Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

Building a model is just the start. Post-training makes it useful. Our CTO Mathias Lechner (Mathias Lechner) sits down for a conversation with Maxime Labonne (Maxime Labonne), our head of post-training, on the pipeline that takes a base model from autocomplete to something that can reason and follow instructions.

Liquid AI

33,985 subscribers

26,121 görüntüleme • 3 ay önce •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

Most multimodal systems need data that combines every modality together. Hard to get, expensive to build. Our CTO Mathias Lechner, Mathias Lechner, sits down with Saniya Karwa, Saniya Karwa, from our multimodal research team to talk about building a mode that handles text, audio, and image, and why you might not need as much combined training data as you think.

Most multimodal systems need data that combines every modality together. Hard to get, expensive to build. Our CTO Mathias Lechner, Mathias Lechner, sits down with Saniya Karwa, Saniya Karwa, from our multimodal research team to talk about building a mode that handles text, audio, and image, and why you might not need as much combined training data as you think.

Liquid AI

15,382 görüntüleme • 2 ay önce

Training LFMs at scale means solving parallelism across every layer of the architecture. And not all layers are the same. Our CTO Mathias Lechner (Mathias Lechner) sits down with Liquid's founding engineer Paul Pak (Paul Pak) to talk training infrastructure: Data, tensor, pipeline, expert, and context parallelism, and how they make context parallelism work across hybrid architectures with both attention and convolution operators.

Training LFMs at scale means solving parallelism across every layer of the architecture. And not all layers are the same. Our CTO Mathias Lechner (Mathias Lechner) sits down with Liquid's founding engineer Paul Pak (Paul Pak) to talk training infrastructure: Data, tensor, pipeline, expert, and context parallelism, and how they make context parallelism work across hybrid architectures with both attention and convolution operators.

Liquid AI

17,908 görüntüleme • 2 ay önce

The bottleneck in LLM inference isn't compute. It's how fast you can move the weights. Our CTO Mathias Lechner, Mathias Lechner, joins Piotr Mazurek, Piotr Mazurek (in SF 🌉), from our inference team, to discuss what actually limits token throughput and how we're optimizing for it.

The bottleneck in LLM inference isn't compute. It's how fast you can move the weights. Our CTO Mathias Lechner, Mathias Lechner, joins Piotr Mazurek, Piotr Mazurek (in SF 🌉), from our inference team, to discuss what actually limits token throughput and how we're optimizing for it.

Liquid AI

21,393 görüntüleme • 3 ay önce

New Course: Post-training of LLMs Learn to post-train and customize an LLM in this short course, taught by Banghua Zhu, Assistant Professor at the University of Washington University of Washington, and co-founder of @NexusflowX. Training an LLM to follow instructions or answer questions has two key stages: pre-training and post-training. In pre-training, it learns to predict the next word or token from large amounts of unlabeled text. In post-training, it learns useful behaviors such as following instructions, tool use, and reasoning. Post-training transforms a general-purpose token predictor—trained on trillions of unlabeled text tokens—into an assistant that follows instructions and performs specific tasks. Because it is much cheaper than pre-training, it is practical for many more teams to incorporate post-training methods into their workflows than pre-training. In this course, you’ll learn three common post-training methods—Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and Online Reinforcement Learning (RL)—and how to use each one effectively. With SFT, you train the model on pairs of input and ideal output responses. With DPO, you provide both a preferred (chosen) and a less preferred (rejected) response and train the model to favor the preferred output. With RL, the model generates an output, receives a reward score based on human or automated feedback, and updates the model to improve performance. You’ll learn the basic concepts, common use cases, and principles for curating high-quality data for effective training. Through hands-on labs, you’ll download a pre-trained model from Hugging Face and post-train it using SFT, DPO, and RL to see how each technique shapes model behavior. In detail, you’ll: - Understand what post-training is, when to use it, and how it differs from pre-training. - Build an SFT pipeline to turn a base model into an instruct model. - Explore how DPO reshapes behavior by minimizing contrastive loss—penalizing poor responses and reinforcing preferred ones. - Implement a DPO pipeline to change the identity of a chat assistant. - Learn online RL methods such as Proximal Policy Optimization (PPO) and Group Relative Policy Optimization (GRPO), and how to design reward functions. - Train a model with GRPO to improve its math capabilities using a verifiable reward. Post-training is one of the most rapidly developing areas of LLM training. Whether you’re building a high-accuracy context-specific assistant, fine-tuning a model's tone, or improving task-specific accuracy, this course will give you experience with the most important techniques shaping how LLMs are post-trained today. Please sign up here:

New Course: Post-training of LLMs Learn to post-train and customize an LLM in this short course, taught by Banghua Zhu, Assistant Professor at the University of Washington University of Washington, and co-founder of @NexusflowX. Training an LLM to follow instructions or answer questions has two key stages: pre-training and post-training. In pre-training, it learns to predict the next word or token from large amounts of unlabeled text. In post-training, it learns useful behaviors such as following instructions, tool use, and reasoning. Post-training transforms a general-purpose token predictor—trained on trillions of unlabeled text tokens—into an assistant that follows instructions and performs specific tasks. Because it is much cheaper than pre-training, it is practical for many more teams to incorporate post-training methods into their workflows than pre-training. In this course, you’ll learn three common post-training methods—Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and Online Reinforcement Learning (RL)—and how to use each one effectively. With SFT, you train the model on pairs of input and ideal output responses. With DPO, you provide both a preferred (chosen) and a less preferred (rejected) response and train the model to favor the preferred output. With RL, the model generates an output, receives a reward score based on human or automated feedback, and updates the model to improve performance. You’ll learn the basic concepts, common use cases, and principles for curating high-quality data for effective training. Through hands-on labs, you’ll download a pre-trained model from Hugging Face and post-train it using SFT, DPO, and RL to see how each technique shapes model behavior. In detail, you’ll: - Understand what post-training is, when to use it, and how it differs from pre-training. - Build an SFT pipeline to turn a base model into an instruct model. - Explore how DPO reshapes behavior by minimizing contrastive loss—penalizing poor responses and reinforcing preferred ones. - Implement a DPO pipeline to change the identity of a chat assistant. - Learn online RL methods such as Proximal Policy Optimization (PPO) and Group Relative Policy Optimization (GRPO), and how to design reward functions. - Train a model with GRPO to improve its math capabilities using a verifiable reward. Post-training is one of the most rapidly developing areas of LLM training. Whether you’re building a high-accuracy context-specific assistant, fine-tuning a model's tone, or improving task-specific accuracy, this course will give you experience with the most important techniques shaping how LLMs are post-trained today. Please sign up here:

Andrew Ng

125,146 görüntüleme • 1 yıl önce

MIT HANDED ITS DEEP LEARNING COURSE TO A FRONTIER-LAB ENGINEER FOR 68 MINUTES BECAUSE 90% OF PEOPLE SHIPPING AI CODE CAN'T EXPLAIN HOW THE MODEL ACTUALLY WORKS This is Maxime Labonne. He runs post-training at Liquid AI and wrote the LLM Engineer's Handbook. MIT gave him the room to break down the engine sitting inside every coding agent you've ever prompted. Twenty minutes in it stops being abstract. You finally see why the model confidently invents things that don't exist, why context is everything, and why "Just tell it to try again" sometimes fixes it and sometimes makes it worse. In 2026 "I use AI to code" stopped being a skill. Knowing why the model behaves the way it does -> tokens, context, post-training, where it quietly breaks -> is what separates someone who ships from someone babysitting a black box. Understanding an LLM isn't a research-team luxury anymore -> it's the difference between driving the agent and being driven by it. Anyone can prompt. The person who knows what's under the hood is the one still standing when the prompt stops working. Save this one & actually finish it ↓

MIT HANDED ITS DEEP LEARNING COURSE TO A FRONTIER-LAB ENGINEER FOR 68 MINUTES BECAUSE 90% OF PEOPLE SHIPPING AI CODE CAN'T EXPLAIN HOW THE MODEL ACTUALLY WORKS This is Maxime Labonne. He runs post-training at Liquid AI and wrote the LLM Engineer's Handbook. MIT gave him the room to break down the engine sitting inside every coding agent you've ever prompted. Twenty minutes in it stops being abstract. You finally see why the model confidently invents things that don't exist, why context is everything, and why "Just tell it to try again" sometimes fixes it and sometimes makes it worse. In 2026 "I use AI to code" stopped being a skill. Knowing why the model behaves the way it does -> tokens, context, post-training, where it quietly breaks -> is what separates someone who ships from someone babysitting a black box. Understanding an LLM isn't a research-team luxury anymore -> it's the difference between driving the agent and being driven by it. Anyone can prompt. The person who knows what's under the hood is the one still standing when the prompt stops working. Save this one & actually finish it ↓

slash1s

236,758 görüntüleme • 3 ay önce

Emerging as the global frontier of model-reasoning has been a core vision of Affine since its inception. In pursuit of this vision, we've been working relentlessly to forge a repeatable training loop: a mechanism that uses benchmark driven post-training methodology to facilitate the improvement of reasoning itself. Through applying our training methodology onto Qwen3-32B as our base model, Affine’s miners have been able to push the Pareto frontier outward. We’ve now reached saturation; our models have become so good at reasoning that any further improvements are producing diminishing returns. As a result we now move our base model to Qwen3.6-35B-A3B. It provides a stronger basis, offering an extended context window, as well as an improved foundation for agentic work. The same training methodology will be applied going forward. Our objective is no longer simply to improve a single model, but to demonstrate that the process in itself is repeatable, scalable, and model agnostic. We view the commoditization of reasoning as vital to ensure our technology is not only transparent, but also co-owned by humanity.

Emerging as the global frontier of model-reasoning has been a core vision of Affine since its inception. In pursuit of this vision, we've been working relentlessly to forge a repeatable training loop: a mechanism that uses benchmark driven post-training methodology to facilitate the improvement of reasoning itself. Through applying our training methodology onto Qwen3-32B as our base model, Affine’s miners have been able to push the Pareto frontier outward. We’ve now reached saturation; our models have become so good at reasoning that any further improvements are producing diminishing returns. As a result we now move our base model to Qwen3.6-35B-A3B. It provides a stronger basis, offering an extended context window, as well as an improved foundation for agentic work. The same training methodology will be applied going forward. Our objective is no longer simply to improve a single model, but to demonstrate that the process in itself is repeatable, scalable, and model agnostic. We view the commoditization of reasoning as vital to ensure our technology is not only transparent, but also co-owned by humanity.

Affine

14,866 görüntüleme • 2 ay önce

Liquid AI's head of post-training explained how they built a small model that runs on-device under 1 GB in 20 minutes - better than $2500 small-model bootcamps. pick LFM2.5 base -> on-policy preference alignment -> agentic reinforcement learning -> curriculum training -> iterative model merging -> ship a 1B model that reliably calls tools on your phone. That loop is why frontier small models now beat 70B models on the tasks that actually matter. LFM2.5 + on-policy DPO + agentic RL + curriculum training + iterative merging - that's the stack. Watch and save it, then run a 1B agent on your phone tonight.

Liquid AI's head of post-training explained how they built a small model that runs on-device under 1 GB in 20 minutes - better than $2500 small-model bootcamps. pick LFM2.5 base -> on-policy preference alignment -> agentic reinforcement learning -> curriculum training -> iterative model merging -> ship a 1B model that reliably calls tools on your phone. That loop is why frontier small models now beat 70B models on the tasks that actually matter. LFM2.5 + on-policy DPO + agentic RL + curriculum training + iterative merging - that's the stack. Watch and save it, then run a 1B agent on your phone tonight.

h100envy

86,872 görüntüleme • 1 ay önce

In case you missed it, we recently launched "Post-training of LLMs," a short course where you'll: ✅ Understand when and why to use post-training methods like Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and Online Reinforcement Learning. ✅ Learn the concepts underlying the three post-training methods of SFT, DPO, and Online RL, their common use-cases, and how to curate high-quality data to effectively train a model using each method. ✅ Download a pre-trained model and implement post-training pipelines to turn a base model into an instruct model, change the identity of a chat assistant, and improve a model’s math capabilities. Learn more and enroll for free:

In case you missed it, we recently launched "Post-training of LLMs," a short course where you'll: ✅ Understand when and why to use post-training methods like Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and Online Reinforcement Learning. ✅ Learn the concepts underlying the three post-training methods of SFT, DPO, and Online RL, their common use-cases, and how to curate high-quality data to effectively train a model using each method. ✅ Download a pre-trained model and implement post-training pipelines to turn a base model into an instruct model, change the identity of a chat assistant, and improve a model’s math capabilities. Learn more and enroll for free:

DeepLearning.AI

16,779 görüntüleme • 1 yıl önce

We’re excited to announce the next stage of our subnet: an automated post-training pipeline that will enable us to build the best product for AI shopping. It’s only been 50 days, but we’re now getting 20k high-quality trajectories per day that are rich training signals for online shopping tasks. Using the trajectories we have thus far, we saw an 18% → 42% climb on Qwen3-4B base using our post-training pipeline.

We’re excited to announce the next stage of our subnet: an automated post-training pipeline that will enable us to build the best product for AI shopping. It’s only been 50 days, but we’re now getting 20k high-quality trajectories per day that are rich training signals for online shopping tasks. Using the trajectories we have thus far, we saw an 18% → 42% climb on Qwen3-4B base using our post-training pipeline.

ORO

391,331 görüntüleme • 2 ay önce

An exciting new course: Fine-tuning and Reinforcement Learning for LLMs: Intro to Post-training, taught by Sharon Zhou, VP of AI at AMD. Available now at Post-training is the key technique used by frontier labs to turn a base LLM--a model trained on massive unlabeled text to predict the next word/token--into a helpful, reliable assistant that can follow instructions. I've also seen many applications where post-training is what turns a demo application that works only 80% of the time into a reliable system that consistently performs. This course will teach you the most important post-training techniques! In this 5 module course, Sharon walks you through the complete post-training pipeline: supervised fine-tuning, reward modeling, RLHF, and techniques like PPO and GRPO. You'll also learn to use LoRA for efficient training, and to design evals that catch problems before and after deployment. Skills you'll gain: - Apply supervised fine-tuning and reinforcement learning (RLHF, PPO, GRPO) to align models to desired behaviors - Use LoRA for efficient fine-tuning without retraining entire models - Prepare datasets and generate synthetic data for post-training - Understand how to operate LLM production pipelines, with go/no-go decision points and feedback loops These advanced methods aren’t limited to frontier AI labs anymore, and you can now use them in your own applications. Learn here:

An exciting new course: Fine-tuning and Reinforcement Learning for LLMs: Intro to Post-training, taught by Sharon Zhou, VP of AI at AMD. Available now at Post-training is the key technique used by frontier labs to turn a base LLM--a model trained on massive unlabeled text to predict the next word/token--into a helpful, reliable assistant that can follow instructions. I've also seen many applications where post-training is what turns a demo application that works only 80% of the time into a reliable system that consistently performs. This course will teach you the most important post-training techniques! In this 5 module course, Sharon walks you through the complete post-training pipeline: supervised fine-tuning, reward modeling, RLHF, and techniques like PPO and GRPO. You'll also learn to use LoRA for efficient training, and to design evals that catch problems before and after deployment. Skills you'll gain: - Apply supervised fine-tuning and reinforcement learning (RLHF, PPO, GRPO) to align models to desired behaviors - Use LoRA for efficient fine-tuning without retraining entire models - Prepare datasets and generate synthetic data for post-training - Understand how to operate LLM production pipelines, with go/no-go decision points and feedback loops These advanced methods aren’t limited to frontier AI labs anymore, and you can now use them in your own applications. Learn here:

Andrew Ng

132,304 görüntüleme • 10 ay önce

I like to think of evals as something active, not passive -- it's a North Star that steers LLMs toward higher intelligence. Evals should drive your RL/SFT/post-training decisions. Internal evals at frontier labs make a huge difference -- and you can see it in how models behave differently (GPT seems better at one-shot tasks, Claude at multi-turn). If you want to learn more about building evals that actually improve your model in post-training, check out our AMD x DeeplearningAI course "Fine-tuning & RL for LLMs: Intro to Post-training" (content is free):

I like to think of evals as something active, not passive -- it's a North Star that steers LLMs toward higher intelligence. Evals should drive your RL/SFT/post-training decisions. Internal evals at frontier labs make a huge difference -- and you can see it in how models behave differently (GPT seems better at one-shot tasks, Claude at multi-turn). If you want to learn more about building evals that actually improve your model in post-training, check out our AMD x DeeplearningAI course "Fine-tuning & RL for LLMs: Intro to Post-training" (content is free):

Sharon Zhou

16,836 görüntüleme • 6 ay önce

Excited to share that Structify has raised a $4M seed round, led by Bain Capital Ventures & @8VC! We’ve been heads-down training our model & building our UI—and we’re just getting started. 🚀

Excited to share that Structify has raised a $4M seed round, led by Bain Capital Ventures & @8VC! We’ve been heads-down training our model & building our UI—and we’re just getting started. 🚀

Alex Reichenbach

35,780 görüntüleme • 1 yıl önce

From Palantir and Two Sigma to turning mechanistic interpretability into a production-grade platform, Mark Bissell (Member of Technical Staff) and Myra Deng (Head of Product) are building Goodfire on the belief that “understanding what’s inside the model” is the path to safer, more controllable AI and Goodfire just raised a $150M Series B at a $1.25B valuation to scale that bet. We sat down with Mark and Myra to unpack what actionable interpretability looks like beyond demos: why SAE features can lose to raw-activation probes on real detection tasks, how they deployed token-level PII monitoring with Rakuten across English + Japanese without training on real customer data, and what it takes to do real-time steering on a trillion-parameter model (including the infamous Gen-Z feature). We also dig into hallucination detection, surgical post-training edits for bias/unlearning, the emerging equivalence between activation steering and in-context learning, and their push to bring interpretability into training so model development isn’t just “data in, weights out.” Goodfire mark bissell Myra Deng

From Palantir and Two Sigma to turning mechanistic interpretability into a production-grade platform, Mark Bissell (Member of Technical Staff) and Myra Deng (Head of Product) are building Goodfire on the belief that “understanding what’s inside the model” is the path to safer, more controllable AI and Goodfire just raised a $150M Series B at a $1.25B valuation to scale that bet. We sat down with Mark and Myra to unpack what actionable interpretability looks like beyond demos: why SAE features can lose to raw-activation probes on real detection tasks, how they deployed token-level PII monitoring with Rakuten across English + Japanese without training on real customer data, and what it takes to do real-time steering on a trillion-parameter model (including the infamous Gen-Z feature). We also dig into hallucination detection, surgical post-training edits for bias/unlearning, the emerging equivalence between activation steering and in-context learning, and their push to bring interpretability into training so model development isn’t just “data in, weights out.” Goodfire mark bissell Myra Deng

Latent.Space

19,389 görüntüleme • 6 ay önce

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 görüntüleme • 1 yıl önce

Training a Whole-Body Control Foundation Model -- new work from my team at Agility Robotics A neural network for controlling our humanoid robots which is robust to disturbances, can handle heavy objects, and is a powerful platform for learning new whole-body skills learn more in our blog post ->

Training a Whole-Body Control Foundation Model -- new work from my team at Agility Robotics A neural network for controlling our humanoid robots which is robust to disturbances, can handle heavy objects, and is a powerful platform for learning new whole-body skills learn more in our blog post ->

Chris Paxton

45,068 görüntüleme • 1 yıl önce

Just wrapped up a week of training on Soyuz and station with our crew for Expedition 75. Our training included emergencies on station and Soyuz. We brought it all together from an emergency on station (ammonia or fire in photos) that caused us to move to the Soyuz.

Just wrapped up a week of training on Soyuz and station with our crew for Expedition 75. Our training included emergencies on station and Soyuz. We brought it all together from an emergency on station (ammonia or fire in photos) that caused us to move to the Soyuz.

Anil Menon

11,776 görüntüleme • 7 ay önce

"I hope I can be a role model." Episode 2 of our #BlackHistoryMonth series features rising star Davina Perrin as she reflects on her journey through cricket, the players that inspire her - and sits down for a heartfelt conversation with her grandfather Cecil, who helped spark her love of the game. #RaisingTheGame

"I hope I can be a role model." Episode 2 of our #BlackHistoryMonth series features rising star Davina Perrin as she reflects on her journey through cricket, the players that inspire her - and sits down for a heartfelt conversation with her grandfather Cecil, who helped spark her love of the game. #RaisingTheGame

England and Wales Cricket Board

18,894 görüntüleme • 10 ay önce

People often ask us: "Why should I join Action Model?" The answer is simple. Action Model is building a community-owned AI ecosystem where people can earn ownership based on the value they help create. Whether that's: • Training the model • Completing ActionFi tasks • Inviting friends • Contributing to the community • Building automations with Actionist Every action helps strengthen the ecosystem. And if AI is going to reshape the world, we want that future to be owned by more than just a handful of billionaires. If you believe this to, then join our movement.

People often ask us: "Why should I join Action Model?" The answer is simple. Action Model is building a community-owned AI ecosystem where people can earn ownership based on the value they help create. Whether that's: • Training the model • Completing ActionFi tasks • Inviting friends • Contributing to the community • Building automations with Actionist Every action helps strengthen the ecosystem. And if AI is going to reshape the world, we want that future to be owned by more than just a handful of billionaires. If you believe this to, then join our movement.

Action Model

26,529 görüntüleme • 23 gün önce

"If you have a vision of building something, get off your ass and actually do it... Then do whatever it takes to turn that idea into something everyone can use and enjoy." @Retrimentum from Upshot, building on Base.

"If you have a vision of building something, get off your ass and actually do it... Then do whatever it takes to turn that idea into something everyone can use and enjoy." @Retrimentum from Upshot, building on Base.

Base

680,819 görüntüleme • 3 ay önce