Sign in

Patrice Bechard

@patricebechard.bsky.social
19 followers 86 following 19 posts

Applied Research Scientist working on LLMs at @ServiceNow. Opinions are my own.

PostsRepliesMedia
Patrice Bechard @patricebechard.bsky.social · 29/05/2025
🚀 New paper from our team at @servicenowresearch.bsky.social!⁣ ⁣ 💫𝐒𝐭𝐚𝐫𝐅𝐥𝐨𝐰: 𝐆𝐞𝐧𝐞𝐫𝐚𝐭𝐢𝐧𝐠 𝐒𝐭𝐫𝐮𝐜𝐭𝐮𝐫𝐞𝐝 𝐖𝐨𝐫𝐤𝐟𝐥𝐨𝐰 𝐎𝐮𝐭𝐩𝐮𝐭𝐬 𝐅𝐫𝐨𝐦 𝐒𝐤𝐞𝐭𝐜𝐡 𝐈𝐦𝐚𝐠𝐞𝐬⁣ We use VLMs to turn 𝘩𝘢𝘯𝘥-𝘥𝘳𝘢𝘸𝘯 𝘴𝘬𝘦𝘵𝘤𝘩𝘦𝘴 and diagrams into executable workflows 🖍️→⚙️⁣ ⁣ 🔗 arxiv.org/abs/2503.218... 📝 tinyurl.com/3utdbn97%E2%... #Sketch2Flow #AI #VLM
101
Patrice Bechard @patricebechard.bsky.social · 09/01/2025
🚀 Excited to share our new work on making RAG actually work for enterprise applications! We present a recipe to build a custom retriever that handles multiple retrieval tasks simultaneously for domain-specific RAG applications 🧵
110
Reposted by Patrice Bechard
Alexandre Lacoste @alex-lacoste.bsky.social · 12/12/2024
We’re really excited to release this large collaborative work for unifying web agent benchmarks under the same roof. In this TMLR paper, we dive in-depth into #BrowserGym and #AgentLab. We also present some unexpected performances from Claude 3.5-Sonnet
12111
Reposted by Patrice Bechard
Juan Rodriguez @joanrod.bsky.social · 10/12/2024
🎉 Excited to introduce BigDocs! An open, transparent multimodal dataset designed for: 📄 Documents 🌐 Web content 🖥️ GUI understanding 👨‍💻 Code generation from images We’re also launching BigDocs-Bench: ➡️ Document, Web, GUI Visual reasoning ➡️ Converting images into JSON, Markdown, LaTeX, SVG, and more!
1168
Patrice Bechard @patricebechard.bsky.social · 03/12/2024
Looking to build an LLM-powered app but finding it hard to make it robust? We’ve got you covered! Our new paper explores how Task Decomposition and Retrieval-Augmented Generation (RAG) can help you create reliable systems. 🧵👇
100