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

4,899 subscribers

42,989 views • 8 months 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 MiniCPM 4.1-8B: First Open-Source Reasoning LLM with Trainable Sparse Attention ✅ Strong Reasoning Capability: Surpasses similar-sized models on 15 tasks! ✅ Fast Generation: 3x decoding speedup for reasoning ✅ Efficient Architecture: Trainable sparse attention, frequency-ranked speculative decoding Download Models: Huggingface: Github: Technical Report: #AI #MiniCPM #LLM #OpenBMB #ArtificialIntelligence #MachineLearning

Introducing MiniCPM 4.1-8B: First Open-Source Reasoning LLM with Trainable Sparse Attention ✅ Strong Reasoning Capability: Surpasses similar-sized models on 15 tasks! ✅ Fast Generation: 3x decoding speedup for reasoning ✅ Efficient Architecture: Trainable sparse attention, frequency-ranked speculative decoding Download Models: Huggingface: Github: Technical Report: #AI #MiniCPM #LLM #OpenBMB #ArtificialIntelligence #MachineLearning

OpenBMB

19,070 views • 9 months ago

🚀 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

🚀 Big news from Recursion! Our 2nd Neuroscience Phenomap — a whole-genome map of the brain’s immune cells 🧠 — has been accepted by Roche & Genentech, triggering a $30M milestone! A massive step toward decoding biology to radically improve lives. 💥 #TechBio #AI #Neuroscience

🚀 Big news from Recursion! Our 2nd Neuroscience Phenomap — a whole-genome map of the brain’s immune cells 🧠 — has been accepted by Roche & Genentech, triggering a $30M milestone! A massive step toward decoding biology to radically improve lives. 💥 #TechBio #AI #Neuroscience

Chris Gibson

25,440 views • 7 months ago

🚀 Introducing Zed v0.159! Today we're excited to launch Zed SSH Remoting in Beta. 💻🌐🎉 See the blog post for more details.

🚀 Introducing Zed v0.159! Today we're excited to launch Zed SSH Remoting in Beta. 💻🌐🎉 See the blog post for more details.

Zed

56,862 views • 1 year ago

Decoding Morse Code.

Decoding Morse Code.

Interesting STEM

32,705 views • 1 year ago

🚀Create complex, modular 3D assets and scenes.🚀 Introducing #MoCA (Mixture-of-Components Attention), a new sparse attention method for compositional 3D generation. It scales to *many * components. paper: code:

🚀Create complex, modular 3D assets and scenes.🚀 Introducing #MoCA (Mixture-of-Components Attention), a new sparse attention method for compositional 3D generation. It scales to many components. paper: code:

Tengfei Wang

27,013 views • 6 months ago

Introducing: the new llama-cli 🦙🦙 > Clean looking interface > Multimodal support > Conversation control via commands > Speculative decoding support > Jinja fully supported

Introducing: the new llama-cli 🦙🦙 > Clean looking interface > Multimodal support > Conversation control via commands > Speculative decoding support > Jinja fully supported

Xuan-Son Nguyen

21,343 views • 6 months ago

Fast Byte Latent Transformer is accepted to ICML 2026! ⚡🥪 Byte-level LMs promise to free us from subword tokenizers, but decoding one byte at a time is super slow. We make BLT generation more efficient with BLT-D: text diffusion for parallel byte decoding. 1/

Fast Byte Latent Transformer is accepted to ICML 2026! ⚡🥪 Byte-level LMs promise to free us from subword tokenizers, but decoding one byte at a time is super slow. We make BLT generation more efficient with BLT-D: text diffusion for parallel byte decoding. 1/

Julie Kallini ✨

96,830 views • 1 month ago

Speculative decoding speeds up generation from LLMs significantly by computing several potential tokens in parallel. Learn about this technique and how it has been utilized to achieve 2–3x speed-ups at inference:

Speculative decoding speeds up generation from LLMs significantly by computing several potential tokens in parallel. Learn about this technique and how it has been utilized to achieve 2–3x speed-ups at inference:

Google AI

38,566 views • 1 year ago

This Decoding.. code micky #ForNothing

This Decoding.. code micky #ForNothing

Kofi Kinaata

16,269 views • 1 month ago

Code Micky - Momo Yaa |(Decoding)

Code Micky - Momo Yaa |(Decoding)

code micky

188,639 views • 2 years ago

🤖 New paper: MobileVLA-R1 A unified VLA system that brings real reasoning + continuous control to quadruped robots. CoT dataset, 2-stage training, real-world deployment. 📄paper & code & demo:

🤖 New paper: MobileVLA-R1 A unified VLA system that brings real reasoning + continuous control to quadruped robots. CoT dataset, 2-stage training, real-world deployment. 📄paper & code & demo:

Hao Tang (hiring postdocs)

27,232 views • 6 months ago

PSA: DeepSeek R1 Distill Llama 70B speculative decoding version is now live on Groq Inc for Dev Tier. We just made fast even faster for instant reasoning. 🏁

PSA: DeepSeek R1 Distill Llama 70B speculative decoding version is now live on Groq Inc for Dev Tier. We just made fast even faster for instant reasoning. 🏁

Hatice Ozen

44,675 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

16,277 views • 1 year ago

🌟 Can you imagine aligning your AI model 🤖 on the fly, without updating its core parameters so much that it becomes unsuitable for others with different preferences? 🚀 Introducing "Transfer Q Star: Principled Decoding for #LLM #Alignment" 🔗: A 🧵👇

🌟 Can you imagine aligning your AI model 🤖 on the fly, without updating its core parameters so much that it becomes unsuitable for others with different preferences? 🚀 Introducing "Transfer Q Star: Principled Decoding for #LLM #Alignment" 🔗: A 🧵👇

Furong Huang

49,161 views • 2 years ago

pretty boy decoding morse code #kaeflix

pretty boy decoding morse code #kaeflix

Kaelix Clips 🎫🕶️

24,348 views • 1 year ago

New paper out today in Nature Machine Intelligence, where we show robust neural to speech decoding across 48 patients.

New paper out today in Nature Machine Intelligence, where we show robust neural to speech decoding across 48 patients.

Adeen Flinker 🇮🇱🇺🇦🎗️

260,338 views • 2 years ago

Introducing a more powerful NotebookLM 🚀 Massive upgrades deliver agentic capabilities in chat, more advanced reasoning, and a suite of new output formats. Tackling complex, multi-step research problems has never been easier. Rolling out now to Google AI Ultra subscribers.

Introducing a more powerful NotebookLM 🚀 Massive upgrades deliver agentic capabilities in chat, more advanced reasoning, and a suite of new output formats. Tackling complex, multi-step research problems has never been easier. Rolling out now to Google AI Ultra subscribers.

NotebookLM

838,462 views • 3 days ago