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.

Gemini has always been my go-to LLM for document extraction - but accurate bounding boxes with agentic vision are a huge value-add in the latest Gemini models. Shown: extracting structured data from an oil & gas lease in Ector County Texas with the best bboxes I've seen yet.

Kyle Walker

19,267 subscribers

79,632 views • 5 months ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

See Google’s Gemini 2.5 Pro in action with the Box AI API! We put it to the test on complex invoice calculations and analyzing 10-K financial documents. Leverage Gemini 2.5 Pro via the Box AI API for advanced document processing, data extraction, and Q&A in your applications.

See Google’s Gemini 2.5 Pro in action with the Box AI API! We put it to the test on complex invoice calculations and analyzing 10-K financial documents. Leverage Gemini 2.5 Pro via the Box AI API for advanced document processing, data extraction, and Q&A in your applications.

Box

489,084 views • 1 year ago

Announcing: Agentic Document Extraction! PDF files represent information visually - via layout, charts, graphs, etc. - and are more than just text. Unlike traditional OCR and most PDF-to-text approaches, which focus on extracting the text, an agentic approach lets us break a document down into components and reason about them, resulting in more accurate extraction of the underlying meaning for RAG and other applications. Watch the video for details.

Announcing: Agentic Document Extraction! PDF files represent information visually - via layout, charts, graphs, etc. - and are more than just text. Unlike traditional OCR and most PDF-to-text approaches, which focus on extracting the text, an agentic approach lets us break a document down into components and reason about them, resulting in more accurate extraction of the underlying meaning for RAG and other applications. Watch the video for details.

Andrew Ng

689,328 views • 1 year ago

Today at #GoogleIO, we’re demonstrating how our partnership with Google Cloud is redefining the landscape of Intelligent Content Management. Leveraging the advanced capabilities of Google’s Gemini 2.5 Pro, our new AI Agent with enhanced data extraction transforms complex, unstructured data from various sources—including scanned PDFs, images, and diverse forms—into structured, actionable insights. Check out the demo below to watch Gemini 2.5 Pro and Box AI agents in action. With the Box AI Agent powered by Gemini 2.5 Pro you can: ⭐ Automatically, and instantly, classify and organize documents ⭐ Extract accurate insights and information from documents and images ⭐ Enable workflow automation by leveraging structured and easily retrievable content Our partnership with Google is not just about enhancing current capabilities; it’s about unlocking the full potential of AI, and models like Gemini 2.5 Pro, for intricate enterprise use cases.

Today at #GoogleIO, we’re demonstrating how our partnership with Google Cloud is redefining the landscape of Intelligent Content Management. Leveraging the advanced capabilities of Google’s Gemini 2.5 Pro, our new AI Agent with enhanced data extraction transforms complex, unstructured data from various sources—including scanned PDFs, images, and diverse forms—into structured, actionable insights. Check out the demo below to watch Gemini 2.5 Pro and Box AI agents in action. With the Box AI Agent powered by Gemini 2.5 Pro you can: ⭐ Automatically, and instantly, classify and organize documents ⭐ Extract accurate insights and information from documents and images ⭐ Enable workflow automation by leveraging structured and easily retrievable content Our partnership with Google is not just about enhancing current capabilities; it’s about unlocking the full potential of AI, and models like Gemini 2.5 Pro, for intricate enterprise use cases.

Box

10,565 views • 1 year ago

Today, we're introducing not one but TWO new models, striking the balance between efficiency and quality to enable you to build production AI agents. — Gemini 3.6 Flash: Addresses efficiency feedback we received from Gemini 3.5 Flash with upgrades in coding, knowledge work, and multimodal tasks faster, more accurately, and with substantially fewer tokens per task — Gemini 3.5 Flash-Lite: Our fastest, most cost-effective 3.5-class model yet built for agentic workflows, hitting ~350 output tokens/sec with improved coding and overall quality Start building with these today via the Gemini API in Google AI Studio or try them out in the Google Gemini

Today, we're introducing not one but TWO new models, striking the balance between efficiency and quality to enable you to build production AI agents. — Gemini 3.6 Flash: Addresses efficiency feedback we received from Gemini 3.5 Flash with upgrades in coding, knowledge work, and multimodal tasks faster, more accurately, and with substantially fewer tokens per task — Gemini 3.5 Flash-Lite: Our fastest, most cost-effective 3.5-class model yet built for agentic workflows, hitting ~350 output tokens/sec with improved coding and overall quality Start building with these today via the Gemini API in Google AI Studio or try them out in the Google Gemini

Google AI

424,998 views • 6 days ago

Here we go: Gemini 3.0 is live! Thankfully, I was able to be an early tester. It's the best model I've ever tested - nothing comes even close to it. OpenAI will have a very hard time to keep up with Google, because Gemini 3.0 will now be the benchmark for all future models. I have been invited by Google DeepMind / Google - Thanks to Google DeepMind for the #EarlyAccess Here's a summary of Gemini 3.0 with all the important benchmark evals:

Here we go: Gemini 3.0 is live! Thankfully, I was able to be an early tester. It's the best model I've ever tested - nothing comes even close to it. OpenAI will have a very hard time to keep up with Google, because Gemini 3.0 will now be the benchmark for all future models. I have been invited by Google DeepMind / Google - Thanks to Google DeepMind for the #EarlyAccess Here's a summary of Gemini 3.0 with all the important benchmark evals:

Chubby♨️

108,611 views • 8 months ago

Today we’re taking a big step on the path toward AGI and releasing Gemini 3— our most intelligent model yet. With Gemini 3, you can bring any idea to life. It is state-of-the-art in reasoning, the best model in the world for multimodal understanding, and our best agentic and vibe coding model.

Today we’re taking a big step on the path toward AGI and releasing Gemini 3— our most intelligent model yet. With Gemini 3, you can bring any idea to life. It is state-of-the-art in reasoning, the best model in the world for multimodal understanding, and our best agentic and vibe coding model.

Google AI

492,917 views • 8 months ago

New course: Document AI: From OCR to Agentic Doc Extraction, built with LandingAI, where I'm executive chairman, and taught by David Park and Andrea Kropp. Much of the world's data is locked in PDFs, JPEGs, and other documents. This short course shows you how to build agentic workflows that process documents accurately: breaking them into parts, examining each piece carefully, and extracting information through multiple iterations. Traditional Optical Character Recognition (OCR) captures text but loses context from table headers, chart captions, or reading order of columns. After exploring OCR's limitations, you’ll use LandingAI's Agentic Document Extraction (ADE) framework to process documents. ADE treats pages as visually -- as images -- to parse information and extract fields. Skills you'll gain: - Build agents to convert unstructured files into structured Markdown/HTML and JSON - Use ADE to parse complex data like forms, handwriting, or equations - Map extracted information to named fields using a specified schema, with bounding boxes for grounding and validation - Deploy RAG applications with event-driven document processing Come learn about the best tools for processing documents like financial invoices, medical records, or academic papers intelligently:

New course: Document AI: From OCR to Agentic Doc Extraction, built with LandingAI, where I'm executive chairman, and taught by David Park and Andrea Kropp. Much of the world's data is locked in PDFs, JPEGs, and other documents. This short course shows you how to build agentic workflows that process documents accurately: breaking them into parts, examining each piece carefully, and extracting information through multiple iterations. Traditional Optical Character Recognition (OCR) captures text but loses context from table headers, chart captions, or reading order of columns. After exploring OCR's limitations, you’ll use LandingAI's Agentic Document Extraction (ADE) framework to process documents. ADE treats pages as visually -- as images -- to parse information and extract fields. Skills you'll gain: - Build agents to convert unstructured files into structured Markdown/HTML and JSON - Use ADE to parse complex data like forms, handwriting, or equations - Map extracted information to named fields using a specified schema, with bounding boxes for grounding and validation - Deploy RAG applications with event-driven document processing Come learn about the best tools for processing documents like financial invoices, medical records, or academic papers intelligently:

Andrew Ng

200,141 views • 6 months ago

Most organizations run on unstructured content, but it’s the data locked within that content moves business forward. Box Extract is now generally available, delivering agentic data extraction at scale for smart process automation. Combining the latest AI models with advanced OCR capabilities, and agentic approaches that understand document structure and meaning, Box Extract automatically and accurately extracts high quality data from a variety of content to automate workflows, speed content discovery, and drive smarter business decisions.

Most organizations run on unstructured content, but it’s the data locked within that content moves business forward. Box Extract is now generally available, delivering agentic data extraction at scale for smart process automation. Combining the latest AI models with advanced OCR capabilities, and agentic approaches that understand document structure and meaning, Box Extract automatically and accurately extracts high quality data from a variety of content to automate workflows, speed content discovery, and drive smarter business decisions.

Box

759,033 views • 6 months ago

The Opera Neon browser impressed me with how seamlessly it fits into my workflow. One agentic browser. No subscription juggling. Access to top models like Gemini 3 Pro, GPT-5.2, Sora 2, Grok & more. See it in action finding the best flight → #collab

The Opera Neon browser impressed me with how seamlessly it fits into my workflow. One agentic browser. No subscription juggling. Access to top models like Gemini 3 Pro, GPT-5.2, Sora 2, Grok & more. See it in action finding the best flight → #collab

Mukul Sharma

65,840 views • 5 months ago

With our new Ask Maps feature, you can truly ask anything about anywhere, with help from the latest Gemini models. Ready to roll? Try asking for a walking ghost tour in your city. 👻 Now rolling out in the US and India.

With our new Ask Maps feature, you can truly ask anything about anywhere, with help from the latest Gemini models. Ready to roll? Try asking for a walking ghost tour in your city. 👻 Now rolling out in the US and India.

Google Maps

70,159 views • 4 months ago

Gemini for Android is here! This new app makes it easier to access Google's chatbot, powered by the Gemini Pro LLM, right from your Android device. You can ask Gemini a question by tapping the launcher icon or long-pressing the power button. Once invoked, the Gemini overlay lets you enter a text or text+image prompt. You can tap the camera icon to snap a photo or press the "add this screen" button to take a screenshot of the current page to include in your prompt. The Gemini app for Android is available on Google Play with support for English, but support for Korean and Japanese will be coming next week. While there won't be an app for iOS, iPhone users can access Gemini by opening the Google App and tapping the "Gemini" button up top. How can you long-press the power button to invoke Gemini if that gesture is handled by Google Assistant? The answer is that the Gemini Android app can replace Google Assistant as your default assistant if you want, meaning all the ways you'd normally invoke Google Assistant on your phone can instead invoke Gemini. Unfortunately, Gemini currently doesn't offer ALL the same functionality as Google Assistant and requires an active data connection, but more features will be added over time. There's also now a Gemini Advanced tier, which offers access to Google's most powerful Ultra 1.0 LLM. Access to Gemini Advanced requires a subscription to the new $20/month "AI Premium" Google One plan, which offers the same benefits as the 2TB plan but adds access to Gemini Advanced and soon Gemini features in Gmail, Docs, & other Workspace apps (formerly under the Duet AI umbrella). Gemini Advanced is available in English on the web.

Gemini for Android is here! This new app makes it easier to access Google's chatbot, powered by the Gemini Pro LLM, right from your Android device. You can ask Gemini a question by tapping the launcher icon or long-pressing the power button. Once invoked, the Gemini overlay lets you enter a text or text+image prompt. You can tap the camera icon to snap a photo or press the "add this screen" button to take a screenshot of the current page to include in your prompt. The Gemini app for Android is available on Google Play with support for English, but support for Korean and Japanese will be coming next week. While there won't be an app for iOS, iPhone users can access Gemini by opening the Google App and tapping the "Gemini" button up top. How can you long-press the power button to invoke Gemini if that gesture is handled by Google Assistant? The answer is that the Gemini Android app can replace Google Assistant as your default assistant if you want, meaning all the ways you'd normally invoke Google Assistant on your phone can instead invoke Gemini. Unfortunately, Gemini currently doesn't offer ALL the same functionality as Google Assistant and requires an active data connection, but more features will be added over time. There's also now a Gemini Advanced tier, which offers access to Google's most powerful Ultra 1.0 LLM. Access to Gemini Advanced requires a subscription to the new $20/month "AI Premium" Google One plan, which offers the same benefits as the 2TB plan but adds access to Gemini Advanced and soon Gemini features in Gmail, Docs, & other Workspace apps (formerly under the Duet AI umbrella). Gemini Advanced is available in English on the web.

Mishaal Rahman

38,428 views • 2 years ago

Learning from Human Demonstrations: Show the Robot How to Act! The pipeline is very similar to older experiments using Gemini & pi0 with LeRobot. Pi-zero runs locally, while Gemini Flash generates the affordances and the high-level task. (More details are in the thread.) The new component is learning from demonstrations via Gemini 2.5 Pro. I capture a video while demoing & take one of the last frames. Gemini 2.5 Pro then extracts the instructions & passes them to Gemini Flash to process the scene. The fun part is that there's no fancy insight that came from me; other than the days spent figuring out the right prompts. It's the bitter lesson hitting you in the face -> Enhanced Gemini capabilities make this possible. For example, Gemini Flash cannot do Russian doll stacking, but Gemini 2.5 Pro can do it consistently. The current limitation is low-level manipulation: - As you can see, I'm aligning the objects so they are easy to grasp using the same technique from the training data. I couldn't get Gemini Flash to consistently output an accurate grasping angle, and Gemini 1.5 Pro was too expensive and slow for real-time deployment. - Getting a symmetrical gripper should also help a lot. Adding rubber to the tips would probably also help prevent objects from slipping. Collecting & curating the data was the most time consuming & labor intensive part. Next, to improve low-level manipulation and make the system more real-time, I'm shifting to focus more on sims & synthetic data. This aligns better with my core competence. I'm open to tips and suggestions.

Learning from Human Demonstrations: Show the Robot How to Act! The pipeline is very similar to older experiments using Gemini & pi0 with LeRobot. Pi-zero runs locally, while Gemini Flash generates the affordances and the high-level task. (More details are in the thread.) The new component is learning from demonstrations via Gemini 2.5 Pro. I capture a video while demoing & take one of the last frames. Gemini 2.5 Pro then extracts the instructions & passes them to Gemini Flash to process the scene. The fun part is that there's no fancy insight that came from me; other than the days spent figuring out the right prompts. It's the bitter lesson hitting you in the face -> Enhanced Gemini capabilities make this possible. For example, Gemini Flash cannot do Russian doll stacking, but Gemini 2.5 Pro can do it consistently. The current limitation is low-level manipulation: - As you can see, I'm aligning the objects so they are easy to grasp using the same technique from the training data. I couldn't get Gemini Flash to consistently output an accurate grasping angle, and Gemini 1.5 Pro was too expensive and slow for real-time deployment. - Getting a symmetrical gripper should also help a lot. Adding rubber to the tips would probably also help prevent objects from slipping. Collecting & curating the data was the most time consuming & labor intensive part. Next, to improve low-level manipulation and make the system more real-time, I'm shifting to focus more on sims & synthetic data. This aligns better with my core competence. I'm open to tips and suggestions.

Shreyas Gite

22,555 views • 1 year ago

Announcing a significant upgrade to Agentic Document Extraction! LandingAI's new DPT (Document Pre-trained Transformer) accurately extracts even from complex docs. For example, from large, complex tables, which is important for many finance and healthcare applications. And a new SDK makes using it require only 3 simple lines of code. Please see the video for technical details. I hope this unlocks a lot of value from the "dark data" currently stuck in PDF files, and that you'll build something cool with this!

Announcing a significant upgrade to Agentic Document Extraction! LandingAI's new DPT (Document Pre-trained Transformer) accurately extracts even from complex docs. For example, from large, complex tables, which is important for many finance and healthcare applications. And a new SDK makes using it require only 3 simple lines of code. Please see the video for technical details. I hope this unlocks a lot of value from the "dark data" currently stuck in PDF files, and that you'll build something cool with this!

Andrew Ng

299,381 views • 10 months ago

The way you use Google Maps will never be the same. Introducing Ask Maps, a new way for you to ask anything about anywhere, with help from the latest Gemini models. Rolling out now on Android and iOS in the US and India.

The way you use Google Maps will never be the same. Introducing Ask Maps, a new way for you to ask anything about anywhere, with help from the latest Gemini models. Rolling out now on Android and iOS in the US and India.

Google Maps

491,775 views • 4 months ago

2025 has been the hardest year of life I’ve had to deal with yet. The reason i began Moshpxt was to put Xelly in a position to win and losing him almost made me lose my vision and purpose for everything but God always has a plan, from now on everything turned up 2000% #LLX #XMG

2025 has been the hardest year of life I’ve had to deal with yet. The reason i began Moshpxt was to put Xelly in a position to win and losing him almost made me lose my vision and purpose for everything but God always has a plan, from now on everything turned up 2000% #LLX #XMG

Moshpxt

35,097 views • 6 months ago

Love this example! Congrats to Google DeepMind! I successfully replicated the Boggle game on SWE Arena. TLDR: Gemini 2.0 Pro won! In the case of Claude 3.5 Sonnet vs Gemini 2.0 Pro, both are given the image and prompt to generate the algo to get the results. The image and prompt are exactly the same. Try it out on SWE Arena: BTW can we get a bigger streaming rate limit for our API, so that ppl can better compare the latest Gemini models with other frontier models? Jeff Dean Logan Kilpatrick 👀

Love this example! Congrats to Google DeepMind! I successfully replicated the Boggle game on SWE Arena. TLDR: Gemini 2.0 Pro won! In the case of Claude 3.5 Sonnet vs Gemini 2.0 Pro, both are given the image and prompt to generate the algo to get the results. The image and prompt are exactly the same. Try it out on SWE Arena: BTW can we get a bigger streaming rate limit for our API, so that ppl can better compare the latest Gemini models with other frontier models? Jeff Dean Logan Kilpatrick 👀

Terry Yue Zhuo

48,220 views • 1 year ago

The best way to bring the composition from your head into an image → Ideogram V4 + drawing bounding boxes in Comfy. The control here is quite unique. The model uses structured JSON so drawing bounding boxes to get the exact placement works very well. The model only needs 12 steps (turbo), so iterating with different seeds + very impressive text rendering capability leads me to say this is a state of the art open source image model right now. Using the 'Ideogram 4 Prompt Builder' node by Kijai.

The best way to bring the composition from your head into an image → Ideogram V4 + drawing bounding boxes in Comfy. The control here is quite unique. The model uses structured JSON so drawing bounding boxes to get the exact placement works very well. The model only needs 12 steps (turbo), so iterating with different seeds + very impressive text rendering capability leads me to say this is a state of the art open source image model right now. Using the 'Ideogram 4 Prompt Builder' node by Kijai.

rob - comfyui

24,794 views • 1 month ago

Video Game Bench introduce a research preview of VideoGameBench, a benchmark which challenges vision-language models to complete, in real-time, a suite of 20 different popular video games from both hand-held consoles and PC GPT-4o, Claude Sonnet 3.7, Gemini 2.5 Pro, and Gemini 2.0 Flash playing Doom II (default difficulty) on VideoGameBench-Lite with the same input prompt! Models achieve varying levels of success but none are able to pass even the first level.

Video Game Bench introduce a research preview of VideoGameBench, a benchmark which challenges vision-language models to complete, in real-time, a suite of 20 different popular video games from both hand-held consoles and PC GPT-4o, Claude Sonnet 3.7, Gemini 2.5 Pro, and Gemini 2.0 Flash playing Doom II (default difficulty) on VideoGameBench-Lite with the same input prompt! Models achieve varying levels of success but none are able to pass even the first level.

AK

154,169 views • 1 year ago

🎉 恭喜发财🧧🐍 As we welcome the Chinese New Year, we're thrilled to announce the launch of Qwen2.5-VL , our latest flagship vision-language model! 🚀 💗 Qwen Chat: 📖 Blog: 🤗 Hugging Face: 🤖 ModelScope: 🌟 Key Highlights: * Visual Understanding : From flowers to complex charts, Qwen2.5-VL sees it all! * Agentic Capabilities : It’s a visual agent that can reason and interact with tools like computers & phones. * Long Video Comprehension : Captures events in videos over 1 hour long! ⏳🎥 * Precise Localization : Generates bounding boxes & JSON outputs for accurate object detection. * Structured Data Outputs : Perfect for finance & commerce, handling invoices, forms & more! 💼📊 Try Qwen2.5-VL now at Qwen Chat or explore models on Hugging Face & ModelScope . 🌐

🎉 恭喜发财🧧🐍 As we welcome the Chinese New Year, we're thrilled to announce the launch of Qwen2.5-VL , our latest flagship vision-language model! 🚀 💗 Qwen Chat: 📖 Blog: 🤗 Hugging Face: 🤖 ModelScope: 🌟 Key Highlights: * Visual Understanding : From flowers to complex charts, Qwen2.5-VL sees it all! * Agentic Capabilities : It’s a visual agent that can reason and interact with tools like computers & phones. * Long Video Comprehension : Captures events in videos over 1 hour long! ⏳🎥 * Precise Localization : Generates bounding boxes & JSON outputs for accurate object detection. * Structured Data Outputs : Perfect for finance & commerce, handling invoices, forms & more! 💼📊 Try Qwen2.5-VL now at Qwen Chat or explore models on Hugging Face & ModelScope . 🌐

Qwen

762,314 views • 1 year ago

LISTEN UP California Voters Riverside County Sheriff Chad Bianco is running for California Governor to replace Gavin Newsom “Stroke of a pen, on day one, a minimum of $2.20 will be removed from a gallon of gas. Then a second signature will be allowing California companies to drill for oil. California has more oil than Texas. More oil than Texas. Get that through your head. That is an absolute fact. It has been kept to us and lied to us for decades. We import. We're the largest state in the country, 42 million people plus. We are the biggest consumer of gasoline, of oil. And we import 80% of our gas and oil from other countries. We make other countries rich at your expense. That ends on day one with me as your governor.”

LISTEN UP California Voters Riverside County Sheriff Chad Bianco is running for California Governor to replace Gavin Newsom “Stroke of a pen, on day one, a minimum of $2.20 will be removed from a gallon of gas. Then a second signature will be allowing California companies to drill for oil. California has more oil than Texas. More oil than Texas. Get that through your head. That is an absolute fact. It has been kept to us and lied to us for decades. We import. We're the largest state in the country, 42 million people plus. We are the biggest consumer of gasoline, of oil. And we import 80% of our gas and oil from other countries. We make other countries rich at your expense. That ends on day one with me as your governor.”

Wall Street Apes

682,092 views • 11 months ago