Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

[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

6,640 subscribers

43,199 views • 1 year ago •via X (Twitter)

Education Science & Technology #NeurIPS2025

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

🚀 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 views • 1 year ago

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

16,388 views • 1 year ago

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

179,410 views • 1 year ago

(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

30,163 views • 6 months ago

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

178,407 views • 1 year ago

🚀 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

59,754 views • 4 months ago

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

105,003 views • 3 months ago

🚀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

73,251 views • 3 years ago

(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

94,962 views • 10 months ago

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

14,545 views • 2 years ago

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

96,003 views • 1 year ago

RLVR has become the recipe for agentic post-training. But for Computer-Use Agents, the bottleneck is not the algorithm, it is the data. 🐌 🚀 We introduce CUA-Gym: a scalable, lightweight synthesis engine that turns arbitrary task queries into verifiable RLVR data for computer-use agents. The largest open CUA RLVR dataset to date: 🎯 32,122 verifiable RLVR tasks with programmatic setup scripts + rewards 🌐 110 environments: 16 desktop apps + 94 synthesized mock web apps 🏆 Qwen3.5-based CUA models trained with GSPO reach 72.6% on OSWorld-Verified and 56.6% on WebArena 📄 Paper: 🏠 Homepage: 🤗 Dataset: 💻 Codebase: 🧩 Environments: 🧵[1/6]

RLVR has become the recipe for agentic post-training. But for Computer-Use Agents, the bottleneck is not the algorithm, it is the data. 🐌 🚀 We introduce CUA-Gym: a scalable, lightweight synthesis engine that turns arbitrary task queries into verifiable RLVR data for computer-use agents. The largest open CUA RLVR dataset to date: 🎯 32,122 verifiable RLVR tasks with programmatic setup scripts + rewards 🌐 110 environments: 16 desktop apps + 94 synthesized mock web apps 🏆 Qwen3.5-based CUA models trained with GSPO reach 72.6% on OSWorld-Verified and 56.6% on WebArena 📄 Paper: 🏠 Homepage: 🤗 Dataset: 💻 Codebase: 🧩 Environments: 🧵[1/6]

Bowen Wang

104,223 views • 3 months ago

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

171,055 views • 2 months ago

🤔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

344,754 views • 5 months ago

#WATCH | Delhi: Shiv Sena (UBT) MP Sanjay Raut says, "There will certainly be discussions regarding the anti-paper leak issue, but the world's largest protest against paper leaks took place at Jantar Mantar in India. Now, a new bill has been introduced. Modi ji seems to think he has achieved a monumental feat. It is the same old bill. All that has changed is that the prison term has been increased from one year to ten years, and the fine raised from ₹1 crore to ₹10 crore. The biggest paper leak racket is operating within the Bharatiya Janata Party. The individuals arrested in Maharashtra in connection with the NEET paper leak are all affiliated with the BJP. You are the ones who appoint the Vice-Chancellors. Your people occupy positions on the major education boards, such as those overseeing NEET, so they collude to carry out these activities, and they will continue to do so. Merely introducing a bill will achieve nothing."

#WATCH | Delhi: Shiv Sena (UBT) MP Sanjay Raut says, "There will certainly be discussions regarding the anti-paper leak issue, but the world's largest protest against paper leaks took place at Jantar Mantar in India. Now, a new bill has been introduced. Modi ji seems to think he has achieved a monumental feat. It is the same old bill. All that has changed is that the prison term has been increased from one year to ten years, and the fine raised from ₹1 crore to ₹10 crore. The biggest paper leak racket is operating within the Bharatiya Janata Party. The individuals arrested in Maharashtra in connection with the NEET paper leak are all affiliated with the BJP. You are the ones who appoint the Vice-Chancellors. Your people occupy positions on the major education boards, such as those overseeing NEET, so they collude to carry out these activities, and they will continue to do so. Merely introducing a bill will achieve nothing."

ANI

46,526 views • 1 month ago

You can now watch any AI paper instead of reading it There's a new site called arXivisual that turns ANY arXiv paper into a fully animated breakdown for free. Just add "isual" to the link becomes Paste it and an agent pipeline breaks the paper into sections, finds the concepts worth animating, writes Manim code for each one, and narrates it with voice You scroll, the narration plays, and each animation sits right next to the paragraph it explains Tried it on the original Transformers paper. Attention finally made sense to me in a way 10 blog posts never did, and it's open source. Four college kids built it at a hackathon Here's what I'd do if I were you: 1. Pick the one paper you've been avoiding 2. Change the link and paste it in 3. Scroll through it on your phone with headphones in 4. Ask your AI to explain the one section you still don't get You'll learn more in 20 minutes than a whole weekend of pretending to read PDFs This is how you read research in 2026

You can now watch any AI paper instead of reading it There's a new site called arXivisual that turns ANY arXiv paper into a fully animated breakdown for free. Just add "isual" to the link becomes Paste it and an agent pipeline breaks the paper into sections, finds the concepts worth animating, writes Manim code for each one, and narrates it with voice You scroll, the narration plays, and each animation sits right next to the paragraph it explains Tried it on the original Transformers paper. Attention finally made sense to me in a way 10 blog posts never did, and it's open source. Four college kids built it at a hackathon Here's what I'd do if I were you: 1. Pick the one paper you've been avoiding 2. Change the link and paste it in 3. Scroll through it on your phone with headphones in 4. Ask your AI to explain the one section you still don't get You'll learn more in 20 minutes than a whole weekend of pretending to read PDFs This is how you read research in 2026

Hasan Toor

121,712 views • 12 days ago

🎉 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

87,171 views • 2 years ago

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 views • 1 year ago

🚀 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

59,086 views • 1 year ago

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

290,087 views • 1 year ago