CEO, on: 🔹Race to AGI 🔹Agents 🔹AI & Information Diet 🔹Open Source 🔹Cybersecurity 🔹US vs China Intro AI agents replacing parts of the internet AI agents deciding our information diet Will agents kill the “raw internet”? AI cyberattacks and Google’s defense strategy Should dangerous cyber AI models be held back? The threshold for releasing powerful AI Why Google hasn't open-sourced a large model The broken business model with open-source AI American companies using Chinese AI The risk of building on China’s AI ecosystem Why Google cares so much about cheap, fast AI models Sundar on self-improving AI and the race to AGI Google’s compute situation Google has more AI demand than compute Google’s biggest compute bottleneck

Matthew Berman

300,861 Aufrufe • vor 1 Monat

Hear it directly from our CTO, @leehomyc🌀 Video AI today has three problems: it’s slow, expensive, and centralized. Everlyn solves all three: 🔹 Model: Everlyn-1 runs in ~25s at ~$0.04 per video. 🔹 Agents: Everworld gives you photorealistic twins you can own. 🔹 Protocol: Lyn secures everything on-chain with proof and provenance. This isn’t just video generation. It’s the agentic layer for the next Internet.

Hear it directly from our CTO, @leehomyc🌀 Video AI today has three problems: it’s slow, expensive, and centralized. Everlyn solves all three: 🔹 Model: Everlyn-1 runs in ~25s at ~$0.04 per video. 🔹 Agents: Everworld gives you photorealistic twins you can own. 🔹 Protocol: Lyn secures everything on-chain with proof and provenance. This isn’t just video generation. It’s the agentic layer for the next Internet.

Everlyn

131,568 Aufrufe • vor 9 Monaten

DeepSite V2 just dropped (insane for Vibe Coding) 🤯 🔹Amazingly good at UI Design 🔹DeepSeek-R1 model now available 🔹Targeted Edits on any element 🔹Redesign any existing website 🔹100% open source (UI + models)

DeepSite V2 just dropped (insane for Vibe Coding) 🤯 🔹Amazingly good at UI Design 🔹DeepSeek-R1 model now available 🔹Targeted Edits on any element 🔹Redesign any existing website 🔹100% open source (UI + models)

Victor M

102,584 Aufrufe • vor 1 Jahr

D2E Scaling Vision-Action Pretraining on Desktop Data for Transfer to Embodied AI

D2E Scaling Vision-Action Pretraining on Desktop Data for Transfer to Embodied AI

AK

25,095 Aufrufe • vor 8 Monaten

$ELDE — 24H BLASTOFF! 🔥 Elderglade has made history. 20x ROI on the first-ever GameFi exclusive TGE on Binance Wallet — outperforming top 2024–2025 token launches. Dominating major CEX: 🔹 Trending on #BinanceAlpha and Bybit 🔹 Top Gainers on KuCoin, Gate.io, MEXC Massive traction in the first 24 hours: 🔹 $90M+ trading volume — one of the biggest GameFi openings in years 🔹 390K+ token holders — record-setting GameFi community expansion 🔹 640K+ transactions — unstoppable momentum with real, sustained demand 🔹Trending on CoinMarketCap, CoinGecko & DEXTools — dominating every major discovery platform 🔹Viral across Twitter - taking over feeds with charts and mentions all around the world $ELDE launched with massive traction - and it’s scaling fast. This is only the beginning.

$ELDE — 24H BLASTOFF! 🔥 Elderglade has made history. 20x ROI on the first-ever GameFi exclusive TGE on Binance Wallet — outperforming top 2024–2025 token launches. Dominating major CEX: 🔹 Trending on #BinanceAlpha and Bybit 🔹 Top Gainers on KuCoin, Gate.io, MEXC Massive traction in the first 24 hours: 🔹 $90M+ trading volume — one of the biggest GameFi openings in years 🔹 390K+ token holders — record-setting GameFi community expansion 🔹 640K+ transactions — unstoppable momentum with real, sustained demand 🔹Trending on CoinMarketCap, CoinGecko & DEXTools — dominating every major discovery platform 🔹Viral across Twitter - taking over feeds with charts and mentions all around the world $ELDE launched with massive traction - and it’s scaling fast. This is only the beginning.

Elderglade

15,299 Aufrufe • vor 1 Jahr

Say "Hello" 👋 to the IPinfo ✨FREE✨ IP Data Downloads! 🔹 IP to Country + ASN data 🔹 Updated every 24 hours 🔹 Various formats 🔹 Best accuracy 🔹 Unlimited access Download the dataset 👉 How this changes the IP game🧵👇

Say "Hello" 👋 to the IPinfo ✨FREE✨ IP Data Downloads! 🔹 IP to Country + ASN data 🔹 Updated every 24 hours 🔹 Various formats 🔹 Best accuracy 🔹 Unlimited access Download the dataset 👉 How this changes the IP game🧵👇

IPinfo – IP Data Provider

827,135 Aufrufe • vor 3 Jahren

Synthetix Trading Competition on Ethereum Mainnet launches October 20. 🔹 $1,000,000 top prize 🔹 100 traders 🔹 The first perp DEX on Ethereum Mainnet Let's go! 🧵⬇️

Synthetix Trading Competition on Ethereum Mainnet launches October 20. 🔹 $1,000,000 top prize 🔹 100 traders 🔹 The first perp DEX on Ethereum Mainnet Let's go! 🧵⬇️

Synthetix ⚔️

97,971 Aufrufe • vor 9 Monaten

Introducing Private Mind! 🚀 Our new open-source app, built with React Native ExecuTorch, lets you run LLMs 100% locally on your device. 🔹 Explore and swap pre-exported models 🔹 Benchmark performance, speed & memory 🔹 Customize system prompts 🔹 100% offline, private & free Now available on App Store and Google Play! Links in 🧵

Introducing Private Mind! 🚀 Our new open-source app, built with React Native ExecuTorch, lets you run LLMs 100% locally on your device. 🔹 Explore and swap pre-exported models 🔹 Benchmark performance, speed & memory 🔹 Customize system prompts 🔹 100% offline, private & free Now available on App Store and Google Play! Links in 🧵

Software Mansion

21,764 Aufrufe • vor 11 Monaten

We trained a foundation model on 18 million heart ultrasound videos to predict structure instead of pixels. Introducing EchoJEPA, the first foundation-scale JEPA for medical video. Paper: Code: 🧵 1/n

We trained a foundation model on 18 million heart ultrasound videos to predict structure instead of pixels. Introducing EchoJEPA, the first foundation-scale JEPA for medical video. Paper: Code: 🧵 1/n

Alif Munim (d/acc)

590,454 Aufrufe • vor 5 Monaten