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。

[1/N]🚀New decoding paradigm drop!🚀 Introducing Lookahead Reasoning(LR): step-level speculation that stacks with Speculative Decoding(SD). It has been accepted to #NeurIPS2025 🎉 📖 Blog: 💻 Code: 📄 Paper:

Hao AI Lab

6,584 subscribers

43,177 次观看 • 10 个月前 •via X (Twitter)

教育科学技术 #NeurIPS2025

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

🚀 Introducing #SparseVideoGen: 2x speedup in video generation with HunyuanVideo with high pixel-level fidelity (PSNR = 29)! No training is required, no perceptible difference to the human eye! Blog: Paper: Code: #ArtificialIntelligence #OpenSource [1/7]

🚀 Introducing #SparseVideoGen: 2x speedup in video generation with HunyuanVideo with high pixel-level fidelity (PSNR = 29)! No training is required, no perceptible difference to the human eye! Blog: Paper: Code: #ArtificialIntelligence #OpenSource [1/7]

Haocheng Xi

45,770 次观看 • 1 年前

I’m excited to announce that 💫StarVector has been accepted at CVPR 2025! Over a year in the making, StarVector opens a new paradigm for Scalable Vector Graphics (SVG) generation by harnessing multimodal LLMs to generate SVG code that aesthetically mirrors input images and text. With this milestone, we’re also releasing StarVector on Hugging Face! 🥳🚀

I’m excited to announce that 💫StarVector has been accepted at CVPR 2025! Over a year in the making, StarVector opens a new paradigm for Scalable Vector Graphics (SVG) generation by harnessing multimodal LLMs to generate SVG code that aesthetically mirrors input images and text. With this milestone, we’re also releasing StarVector on Hugging Face! 🥳🚀

Joan Rodriguez

16,304 次观看 • 1 年前

Introducing Reinforcement-Learned Teachers (RLTs): Transforming how we teach LLMs to reason with reinforcement learning (RL). Blog: Paper: Traditional RL focuses on “learning to solve” challenging problems with expensive LLMs and constitutes a key step in making student AI systems ultimately acquire reasoning capabilities via distillation and cold-starting. Enter our RLTs—a new class of models prompted with not only a problem’s question but also its solution, and directly trained to generate clear, step-by-step “explanations” to teach their students. Remarkably, an RLT with only 7B parameters produces superior results when distilling and cold-starting students in competitive and graduate-level reasoning tasks than orders-of-magnitude larger LLMs. RLTs are as effective even when distilling 32B students, much larger than the teacher itself—unlocking a new standard for efficiency in developing reasoning language models with RL. Code:

Introducing Reinforcement-Learned Teachers (RLTs): Transforming how we teach LLMs to reason with reinforcement learning (RL). Blog: Paper: Traditional RL focuses on “learning to solve” challenging problems with expensive LLMs and constitutes a key step in making student AI systems ultimately acquire reasoning capabilities via distillation and cold-starting. Enter our RLTs—a new class of models prompted with not only a problem’s question but also its solution, and directly trained to generate clear, step-by-step “explanations” to teach their students. Remarkably, an RLT with only 7B parameters produces superior results when distilling and cold-starting students in competitive and graduate-level reasoning tasks than orders-of-magnitude larger LLMs. RLTs are as effective even when distilling 32B students, much larger than the teacher itself—unlocking a new standard for efficiency in developing reasoning language models with RL. Code:

Sakana AI

179,276 次观看 • 1 年前

(1/N) Content creators have been stuck with costly and slow video generation APIs for far too long. We couldn’t take it anymore.😅😭 FastVideo’s new real-time inference stack has the fastest 1080p TI2AV pipeline ever.😍🚀🚀 Our optimized LTX-2.3 pipeline creates 5-second 1080p videos with audio in 4.55 s, on a single GPU! 3.9x faster than the next fastest option. 🕹️Live demo: 📜Blog:

(1/N) Content creators have been stuck with costly and slow video generation APIs for far too long. We couldn’t take it anymore.😅😭 FastVideo’s new real-time inference stack has the fastest 1080p TI2AV pipeline ever.😍🚀🚀 Our optimized LTX-2.3 pipeline creates 5-second 1080p videos with audio in 4.55 s, on a single GPU! 3.9x faster than the next fastest option. 🕹️Live demo: 📜Blog:

Hao AI Lab

29,601 次观看 • 4 个月前

Introducing The Matrix --- a foundation world model for generating infinite-length, hyper-realistic videos with real-time, frame-level control: - Infinite-length video generation - 720p high-quality rendering - Real-time, frame-level control at 16 FPS - Generalization to real-world video control 🔗Blog: 📄Paper: 💻Code & Playable Demo: Coming soon! Key Innovation: A brand new technique called the shift-window denoise process model, enabling auto-regressive generation for diffusion and consistency models in real-time. Special thanks to project leader Ruili Feng and the entire Matrix team for their dedication and hard work over the year-long project.

Hongyang Zhang

178,322 次观看 • 1 年前

🚀 Excited to release LongLive 2.0! 🎬 An end-to-end infrastructure for long video generation, with FP4 and parallelism at the core of both training and inference. ⚡45.7 FPS generation speed on 5B model⚡ ✨ LongLive 2.0 supports real-video training, few-step distillation, multi-shot training/inference, sequence-parallel acceleration, NVFP4 KV cache, and async VAE decoding deployment. 🧩 To our knowledge, this is the first open-source 4-bit long video generation infra that covers both training and inference. 🙌 Welcome to check it out, try it, and share feedback! 🔗 Code: 📰 Paper: 🎥 Demo: #LongVideoGeneration #VideoGeneration #Realtime #AIInfra #EfficientAI #FP4 #Parallel #NVIDIA

🚀 Excited to release LongLive 2.0! 🎬 An end-to-end infrastructure for long video generation, with FP4 and parallelism at the core of both training and inference. ⚡45.7 FPS generation speed on 5B model⚡ ✨ LongLive 2.0 supports real-video training, few-step distillation, multi-shot training/inference, sequence-parallel acceleration, NVFP4 KV cache, and async VAE decoding deployment. 🧩 To our knowledge, this is the first open-source 4-bit long video generation infra that covers both training and inference. 🙌 Welcome to check it out, try it, and share feedback! 🔗 Code: 📰 Paper: 🎥 Demo: #LongVideoGeneration #VideoGeneration #Realtime #AIInfra #EfficientAI #FP4 #Parallel #NVIDIA

Yukang Chen

58,936 次观看 • 2 个月前

1/5 🚀 Thrilled to open-source OSCAR 🤖 — an action-conditioned world model for robotics, led by the visiting student in my group Zhuoyuan Wu! It generalizes across different robot embodiments with precise action controllability. All trained on a single GH200 GPU, and outperforms existing open-sourced baselines, which have larger model capacity and need more compute. Everything is public, including training data. 📄 Paper: 🌐 Project: 💻 Code: 🤗 Robot data: 🤗 Human data: 🤗 Weights: #Robotics #WorldModels #AI #OpenSource

1/5 🚀 Thrilled to open-source OSCAR 🤖 — an action-conditioned world model for robotics, led by the visiting student in my group Zhuoyuan Wu! It generalizes across different robot embodiments with precise action controllability. All trained on a single GH200 GPU, and outperforms existing open-sourced baselines, which have larger model capacity and need more compute. Everything is public, including training data. 📄 Paper: 🌐 Project: 💻 Code: 🤗 Robot data: 🤗 Human data: 🤗 Weights: #Robotics #WorldModels #AI #OpenSource

Jun Gao

104,280 次观看 • 1 个月前

🚀Excited to announce Superblocks AI – the AI coding assistant for internal apps! ⚡ Superblocks AI combines the power of the Superblocks drag-and-drop App Builder, with the speed of AI code generation, performance optimization, code explanation, mock data generation, and API call generation across SQL, Python, JavaScript, JSON and HTML. 🐨Our goal at Superblocks has always been to help developers ship mission-critical apps faster to elevate internal operations, and our deeply integrated AI coding assistant does exactly that! Blog:

🚀Excited to announce Superblocks AI – the AI coding assistant for internal apps! ⚡ Superblocks AI combines the power of the Superblocks drag-and-drop App Builder, with the speed of AI code generation, performance optimization, code explanation, mock data generation, and API call generation across SQL, Python, JavaScript, JSON and HTML. 🐨Our goal at Superblocks has always been to help developers ship mission-critical apps faster to elevate internal operations, and our deeply integrated AI coding assistant does exactly that! Blog:

Brad Menezes

73,242 次观看 • 3 年前

(1/5) Gemini 3, our most intelligent model, is landing in Google Search today – starting with AI Mode. Excited that this is the first time we’re shipping a new Gemini model in Search on day one! 🚀 In Search, Gemini 3 with generative layouts will make it easy to get a rich understanding of anything on your mind. It has state-of-the-art reasoning, deep multimodal understanding and advanced agentic capabilities. That allows the model to shine when you ask it to explain advanced concepts or ideas – it reasons and can code interactive visuals in real-time. It can tackle your toughest questions like advanced science.

(1/5) Gemini 3, our most intelligent model, is landing in Google Search today – starting with AI Mode. Excited that this is the first time we’re shipping a new Gemini model in Search on day one! 🚀 In Search, Gemini 3 with generative layouts will make it easy to get a rich understanding of anything on your mind. It has state-of-the-art reasoning, deep multimodal understanding and advanced agentic capabilities. That allows the model to shine when you ask it to explain advanced concepts or ideas – it reasons and can code interactive visuals in real-time. It can tackle your toughest questions like advanced science.

Robby Stein

94,877 次观看 • 8 个月前

One of the big challenges we have been facing to onboard mainstream to web3 at our Private Foxes NFT cafe is teaching every new customer about #Solana wallets. We have been spending almost 15 minutes with each customer to show them how to install and create a wallet using Phantom or @solflare_wallet (not sponsored by either, YET), It was time-consuming. That is why I came up with this new solution and product, we call it Paper Wallet. Our clients can get a wallet with one simple click that they can use inside the cafe for NFTs or $POX tokens, no phone needed anymore. After using Paper Wallet at the cafe, clients can effortlessly import their wallets at home using Phantom or Solflare, following our step by step guide. We’re committed to use our brand and products to continually onboard the mainstream into web3. 🚀 #PaperWallet #Web3Onboarding

Youness KASMI

14,517 次观看 • 2 年前

Introducing AI Assistance in Chrome DevTools! 🤯🚀 Ever wish you could have a coding buddy to help you with CSS and layout? Well, your wish is granted! The new AI Assistance in Chrome DevTools is here to make your life as a developer easier, powered by Gemini. The new panel aims to help you find and fix issues. Just ask it questions about your code, and it provides tailored explanations and even suggests solutions. This is our first exploration into agentic AI in DevTools and we're excited to hear what you think of it. Some key features: 1. Conversational prompts: Get tailored suggestions and code snippets. 2. Contextual understanding: AI understands the code you're working on. 3. Step-by-step guidance: Get help with everything from styling to debugging. Want to see it in action? Check out my screencast below to see how I used it to add a dark mode.

Introducing AI Assistance in Chrome DevTools! 🤯🚀 Ever wish you could have a coding buddy to help you with CSS and layout? Well, your wish is granted! The new AI Assistance in Chrome DevTools is here to make your life as a developer easier, powered by Gemini. The new panel aims to help you find and fix issues. Just ask it questions about your code, and it provides tailored explanations and even suggests solutions. This is our first exploration into agentic AI in DevTools and we're excited to hear what you think of it. Some key features: 1. Conversational prompts: Get tailored suggestions and code snippets. 2. Contextual understanding: AI understands the code you're working on. 3. Step-by-step guidance: Get help with everything from styling to debugging. Want to see it in action? Check out my screencast below to see how I used it to add a dark mode.

Addy Osmani

95,935 次观看 • 1 年前

Two years ago, we built OSWorld 1.0 — the benchmark that became the standard for computer-use agents. Agents now score 83.5% on it. Problem solved? Not even close. 🚀Today we introduce OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks. What's new: 🎯 108 real-world workflows, each ~1.6 hours ⏱️ for a skilled human ⚙️ ~318 tool calls/task vs. ~30 in OSWorld 1.0 🌍 Grounded in authentic artifacts & stateful user profiles ⚡ Captures real phenomena: dynamic environments, streaming interaction, cross-source reasoning, implicit-state inference & more 📊 Best results: Claude Opus 4.8 reaches the highest accuracy at 20.6%, while GPT-5.5 is far more token-efficient but plateaus near 13%. No one is close to solving real computer use. 🏠 Homepage: 📄 Paper: 💻 Code: 🤗 Dataset: 🧵 [1/8]

Two years ago, we built OSWorld 1.0 — the benchmark that became the standard for computer-use agents. Agents now score 83.5% on it. Problem solved? Not even close. 🚀Today we introduce OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks. What's new: 🎯 108 real-world workflows, each ~1.6 hours ⏱️ for a skilled human ⚙️ ~318 tool calls/task vs. ~30 in OSWorld 1.0 🌍 Grounded in authentic artifacts & stateful user profiles ⚡ Captures real phenomena: dynamic environments, streaming interaction, cross-source reasoning, implicit-state inference & more 📊 Best results: Claude Opus 4.8 reaches the highest accuracy at 20.6%, while GPT-5.5 is far more token-efficient but plateaus near 13%. No one is close to solving real computer use. 🏠 Homepage: 📄 Paper: 💻 Code: 🤗 Dataset: 🧵 [1/8]

XLANG NLP Lab

157,189 次观看 • 25 天前

🤔The more I studied diffusion language models, the more I came to appreciate the simplicity of autoregressive (AR) language models. AR models are trained to agree with what they generate, and their serving stacks are built to preserve that structure. DLMs often do neither: they lack introspective consistency, and high TPF does not necessarily translate into high real-world TPS. We propose Introspective Diffusion Language Model (I-DLM), which unifies introspection and generation in a single pass: 1. 🧑‍🎓I-DLM brings introspective consistency to DLMs with only 5B training tokens, achieving AR-thinking-level quality. 2. 🚀 I-DLM carefully trades compute for higher TPF while converting that advantage into real TPS under high-concurrency serving. 📖Website: ⌨️Code:

🤔The more I studied diffusion language models, the more I came to appreciate the simplicity of autoregressive (AR) language models. AR models are trained to agree with what they generate, and their serving stacks are built to preserve that structure. DLMs often do neither: they lack introspective consistency, and high TPF does not necessarily translate into high real-world TPS. We propose Introspective Diffusion Language Model (I-DLM), which unifies introspection and generation in a single pass: 1. 🧑‍🎓I-DLM brings introspective consistency to DLMs with only 5B training tokens, achieving AR-thinking-level quality. 2. 🚀 I-DLM carefully trades compute for higher TPF while converting that advantage into real TPS under high-concurrency serving. 📖Website: ⌨️Code:

Chenfeng_X

344,484 次观看 • 3 个月前

🎉 EXCITING NEWS! STEP APP CELEBRATES 1 YEAR! 🚀 is not just a #MoveToEarn anymore; we're something entirely different. From epic community events to groundbreaking features, Step 2.0 is here with major announcements. Brace yourselves for exciting updates! 🎁 🔄 Rebranding Alert! 🎨 Introducing Step App's fresh identity, revamped brand look, logo, and UI. A visual testament to our commitment to innovation. What's coming in the next few days? 💪 Disrupting Fitness Industry: AI-Driven Workouts! Experience the future of fitness with our groundbreaking AI-powered workouts! Become a trailblazer in the fitness world as we redefine exercise routines. Let technology guide you towards your goals while earning KCAL tokens, transforming your workout into an exciting adventure. Get ready to break barriers and achieve your best self!🏋️‍♂️ 💸 Step Wallet Upgrade: Beyond a Makeover. Redesigned for your convenience, our wallet is set for a substantial upgrade. Cutting-edge features will soon streamline buying, swapping, and managing your crypto assets seamlessly. 🌐💳 🚀 More Enhancements Await! Stay tuned for the many exciting updates - the new feature that will skyrocket your earnings up to 1500%, new, value-enhancing $KCAL utility as well as major upgrades across the Step Ecosystem, including Step Ex and Step Bridge. In the coming 2 months, exciting announcements and partnerships are coming your way. Join our Community Chat to be the first in the know. Your #StepApp experience is evolving for more convenience and rewards! 📖 Read more about the celebrations and updates in our blog post: 🎉 Step 2.0—A Stride into the Future. More than a stride, it's a deliberate march towards a dynamic future. Grateful for the steps you've taken with us in this year of progress. Here's to exploring the next horizon together! 🌅👟

Step App | The Future of Fitness

87,136 次观看 • 2 年前

Structured Outputs: The Building Blocks for Reliable AI! 🏗️ I am SUPER EXCITED to publish our newest Weaviate Podcast featuring Will Kurt (Will Kurt) and Cameron Pfiffer (Cameron) from .txt! 🎙️🎉 Dottxt is the company behind Outlines, reshaping how we control LLM outputs with constrained decoding! 🚀 This podcast dives into all sorts of details from new applications in metadata and information extraction, such as self-expanding knowledge graphs, to structured reasoning, report generation, and more! We also dove into the details of how this leverages Automata Theory and Finite State Machines to achieve this, how it is packaged with inference engines such as vLLM, and a rebuttal to Let Me Speak Freely, discussing how Structured Generation actually improve the quality of LLM outputs, in addition to speeding up inference, and of course, making it more reliable! I hope you find the podcast interesting, this was a super fun one! Links below!

Structured Outputs: The Building Blocks for Reliable AI! 🏗️ I am SUPER EXCITED to publish our newest Weaviate Podcast featuring Will Kurt (Will Kurt) and Cameron Pfiffer (Cameron) from .txt! 🎙️🎉 Dottxt is the company behind Outlines, reshaping how we control LLM outputs with constrained decoding! 🚀 This podcast dives into all sorts of details from new applications in metadata and information extraction, such as self-expanding knowledge graphs, to structured reasoning, report generation, and more! We also dove into the details of how this leverages Automata Theory and Finite State Machines to achieve this, how it is packaged with inference engines such as vLLM, and a rebuttal to Let Me Speak Freely, discussing how Structured Generation actually improve the quality of LLM outputs, in addition to speeding up inference, and of course, making it more reliable! I hope you find the podcast interesting, this was a super fun one! Links below!

Connor Shorten

12,742 次观看 • 1 年前

🚀 Introducing scGPT-spatial! 🧬🌍 A game-changing spatial-omic foundation model, built on the powerful scGPT framework with MoE (mixture of experts) and continually pretrained on a massive 30 million spatial single-cell profiles! 🧠 What’s the challenge? Spatial transcriptomics is next-level complex—not only must we model single-cell/spot profiles, but we also need to capture intricate spatial relationships while handling diverse sequencing protocols (imaging-based vs. sequencing-based). 🔥 Why scGPT-spatial? ✨ A Spatial-omic Foundation Model with Continual Pretraining – Built on scGPT’s robust initialization, it unlocks spatial context in tissues. ✨ SpatialHuman30M Dataset – The largest curated dataset: 30M profiles from Visium, Visium HD, Xenium, and MERFISH across 821 slides. ✨ Revolutionary MoE Decoders – A cutting-edge Mixture of Experts (MoE) architecture for protocol-aware gene expression decoding. ✨ Spatially-Aware Training Strategy – A neighborhood-based masked reconstruction approach to capture complex cell-type colocalization. ✨ Multi-Modal & Multi-Slide Integration – Seamless clustering & spatial domain identification across slides and modalities. ✨ Cell-Type Deconvolution & Gene Imputation – Unlocks cross-resolution & cross-modality harmonization with fine-tuned embeddings. 📄 Read the preprint: 💻 Explore the code/weights: #SpatialTranscriptomics #SingleCell #AIResearch #MachineLearning #SpatialData Huge shoutout to the incredible PHD students Chloe (ChloeXWang) and Haotian (Haotian Cui) for leading this groundbreaking project! 🎉 Massive thanks to our amazing co-authors Andrew, Ronald, and Hani (Hani Goodarzi) from Arc Institute—this work wouldn't have been possible without you! 👏

🚀 Introducing scGPT-spatial! 🧬🌍 A game-changing spatial-omic foundation model, built on the powerful scGPT framework with MoE (mixture of experts) and continually pretrained on a massive 30 million spatial single-cell profiles! 🧠 What’s the challenge? Spatial transcriptomics is next-level complex—not only must we model single-cell/spot profiles, but we also need to capture intricate spatial relationships while handling diverse sequencing protocols (imaging-based vs. sequencing-based). 🔥 Why scGPT-spatial? ✨ A Spatial-omic Foundation Model with Continual Pretraining – Built on scGPT’s robust initialization, it unlocks spatial context in tissues. ✨ SpatialHuman30M Dataset – The largest curated dataset: 30M profiles from Visium, Visium HD, Xenium, and MERFISH across 821 slides. ✨ Revolutionary MoE Decoders – A cutting-edge Mixture of Experts (MoE) architecture for protocol-aware gene expression decoding. ✨ Spatially-Aware Training Strategy – A neighborhood-based masked reconstruction approach to capture complex cell-type colocalization. ✨ Multi-Modal & Multi-Slide Integration – Seamless clustering & spatial domain identification across slides and modalities. ✨ Cell-Type Deconvolution & Gene Imputation – Unlocks cross-resolution & cross-modality harmonization with fine-tuned embeddings. 📄 Read the preprint: 💻 Explore the code/weights: #SpatialTranscriptomics #SingleCell #AIResearch #MachineLearning #SpatialData Huge shoutout to the incredible PHD students Chloe (ChloeXWang) and Haotian (Haotian Cui) for leading this groundbreaking project! 🎉 Massive thanks to our amazing co-authors Andrew, Ronald, and Hani (Hani Goodarzi) from Arc Institute—this work wouldn't have been possible without you! 👏

Bo Wang

59,008 次观看 • 1 年前

Introducing Continuous Thought Machines New Blog: Modern AI is powerful, but it’s still distinct from human-like flexible intelligence. We believe neural timing is key. Our Continuous Thought Machine is built from the ground up to use neural dynamics as a powerful representation for intelligence. Thought takes time, and reasoning is a process. Biological brains inspire us with their complex neural activity, where neural timing is critical to intelligence. We’re exploring how to bring that power to AI. The Continuous Thought Machine (CTM) incorporates neuron-level temporal processing and neural synchronization, moving beyond current AI limitations. Our approach has two core innovations: (1) neuron-level temporal processing, where each neuron uses unique parameters to process a history of incoming signals for fine-grained temporal dynamics, and (2) neural synchronization, used as a direct latent representation to modulate data and produce outputs, encoding information directly in the timing of neural activity. Learn more about our approach: Interactive Report: Full Paper: GitHub :

Introducing Continuous Thought Machines New Blog: Modern AI is powerful, but it’s still distinct from human-like flexible intelligence. We believe neural timing is key. Our Continuous Thought Machine is built from the ground up to use neural dynamics as a powerful representation for intelligence. Thought takes time, and reasoning is a process. Biological brains inspire us with their complex neural activity, where neural timing is critical to intelligence. We’re exploring how to bring that power to AI. The Continuous Thought Machine (CTM) incorporates neuron-level temporal processing and neural synchronization, moving beyond current AI limitations. Our approach has two core innovations: (1) neuron-level temporal processing, where each neuron uses unique parameters to process a history of incoming signals for fine-grained temporal dynamics, and (2) neural synchronization, used as a direct latent representation to modulate data and produce outputs, encoding information directly in the timing of neural activity. Learn more about our approach: Interactive Report: Full Paper: GitHub :

Sakana AI

289,680 次观看 • 1 年前

1/🧠Humans are the best robot data source — but video alone misses one thing: force. 2/🙁Tactile gloves capture force — but they're costly and block the real touch manipulation depends on. 3/💪Maybe the future of touch lives on your wrist: surface EMG reads the muscles that cause force — tactile sensing without ever touching a tactile sensor. 4/🔥Want a fully open-source framework — hardware + software — to train your own force-aware learn-from-human-data robot policy? 🚀We introduce ForceBand: Learning Forceful Manipulation with sEMG -- bring force into human videos with sEMG, for force-aware manipulation ⬇️ ✦ Zero-Shot Human-to-Robot Transfer ✦ Force Beyond Vision ✦ Free-Hand Force Sensing ✦ Collect by Anyone, Anytime, Anywhere ✦ Deploy on Any Robot, Any Camera, Any Environment ✦ Open-Source & Low-Cost & Easy-to-Implement Let's squeeze every bit of signal out of human data, and let robots feel the force! 🌐 Website: 📄 Paper: 💻 Code: 🎥 Video: 🧵 1/n

1/🧠Humans are the best robot data source — but video alone misses one thing: force. 2/🙁Tactile gloves capture force — but they're costly and block the real touch manipulation depends on. 3/💪Maybe the future of touch lives on your wrist: surface EMG reads the muscles that cause force — tactile sensing without ever touching a tactile sensor. 4/🔥Want a fully open-source framework — hardware + software — to train your own force-aware learn-from-human-data robot policy? 🚀We introduce ForceBand: Learning Forceful Manipulation with sEMG -- bring force into human videos with sEMG, for force-aware manipulation ⬇️ ✦ Zero-Shot Human-to-Robot Transfer ✦ Force Beyond Vision ✦ Free-Hand Force Sensing ✦ Collect by Anyone, Anytime, Anywhere ✦ Deploy on Any Robot, Any Camera, Any Environment ✦ Open-Source & Low-Cost & Easy-to-Implement Let's squeeze every bit of signal out of human data, and let robots feel the force! 🌐 Website: 📄 Paper: 💻 Code: 🎥 Video: 🧵 1/n

Zhi (Leo) Wang

49,738 次观看 • 25 天前

We are back. After one year of quiet building. Introducing GENE-26.5, our first robotic brain that takes a major step toward human-level capability. For years, robotics has struggled to learn from the world’s largest and valuable data source: Humans. Solving it means rethinking the whole stack from the ground up: - A robotics-native foundation model. - A 1:1 human-like robotic hand. - A noninvasive data collection glove for motion, force, and touch. - A simulator that turns weeks of experiments into minutes. GENE-26.5 is trained across language, vision, proprioception, tactile, and action. We designed a set of tasks to test how far we can go with this new paradigm. Fully autonomous, 1x speed, one model, same weights. (Enjoy with sound on) We are approaching the endgame for robotics. And this is just a beginning.

We are back. After one year of quiet building. Introducing GENE-26.5, our first robotic brain that takes a major step toward human-level capability. For years, robotics has struggled to learn from the world’s largest and valuable data source: Humans. Solving it means rethinking the whole stack from the ground up: - A robotics-native foundation model. - A 1:1 human-like robotic hand. - A noninvasive data collection glove for motion, force, and touch. - A simulator that turns weeks of experiments into minutes. GENE-26.5 is trained across language, vision, proprioception, tactile, and action. We designed a set of tasks to test how far we can go with this new paradigm. Fully autonomous, 1x speed, one model, same weights. (Enjoy with sound on) We are approaching the endgame for robotics. And this is just a beginning.

Genesis AI

2,715,266 次观看 • 2 个月前

🚀 New Paper: Pixel Reasoner 🧠🖼️ How can Vision-Language Models (VLMs) perform chain-of-thought reasoning within the image itself? We introduce Pixel Reasoner, the first open-source framework that enables VLMs to “think in pixel space” through curiosity-driven reinforcement learning. Current VLMs reason only in text — even when grounded in rich images or videos, their logical steps are verbalized in natural language. This restricts their ability to interrogate visual evidence and demonstrate how conclusions are drawn. 🔍 So we ask: What if we could make VLMs "show their work" by reasoning directly in the pixel space? Inspired by GPT-o3’s "think-in-image" ability, we propose a framework where VLMs use interactive visual operations — zoom, select-frame, highlight — to reason through complex visual inputs. To do this, we design a two-stage training process: Instruction tuning with synthesized visual reasoning traces. Reinforcement learning with curiosity-driven reward to balance exploration between pixel and text reasoning ✨ With this, Pixel Reasoner achieves near-SoTA performance on many information-rich multimodal benchmarks: 📊 84% on InfographicsVQA 🧠 84% on V* benchmark 🧩 74% on TallyQA-Complex It also achieves strong accuracy of 68% on MVBench (a video benchmark). Website: Paper: Code: Demo: (coming soon)

🚀 New Paper: Pixel Reasoner 🧠🖼️ How can Vision-Language Models (VLMs) perform chain-of-thought reasoning within the image itself? We introduce Pixel Reasoner, the first open-source framework that enables VLMs to “think in pixel space” through curiosity-driven reinforcement learning. Current VLMs reason only in text — even when grounded in rich images or videos, their logical steps are verbalized in natural language. This restricts their ability to interrogate visual evidence and demonstrate how conclusions are drawn. 🔍 So we ask: What if we could make VLMs "show their work" by reasoning directly in the pixel space? Inspired by GPT-o3’s "think-in-image" ability, we propose a framework where VLMs use interactive visual operations — zoom, select-frame, highlight — to reason through complex visual inputs. To do this, we design a two-stage training process: Instruction tuning with synthesized visual reasoning traces. Reinforcement learning with curiosity-driven reward to balance exploration between pixel and text reasoning ✨ With this, Pixel Reasoner achieves near-SoTA performance on many information-rich multimodal benchmarks: 📊 84% on InfographicsVQA 🧠 84% on V* benchmark 🧩 74% on TallyQA-Complex It also achieves strong accuracy of 68% on MVBench (a video benchmark). Website: Paper: Code: Demo: (coming soon)

Wenhu Chen

82,829 次观看 • 1 年前