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。

“Next-token prediction” just got a serious rival 🤯 Ant Group just dropped LLaDA 2.1, and it challenges the dominant paradigm of LLMs. Unlike most models that generate one token at a time, LLaDA 2.1 uses diffusion to generate blocks of text in parallel. Why this changes everything: → Global... show more

Alvaro Cintas

129,988 subscribers

31,277 次观看 • 5 个月前 •via X (Twitter)

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

🚨 One orchestrator. 10 parallel agents. 100+ tokens a second. All local. The Google Gemma team just dropped a MASSIVE demo for Gemma 4 26B. They built a concurrent workflow that lets the 26B model coordinate an entire team of sub-agents on your machine. Out of the box, the cookbook lets you run 10 parallel agents to: → Code an entire SVG art gallery in seconds → Translate text simultaneously → Generate ASCII art → Write parallel code Spinning up multi-agent systems locally has never looked this fast or this accessible. 100% free and open-source. repo link in 🧵↓

🚨 One orchestrator. 10 parallel agents. 100+ tokens a second. All local. The Google Gemma team just dropped a MASSIVE demo for Gemma 4 26B. They built a concurrent workflow that lets the 26B model coordinate an entire team of sub-agents on your machine. Out of the box, the cookbook lets you run 10 parallel agents to: → Code an entire SVG art gallery in seconds → Translate text simultaneously → Generate ASCII art → Write parallel code Spinning up multi-agent systems locally has never looked this fast or this accessible. 100% free and open-source. repo link in 🧵↓

Charly Wargnier

31,627 次观看 • 1 个月前

NVIDIA just removed the biggest friction point in Voice AI 🤯 They've open-sourced PersonaPlex-7B, a full-duplex conversational model that can listen and speak at the same time. Instead of waiting for you to finish talking, it uses a dual-stream architecture to process and respond in real-time. 100% Open-Source and Free.

NVIDIA just removed the biggest friction point in Voice AI 🤯 They've open-sourced PersonaPlex-7B, a full-duplex conversational model that can listen and speak at the same time. Instead of waiting for you to finish talking, it uses a dual-stream architecture to process and respond in real-time. 100% Open-Source and Free.

Simplifying AI

278,796 次观看 • 6 个月前

We've officially released and open-sourced HunyuanImage 2.1, our latest text-to-image model. The new model delivers on our commitment to balancing performance and quality. With native 2K image generation, HunyuanImage 2.1 is an advanced open-source text-to-image model.🎨 ✨ New in 2.1: 🔹Advanced Semantics: Supports ultra-long and complex prompts of up to 1000 tokens, and precisely controls the generation of multiple subjects in a single image. 🔹Precise Chinese and English Text Rendering with seamless image–text integration: The model naturally integrates text into images, making it suitable for a wide range of applications such as product covers, illustrations, and poster design to meet the needs of various fields. 🔹Rich Styles and High Aesthetic: Capable of generating images in various styles—including photorealistic portraits, comics, and vinyl figures—it delivers outstanding visual appeal and artistic quality. 🔹High-Quality Generation: Efficiently produces ultra-high-definition (2K) images in the same time other models take to generate a 1K image. HunyuanImage 2.1 uses two text encoders: a multimodal large language model (MLLM) to improve the model's image and text alignment capabilities, and a multi-language character-aware encoder to improve text rendering capabilities. The model is a single- and double-stream diffusion transformer with 17B parameters. We've also open-sourced the weights of the the accelerated version with meanflow which reduces inference steps from 100 to just 8, and PromptEnhancer, the first industrial-grade rewriting model that enhances your prompts for more nuanced and expressive image generation. Now, creators turn complex ideas—like posters with slogans or multi-panel comics—into visuals faster than ever. We’re just getting started. Stay tuned for our native multimodal image generation model coming soon. 🌐Website: 🔗Github: 🤗Hugging Face: ✨Hugging Face Demo:

We've officially released and open-sourced HunyuanImage 2.1, our latest text-to-image model. The new model delivers on our commitment to balancing performance and quality. With native 2K image generation, HunyuanImage 2.1 is an advanced open-source text-to-image model.🎨 ✨ New in 2.1: 🔹Advanced Semantics: Supports ultra-long and complex prompts of up to 1000 tokens, and precisely controls the generation of multiple subjects in a single image. 🔹Precise Chinese and English Text Rendering with seamless image–text integration: The model naturally integrates text into images, making it suitable for a wide range of applications such as product covers, illustrations, and poster design to meet the needs of various fields. 🔹Rich Styles and High Aesthetic: Capable of generating images in various styles—including photorealistic portraits, comics, and vinyl figures—it delivers outstanding visual appeal and artistic quality. 🔹High-Quality Generation: Efficiently produces ultra-high-definition (2K) images in the same time other models take to generate a 1K image. HunyuanImage 2.1 uses two text encoders: a multimodal large language model (MLLM) to improve the model's image and text alignment capabilities, and a multi-language character-aware encoder to improve text rendering capabilities. The model is a single- and double-stream diffusion transformer with 17B parameters. We've also open-sourced the weights of the the accelerated version with meanflow which reduces inference steps from 100 to just 8, and PromptEnhancer, the first industrial-grade rewriting model that enhances your prompts for more nuanced and expressive image generation. Now, creators turn complex ideas—like posters with slogans or multi-panel comics—into visuals faster than ever. We’re just getting started. Stay tuned for our native multimodal image generation model coming soon. 🌐Website: 🔗Github: 🤗Hugging Face: ✨Hugging Face Demo:

Tencent Hy

89,257 次观看 • 10 个月前

NVIDIA did it again.. they trained a GPT that generates human movement instead of text.. next-token prediction, but the tokens are body motions. it's called GPC and it hit a 99.98% success rate reproducing a massive corpus of motion clips.. cartwheels, vaults, flips, all of it. → 99.98% success rate reproducing motion clips → learns cartwheels, flips, vaulting from raw data → adapts to new tasks with <1% extra parameters studios spend 6-12 months and millions of dollars building custom controllers for one character in one game. GPC does it in one forward pass. Pixar, Ubisoft, and every mocap studio on the planet just felt a chill down their spine. the same next-token trick that gave us ChatGPT is now doing parkour inside a physics engine.

NVIDIA did it again.. they trained a GPT that generates human movement instead of text.. next-token prediction, but the tokens are body motions. it's called GPC and it hit a 99.98% success rate reproducing a massive corpus of motion clips.. cartwheels, vaults, flips, all of it. → 99.98% success rate reproducing motion clips → learns cartwheels, flips, vaulting from raw data → adapts to new tasks with <1% extra parameters studios spend 6-12 months and millions of dollars building custom controllers for one character in one game. GPC does it in one forward pass. Pixar, Ubisoft, and every mocap studio on the planet just felt a chill down their spine. the same next-token trick that gave us ChatGPT is now doing parkour inside a physics engine.

How To Prompt

73,203 次观看 • 1 天前

3Blue1Brown’s new video explains why every LLM is actually a compression machine. everyone describes pre-training as “next token prediction” but that’s just the surface-level objective. in reality it is a means to making the most efficient text compressor. prediction and compression are two sides of the same coin. when you train the model to predict the next token you’re not just teaching it to guess the next word but how to best encode the human knowledge it sees. better compression means better abstraction means better reasoning at some point, compression stops looking like storage or a database (as some like to call it on X) and looks like an approximation of understanding.

3Blue1Brown’s new video explains why every LLM is actually a compression machine. everyone describes pre-training as “next token prediction” but that’s just the surface-level objective. in reality it is a means to making the most efficient text compressor. prediction and compression are two sides of the same coin. when you train the model to predict the next token you’re not just teaching it to guess the next word but how to best encode the human knowledge it sees. better compression means better abstraction means better reasoning at some point, compression stops looking like storage or a database (as some like to call it on X) and looks like an approximation of understanding.

ℏεsam

119,751 次观看 • 1 个月前

🚨 ALIBABA JUST OPEN-SOURCED THE MOST POWERFUL MODEL IN THE WORLD - Qwen3.5 plus And it changes the AI race forever. This is not another “bigger model” release. This is a complete architectural reset. 397B parameters → only 17B active at inference, Qwen3.5 plus delivers performance on par with GPT-5.2 and Gemini-3-Pro. A new Hybrid Sparse MoE + Linear Attention architecture + Multi-Token Prediction = near-instant long-context responses and massive speed gains. Built as a true native multimodal model, it doesn’t just chat it builds. With a single prompt: “Use the React framework to create a visually impressive Mapbox demo featuring locations in Beijing and Shanghai” it generates a live interactive 3D map UI, structured components, real layouts, and production-ready frontend logic. This is real agentic, multimodal coding not a static code block. MMLU-Pro: 87.8 GPQA: 88.4 IFBench: 76.5 ⚡ up to 8× faster inference And it’s fully open-sourced under Apache-2.0. No locked APIs. No restricted tiers. 201 languages supported bringing frontier AI to developers, startups, and researchers worldwide. The race is no longer about the biggest model. It’s about the most usable intelligence. Open source just entered the top tier.

🚨 ALIBABA JUST OPEN-SOURCED THE MOST POWERFUL MODEL IN THE WORLD - Qwen3.5 plus And it changes the AI race forever. This is not another “bigger model” release. This is a complete architectural reset. 397B parameters → only 17B active at inference, Qwen3.5 plus delivers performance on par with GPT-5.2 and Gemini-3-Pro. A new Hybrid Sparse MoE + Linear Attention architecture + Multi-Token Prediction = near-instant long-context responses and massive speed gains. Built as a true native multimodal model, it doesn’t just chat it builds. With a single prompt: “Use the React framework to create a visually impressive Mapbox demo featuring locations in Beijing and Shanghai” it generates a live interactive 3D map UI, structured components, real layouts, and production-ready frontend logic. This is real agentic, multimodal coding not a static code block. MMLU-Pro: 87.8 GPQA: 88.4 IFBench: 76.5 ⚡ up to 8× faster inference And it’s fully open-sourced under Apache-2.0. No locked APIs. No restricted tiers. 201 languages supported bringing frontier AI to developers, startups, and researchers worldwide. The race is no longer about the biggest model. It’s about the most usable intelligence. Open source just entered the top tier.

RAVI KUMAR SAHU

380,093 次观看 • 5 个月前

New short course with Mistral AI ! Mistral's open-source Mixtral 8x7B model uses a "mixture of experts" (MoE) architecture. Unlike a standard transformer, an MoE model has multiple expert feed-forward networks (8 in this case), with a gating network selecting two experts at inference time. This enables MoE to match the performance of a large model but faster inference. Mixtral 8x7B has 46.7B parameters but activates only 12.9B at inference to predict the next token. In Getting Started with Mistral, you’ll learn from Mistral’s Sophia Yang, Ph.D. to: - Explore Mistral's open-source models (Mistral 7B, Mixtral 8x7B) and commercial models via API calls and Mistral AI's Le Chat website - Implement JSON mode to generate structured outputs to integrate directly into larger software systems. - Use function calling for Tool Use, such as calling custom Python code that queries tabular data - Ground your LLM's response with external knowledge sources using RAG - Build a Mistral-powered chat interface that can reference external documents This course will help deepen your prompt engineering skills. Please sign up here:

New short course with Mistral AI ! Mistral's open-source Mixtral 8x7B model uses a "mixture of experts" (MoE) architecture. Unlike a standard transformer, an MoE model has multiple expert feed-forward networks (8 in this case), with a gating network selecting two experts at inference time. This enables MoE to match the performance of a large model but faster inference. Mixtral 8x7B has 46.7B parameters but activates only 12.9B at inference to predict the next token. In Getting Started with Mistral, you’ll learn from Mistral’s Sophia Yang, Ph.D. to: - Explore Mistral's open-source models (Mistral 7B, Mixtral 8x7B) and commercial models via API calls and Mistral AI's Le Chat website - Implement JSON mode to generate structured outputs to integrate directly into larger software systems. - Use function calling for Tool Use, such as calling custom Python code that queries tabular data - Ground your LLM's response with external knowledge sources using RAG - Build a Mistral-powered chat interface that can reference external documents This course will help deepen your prompt engineering skills. Please sign up here:

Andrew Ng

387,018 次观看 • 2 年前

A GERMAN DEVELOPER REPLACED HIS ENTIRE DEV TEAM WITH KIMI K2.6, VISUALIZED EVERYTHING IN OBSIDIAN AND NOW MAKES $80,000/MONTH SOLO 1 trillion parameters, 32 billion activated per token and a SWE-Bench score of 65.8 - Kimi K2.6 reads the entire client codebase, understands the architecture, writes production code and ships for $150-300 in API costs while a traditional agency pays developers $4,800 for the exact same project. 300 parallel agents per run deliver 100+ files simultaneously - search, analysis, coding and writing all in parallel - and Obsidian visualizes the entire knowledge graph in real time while the agents work. A traditional agency with 10-15 people keeps 30% margin after salaries. He keeps 90% - $72,000 in monthly profit with $500 in overhead. By month 10 Kimi handles 80% of the technical work and he manages only strategy and client relationships - while Obsidian maps every project, every client and every agent in one graph that updates itself.

A GERMAN DEVELOPER REPLACED HIS ENTIRE DEV TEAM WITH KIMI K2.6, VISUALIZED EVERYTHING IN OBSIDIAN AND NOW MAKES $80,000/MONTH SOLO 1 trillion parameters, 32 billion activated per token and a SWE-Bench score of 65.8 - Kimi K2.6 reads the entire client codebase, understands the architecture, writes production code and ships for $150-300 in API costs while a traditional agency pays developers $4,800 for the exact same project. 300 parallel agents per run deliver 100+ files simultaneously - search, analysis, coding and writing all in parallel - and Obsidian visualizes the entire knowledge graph in real time while the agents work. A traditional agency with 10-15 people keeps 30% margin after salaries. He keeps 90% - $72,000 in monthly profit with $500 in overhead. By month 10 Kimi handles 80% of the technical work and he manages only strategy and client relationships - while Obsidian maps every project, every client and every agent in one graph that updates itself.

Noisy

848,487 次观看 • 2 个月前

We’re excited to announce the release and open-source of HunyuanImage 3.0 — the largest and most powerful open-source text-to-image model to date, with over 80 billion total parameters, of which 13 billion are activated per token during inference.The effect is completely comparable to the industry’s flagship closed-source model.🚀🚀🚀 HunyuanImage 3.0 originates from our internally developed native multimodal large language model, with fine-tuning and post-training focused on text-to-image generation. This unique foundation gives the model a powerful set of capabilities: ✅Reason with world knowledge ✅Understand complex, thousand-word prompts ✅Generate precise text within images Different from traditional DiT architecture image generation models, HunyuanImage 3.0’s MoE architecture uses a Transfusion-based approach to deeply couple Diffusion and LLM training for a single, powerful system. Built on Hunyuan-A13B, HunyuanImage 3.0 was trained on a massive dataset: 5 billion image-text pairs, video frames, interleaved image-text data, and 6 trillion tokens of text corpora. This hybrid training across multimodal generation, understanding, and LLM capabilities allows the model to seamlessly integrate multiple tasks. Whether you're an illustrator, designer, or creator, this is built to slash your workflow from hours to minutes. HunyuanImage 3.0 can generate intricate text, detailed comics, expressive emojis, and lively, engaging illustrations for educational content. The current release focuses solely on text-to-image generation and future updates will include image-to-image, image editing, multi-turn interaction, and more. 👉🏻Try it now: 🔗GitHub: 🤗Hugging Face:

We’re excited to announce the release and open-source of HunyuanImage 3.0 — the largest and most powerful open-source text-to-image model to date, with over 80 billion total parameters, of which 13 billion are activated per token during inference.The effect is completely comparable to the industry’s flagship closed-source model.🚀🚀🚀 HunyuanImage 3.0 originates from our internally developed native multimodal large language model, with fine-tuning and post-training focused on text-to-image generation. This unique foundation gives the model a powerful set of capabilities: ✅Reason with world knowledge ✅Understand complex, thousand-word prompts ✅Generate precise text within images Different from traditional DiT architecture image generation models, HunyuanImage 3.0’s MoE architecture uses a Transfusion-based approach to deeply couple Diffusion and LLM training for a single, powerful system. Built on Hunyuan-A13B, HunyuanImage 3.0 was trained on a massive dataset: 5 billion image-text pairs, video frames, interleaved image-text data, and 6 trillion tokens of text corpora. This hybrid training across multimodal generation, understanding, and LLM capabilities allows the model to seamlessly integrate multiple tasks. Whether you're an illustrator, designer, or creator, this is built to slash your workflow from hours to minutes. HunyuanImage 3.0 can generate intricate text, detailed comics, expressive emojis, and lively, engaging illustrations for educational content. The current release focuses solely on text-to-image generation and future updates will include image-to-image, image editing, multi-turn interaction, and more. 👉🏻Try it now: 🔗GitHub: 🤗Hugging Face:

Tencent Hy

412,658 次观看 • 10 个月前

Chamath: Two terms you need to pay attention to in AI are Prefill and Decode “There's two terms that I think you're going to hear a ton about over these next few years.” “The first term is prefill, and the next is decode.” “What prefill and decode are, are two very distinct ways of how models think, and how a model goes through the process of answering a question that you ask it.” “And so when you send a prompt to AI, what happens is that the model processes it. This is called the reading phase or prefill.” “It reads your entire prompt all at once. And then it does a bunch of math, calculates all these relationships between all the words, and it stores them in temporary memory.” “The problem is that this is really compute bound. So it requires massive brute force. And Nvidia GPUs crush here.” “And their architecture is designed for massive parallel processing, which makes them really amazing at digesting these long prompts.” “So the problem just gets bigger and bigger, Nvidia just completely dominates.” “But the next phase though, this critical phase, the decode phase, is the writing phase, right?” “So the model starts to generate a response, you ask it a question and its response, one token at a time.” “And then to pick the next token to pick the next word, it has to look back at everything it has said already so that it doesn't hallucinate.” “The problem is that this is incredibly memory bandwidth constrained.” “And in our architecture, a long time ago, we made these design decisions from day one.” “And so what we did was we took a very different architectural approach, we took a very conservative process technology. We weren't pushing the boundaries of physics.” “And we used a lot of what's called SRAM. So memory on the chip so that we could do this decode thing as well or better than everybody else.” “And so now when you put these two things together, I just think it's going to create a huge acceleration in the ability for this entire infrastructure layer to get much cheaper and much more valuable, which I suspect then it'll have a lot more developer pull, you'll get a lot more applications being built, billions and billions of more people using it.”

Chamath: Two terms you need to pay attention to in AI are Prefill and Decode “There's two terms that I think you're going to hear a ton about over these next few years.” “The first term is prefill, and the next is decode.” “What prefill and decode are, are two very distinct ways of how models think, and how a model goes through the process of answering a question that you ask it.” “And so when you send a prompt to AI, what happens is that the model processes it. This is called the reading phase or prefill.” “It reads your entire prompt all at once. And then it does a bunch of math, calculates all these relationships between all the words, and it stores them in temporary memory.” “The problem is that this is really compute bound. So it requires massive brute force. And Nvidia GPUs crush here.” “And their architecture is designed for massive parallel processing, which makes them really amazing at digesting these long prompts.” “So the problem just gets bigger and bigger, Nvidia just completely dominates.” “But the next phase though, this critical phase, the decode phase, is the writing phase, right?” “So the model starts to generate a response, you ask it a question and its response, one token at a time.” “And then to pick the next token to pick the next word, it has to look back at everything it has said already so that it doesn't hallucinate.” “The problem is that this is incredibly memory bandwidth constrained.” “And in our architecture, a long time ago, we made these design decisions from day one.” “And so what we did was we took a very different architectural approach, we took a very conservative process technology. We weren't pushing the boundaries of physics.” “And we used a lot of what's called SRAM. So memory on the chip so that we could do this decode thing as well or better than everybody else.” “And so now when you put these two things together, I just think it's going to create a huge acceleration in the ability for this entire infrastructure layer to get much cheaper and much more valuable, which I suspect then it'll have a lot more developer pull, you'll get a lot more applications being built, billions and billions of more people using it.”

The All-In Podcast

563,785 次观看 • 6 个月前

Content creation just leveled up with AI agents. I just tested Superagent by Airtable, and it’s insane… Instead of doing research + planning + writing manually, you can run multiple AI agents at the same time and get a complete Super Report at the end. What surprised me the most: ✅ Agents work in parallel (faster and more organized) ✅ The report is interactive and easy to explore ✅ It includes cited sources, so it’s actually reliable ✅ You can even generate outputs like docs / slides / websites It feels like having a full strategy team… on demand. Get 2 FREE months of Superagent using the code: ADAM2FREE → #SuperagentPartner #ad #SuperagentbyAirtable Airtable Superagent

Content creation just leveled up with AI agents. I just tested Superagent by Airtable, and it’s insane… Instead of doing research + planning + writing manually, you can run multiple AI agents at the same time and get a complete Super Report at the end. What surprised me the most: ✅ Agents work in parallel (faster and more organized) ✅ The report is interactive and easy to explore ✅ It includes cited sources, so it’s actually reliable ✅ You can even generate outputs like docs / slides / websites It feels like having a full strategy team… on demand. Get 2 FREE months of Superagent using the code: ADAM2FREE → #SuperagentPartner #ad #SuperagentbyAirtable Airtable Superagent

Adam

17,913 次观看 • 5 个月前

you tend to hear this a lot from people outside or new to ML, and I often point to a talk Ilya gave a few years back: 1) think of any decent deep neural net that has enough memory and sequential ops as just a big parallel computer 2) training this neural net is doing search over computer programs that maximize your objective 3)unless you have some large bottleneck (and given you can successfully optimize this system) you’ll find that these parallel computers are highly robust to architectural changes. 4) this is because computers are great at simulating each other. your new architecture can usually be straightforwardly simulated ‘inside’ your old architecture. 5) it’s not that architecture doesn’t matter, but it mostly matters with respect to (1) fundamental bottlenecks in this parallel computer (2) modifications that make models easier to optimize, since this argument only holds if your optimization is good (3) compute efficiency/system efficiency wins that make learning easier or faster. 6) it’s quite possible that new architectures will lead to breakthroughs in machine learning, but we should first start with bottlenecks, not naturalist intuitions about the ‘form’ of AI should take. until you understand this it seems surprising that small models trained longer are better than undertrained big models, that depth and width are surprisingly interchangeable, that talking to a model with an MoE or sparse attention or linear attention is approximately the same iso evals.

you tend to hear this a lot from people outside or new to ML, and I often point to a talk Ilya gave a few years back: 1) think of any decent deep neural net that has enough memory and sequential ops as just a big parallel computer 2) training this neural net is doing search over computer programs that maximize your objective 3)unless you have some large bottleneck (and given you can successfully optimize this system) you’ll find that these parallel computers are highly robust to architectural changes. 4) this is because computers are great at simulating each other. your new architecture can usually be straightforwardly simulated ‘inside’ your old architecture. 5) it’s not that architecture doesn’t matter, but it mostly matters with respect to (1) fundamental bottlenecks in this parallel computer (2) modifications that make models easier to optimize, since this argument only holds if your optimization is good (3) compute efficiency/system efficiency wins that make learning easier or faster. 6) it’s quite possible that new architectures will lead to breakthroughs in machine learning, but we should first start with bottlenecks, not naturalist intuitions about the ‘form’ of AI should take. until you understand this it seems surprising that small models trained longer are better than undertrained big models, that depth and width are surprisingly interchangeable, that talking to a model with an MoE or sparse attention or linear attention is approximately the same iso evals.

will depue

215,019 次观看 • 7 个月前

Meta just released MusicGen, a simple and controllable model for music generation MusicGen is a single stage auto-regressive Transformer model trained over a 32kHz EnCodec tokenizer with 4 codebooks sampled at 50 Hz. Unlike existing methods like MusicLM, MusicGen doesn't not require a self-supervised semantic representation, and it generates all 4 codebooks in one pass. By introducing a small delay between the codebooks, can predict them in parallel, thus having only 50 auto-regressive steps per second of audio try out the Gradio demo: Models on Hugging Face: github:

Sensitive content

Meta just released MusicGen, a simple and controllable model for music generation MusicGen is a single stage auto-regressive Transformer model trained over a 32kHz EnCodec tokenizer with 4 codebooks sampled at 50 Hz. Unlike existing methods like MusicLM, MusicGen doesn't not require a self-supervised semantic representation, and it generates all 4 codebooks in one pass. By introducing a small delay between the codebooks, can predict them in parallel, thus having only 50 auto-regressive steps per second of audio try out the Gradio demo: Models on Hugging Face: github:

AK

627,450 次观看 • 3 年前

New course: Transformers in Practice. You'll get a practical view of how transformer-based LLMs work, so you can reason about their behavior, diagnose problems like slow inference, and make smarter decisions about deployment. This course is built in partnership with AMD and taught by Sharon Zhou. You'll see how transformers generate text one token at a time, how the model decides which earlier words matter most when predicting the next one, and how techniques like quantization speed up inference on GPUs. This is not a video-only course; interactive visualizations throughout let you play with these concepts and build intuition that sticks. Skills you'll gain: - Understand why LLMs hallucinate, and RAG and chain-of-thought shape what they generate - Look inside the model to see how attention and layers combine to predict the next token - Diagnose inference bottlenecks and learn the techniques that speed up transformers on GPUs Join and understand what's really happening inside your LLMs:

New course: Transformers in Practice. You'll get a practical view of how transformer-based LLMs work, so you can reason about their behavior, diagnose problems like slow inference, and make smarter decisions about deployment. This course is built in partnership with AMD and taught by Sharon Zhou. You'll see how transformers generate text one token at a time, how the model decides which earlier words matter most when predicting the next one, and how techniques like quantization speed up inference on GPUs. This is not a video-only course; interactive visualizations throughout let you play with these concepts and build intuition that sticks. Skills you'll gain: - Understand why LLMs hallucinate, and RAG and chain-of-thought shape what they generate - Look inside the model to see how attention and layers combine to predict the next token - Diagnose inference bottlenecks and learn the techniques that speed up transformers on GPUs Join and understand what's really happening inside your LLMs:

Andrew Ng

119,783 次观看 • 2 个月前

New episode of the Information Bottleneck! We talked with Stefano Ermon about why he thinks diffusion LLMs will replace autoregressive ones. Stefano co-invented DDIM, FlashAttention, DPO, and score-based diffusion models. He's a Stanford professor and now runs Inception AI, where they built Mercury II. We go deep but also cover the bigger picture - the startup journey, PhD vs industry, and where AI is heading. A few things that stuck with me: - He thinks of autoregressive models as typewriters and diffusion models as editors. One goes left to right. The other starts messy and refines. - Mercury II (their text difussion model) already beats the fastest autoregressive models on latency-critical stuff as voice agents, code suggestions, anything where you have a tight time budget. And it does it because diffusion generates tokens in parallel instead of one at a time. - We also got into whether AI will actually replace software engineers (his answer: no), PhD vs industry advice, and what it was like going from an ICML best paper to raising money.

New episode of the Information Bottleneck! We talked with Stefano Ermon about why he thinks diffusion LLMs will replace autoregressive ones. Stefano co-invented DDIM, FlashAttention, DPO, and score-based diffusion models. He's a Stanford professor and now runs Inception AI, where they built Mercury II. We go deep but also cover the bigger picture - the startup journey, PhD vs industry, and where AI is heading. A few things that stuck with me: - He thinks of autoregressive models as typewriters and diffusion models as editors. One goes left to right. The other starts messy and refines. - Mercury II (their text difussion model) already beats the fastest autoregressive models on latency-critical stuff as voice agents, code suggestions, anything where you have a tight time budget. And it does it because diffusion generates tokens in parallel instead of one at a time. - We also got into whether AI will actually replace software engineers (his answer: no), PhD vs industry advice, and what it was like going from an ICML best paper to raising money.

Ravid Shwartz Ziv

22,350 次观看 • 4 个月前

Standard Intelligence's devansh responds to roon's tweet that "text is the universal interface," and explains why their new foundation model is trained on video: "At some point in the arbitrarily long future, if we only use text models, we could force most things to be text. But I think there are just a lot of things that are much more native when done from a computer-use [perspective]." "GUIs are designed for humans to use. We have this massive long tail of things on the internet that are entirely undoable by LLMs." "For example, when I do ML engineering most of my time is spent doing the grunt work of engineering. It's a lot of looking at graphs, analyzing, and comparing loss curves. You can do this in text, but it's a much larger pain than doing it in the native interface." "There's a reason humans don't interact with a computer purely through text, it would kind of suck."

Standard Intelligence's devansh responds to roon's tweet that "text is the universal interface," and explains why their new foundation model is trained on video: "At some point in the arbitrarily long future, if we only use text models, we could force most things to be text. But I think there are just a lot of things that are much more native when done from a computer-use [perspective]." "GUIs are designed for humans to use. We have this massive long tail of things on the internet that are entirely undoable by LLMs." "For example, when I do ML engineering most of my time is spent doing the grunt work of engineering. It's a lot of looking at graphs, analyzing, and comparing loss curves. You can do this in text, but it's a much larger pain than doing it in the native interface." "There's a reason humans don't interact with a computer purely through text, it would kind of suck."

TBPN

64,434 次观看 • 4 个月前

I just built an open NotebookLM clone! Here's what it can do for you: - Process multi-modal data - Scrape websites and YouTube videos - Create a unified knowledge base - Lets you do RAG over it - Remember every conversation - Generate a podcast 🎙️ The idea here is not to reinvent the wheel but to understand how one of the most powerful tools for learning and research actually works, by building it step-by-step! So by the end of this video, you'll learn how to: ↳ Process multimodal data (text, audio, video, URLs, and YouTube videos) into a format ready for LLMs ↳ Store everything in a vector database for fast retrieval ↳ Add a memory layer that remembers conversations and preferences for a personalized experience ↳ Chat with your knowledge base or generate podcasts using a fully open-source, locally running text-to-speech model The podcast generation feature is my favorite part! There's something powerful about turning written content into conversational audio that you can listen to while doing something else. The entire code is 100% open-source. I've shared a link in the replies! ____ Don't forget to drop a like if you enjoy my videos. It shows me I should be making more content like this. Cheers! :)

I just built an open NotebookLM clone! Here's what it can do for you: - Process multi-modal data - Scrape websites and YouTube videos - Create a unified knowledge base - Lets you do RAG over it - Remember every conversation - Generate a podcast 🎙️ The idea here is not to reinvent the wheel but to understand how one of the most powerful tools for learning and research actually works, by building it step-by-step! So by the end of this video, you'll learn how to: ↳ Process multimodal data (text, audio, video, URLs, and YouTube videos) into a format ready for LLMs ↳ Store everything in a vector database for fast retrieval ↳ Add a memory layer that remembers conversations and preferences for a personalized experience ↳ Chat with your knowledge base or generate podcasts using a fully open-source, locally running text-to-speech model The podcast generation feature is my favorite part! There's something powerful about turning written content into conversational audio that you can listen to while doing something else. The entire code is 100% open-source. I've shared a link in the replies! ____ Don't forget to drop a like if you enjoy my videos. It shows me I should be making more content like this. Cheers! :)

Akshay 🚀

83,187 次观看 • 9 个月前

🚨NEW DETAILS CONTINUE TO SURFACE ABOUT XRP’S ORIGINS — AND NONE OF IT LOOKS ACCIDENTAL. RIPPLE PULLING BACK ONLY HIGHLIGHTS THE REALITY: #XRP WAS DESIGNED FOR GLOBAL-SCALE USE FROM THE START. AS LEGACY SYSTEMS STRAIN, THE NEED FOR A FUNCTIONAL, READY-TO-USE NETWORK BECOMES OBVIOUS — AND XRP CHECKS THAT BOX. THAT’S WHY MANY BELIEVE XRP’S LONG-TERM ROLE GOES BEYOND BITCOIN. IN PARALLEL, MEDIA IS BEING REBUILT ON-CHAIN ON THE XRP LEDGER, WITH DECENTRALIZED PUBLISHING POWERED BY BXE TOKEN. BXE IS STILL AROUND $0.03 WITH A FIXED SUPPLY OF JUST 500 MILLION TOKENS. DYOR/NFA BXE TOKEN TRADE LINK ON XMAGNETIC: BXE TOKEN TRADE LINK ON MEXC:

🚨NEW DETAILS CONTINUE TO SURFACE ABOUT XRP’S ORIGINS — AND NONE OF IT LOOKS ACCIDENTAL. RIPPLE PULLING BACK ONLY HIGHLIGHTS THE REALITY: #XRP WAS DESIGNED FOR GLOBAL-SCALE USE FROM THE START. AS LEGACY SYSTEMS STRAIN, THE NEED FOR A FUNCTIONAL, READY-TO-USE NETWORK BECOMES OBVIOUS — AND XRP CHECKS THAT BOX. THAT’S WHY MANY BELIEVE XRP’S LONG-TERM ROLE GOES BEYOND BITCOIN. IN PARALLEL, MEDIA IS BEING REBUILT ON-CHAIN ON THE XRP LEDGER, WITH DECENTRALIZED PUBLISHING POWERED BY BXE TOKEN. BXE IS STILL AROUND $0.03 WITH A FIXED SUPPLY OF JUST 500 MILLION TOKENS. DYOR/NFA BXE TOKEN TRADE LINK ON XMAGNETIC: BXE TOKEN TRADE LINK ON MEXC:

JackTheRippler ©️

90,486 次观看 • 5 个月前

NVIDIA just removed one of the biggest friction points in Voice AI. PersonaPlex-7B is an open-source, full-duplex conversational model. Free, open source (MIT), with open model weights on Hugging Face 🤗 Links to repo and weights in 🧵↓ The traditional ASR → LLM → TTS pipeline forces rigid turn-taking. It’s efficient, but it never feels natural. PersonaPlex-7B changes that. This NVIDIA model can listen and speak at the same time. It runs directly on continuous audio tokens with a dual-stream transformer, generating text and audio in parallel instead of passing control between components. That unlocks: → instant back-channel responses → interruptions that feel human → real conversational rhythm Persona control is fully zero-shot! If you’re building low-latency assistants or support agents, this is a big step forward 🔥

NVIDIA just removed one of the biggest friction points in Voice AI. PersonaPlex-7B is an open-source, full-duplex conversational model. Free, open source (MIT), with open model weights on Hugging Face 🤗 Links to repo and weights in 🧵↓ The traditional ASR → LLM → TTS pipeline forces rigid turn-taking. It’s efficient, but it never feels natural. PersonaPlex-7B changes that. This NVIDIA model can listen and speak at the same time. It runs directly on continuous audio tokens with a dual-stream transformer, generating text and audio in parallel instead of passing control between components. That unlocks: → instant back-channel responses → interruptions that feel human → real conversational rhythm Persona control is fully zero-shot! If you’re building low-latency assistants or support agents, this is a big step forward 🔥

Charly Wargnier

565,090 次观看 • 6 个月前

Breaking news: Cosmos 3 is here. They are attempting to do something completely new 🤯 Why is Physical AI much harder than building a chatbot? Understanding the world is not enough, robots need to predict it and act inside it. That's the idea behind NVIDIA Cosmos 3: → Reasoning model understands what's happening from video, images, text, and actions. → World model generates future states of the environment. → Action model generates the actions needed to achieve a goal. Previous systems often stitched these capabilities together using separate models. Cosmos 3 combines them into a single architecture with two components: ▪️ Reasoner Tower Analyzes observations and builds an understanding of objects, motion, interactions, and physical context. ▪️ Generator Tower Uses that understanding to generate future videos and action sequences that obey physical constraints. So Cosmos 3 moves from: Perception → Model A Prediction → Model B Actions → Model C to: Perception + Prediction + Actions → One unified system. The goal is to make robots, autonomous vehicles, and smart environments better at answering three questions: 1. What is happening? 2. What will happen next? 3. What should I do? That's a big shift from today's AI, which mostly focuses on generating text. And check the benchmarks! Physical AI needs to generate decisions that survive contact with the real world. 🚗🤖

Breaking news: Cosmos 3 is here. They are attempting to do something completely new 🤯 Why is Physical AI much harder than building a chatbot? Understanding the world is not enough, robots need to predict it and act inside it. That's the idea behind NVIDIA Cosmos 3: → Reasoning model understands what's happening from video, images, text, and actions. → World model generates future states of the environment. → Action model generates the actions needed to achieve a goal. Previous systems often stitched these capabilities together using separate models. Cosmos 3 combines them into a single architecture with two components: ▪️ Reasoner Tower Analyzes observations and builds an understanding of objects, motion, interactions, and physical context. ▪️ Generator Tower Uses that understanding to generate future videos and action sequences that obey physical constraints. So Cosmos 3 moves from: Perception → Model A Prediction → Model B Actions → Model C to: Perception + Prediction + Actions → One unified system. The goal is to make robots, autonomous vehicles, and smart environments better at answering three questions: 1. What is happening? 2. What will happen next? 3. What should I do? That's a big shift from today's AI, which mostly focuses on generating text. And check the benchmarks! Physical AI needs to generate decisions that survive contact with the real world. 🚗🤖

Turing Post

13,755 次观看 • 1 个月前