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。

Sharing our work at NeurIPS Conference on reasoning with EBMs! We learn an EBM over simple subproblems and combine EBMs at test-time to solve complex reasoning problems (3-SAT, graph coloring, crosswords). Generalizes well to complex 3-SAT / graph coloring/ N-queens problems.

Yilun Du

12,408 subscribers

47,660 次观看 • 9 个月前 •via X (Twitter)

教育健康养生科学技术

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Introducing Agent Blocks. AI agents can now work together to solve more complex problems. - Start with simple agents - Combine them into sophisticated solutions - Build on top of other's work Available now in the AutoGPT Platform ✅ Learn more ➡️

Introducing Agent Blocks. AI agents can now work together to solve more complex problems. - Start with simple agents - Combine them into sophisticated solutions - Build on top of other's work Available now in the AutoGPT Platform ✅ Learn more ➡️

AutoGPT

27,237 次观看 • 1 年前

yeah, genius phuwin by the way.... - got accelerated (graduated at 20) - 2nd honors (chula uni - engineering) - can speak 3 languages • thai • english • chinese - can solve and explain complex math problems - studying all while having tons of work and projects - academic slayer • ielts (8.5/9) • Sat Math (780) • Sat Chemistry (750) • Sat Physics (770) • Sat Verbal (680) • top 5% nationally • top 9% of all SAT takers - can play different types of musical instruments - can sing - can dance - can act #phuwintang

yeah, genius phuwin by the way.... - got accelerated (graduated at 20) - 2nd honors (chula uni - engineering) - can speak 3 languages • thai • english • chinese - can solve and explain complex math problems - studying all while having tons of work and projects - academic slayer • ielts (8.5/9) • Sat Math (780) • Sat Chemistry (750) • Sat Physics (770) • Sat Verbal (680) • top 5% nationally • top 9% of all SAT takers - can play different types of musical instruments - can sing - can dance - can act #phuwintang

ciara

126,480 次观看 • 5 个月前

We sat down with Joe Lonsdale (Joe Lonsdale) and explained why “Dental Billing” is one of the most compelling & complex applications of LLMs. - AI Phone calls to insurance companies - vLLMs to read 300+ page pdfs - Web agents to navigate insurance portals - Reasoning models to dispute denials At DayDream we are transforming American small businesses with AI & allowing dentists to focus on what they love – treating patients. If you're serious about working on difficult problems, we're hiring for Eng/Ops/Sales roles! DM me or see

We sat down with Joe Lonsdale (Joe Lonsdale) and explained why “Dental Billing” is one of the most compelling & complex applications of LLMs. - AI Phone calls to insurance companies - vLLMs to read 300+ page pdfs - Web agents to navigate insurance portals - Reasoning models to dispute denials At DayDream we are transforming American small businesses with AI & allowing dentists to focus on what they love – treating patients. If you're serious about working on difficult problems, we're hiring for Eng/Ops/Sales roles! DM me or see

anton lin

162,897 次观看 • 1 年前

Open sourcing Dynamic Graph Memory by mem0. Memory is fundamental to human reasoning, shaping how we approach tasks and make decisions. At Mem0, we believe that AI agents & apps should reflect this principle. Our Dynamic Graph Memory emulates human memory, advancing AI agents toward more intelligent, human-like reasoning. This is a significant step forward in building AI that truly understands and interacts with the world like we do. All credit to Dev Khant Deshraj Yadav Prateek Chhikara for their countless nights spent on bringing this to life. Link:

Open sourcing Dynamic Graph Memory by mem0. Memory is fundamental to human reasoning, shaping how we approach tasks and make decisions. At Mem0, we believe that AI agents & apps should reflect this principle. Our Dynamic Graph Memory emulates human memory, advancing AI agents toward more intelligent, human-like reasoning. This is a significant step forward in building AI that truly understands and interacts with the world like we do. All credit to Dev Khant Deshraj Yadav Prateek Chhikara for their countless nights spent on bringing this to life. Link:

Taranjeet

51,129 次观看 • 2 年前

Everyone is focused on tracking the ways LLMs are getting better. And they are. But we know there are still things that LLMs can’t do well—the tasks where you can feel the architecture fighting the problem. So I was excited to chat with Eve Bodnia (@eve_bodnia), who is developing an alternative AI model to LLMs, on Every 📧's AI & I. Eve's argument: energy-based models (EBMs), which map possible outcomes onto a mathematical landscape, will lead to the next AI phase shift. We get into: - How energy-based models work. Likely outcomes sit in valleys, and unlikely ones sit on peaks. Whereas LLMs process one token at a time, an EBM scans the full terrain to find the lowest point, or the most probable answer. - Language-based versus data-native models. LLMs are language-dependent even when the problem has nothing to do with language. "If your data is numbers, relationships, and functions, and you try to map those rules into words and then search for the next word, you're losing a lot of information," Bodnia says. EBMs work directly with the underlying data structure, including numbers and spatial coordinates. - Sequential versus panoramic reasoning. An LLM is like driving through San Francisco without a map. Each turn constrains the next, and if you go down the wrong street, you can't reverse course. An EBM has the bird's-eye view—it can evaluate multiple routes at once and course-correct before hitting a dead end. - The LLM plateau no one wants to talk about. LLMs are getting incrementally better, step-change improvements aren’t coming, Eve argues. To achieve that, we need new solutions that compensate for what LLMs are inherently bad at, like non-language reasoning, verification, and real-time data analysis. This is a must-watch for anyone who's curious what might come after the LLM. Watch below! Timestamps: Introduction: 00:00:51 Why correctness and verifiability matter in AI: 00:02:09 What an energy-based model is: 00:09:33 How EBMs construct energy landscapes to understand data: 00:14:21 Why modeling intelligence through language alone is a flawed approach: 00:19:00 What it means for a model to "understand" data: 00:26:54 How EBMs solve the vibe coding problem and enable formally verified code: 00:37:21 Why LLM progress is plateauing: 00:43:21 Mission-critical industries haven't adopted LLMs, and why EBMs can fill that gap: 00:49:54

Everyone is focused on tracking the ways LLMs are getting better. And they are. But we know there are still things that LLMs can’t do well—the tasks where you can feel the architecture fighting the problem. So I was excited to chat with Eve Bodnia (@eve_bodnia), who is developing an alternative AI model to LLMs, on Every 📧's AI & I. Eve's argument: energy-based models (EBMs), which map possible outcomes onto a mathematical landscape, will lead to the next AI phase shift. We get into: - How energy-based models work. Likely outcomes sit in valleys, and unlikely ones sit on peaks. Whereas LLMs process one token at a time, an EBM scans the full terrain to find the lowest point, or the most probable answer. - Language-based versus data-native models. LLMs are language-dependent even when the problem has nothing to do with language. "If your data is numbers, relationships, and functions, and you try to map those rules into words and then search for the next word, you're losing a lot of information," Bodnia says. EBMs work directly with the underlying data structure, including numbers and spatial coordinates. - Sequential versus panoramic reasoning. An LLM is like driving through San Francisco without a map. Each turn constrains the next, and if you go down the wrong street, you can't reverse course. An EBM has the bird's-eye view—it can evaluate multiple routes at once and course-correct before hitting a dead end. - The LLM plateau no one wants to talk about. LLMs are getting incrementally better, step-change improvements aren’t coming, Eve argues. To achieve that, we need new solutions that compensate for what LLMs are inherently bad at, like non-language reasoning, verification, and real-time data analysis. This is a must-watch for anyone who's curious what might come after the LLM. Watch below! Timestamps: Introduction: 00:00:51 Why correctness and verifiability matter in AI: 00:02:09 What an energy-based model is: 00:09:33 How EBMs construct energy landscapes to understand data: 00:14:21 Why modeling intelligence through language alone is a flawed approach: 00:19:00 What it means for a model to "understand" data: 00:26:54 How EBMs solve the vibe coding problem and enable formally verified code: 00:37:21 Why LLM progress is plateauing: 00:43:21 Mission-critical industries haven't adopted LLMs, and why EBMs can fill that gap: 00:49:54

Dan Shipper 📧

26,900 次观看 • 4 个月前

🆕Scaling Test Time Compute to Multi-Agent Civilizations, with Noam Brown We're excited to publish our full conversation with Noam Brown on the frontiers of the new reasoning paradigm at OpenAI! - first principles for starting the "Multi-Agents" team - what's not captured by the "System 1/System 2" analogy for inference time compute - how Ilya Sutskever convinced him that reasoning was closer than he thought - Deep Research is existence proof that RL generalizes beyond verifiable rewards - the relationship between AI for imperfect information games (like Poker, Stratego, Diplomacy) and reasoning Enjoy! on youtube, or wherever fine podcasts are sold.

🆕Scaling Test Time Compute to Multi-Agent Civilizations, with Noam Brown We're excited to publish our full conversation with Noam Brown on the frontiers of the new reasoning paradigm at OpenAI! - first principles for starting the "Multi-Agents" team - what's not captured by the "System 1/System 2" analogy for inference time compute - how Ilya Sutskever convinced him that reasoning was closer than he thought - Deep Research is existence proof that RL generalizes beyond verifiable rewards - the relationship between AI for imperfect information games (like Poker, Stratego, Diplomacy) and reasoning Enjoy! on youtube, or wherever fine podcasts are sold.

Latent.Space

105,923 次观看 • 1 年前

Elon nails exactly what's wrong with education here and what needs to change. You may not know he actually started a remarkable school at SpaceX for his kids based on his principles... The school was called Ad Astra, Latin for “to the stars”. Elon hired Josh Dahn to build and run the school. When Elon’s kids graduated, Josh and I cofounded Synthesis together. Our goal is to take the best parts of the SpaceX school and make them accessible to everyone. Elon famously follows a “first principles” approach. The primary principle of the school: A good education should produce people who can SOLVE PROBLEMS — real, complex problems with a team. Like how to colonize Mars. Not fake school worksheet problems. This principle was embodied in a class at the school called “Synthesis”. In the class, kids worked in teams to solve problems via complex games and simulations. The skills they build in Synthesis — working with a team, making tradeoffs, risk assessment and critical thinking — are the foundational skills they’ll need to solve problems in any domain. 1/2

Elon nails exactly what's wrong with education here and what needs to change. You may not know he actually started a remarkable school at SpaceX for his kids based on his principles... The school was called Ad Astra, Latin for “to the stars”. Elon hired Josh Dahn to build and run the school. When Elon’s kids graduated, Josh and I cofounded Synthesis together. Our goal is to take the best parts of the SpaceX school and make them accessible to everyone. Elon famously follows a “first principles” approach. The primary principle of the school: A good education should produce people who can SOLVE PROBLEMS — real, complex problems with a team. Like how to colonize Mars. Not fake school worksheet problems. This principle was embodied in a class at the school called “Synthesis”. In the class, kids worked in teams to solve problems via complex games and simulations. The skills they build in Synthesis — working with a team, making tradeoffs, risk assessment and critical thinking — are the foundational skills they’ll need to solve problems in any domain. 1/2

Chrisman

408,221 次观看 • 2 年前

Our new short course, Knowledge Graphs for RAG, is now available! Knowledge graphs are a data structure that is great at capturing complex relationships between data of multiple types. By enabling more sophisticated retrieval of text than similarity search alone, knowledge graphs can improve the context you pass to the LLM and the performance of your RAG applications. In this course, taught by Andreas Kollegger of Neo4j, you’ll - Explore how knowledge graphs work by building a graph of public financial documents from scratch - Learn to write queries that retrieve text and data from the graph and use it to enhance the context you pass to an LLM chatbot - Combine a knowledge graph with a question-answer chain to build better RAG-powered chat systems Sign up here!

Our new short course, Knowledge Graphs for RAG, is now available! Knowledge graphs are a data structure that is great at capturing complex relationships between data of multiple types. By enabling more sophisticated retrieval of text than similarity search alone, knowledge graphs can improve the context you pass to the LLM and the performance of your RAG applications. In this course, taught by Andreas Kollegger of Neo4j, you’ll - Explore how knowledge graphs work by building a graph of public financial documents from scratch - Learn to write queries that retrieve text and data from the graph and use it to enhance the context you pass to an LLM chatbot - Combine a knowledge graph with a question-answer chain to build better RAG-powered chat systems Sign up here!

Andrew Ng

244,403 次观看 • 2 年前

$2M a year is the sweet spot. Everybody wants to get rich but most people don’t understand the problems that come with it. New levels new devils. I’ve been on every side of wealth. Dead ass broke to having massive success. After $2M a year there is a diminishing return. You start to run out of things to buy while at the same time the problems get bigger, more complex, and harder to solve.

$2M a year is the sweet spot. Everybody wants to get rich but most people don’t understand the problems that come with it. New levels new devils. I’ve been on every side of wealth. Dead ass broke to having massive success. After $2M a year there is a diminishing return. You start to run out of things to buy while at the same time the problems get bigger, more complex, and harder to solve.

Eric Spofford

263,751 次观看 • 4 个月前

Recently we: 1. Signed to acquire AOL and Vimeo 2. Raised $2.8B in debt 3. Raised $700M in equity at an $11B valuation Rebecca and I sat down with our CEO Luca to break down the news! 👇

Recently we: 1. Signed to acquire AOL and Vimeo 2. Raised $2.8B in debt 3. Raised $700M in equity at an $11B valuation Rebecca and I sat down with our CEO Luca to break down the news! 👇

Federico Simionato

256,040 次观看 • 9 个月前

Jan-v2-VL-Max-Instruct is out on 💛 Our newest 30B vision-language model, extending the Jan-v2-VL family. This is our experiment bringing interleaved reasoning to an Instruct model. It handles long tasks well and stays on track when things get complicated. Good for research, multi-step problems, anything that needs patience. Try it now at

Jan-v2-VL-Max-Instruct is out on 💛 Our newest 30B vision-language model, extending the Jan-v2-VL family. This is our experiment bringing interleaved reasoning to an Instruct model. It handles long tasks well and stays on track when things get complicated. Good for research, multi-step problems, anything that needs patience. Try it now at

👋 Jan

23,063 次观看 • 7 个月前

🚨 Breaking the Hype 🚨 Since #DeepSeek is all the rage, I decided to test what the fuss is about. And guess what? I “broke” it on my first try! 🤯 Here’s the simple prompt that sent DeepSeek into an endless logic loop, I had to manually cancel the reasoning loop 💬 If a train leaves New York at 2 PM traveling 60 mph and another train leaves Los Angeles at 3 PM traveling 70 mph, when do they meet? Looks like DeepSeek needs more 🚧 work on reasoning! 🚧 In comparison #ChatGPT (OpenAI) didn’t break a sweat. I didnt check the math but the reasoning is very simple and plausible. Anyone else trying to push its limits? Let’s share! #AI #PromptEngineering #TechFun

🚨 Breaking the Hype 🚨 Since #DeepSeek is all the rage, I decided to test what the fuss is about. And guess what? I “broke” it on my first try! 🤯 Here’s the simple prompt that sent DeepSeek into an endless logic loop, I had to manually cancel the reasoning loop 💬 If a train leaves New York at 2 PM traveling 60 mph and another train leaves Los Angeles at 3 PM traveling 70 mph, when do they meet? Looks like DeepSeek needs more 🚧 work on reasoning! 🚧 In comparison #ChatGPT (OpenAI) didn’t break a sweat. I didnt check the math but the reasoning is very simple and plausible. Anyone else trying to push its limits? Let’s share! #AI #PromptEngineering #TechFun

Dreams of Mars 🕊❤️🚀🌕

100,806 次观看 • 1 年前

🧠David Friedberg explains the great hope of Artificial Superintelligence: Massive leverage on time to solve thousand-year problems "I don't think that humans are limited in our ability to solve problems." "I think we're limited in terms of time, and what digital intelligence gives us is leverage on time so that we can now tackle ever more complex tasks." "This idea of superintelligence is that it could give us immense leverage in solving that complex problem that we otherwise may be challenged to solve over decades, or hundreds of years, or think about one day solving a problem that would take humans thousands of years to solve." "So if I as a human said, 'I would like to harness fusion power similar to what the sun uses to make energy, and I wanna do that on Earth,' today, we're in, call it year 40 or 50 of a research cycle of humans trying to solve that particularly complex problem." "It's a scientific problem, it's a discovery problem, it's an engineering problem." "Functionally, leveraging to complexity is where this becomes super compelling for humans." "And it's why I think we can and should be highly optimistic about living very long lives, and traveling anywhere we want, and having abundance in food, and having abundance in resources, and having abundance in recouping our time to do the things we want to do instead of the things that we have to do today."

🧠David Friedberg explains the great hope of Artificial Superintelligence: Massive leverage on time to solve thousand-year problems "I don't think that humans are limited in our ability to solve problems." "I think we're limited in terms of time, and what digital intelligence gives us is leverage on time so that we can now tackle ever more complex tasks." "This idea of superintelligence is that it could give us immense leverage in solving that complex problem that we otherwise may be challenged to solve over decades, or hundreds of years, or think about one day solving a problem that would take humans thousands of years to solve." "So if I as a human said, 'I would like to harness fusion power similar to what the sun uses to make energy, and I wanna do that on Earth,' today, we're in, call it year 40 or 50 of a research cycle of humans trying to solve that particularly complex problem." "It's a scientific problem, it's a discovery problem, it's an engineering problem." "Functionally, leveraging to complexity is where this becomes super compelling for humans." "And it's why I think we can and should be highly optimistic about living very long lives, and traveling anywhere we want, and having abundance in food, and having abundance in resources, and having abundance in recouping our time to do the things we want to do instead of the things that we have to do today."

The All-In Podcast

53,187 次观看 • 1 年前

📄We just launched PDF uploads in Arena. Upload PDFs with your prompts to add richer context and test models on document reasoning, bringing evaluations closer to real-world use. ▪️Ask questions directly against documents ▪️Digest complex, technical content in minutes ▪️Extract summaries and key takeaways instantly Try it across 10 models today - we’ll be adding more over time. Leaderboard coming soon. Start uploading, comparing, and voting!

📄We just launched PDF uploads in Arena. Upload PDFs with your prompts to add richer context and test models on document reasoning, bringing evaluations closer to real-world use. ▪️Ask questions directly against documents ▪️Digest complex, technical content in minutes ▪️Extract summaries and key takeaways instantly Try it across 10 models today - we’ll be adding more over time. Leaderboard coming soon. Start uploading, comparing, and voting!

Arena.ai

46,578 次观看 • 6 个月前

Welcome to Shipmas Day 3 part 1… the big one. 🚢🎁 Today, we remove the ceiling on what you can generate. Starting today, our new default agent is Thinking with Gemini 3 Pro. This agent uses advanced reasoning to "think" through your design before writing a single line of code. The community has been calling Gemini 3 "too good at frontend" and "unmatched in visual reasoning." We agree. It handles complex dashboards, intricate DOM manipulation, and pixel-perfect CSS better than anything we've tested. All designs are backed by code and exportable to your favorite coding agent. The video below shows some single prompt examples to inspire you. Sound on for a preview of the new Stitch theme song 🔊

Welcome to Shipmas Day 3 part 1… the big one. 🚢🎁 Today, we remove the ceiling on what you can generate. Starting today, our new default agent is Thinking with Gemini 3 Pro. This agent uses advanced reasoning to "think" through your design before writing a single line of code. The community has been calling Gemini 3 "too good at frontend" and "unmatched in visual reasoning." We agree. It handles complex dashboards, intricate DOM manipulation, and pixel-perfect CSS better than anything we've tested. All designs are backed by code and exportable to your favorite coding agent. The video below shows some single prompt examples to inspire you. Sound on for a preview of the new Stitch theme song 🔊

Stitch by Google

192,446 次观看 • 8 个月前

With enough data, robots and AI can learn “world models” that let them predict the results of their actions. These models are a way to learn how embodied AI agents can perform a wide variety of useful tasks — but they require a huge amount of data. The team at General Intuition General Intuition has a solution: use data from video games! Games teach movement, problem solving, and complex spatial reasoning, and they come in a staggering diversity of forms, covering a wide variety of problems. What’s more, the captured data is high-quality, without the noise or annotation error that can come from We sat down with Pim de Witte and Adam Jelley from the General Intuition team to learn more about their history, their plans, and their philosophy.

With enough data, robots and AI can learn “world models” that let them predict the results of their actions. These models are a way to learn how embodied AI agents can perform a wide variety of useful tasks — but they require a huge amount of data. The team at General Intuition General Intuition has a solution: use data from video games! Games teach movement, problem solving, and complex spatial reasoning, and they come in a staggering diversity of forms, covering a wide variety of problems. What’s more, the captured data is high-quality, without the noise or annotation error that can come from We sat down with Pim de Witte and Adam Jelley from the General Intuition team to learn more about their history, their plans, and their philosophy.

RoboPapers

85,927 次观看 • 9 个月前

Grok CLI >>> Cursor and Claude Code We wanted an IDE for xAI's Grok so we did something meta: we prompted the newly released Grok 4 to create... Grok CLI itself! Grok CLI can: 1. Modify local files and use the shell 2. Go through huge codebases and fix them 3. Persist for longer and solve really complex math and physics problems Instant setup on Replit ⠕ Bonus: Can create and run ai agents with it's completely open source!! link to the code: link to the repl:

Grok CLI >>> Cursor and Claude Code We wanted an IDE for xAI's Grok so we did something meta: we prompted the newly released Grok 4 to create... Grok CLI itself! Grok CLI can: 1. Modify local files and use the shell 2. Go through huge codebases and fix them 3. Persist for longer and solve really complex math and physics problems Instant setup on Replit ⠕ Bonus: Can create and run ai agents with it's completely open source!! link to the code: link to the repl:

Karan Vaidya

345,808 次观看 • 1 年前