Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

We’re open sourcing the first document OCR benchmark for the agentic era, ParseBench. Document parsing is the foundation of every AI agent that works with real-world files. ParseBench is a benchmark that measures parsing quality specifically for agent knowledge work: ✅ It optimizes for semantic correctness (instead of exact...

jerryjliu0's profile picture

Jerry Liu

80,829 subscribers

108,093 Aufrufe • vor 5 Monaten •via X (Twitter)

BildungNachrichten & PolitikWissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Document OCR benchmarks are still an open problem Existing document OCR benchmarks are either too narrowly focused on a specific type (e.g. FinTabNet, ChartQA), or on documents that aren’t reflective of real-world tasks (e.g. OmniDocBench, OlmOCR-bench on over academic papers) ParseBench is a step towards solving this problem. * It tries to comprehensively cover real-world document distributions within the enterprise. * It contains comprehensive evaluations across 5 different dimensions (tables, charts, content faithfulness, formatting, grounding). * It tries to use metrics that optimize for agent semantic understanding rather than structural similarity. We released this yesterday, and there’s a TON of content: 1. Whitepaper 2. HF dataset 3. Github repo 4. Blog 5. Video And today, we’re excited to feature our home page website for ParseBench 💫 come check it out! Take a look at some of our other materials if you’re interested: Blog: Paper:
0:46

Document OCR benchmarks are still an open problem Existing document OCR benchmarks are either too narrowly focused on a specific type (e.g. FinTabNet, ChartQA), or on documents that aren’t reflective of real-world tasks (e.g. OmniDocBench, OlmOCR-bench on over academic papers) ParseBench is a step towards solving this problem. * It tries to comprehensively cover real-world document distributions within the enterprise. * It contains comprehensive evaluations across 5 different dimensions (tables, charts, content faithfulness, formatting, grounding). * It tries to use metrics that optimize for agent semantic understanding rather than structural similarity. We released this yesterday, and there’s a TON of content: 1. Whitepaper 2. HF dataset 3. Github repo 4. Blog 5. Video And today, we’re excited to feature our home page website for ParseBench 💫 come check it out! Take a look at some of our other materials if you’re interested: Blog: Paper:

Jerry Liu

21,657 Aufrufe • vor 5 Monaten

If you’re building an “agent over your PDFs” in 2026, one of the most underrated things you can do is to provide exact grounding back to the source document for any agentic answers. Specifically, showing the exact word, line, or region that the answer came from. Frontier vision models do a terrible job at this. They have a hard time predicting exact bounding boxes over region, tying it back to the source answer, and surfacing it as context in a cost-effective and accurate manner. Dedicated VLM-based document OCR/extraction tools like LlamaParse are a lot better at visual grounding and specifically tying it to extracted outputs. One of our main evaluation areas in ExtractBench, our recently released real-world benchmark, is to evaluate the visual grounding capabilities of document extraction. ExtractBench: If you want to give LlamaParse a shot, come check it out:
0:52

If you’re building an “agent over your PDFs” in 2026, one of the most underrated things you can do is to provide exact grounding back to the source document for any agentic answers. Specifically, showing the exact word, line, or region that the answer came from. Frontier vision models do a terrible job at this. They have a hard time predicting exact bounding boxes over region, tying it back to the source answer, and surfacing it as context in a cost-effective and accurate manner. Dedicated VLM-based document OCR/extraction tools like LlamaParse are a lot better at visual grounding and specifically tying it to extracted outputs. One of our main evaluation areas in ExtractBench, our recently released real-world benchmark, is to evaluate the visual grounding capabilities of document extraction. ExtractBench: If you want to give LlamaParse a shot, come check it out:

Jerry Liu

14,515 Aufrufe • vor 1 Monat

i'm flattered by the shoutout, but there's no free lunch for document parsing Cohere parse starts at $1.50 / 1k pages, which is indeed on the cheaper end of doc OCR solutions, but it scores ~50% when averaged across all 5 ParseBench dimensions: * It lacks high-quality visual grounding, doing coarse segmentation for tables and images, but lacking finer-grained bboxes at the word/cell/line-level. this is quite important for any sensitive AI application that requires precise citations back to the source. * It lacks general visual / chart parsing capabilities, which are prevalent across finance, manufacturing, healthcare, and more * to its credit, it does a decent job over tables (87%) compared to other comparable solutions at the price point our cost-effective mode in LlamaParse starts at 0.375c / page and is more consistently strong across all dimensions. also there's various ways to bring it down with volume discounts if you're interested in learning more about various document parsing modes and comparing tradeoffs in price/accuracy, come talk to us! LlamaParse:
0:26

i'm flattered by the shoutout, but there's no free lunch for document parsing Cohere parse starts at $1.50 / 1k pages, which is indeed on the cheaper end of doc OCR solutions, but it scores ~50% when averaged across all 5 ParseBench dimensions: * It lacks high-quality visual grounding, doing coarse segmentation for tables and images, but lacking finer-grained bboxes at the word/cell/line-level. this is quite important for any sensitive AI application that requires precise citations back to the source. * It lacks general visual / chart parsing capabilities, which are prevalent across finance, manufacturing, healthcare, and more * to its credit, it does a decent job over tables (87%) compared to other comparable solutions at the price point our cost-effective mode in LlamaParse starts at 0.375c / page and is more consistently strong across all dimensions. also there's various ways to bring it down with volume discounts if you're interested in learning more about various document parsing modes and comparing tradeoffs in price/accuracy, come talk to us! LlamaParse:

Jerry Liu

25,524 Aufrufe • vor 5 Tagen

The latest RAG trend for the current agent harnesses (Codex, Cowork) is to do two passes of document processing to solve a knowledge work task over a data room of documents: 1️⃣ A fast and light pass, oftentimes using a free/OSS doc parsing tool. This can be cheaply run across 10-100-1k’s of files, and enables the agent to then do retrieval (e.g. grep, semantic) to find relevant subsets of context. 2️⃣ A “just-in-time” VLM-based pass. Once the agent finds the relevant pages of context, it will screenshot the documents can call its own VLM (or write code) to dissect the pages. The issue with only using VLM-based OCR tools over massive ad-hoc customer file dumps is that it’s slow and expensive. Doing JIT VLM OCR allows the agent to filter through the data cheaply, but still preserve accuracy for the context that’s needed for the task. The agent harnesses do two-pass document processing by default using off the shelf-tools: pdf2text as the first pass, and using itself (Opus 5) as the second pass. See the below video where Cowork runs over a bunch of PDFs to answer a question about a benchmark graph in the Kimi k3 paper. The main issues here with the “out of the box” doc processing these agents offer are: * Opus 5 is not the best VLM for OCR. It is also way too expensive at scale and lacks grounding * The OSS tools like pypdf, pdf2text, may not be versatile enough as the first pass. * The agent will write a lot of throwaway code to rewrite things an OCR tool would’ve provided out of the box, like chart processing, bounding boxes, confidence scores, leading to increased cost and speed. We have all the tools within LlamaIndex 🦙 to help any agent do two-pass document processing with higher accuracy and lower cost. 1️⃣ We have liteparse for the first pass - a free/OSS parser written in Rust that’s faster/more accurate than other OSS parsers, and supports 50+ document types 2️⃣ We have LlamaParse for the second pass - an agentic document engine that uses VLMs+harnesses to achieve SOTA in accuracy and cost across various doc parsing and extraction tasks. It can be called from any agent harness as an MCP or skill. It takes in page numbers as input, so that the agent can choose to run LlamaParse over a subset of the doc instead of the full doc as a “zoom-in” pass. Come check it out! LiteParse: LlamaParse: All the relevant docs, including MCP, are here:
1:24

The latest RAG trend for the current agent harnesses (Codex, Cowork) is to do two passes of document processing to solve a knowledge work task over a data room of documents: 1️⃣ A fast and light pass, oftentimes using a free/OSS doc parsing tool. This can be cheaply run across 10-100-1k’s of files, and enables the agent to then do retrieval (e.g. grep, semantic) to find relevant subsets of context. 2️⃣ A “just-in-time” VLM-based pass. Once the agent finds the relevant pages of context, it will screenshot the documents can call its own VLM (or write code) to dissect the pages. The issue with only using VLM-based OCR tools over massive ad-hoc customer file dumps is that it’s slow and expensive. Doing JIT VLM OCR allows the agent to filter through the data cheaply, but still preserve accuracy for the context that’s needed for the task. The agent harnesses do two-pass document processing by default using off the shelf-tools: pdf2text as the first pass, and using itself (Opus 5) as the second pass. See the below video where Cowork runs over a bunch of PDFs to answer a question about a benchmark graph in the Kimi k3 paper. The main issues here with the “out of the box” doc processing these agents offer are: * Opus 5 is not the best VLM for OCR. It is also way too expensive at scale and lacks grounding * The OSS tools like pypdf, pdf2text, may not be versatile enough as the first pass. * The agent will write a lot of throwaway code to rewrite things an OCR tool would’ve provided out of the box, like chart processing, bounding boxes, confidence scores, leading to increased cost and speed. We have all the tools within LlamaIndex 🦙 to help any agent do two-pass document processing with higher accuracy and lower cost. 1️⃣ We have liteparse for the first pass - a free/OSS parser written in Rust that’s faster/more accurate than other OSS parsers, and supports 50+ document types 2️⃣ We have LlamaParse for the second pass - an agentic document engine that uses VLMs+harnesses to achieve SOTA in accuracy and cost across various doc parsing and extraction tasks. It can be called from any agent harness as an MCP or skill. It takes in page numbers as input, so that the agent can choose to run LlamaParse over a subset of the doc instead of the full doc as a “zoom-in” pass. Come check it out! LiteParse: LlamaParse: All the relevant docs, including MCP, are here:

Jerry Liu

22,763 Aufrufe • vor 28 Tagen

Astra is awesome, but if you're using it specifically to parse and extract a massive volume of documents, you will break the bank (10c+ per page on parsing and extraction!) We've added a native LlamaParse connector to ChatGPT that gives the model access to high-quality document OCR and extraction at the pareto frontier of accuracy and cost. It contains native access to our parse and extract endpoints. Upload your most complex documents, and you can do the following: * digitalize it into extremely accurate context for any QA task * perform large-scale extraction from a set of documents with accurate grounding and citations Offload the higher-level reasoning to Astra, leave specialized doc parsing and extraction to us. ChatGPT plugin: Come sign up here:
0:31

Astra is awesome, but if you're using it specifically to parse and extract a massive volume of documents, you will break the bank (10c+ per page on parsing and extraction!) We've added a native LlamaParse connector to ChatGPT that gives the model access to high-quality document OCR and extraction at the pareto frontier of accuracy and cost. It contains native access to our parse and extract endpoints. Upload your most complex documents, and you can do the following: * digitalize it into extremely accurate context for any QA task * perform large-scale extraction from a set of documents with accurate grounding and citations Offload the higher-level reasoning to Astra, leave specialized doc parsing and extraction to us. ChatGPT plugin: Come sign up here:

Jerry Liu

11,083 Aufrufe • vor 11 Tagen

Introducing ExtractBench, the most comprehensive benchmark for information extraction from complex enterprise documents. The latest models are pushing the frontier of coding and knowledge work, but surprisingly they still struggle on complex doc extraction tasks in production. A well-tuned extractor must parse multi-page filings without dropping rows, emit exact spatial citations for auditability, and handle messy scans. Also they must do all of this at a viable per-page cost so that you can scale this to millions of docs in production (you can’t be paying upwards of $1 in tokens per page!) Existing extraction benchmarks fall short: they are not large/diverse enough in document domain (finance, energy, gov, auto), elements (long records, scans, grounding), and schemas. So our applied research team built ExtractBench. We evaluated 14 systems: frontier VLMs, coding agents, and specialized extraction APIs, against 370 enterprise documents: 4,869 pages, 67 document types. Our biggest finding 🧪: Short documents mask critical system flaws. On files past 50 pages, commercial VLMs collapse below 35% recall due to silent list truncation. They hold high precision, but lose output attention and drop most of the table rows. ExtractBench evaluates value accuracy, long-record completeness, spatial grounding, and per-page cost with zero LLM judges. It is 100% deterministic and reproducible. In tandem with ExtractBench, we’re also introducing 𝗔𝗴𝗲𝗻𝘁𝗶𝗰 𝗣𝗹𝘂𝘀, a new Extract tier in LlamaParse that debuts at #1 on the leaderboard: 95.6% value accuracy, at less than a third the cost of the closest peer. Explore the findings, download the dataset, or run the harness: Blog: GitHub: HuggingFace: We will be actively evolving both our extraction benchmark as well as our extraction harness over time. If you check out either ExtractBench or LlamaParse, let us know your feedback!
1:59

Introducing ExtractBench, the most comprehensive benchmark for information extraction from complex enterprise documents. The latest models are pushing the frontier of coding and knowledge work, but surprisingly they still struggle on complex doc extraction tasks in production. A well-tuned extractor must parse multi-page filings without dropping rows, emit exact spatial citations for auditability, and handle messy scans. Also they must do all of this at a viable per-page cost so that you can scale this to millions of docs in production (you can’t be paying upwards of $1 in tokens per page!) Existing extraction benchmarks fall short: they are not large/diverse enough in document domain (finance, energy, gov, auto), elements (long records, scans, grounding), and schemas. So our applied research team built ExtractBench. We evaluated 14 systems: frontier VLMs, coding agents, and specialized extraction APIs, against 370 enterprise documents: 4,869 pages, 67 document types. Our biggest finding 🧪: Short documents mask critical system flaws. On files past 50 pages, commercial VLMs collapse below 35% recall due to silent list truncation. They hold high precision, but lose output attention and drop most of the table rows. ExtractBench evaluates value accuracy, long-record completeness, spatial grounding, and per-page cost with zero LLM judges. It is 100% deterministic and reproducible. In tandem with ExtractBench, we’re also introducing 𝗔𝗴𝗲𝗻𝘁𝗶𝗰 𝗣𝗹𝘂𝘀, a new Extract tier in LlamaParse that debuts at #1 on the leaderboard: 95.6% value accuracy, at less than a third the cost of the closest peer. Explore the findings, download the dataset, or run the harness: Blog: GitHub: HuggingFace: We will be actively evolving both our extraction benchmark as well as our extraction harness over time. If you check out either ExtractBench or LlamaParse, let us know your feedback!

Jerry Liu

75,502 Aufrufe • vor 1 Monat

We’re excited to officially launch LlamaParse, the first genAI-native document parsing solution. Not only is it better at parsing out images/tables/charts 📊📈 than virtually every other parser, it is now steerable through natural language instructions - output the document in whatever format you desire! It is also the only parsing solution that seamlessly allows you to build accurate RAG over complex documents, free of hallucinations 🔥 We launched it in private preview a few weeks ago and hit 2k users, 1M total PDF pages parsed. And now it’s better than ever. LlamaParse contains the following killer features: ✅ SOTA table/chart extraction ✅ Seamless integration with LlamaIndex 🦙 advanced RAG/agents ✅✨ Natural language Parsing Instructions ✅✨JSON mode and image extraction ✅✨Support for ~10 document types (.pdf, .pptx, .docx, .xml) and more Our pricing is simple: 1k free per day, and additional pages at 0.3c a page, or $3 for 1k pages. If you want advanced document RAG and/or private deployments, come get in touch with us to chat about LlamaCloud. Check out our full blog post here: LlamaParse client repo: Signup at 🦙☁️: Come talk to us:
5:07

We’re excited to officially launch LlamaParse, the first genAI-native document parsing solution. Not only is it better at parsing out images/tables/charts 📊📈 than virtually every other parser, it is now steerable through natural language instructions - output the document in whatever format you desire! It is also the only parsing solution that seamlessly allows you to build accurate RAG over complex documents, free of hallucinations 🔥 We launched it in private preview a few weeks ago and hit 2k users, 1M total PDF pages parsed. And now it’s better than ever. LlamaParse contains the following killer features: ✅ SOTA table/chart extraction ✅ Seamless integration with LlamaIndex 🦙 advanced RAG/agents ✅✨ Natural language Parsing Instructions ✅✨JSON mode and image extraction ✅✨Support for ~10 document types (.pdf, .pptx, .docx, .xml) and more Our pricing is simple: 1k free per day, and additional pages at 0.3c a page, or $3 for 1k pages. If you want advanced document RAG and/or private deployments, come get in touch with us to chat about LlamaCloud. Check out our full blog post here: LlamaParse client repo: Signup at 🦙☁️: Come talk to us:

LlamaIndex 🦙

143,189 Aufrufe • vor 2 Jahren

We built an AI agent that lets you vibe-code document extraction - high accuracy and citations over the most complex documents. Our latest release lets you upload documents as context. All you then have to do is describe what you want extracted in natural language. 💡 Our agent will then read the document with file tools to infer the right schema, validation rules, and other pre/postprocessing logic. ✅ It will give you back a workflow that can extract over thousands/millions of documents at scale. You can still of course review and edit every output before approving. Stop handling paperwork manually; just upload files, describe your task, and let our agent handle the rest. Our vision for LlamaAgents is to provide the most advanced and easy-to-use way for you to orchestrate document work. Walkthrough: Check it out: If you’re interested in reducing the operational burden of document extraction (invoices, claims, onboarding forms), come talk to us!
0:58

We built an AI agent that lets you vibe-code document extraction - high accuracy and citations over the most complex documents. Our latest release lets you upload documents as context. All you then have to do is describe what you want extracted in natural language. 💡 Our agent will then read the document with file tools to infer the right schema, validation rules, and other pre/postprocessing logic. ✅ It will give you back a workflow that can extract over thousands/millions of documents at scale. You can still of course review and edit every output before approving. Stop handling paperwork manually; just upload files, describe your task, and let our agent handle the rest. Our vision for LlamaAgents is to provide the most advanced and easy-to-use way for you to orchestrate document work. Walkthrough: Check it out: If you’re interested in reducing the operational burden of document extraction (invoices, claims, onboarding forms), come talk to us!

Jerry Liu

20,857 Aufrufe • vor 6 Monaten

Introducing LiteParse - the best model-free document parsing tool for AI agents 💫 ✅ It’s completely open-source and free. ✅ No GPU required, will process ~500 pages in 2 seconds on commodity hardware ✅ More accurate than PyPDF, PyMuPDF, Markdown. Also way more readable - see below for how we parse tables!! ✅ Supports 50+ file formats, from PDFs to Office docs to images ✅ Is designed to plug and play with Claude Code, OpenClaw, and any other AI agent with a one-line skills install. Supports native screenshotting capabilities. We spent years building up LlamaParse by orchestrating state-of-the-art VLMs over the most complex documents. Along the way we realized that you could get quite far on most docs through fast and cheap text parsing. Take a look at the video below. For really complex tables within PDFs, we output them in a spatial grid that’s both AI and human-interpretable. Any other free/light parser light PyPDF will destroy the representation of this table and output a sequential list. This is not a replacement for a VLM-based OCR tool (it requires 0 GPUs and doesn’t use models), but it is shocking how good it is to parse most documents. Huge shoutout to Logan Markewich and Clelia Bertelli (🦀/acc) for all the work here. Come check it out: Repo:
0:31

Introducing LiteParse - the best model-free document parsing tool for AI agents 💫 ✅ It’s completely open-source and free. ✅ No GPU required, will process ~500 pages in 2 seconds on commodity hardware ✅ More accurate than PyPDF, PyMuPDF, Markdown. Also way more readable - see below for how we parse tables!! ✅ Supports 50+ file formats, from PDFs to Office docs to images ✅ Is designed to plug and play with Claude Code, OpenClaw, and any other AI agent with a one-line skills install. Supports native screenshotting capabilities. We spent years building up LlamaParse by orchestrating state-of-the-art VLMs over the most complex documents. Along the way we realized that you could get quite far on most docs through fast and cheap text parsing. Take a look at the video below. For really complex tables within PDFs, we output them in a spatial grid that’s both AI and human-interpretable. Any other free/light parser light PyPDF will destroy the representation of this table and output a sequential list. This is not a replacement for a VLM-based OCR tool (it requires 0 GPUs and doesn’t use models), but it is shocking how good it is to parse most documents. Huge shoutout to Logan Markewich and Clelia Bertelli (🦀/acc) for all the work here. Come check it out: Repo:

Jerry Liu

257,364 Aufrufe • vor 6 Monaten

Today we’re announcing r-1, our new document parsing model. It’s more accurate than our most powerful agentic OCR models, faster, and up to 6x cheaper. At Reducto, we spent two years building specialized models for complex visual layouts, tables spanning multiple pages, and key formatting like strikethroughs. We then used everything we learned to build r-1, the first in a new generation of models designed to handle the hardest documents without multiplying cost. This early preview delivers a 20% lower error rate than our most accurate legacy agentic models and will keep improving with new checkpoints over the next few weeks. Accuracy is only the beginning. r-1 preview is available at 1¢ per page all-in, with additional volume discounts as you scale. In the near term we’re also going to release r-1 mini, and an auto mode that intelligently selects the right approach for each page. If you’re currently using another parser, we’re offering up to $5,000 in credits to evaluate and migrate. You can claim the migration offer and learn more about r-1 using the links in the comments. Happy parsing!
1:22

Today we’re announcing r-1, our new document parsing model. It’s more accurate than our most powerful agentic OCR models, faster, and up to 6x cheaper. At Reducto, we spent two years building specialized models for complex visual layouts, tables spanning multiple pages, and key formatting like strikethroughs. We then used everything we learned to build r-1, the first in a new generation of models designed to handle the hardest documents without multiplying cost. This early preview delivers a 20% lower error rate than our most accurate legacy agentic models and will keep improving with new checkpoints over the next few weeks. Accuracy is only the beginning. r-1 preview is available at 1¢ per page all-in, with additional volume discounts as you scale. In the near term we’re also going to release r-1 mini, and an auto mode that intelligently selects the right approach for each page. If you’re currently using another parser, we’re offering up to $5,000 in credits to evaluate and migrate. You can claim the migration offer and learn more about r-1 using the links in the comments. Happy parsing!

Adit

299,293 Aufrufe • vor 19 Tagen

🚀Introducing VisualWebBench: A Comprehensive Benchmark for Multimodal Web Page Understanding and Grounding. 🤔What's this all about? Why this benchmark? > Back in Nov 2023, when we released MMMU ( a comprehensive multimodal understanding benchmark, we received feedback that it included very few UI screenshots. Considering the growing importance of UI understanding, especially with the rise of powerful agents like Devin ( which is built on the strong vision capability of #GPT4, we recognized the need for a benchmark focused on UI screenshot understanding.📸👀 > Multimodal #LLMs have significantly boosted web agents' performance on benchmarks like Mind2Web and WebArena. For instance, the SeeAct agent ( showcases the power of integrating vision into web agents. However, these benchmarks primarily evaluate the end-to-end task execution ability of web agents rather than their understanding of web pages. 🌉 Bridging the Gap with VisualWebBench > To provide a comprehensive evaluation of multimodal LLMs' web page understanding capabilities, we introduce VisualWebBench. Our benchmark spans 139 websites 🌐 across 12 domains 🏷️ and 87 sub-domains 🔍, ensuring a diverse and representative dataset. It assesses MLLMs at three levels: website-level, element-level, and action-level 📊, and encompasses seven tasks designed to evaluate understanding, OCR, grounding, and reasoning abilities 🧠💡. 😮 Surprising Findings > 🎉 Open-source models are catching up: Even though closed-source MLLMs are still leading the leaderboard, we are happy to see open-source models like LLaVA 1.6 34B achieve comparable performance to Gemini Pro. > 🧠 Grounding ability, crucial for developing MLLM-based web applications, is a weakness for most MLLMs. > 🖼️ Importance of Image Resolution: The limited image resolution handling capabilities of most open-source MLLMs restrict their utility in web scenarios, where rich text and elements are prevalent. > 🧱 Relatively strong correlation with general understanding benchmarks like MMMU but weak correlation with web agent benchmarks like Mind2Web. Web agent benchmarks primarily evaluate the end-to-end task execution ability of web agents, which involves a series of actions to accomplish a goal. In contrast, VisualWebBench emphasizes evaluating the foundational skills of MLLMs such as understanding and grounding web page elements. 💡Fun Fact > Claude Sonnet is better than Opus on our benchmark :) 🎓 Conclusion > VisualWebBench serves as a valuable resource for the community, driving research and development in the field of multimodal web page understanding and grounding. As MLLMs continue to evolve and improve, we look forward to seeing new applications and breakthroughs. We believe that our benchmark will contribute to the development of more powerful MLLMs in the web domain, ultimately leading to a more intuitive and efficient user experience on the web. Kudos to the student leads Junpeng Liu Yifan Song and the team Bill Yuchen Lin, Wai Lam, Graham Neubig, Yuanzhi Li! 👏 Check out more details in the Junpeng's thread👇
1:26

🚀Introducing VisualWebBench: A Comprehensive Benchmark for Multimodal Web Page Understanding and Grounding. 🤔What's this all about? Why this benchmark? > Back in Nov 2023, when we released MMMU ( a comprehensive multimodal understanding benchmark, we received feedback that it included very few UI screenshots. Considering the growing importance of UI understanding, especially with the rise of powerful agents like Devin ( which is built on the strong vision capability of #GPT4, we recognized the need for a benchmark focused on UI screenshot understanding.📸👀 > Multimodal #LLMs have significantly boosted web agents' performance on benchmarks like Mind2Web and WebArena. For instance, the SeeAct agent ( showcases the power of integrating vision into web agents. However, these benchmarks primarily evaluate the end-to-end task execution ability of web agents rather than their understanding of web pages. 🌉 Bridging the Gap with VisualWebBench > To provide a comprehensive evaluation of multimodal LLMs' web page understanding capabilities, we introduce VisualWebBench. Our benchmark spans 139 websites 🌐 across 12 domains 🏷️ and 87 sub-domains 🔍, ensuring a diverse and representative dataset. It assesses MLLMs at three levels: website-level, element-level, and action-level 📊, and encompasses seven tasks designed to evaluate understanding, OCR, grounding, and reasoning abilities 🧠💡. 😮 Surprising Findings > 🎉 Open-source models are catching up: Even though closed-source MLLMs are still leading the leaderboard, we are happy to see open-source models like LLaVA 1.6 34B achieve comparable performance to Gemini Pro. > 🧠 Grounding ability, crucial for developing MLLM-based web applications, is a weakness for most MLLMs. > 🖼️ Importance of Image Resolution: The limited image resolution handling capabilities of most open-source MLLMs restrict their utility in web scenarios, where rich text and elements are prevalent. > 🧱 Relatively strong correlation with general understanding benchmarks like MMMU but weak correlation with web agent benchmarks like Mind2Web. Web agent benchmarks primarily evaluate the end-to-end task execution ability of web agents, which involves a series of actions to accomplish a goal. In contrast, VisualWebBench emphasizes evaluating the foundational skills of MLLMs such as understanding and grounding web page elements. 💡Fun Fact > Claude Sonnet is better than Opus on our benchmark :) 🎓 Conclusion > VisualWebBench serves as a valuable resource for the community, driving research and development in the field of multimodal web page understanding and grounding. As MLLMs continue to evolve and improve, we look forward to seeing new applications and breakthroughs. We believe that our benchmark will contribute to the development of more powerful MLLMs in the web domain, ultimately leading to a more intuitive and efficient user experience on the web. Kudos to the student leads Junpeng Liu Yifan Song and the team Bill Yuchen Lin, Wai Lam, Graham Neubig, Yuanzhi Li! 👏 Check out more details in the Junpeng's thread👇

Xiang Yue

56,696 Aufrufe • vor 2 Jahren

Over 1 billion PDFs are created every day, but your agents still can’t read them reliably. Today we’re releasing Parse 2.0, the most accurate document parsing API in the world. Extend already processes millions of pages daily for leading AI teams like Brex, Mercury, Opendoor, Flatiron Health, and hundreds of others. Now, its even better. Parse 2.0 is SOTA quality on RealDoc-Bench, our open source benchmark that measures agent success rate on real world docs that agents actually encounter in production. We trained Parse 2.0 on 1M+ pages of the hardest documents seen in production. Here’s how it stacks up: - #1 in healthcare, real estate, logistics, and financial services - 95.7% agent Q&A accuracy on 581 docs (next best: 92%) - 0.847 F1 on layout (next best: 0.759) Give it a try today and build production-ready document agents with Extend.
1:32

Over 1 billion PDFs are created every day, but your agents still can’t read them reliably. Today we’re releasing Parse 2.0, the most accurate document parsing API in the world. Extend already processes millions of pages daily for leading AI teams like Brex, Mercury, Opendoor, Flatiron Health, and hundreds of others. Now, its even better. Parse 2.0 is SOTA quality on RealDoc-Bench, our open source benchmark that measures agent success rate on real world docs that agents actually encounter in production. We trained Parse 2.0 on 1M+ pages of the hardest documents seen in production. Here’s how it stacks up: - #1 in healthcare, real estate, logistics, and financial services - 95.7% agent Q&A accuracy on 581 docs (next best: 92%) - 0.847 F1 on layout (next best: 0.759) Give it a try today and build production-ready document agents with Extend.

Kushal Byatnal

588,535 Aufrufe • vor 3 Monaten

Today, Box is announcing major new AI agent capabilities to let customers tap into the full value of their unstructured data. First, we’re announcing all new updates to the Box AI Studio to make it even easier to build AI agents that tap into your enterprise content for any job function, business process, or industry specific use case. We are also expanding our set of foundational agents that customers will be able to use to work with their enterprise content, including new features like search and research on unstructured data. Next, we’re announcing Box Extract to enable customers to use AI agents seamlessly for complex data extraction from any type of document or content. This makes it easier than ever to pull out data from contracts, invoices, research data, marketing assets, medical charts, and more. Finally, we’re introducing Box Automate, a new workflow automation solution within Box that lets you deploy AI agents across enterprise content-centric workflows. With Box Automate, you can design your business process in a simple drag and drop builder and then drop in AI agents at any step in the process. This ensures agents execute tasks at the right steps in a workflow every time. Best of all, our AI agents and workflow tools are designed to work across any system our customers work within, whether it’s leveraging pre-built integrations, Box APIs, or the new Box MCP Server. Ultimately, all of these capabilities come together to transform how companies can work with their enterprise content. Software has historically only been good at automating work that deals with structured data, which is why ERP, CRM, and HR systems have been mainstays of enterprise software for so long. The data in these systems fits neatly into a database, and the workflows are very ripe for automation. But it turns out most of the work in the world deals with unstructured data. It’s ideating through research documents, working with a client on contracts, reviewing details for a new product launch, looking at a patient’s healthcare record to make a diagnosis, working through due diligence documents for an M&A deal, and so on. For the first time ever, we can begin to bring all new insights and automation to this work with AI agents. At Box, we’re incredibly excited to be on this journey to help customers transform how they work with their most important data.
1:21

Today, Box is announcing major new AI agent capabilities to let customers tap into the full value of their unstructured data. First, we’re announcing all new updates to the Box AI Studio to make it even easier to build AI agents that tap into your enterprise content for any job function, business process, or industry specific use case. We are also expanding our set of foundational agents that customers will be able to use to work with their enterprise content, including new features like search and research on unstructured data. Next, we’re announcing Box Extract to enable customers to use AI agents seamlessly for complex data extraction from any type of document or content. This makes it easier than ever to pull out data from contracts, invoices, research data, marketing assets, medical charts, and more. Finally, we’re introducing Box Automate, a new workflow automation solution within Box that lets you deploy AI agents across enterprise content-centric workflows. With Box Automate, you can design your business process in a simple drag and drop builder and then drop in AI agents at any step in the process. This ensures agents execute tasks at the right steps in a workflow every time. Best of all, our AI agents and workflow tools are designed to work across any system our customers work within, whether it’s leveraging pre-built integrations, Box APIs, or the new Box MCP Server. Ultimately, all of these capabilities come together to transform how companies can work with their enterprise content. Software has historically only been good at automating work that deals with structured data, which is why ERP, CRM, and HR systems have been mainstays of enterprise software for so long. The data in these systems fits neatly into a database, and the workflows are very ripe for automation. But it turns out most of the work in the world deals with unstructured data. It’s ideating through research documents, working with a client on contracts, reviewing details for a new product launch, looking at a patient’s healthcare record to make a diagnosis, working through due diligence documents for an M&A deal, and so on. For the first time ever, we can begin to bring all new insights and automation to this work with AI agents. At Box, we’re incredibly excited to be on this journey to help customers transform how they work with their most important data.

Aaron Levie

91,863 Aufrufe • vor 1 Jahr

The more I learn about DNA and the inner workings of our cells, the more I’m convinced that there is a Creator/Force/God. You can call it what you want but to think it’s all just “evolution”, the result of natural selection, seems absolutely absurd to me. I am not saying evolution isn’t real but I am saying that our understanding about the nature of our reality and where we come from is sorely lacking. We like to tell ourselves the “we know the truth”, but the correct answer is that we really don’t know at all. Human origins is the mystery of all mysteries and our arrogance instead of reverence for that mystery is a big reason why evil has gained such a foothold in our world in my opinion. What do you think? Evolution explains it or something else is at play? I don’t claim to know the truth but instinctually feel our explanations are fundamentally flawed. Watch this stunning animation that explains how our DNA is tightly packed up and tell me you are not left with a sense of wonder for the mysterious nature of it all.
6:35

The more I learn about DNA and the inner workings of our cells, the more I’m convinced that there is a Creator/Force/God. You can call it what you want but to think it’s all just “evolution”, the result of natural selection, seems absolutely absurd to me. I am not saying evolution isn’t real but I am saying that our understanding about the nature of our reality and where we come from is sorely lacking. We like to tell ourselves the “we know the truth”, but the correct answer is that we really don’t know at all. Human origins is the mystery of all mysteries and our arrogance instead of reverence for that mystery is a big reason why evil has gained such a foothold in our world in my opinion. What do you think? Evolution explains it or something else is at play? I don’t claim to know the truth but instinctually feel our explanations are fundamentally flawed. Watch this stunning animation that explains how our DNA is tightly packed up and tell me you are not left with a sense of wonder for the mysterious nature of it all.

Champagne Joshi

149,527 Aufrufe • vor 2 Jahren

The same kinds of productivity gains we've seen in coding with AI agents are heading to the rest of knowledge work. This is the jump when you go from having a chatbot to being able to actually have an agent go off and do work for minutes or even hours and come back with a complete work output that you then review. Here's an example of the new Box Agent filling out an RFP response from an existing knowledge base. This process would normally take hours to fill out, and requires the full attention of the user doing the work. Now, you provide the Box Agent with the RFP questions, and it will go off, make a plan, extract all the relevant questions, read through existing source material to come up with an answer, and then generate a new word document as the final output. All while you're doing something else. The key to this architecture is that the agent is able to use all of the same tools in the background that a user uses to get work done. The agent can search for documents, read entire files, run scripts and tools in the background, and even be able to write code on the fly to automate tasks it hasn't seen before. And best of all, the Box Agent will (soon) work from the Box MCP and CLI so you can invoke it in any agentic system as a step in a process. This kind of agent complexity would have been impossible even 6 months ago. Models consistently failed at tracking long running tasks or using the right tools at the right moment for the task. But this is all now possible because of models like GPT-5.4, Opus 4.6, and Gemini 3, and is only getting better by the month. Just as we moved from engineers writing code and using AI as an assistant to answer questions, in many areas of knowledge work -like legal, finance, consulting, sales, marketing, and more- when we have a problem we'll just kick off the AI agent to just go work on it for us in the background.
2:14

The same kinds of productivity gains we've seen in coding with AI agents are heading to the rest of knowledge work. This is the jump when you go from having a chatbot to being able to actually have an agent go off and do work for minutes or even hours and come back with a complete work output that you then review. Here's an example of the new Box Agent filling out an RFP response from an existing knowledge base. This process would normally take hours to fill out, and requires the full attention of the user doing the work. Now, you provide the Box Agent with the RFP questions, and it will go off, make a plan, extract all the relevant questions, read through existing source material to come up with an answer, and then generate a new word document as the final output. All while you're doing something else. The key to this architecture is that the agent is able to use all of the same tools in the background that a user uses to get work done. The agent can search for documents, read entire files, run scripts and tools in the background, and even be able to write code on the fly to automate tasks it hasn't seen before. And best of all, the Box Agent will (soon) work from the Box MCP and CLI so you can invoke it in any agentic system as a step in a process. This kind of agent complexity would have been impossible even 6 months ago. Models consistently failed at tracking long running tasks or using the right tools at the right moment for the task. But this is all now possible because of models like GPT-5.4, Opus 4.6, and Gemini 3, and is only getting better by the month. Just as we moved from engineers writing code and using AI as an assistant to answer questions, in many areas of knowledge work -like legal, finance, consulting, sales, marketing, and more- when we have a problem we'll just kick off the AI agent to just go work on it for us in the background.

Aaron Levie

24,728 Aufrufe • vor 5 Monaten

As a historian, I can tell you that societies that allow Jews to thrive are societies in history that are flourishing themselves. Look at America. It is the center of the most influential, the wealthiest, the most powerful Jewish community that has ever existed in the world, and it is no surprise it is also the most powerful, the most influential, and the wealthiest force for good the world has ever had. We are privileged to live here. But on the other hand, societies that allow themselves to be taken over by Jew hatred are societies that are sick and dying. Look at the Russia of Kishinev in 1903, the worst pogrom of the 20th century before the Holocaust. It was the biggest country in the world at that time. It had existed for hundreds of years. 14 years later, it was gone. Look at the Germany of Kristallnacht in 1938, the most powerful army, the most powerful air force. It was supposed to be the thousand-year Reich. Just seven years later, it was dead. So not because I'm a Jew, but because I am an American who came here from Venezuela with nothing, knowing no one, and who was embraced by this community and this country with open arms, which has given me and my family every blessing and privilege under the sun, I understand that we, each of us, Jew and not Jew alike, have a moral and practical obligation to root out anti-Semitism in our society because it is the moral rot in the wooden framework of our house. If we are not careful, it will bring the entire edifice tumbling down on all of us, not just the Jews.
2:07

As a historian, I can tell you that societies that allow Jews to thrive are societies in history that are flourishing themselves. Look at America. It is the center of the most influential, the wealthiest, the most powerful Jewish community that has ever existed in the world, and it is no surprise it is also the most powerful, the most influential, and the wealthiest force for good the world has ever had. We are privileged to live here. But on the other hand, societies that allow themselves to be taken over by Jew hatred are societies that are sick and dying. Look at the Russia of Kishinev in 1903, the worst pogrom of the 20th century before the Holocaust. It was the biggest country in the world at that time. It had existed for hundreds of years. 14 years later, it was gone. Look at the Germany of Kristallnacht in 1938, the most powerful army, the most powerful air force. It was supposed to be the thousand-year Reich. Just seven years later, it was dead. So not because I'm a Jew, but because I am an American who came here from Venezuela with nothing, knowing no one, and who was embraced by this community and this country with open arms, which has given me and my family every blessing and privilege under the sun, I understand that we, each of us, Jew and not Jew alike, have a moral and practical obligation to root out anti-Semitism in our society because it is the moral rot in the wooden framework of our house. If we are not careful, it will bring the entire edifice tumbling down on all of us, not just the Jews.

Roy K. Altman

155,318 Aufrufe • vor 4 Monaten

There is no best model. There's a lot of noise about models right now. Who is training them, who owns them, where legal intelligence should live. One question actually matters: what produces the best outcome for the legal task in front of you? That's how we decide things at Legora. We optimize for the end-to-end outcome on a legal task. The model is one layer of that system, not the system. Models are uneven and the frontier changes almost weekly. One model plans a long job well, another runs deep analysis across thousands of documents. Some have to be told exactly what to do, and some are fine with a vague brief. They all break in different ways. So our lawyers write evals and we test them with the Legora BAR, our benchmark for agentic reasoning. Every model takes every test, and the model that wins gets the work. We post-train when we know it buys our customers better performance on a specialized task. Training is a tool we reach for when it helps, nothing more than that. The intelligence that compounds sits in the orchestration layer. Precedents, review standards, client requirements. That knowledge has to stay editable, auditable and portable. In our system, a changed review standard is an edit that takes effect the same day, with no new model training required. No lawyer should have to worry about which model did the work, any more than they think about which chip is in their laptop. They should only care about the quality of the work. That's what we are focused on. If you want the engineering version of this argument rather than the CEO version, our CPO, Bryan Tsao, and CTO, Jacob Lauritzen, take it apart in the video below.
9:33

There is no best model. There's a lot of noise about models right now. Who is training them, who owns them, where legal intelligence should live. One question actually matters: what produces the best outcome for the legal task in front of you? That's how we decide things at Legora. We optimize for the end-to-end outcome on a legal task. The model is one layer of that system, not the system. Models are uneven and the frontier changes almost weekly. One model plans a long job well, another runs deep analysis across thousands of documents. Some have to be told exactly what to do, and some are fine with a vague brief. They all break in different ways. So our lawyers write evals and we test them with the Legora BAR, our benchmark for agentic reasoning. Every model takes every test, and the model that wins gets the work. We post-train when we know it buys our customers better performance on a specialized task. Training is a tool we reach for when it helps, nothing more than that. The intelligence that compounds sits in the orchestration layer. Precedents, review standards, client requirements. That knowledge has to stay editable, auditable and portable. In our system, a changed review standard is an edit that takes effect the same day, with no new model training required. No lawyer should have to worry about which model did the work, any more than they think about which chip is in their laptop. They should only care about the quality of the work. That's what we are focused on. If you want the engineering version of this argument rather than the CEO version, our CPO, Bryan Tsao, and CTO, Jacob Lauritzen, take it apart in the video below.

Max Junestrand

47,797 Aufrufe • vor 3 Tagen

Satya Nadella was asked what Microsoft does when its AI revenue 10x's from $13B to $130B. He refused to answer in revenue - and named the only AGI benchmark he says counts "The first thing we have to observe is GDP growth. There's only one governor in all of this" "This is where a little bit of, we get ahead of ourselves with all this AGI hype" "The developed world is what, 2% growth? And if you adjust for inflation, it's zero. We have a real growth challenge" "When we say this is like the Industrial Revolution - that type of growth means to me 10%, 7%, developed world inflation adjusted, growing at 5%. That's the real marker" "The big winners here are not going to be tech companies. The winners are going to be the broader industry that uses this commodity" "Us self-claiming some AGI milestone - that's just nonsensical benchmark hacking to me. The real benchmark is the world growing at 10%" The CEO with one of the largest AI infrastructure bets on earth just told you to ignore every model benchmark and watch a single number: world GDP. By that test, nothing has happened yet. Developed-world growth is flat, and no lab's press release moves it. Real AGI shows up as the economy compounding at Industrial Revolution rates - or it isn't real.
1:51

Satya Nadella was asked what Microsoft does when its AI revenue 10x's from $13B to $130B. He refused to answer in revenue - and named the only AGI benchmark he says counts "The first thing we have to observe is GDP growth. There's only one governor in all of this" "This is where a little bit of, we get ahead of ourselves with all this AGI hype" "The developed world is what, 2% growth? And if you adjust for inflation, it's zero. We have a real growth challenge" "When we say this is like the Industrial Revolution - that type of growth means to me 10%, 7%, developed world inflation adjusted, growing at 5%. That's the real marker" "The big winners here are not going to be tech companies. The winners are going to be the broader industry that uses this commodity" "Us self-claiming some AGI milestone - that's just nonsensical benchmark hacking to me. The real benchmark is the world growing at 10%" The CEO with one of the largest AI infrastructure bets on earth just told you to ignore every model benchmark and watch a single number: world GDP. By that test, nothing has happened yet. Developed-world growth is flat, and no lab's press release moves it. Real AGI shows up as the economy compounding at Industrial Revolution rates - or it isn't real.

Karl Mehta

82,403 Aufrufe • vor 2 Monaten

Agentic AI will transform every enterprise–but only if agents are trusted experts. The key: Evaluation & tuning on specialized, expert data. I’m excited to announce two new products to support this–Snorkel AI Evaluate & Expert Data-as-a-Service–along w/ our $100M Series D! --- Snorkel Evaluate is our new data-centric agentic AI evaluation platform for specialized, mission-critical enterprise settings where vibe checks and out-of-the-box metrics driven by simple LLM prompts are not enough. Snorkel Expert Data-as-a-Service is our white glove service for expert-level AI datasets, powering frontier LLM developers in areas like expert knowledge, reasoning, agentic action and tool use, and more! Both built on top of Snorkel AI’s Data Development Platform, using our programmatic technology to drive higher-quality expert data, faster– for getting specialized AI to real production value. If you’re building enterprise AI and want to partner around the key ingredient in AI today–the data–book a demo and let's talk! Finally, see thread for details on 🧵👇 - 📽️ A walkthrough of Snorkel Evaluate and Expert Data-as-a-Service on an agentic AI enterprise task - 📅 An upcoming event on Enterprise Agentic AI with innovators from Accenture @BNY Comcast Stanford University QBE & others - 📊 An upcoming series of benchmark datasets and model artifact releases 👀 Want early access to the full agentic AI dataset? Retweet this post and we'll send you the link!
5:42

Agentic AI will transform every enterprise–but only if agents are trusted experts. The key: Evaluation & tuning on specialized, expert data. I’m excited to announce two new products to support this–Snorkel AI Evaluate & Expert Data-as-a-Service–along w/ our $100M Series D! --- Snorkel Evaluate is our new data-centric agentic AI evaluation platform for specialized, mission-critical enterprise settings where vibe checks and out-of-the-box metrics driven by simple LLM prompts are not enough. Snorkel Expert Data-as-a-Service is our white glove service for expert-level AI datasets, powering frontier LLM developers in areas like expert knowledge, reasoning, agentic action and tool use, and more! Both built on top of Snorkel AI’s Data Development Platform, using our programmatic technology to drive higher-quality expert data, faster– for getting specialized AI to real production value. If you’re building enterprise AI and want to partner around the key ingredient in AI today–the data–book a demo and let's talk! Finally, see thread for details on 🧵👇 - 📽️ A walkthrough of Snorkel Evaluate and Expert Data-as-a-Service on an agentic AI enterprise task - 📅 An upcoming event on Enterprise Agentic AI with innovators from Accenture @BNY Comcast Stanford University QBE & others - 📊 An upcoming series of benchmark datasets and model artifact releases 👀 Want early access to the full agentic AI dataset? Retweet this post and we'll send you the link!

Alex Ratner

50,393 Aufrufe • vor 1 Jahr

Our world is vast, but we are all in it together. And this is our shared cause – peace. 🇺🇦 proposed its Peace Formula to the world. As long as invaders remain on our land, no one will sit down at the negotiating table with 🇷🇺. The colonizer must get out. And the world has enough power to force 🇷🇺 to restore peace step by step. We have developed the Peace Formula in a way that ensures each of its points is backed by United Nations 🇺🇳 resolutions. And in a way that everyone in the world can choose the track they can contribute to. From Japan to the Arab countries, from Europe to Latin America, we find support for our Formula. And we continue this work.
0:53

Our world is vast, but we are all in it together. And this is our shared cause – peace. 🇺🇦 proposed its Peace Formula to the world. As long as invaders remain on our land, no one will sit down at the negotiating table with 🇷🇺. The colonizer must get out. And the world has enough power to force 🇷🇺 to restore peace step by step. We have developed the Peace Formula in a way that ensures each of its points is backed by United Nations 🇺🇳 resolutions. And in a way that everyone in the world can choose the track they can contribute to. From Japan to the Arab countries, from Europe to Latin America, we find support for our Formula. And we continue this work.

Volodymyr Zelenskyy / Володимир Зеленський

2,286,871 Aufrufe • vor 3 Jahren