Loading video...

Video Failed to Load

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

📕📖📕Learn how the strong agentic abilities of M2.1 can be harnessed to process arbitrarily long input prompts using Recursive Language Models:

MiniMax (official)

105,917 subscribers

17,201 views • 6 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

The Freemasonic Square & Compass Are Tools You Can Use In Life. ⬛️🧭 Symbols Are Maps. If You Learn To Read Them You Stop Walking Blind. Learn The Language: 📕

The Freemasonic Square & Compass Are Tools You Can Use In Life. ⬛️🧭 Symbols Are Maps. If You Learn To Read Them You Stop Walking Blind. Learn The Language: 📕

vegastar

118,274 views • 5 months ago

Eating Mold? 🤔Deep dive on how heavy metals can be pulled with moldy berries. Books: 📕Allergy Truths: The peanut allergy epidemic 📕Mold truths: We Want to Live Aajonus Vonderplanitz

Eating Mold? 🤔Deep dive on how heavy metals can be pulled with moldy berries. Books: 📕Allergy Truths: The peanut allergy epidemic 📕Mold truths: We Want to Live Aajonus Vonderplanitz

Matt From Cultivate Elevate

206,940 views • 1 year ago

Acoustic levitation, using sound waves to balance the force of gravity Something intangible like sound can be harnessed to exert a physical force that is strong enough to lift or suspend objects

Acoustic levitation, using sound waves to balance the force of gravity Something intangible like sound can be harnessed to exert a physical force that is strong enough to lift or suspend objects

Science girl

900,140 views • 3 years ago

Athletes: This is the real reason you get subbed out. One of the best ways to be a mentally strong athlete is to learn how to own your body language—regardless of external circumstances, opposition, or adversity. Be the athlete whose body language never wavers.

Athletes: This is the real reason you get subbed out. One of the best ways to be a mentally strong athlete is to learn how to own your body language—regardless of external circumstances, opposition, or adversity. Be the athlete whose body language never wavers.

Coach VJ

61,479 views • 3 months ago

🚨 UNCANNY VALLEY: LANGUAGE MODEL TECH IS NOW DRIVING AI THAT CAN SEE AND REASON TOO Swupnil Sahai 🎾🧠: “The new architecture that’s come out for these language models works really well for vision now too. So the kind of math you can use to go from that input to be output is becoming the same now. We’re actually using much lighter weight models. So it’s a slightly different architecture, but it’s the same concept.”

🚨 UNCANNY VALLEY: LANGUAGE MODEL TECH IS NOW DRIVING AI THAT CAN SEE AND REASON TOO Swupnil Sahai 🎾🧠: “The new architecture that’s come out for these language models works really well for vision now too. So the kind of math you can use to go from that input to be output is becoming the same now. We’re actually using much lighter weight models. So it’s a slightly different architecture, but it’s the same concept.”

Mario Nawfal

90,984 views • 1 year ago

New short course: DSPy: Build and Optimize Agentic Apps DSPy is a powerful open-source framework for automatically tuning prompts for GenAI applications. In this course, you'll learn to use DSPy, together with MLflow. This is built in partnership with Databricks and taught by Chen Qian, co-lead of the DSPy framework. Many AI builders spend hours hand-tuning prompts. When given a set of evals, DSPy automates this process. It’s especially useful for optimizing prompts, including few-shot prompts, in complex agentic AI workflows. Further, if you switch an application to a newer LLM, performance can degrade if your prompts were optimized to the previous model. DSPy automatically optimizes the entire system for the new LLM as well, using just a few evaluation examples. This course teaches DSPy works, and best practices for using it. You’ll write programs using DSPy’s signature-based programming model, debug them with MLflow tracing -- to gain visibility into how different parts of a pipeline, as well as how the overall system, are performing -- and automatically improve their accuracy with DSPy Optimizer. Please sign up here:

New short course: DSPy: Build and Optimize Agentic Apps DSPy is a powerful open-source framework for automatically tuning prompts for GenAI applications. In this course, you'll learn to use DSPy, together with MLflow. This is built in partnership with Databricks and taught by Chen Qian, co-lead of the DSPy framework. Many AI builders spend hours hand-tuning prompts. When given a set of evals, DSPy automates this process. It’s especially useful for optimizing prompts, including few-shot prompts, in complex agentic AI workflows. Further, if you switch an application to a newer LLM, performance can degrade if your prompts were optimized to the previous model. DSPy automatically optimizes the entire system for the new LLM as well, using just a few evaluation examples. This course teaches DSPy works, and best practices for using it. You’ll write programs using DSPy’s signature-based programming model, debug them with MLflow tracing -- to gain visibility into how different parts of a pipeline, as well as how the overall system, are performing -- and automatically improve their accuracy with DSPy Optimizer. Please sign up here:

Andrew Ng

181,457 views • 1 year ago

Our course recommendation of the day is “Post-training of LLMs, ” where you’ll learn how to customize pre-trained language models using Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and Online Reinforcement Learning (RL). You'll learn when to use each method, how to curate training data, and implement them in code to shape model behavior effectively. Enroll here:

Our course recommendation of the day is “Post-training of LLMs, ” where you’ll learn how to customize pre-trained language models using Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and Online Reinforcement Learning (RL). You'll learn when to use each method, how to curate training data, and implement them in code to shape model behavior effectively. Enroll here:

DeepLearning.AI

29,369 views • 9 months ago

Ironheart portraying how dangerous the gross misuse of AI can be, how using the likeness of a person (dead or alive) to create a life like image can result in unhealthy attachments, inability to process emotions/grieve properly or disrespecting the memory of a deceased person.

Ironheart portraying how dangerous the gross misuse of AI can be, how using the likeness of a person (dead or alive) to create a life like image can result in unhealthy attachments, inability to process emotions/grieve properly or disrespecting the memory of a deceased person.

HOT GIRL CAP ⍟

168,075 views • 1 year ago

Amanda may be a lot of things but she certainly cleared Dorit with the “At least I can write a book,” 📕 and the “Good Luck to her Ghost Writers” shade. ✍🏻🤣 #RHOBH

Amanda may be a lot of things but she certainly cleared Dorit with the “At least I can write a book,” 📕 and the “Good Luck to her Ghost Writers” shade. ✍🏻🤣 #RHOBH

Albie (Housewives & Madonna Super Fan)

41,043 views • 4 months ago

🚨 NEW LABS EXPERIMENT 🚨 Introducing Opal, our new way to help you build and share AI mini-apps by linking together prompts, models, and tools— all while using simple, natural language (without a single line of code 🤯) Now available in US-only public beta! Learn more ⬇️

🚨 NEW LABS EXPERIMENT 🚨 Introducing Opal, our new way to help you build and share AI mini-apps by linking together prompts, models, and tools— all while using simple, natural language (without a single line of code 🤯) Now available in US-only public beta! Learn more ⬇️

Google Labs

536,907 views • 1 year ago

LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models paper page: github: Recent advancements in text-to-image generation with diffusion models have yielded remarkable results synthesizing highly realistic and diverse images. However, these models still encounter difficulties when generating images from prompts that demand spatial or common sense reasoning. We propose to equip diffusion models with enhanced reasoning capabilities by using off-the-shelf pretrained large language models (LLMs) in a novel two-stage generation process. First, we adapt an LLM to be a text-guided layout generator through in-context learning. When provided with an image prompt, an LLM outputs a scene layout in the form of bounding boxes along with corresponding individual descriptions. Second, we steer a diffusion model with a novel controller to generate images conditioned on the layout. Both stages utilize frozen pretrained models without any LLM or diffusion model parameter optimization. We validate the superiority of our design by demonstrating its ability to outperform the base diffusion model in accurately generating images according to prompts that necessitate both language and spatial reasoning. Additionally, our method naturally allows dialog-based scene specification and is able to handle prompts in a language that is not well-supported by the underlying diffusion model.

LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models paper page: github: Recent advancements in text-to-image generation with diffusion models have yielded remarkable results synthesizing highly realistic and diverse images. However, these models still encounter difficulties when generating images from prompts that demand spatial or common sense reasoning. We propose to equip diffusion models with enhanced reasoning capabilities by using off-the-shelf pretrained large language models (LLMs) in a novel two-stage generation process. First, we adapt an LLM to be a text-guided layout generator through in-context learning. When provided with an image prompt, an LLM outputs a scene layout in the form of bounding boxes along with corresponding individual descriptions. Second, we steer a diffusion model with a novel controller to generate images conditioned on the layout. Both stages utilize frozen pretrained models without any LLM or diffusion model parameter optimization. We validate the superiority of our design by demonstrating its ability to outperform the base diffusion model in accurately generating images according to prompts that necessitate both language and spatial reasoning. Additionally, our method naturally allows dialog-based scene specification and is able to handle prompts in a language that is not well-supported by the underlying diffusion model.

AK

83,657 views • 3 years ago

Will #JalenHurts ever be the QB #Eagles need him to be? @ProFootballHof QB #KurtWarner @Kurt13Warner, on #TheHowardEskinShow questions whether Hurts can learn how to “process” at this point. NFL Network

Will #JalenHurts ever be the QB #Eagles need him to be? @ProFootballHof QB #KurtWarner @Kurt13Warner, on #TheHowardEskinShow questions whether Hurts can learn how to “process” at this point. NFL Network

Howard Eskin

78,116 views • 7 months ago

Sickness is not contagious. Sickness is the bodies way of detoxing and regenerating to keep us alive. Support the detox process, don't blame others, and clean up the terrain. 📕Book on the topic: The Poisoned needle, Can you catch a cold, and the contagion myth.

Sickness is not contagious. Sickness is the bodies way of detoxing and regenerating to keep us alive. Support the detox process, don't blame others, and clean up the terrain. 📕Book on the topic: The Poisoned needle, Can you catch a cold, and the contagion myth.

Matt From Cultivate Elevate

21,947 views • 1 year ago