Zecheng Zhang

I am still too young too simple, sometimes naive😂

Thrilled to share that @TracerootAI has been accepted into @ycombinator S25 batch! Debugging in production is a real pain, and we’re on a mission to fix that. Big things ahead. Stay tuned. #TraceRoot #AI #AIAgents #Debugging #Coding #Python #YC #YCombinator

🚀 Launch countdown of a cool agent product. 🙌We’re recruiting around 10 Power Users of AI products to participate in Beta Testing. 🆓 Get 3 months of the Plus Plan for free! If you’re interested, send a DM.

New Agent Example! Turn any research question into a data visualization, automatically using Gemini 2.5 Pro and @CamelAIOrg's OWL framework. Exciting collaboration! 🚀 🔍 Performs live web research using search engines and browser use. 🐍 Autonomously writes and executes Python…

Thanks to the @googleaidevs team for featuring 𝐎𝐖𝐋🦉 Exciting to see OWL in action with Gemini 2.5 Pro for automating complex tasks.

🦉 Automate complex tasks using Gemini 2.5 Pro and @CamelAIOrg’s OWL (Optimized Workforce Learning), an open-source multi-agent collaboration framework that works together like a real-world project team.

🚀 Introducing KumoRFM — the world’s first Relational Foundation Model purpose-built for enterprise prediction tasks! KumoRFM reasons over complex relational data to deliver instant, accurate, in-context predictions — no task-specific model training required. A true game-changer…

You can build the best Web agent with today's Github trending repos. Don't ask me how 🫡 Mem0 x CAMEL: github.com/camel-ai/camel… BrowserUse x CAMEL: github.com/camel-ai/camel…

🚀 Day 0: Warming up for #OpenSourceWeek! We're a tiny team @deepseek_ai exploring AGI. Starting next week, we'll be open-sourcing 5 repos, sharing our small but sincere progress with full transparency. These humble building blocks in our online service have been documented,…

🎉 PyTorch Frame, our open-source tabular deep learning framework, won the Best Paper Award 🏆 at @TrlWorkshop at @NeurIPSConf 2024! Huge congrats to @Kumo_ai_team @PyG_Team: @weihua916 @yiwenyuan98 @zechengzh, Kaidi Cao, @KocijanVid, Jinu Sunil, @jure, and @rusty1s! 🙌

Thrilled to present PyTorch Frame at @NeurIPSConf this Saturday! 🚀 PyTorch Frame is a cutting-edge tabular deep learning framework supporting: ✅ multi-modal data ✅ various existing models via modular design ✅ integration with GNNs & foundation models

Looking forward to connecting with everyone at @TrlWorkshop and sharing insights on this exciting project! 🙌 A big shout-out to my amazing co-authors @weihua916, @yiwenyuan98, @zechengzh, Kaidi Cao, @KocijanVid, @jure and @rusty1s 🙌

🎉 Excited to announce the release of ContextGNN, our state-of-art and scalable recommendation model from Kumo! 🔗 ContextGNN paper: arxiv.org/abs/2411.19513 What makes ContextGNN unique? It combines pair-wise and two-tower representations into a single architecture, enabling…

#Hawaii #Hilo #coconutisland

#southpointpark #Hawaii #bigisland

PyG 2.6 is here, including new models and examples on how to combine GNNs with LLMs! Thanks to many contributors who have made this release possible. Full release notes👇 github.com/pyg-team/pytor…

Students at Stanford have built alphaXiv, an open discussion forum for arXiv papers.

🚀 GraphRAG: Boost Retrieval Accuracy and RAG Performance! Check out the diagram and tech stack below to see how this works. 🔹@CamelAIOrg: A multi-agent system framework that facilitates the workflow and provides agents such as Knowledge Graph Agent and Chat Agent.…

🚀 Announcing RelBench: an open benchmark for deep learning on relational databases! RelBench is the foundational infrastructure for research in Relational Deep Learning (RDL), which brings modern AI to structured data. RelBench has databases, tasks, loaders, evaluators, and…

Excited about the release of the Hybrid GNN blog post, from my time at Kumo! docs.kumo.ai/docs/hybrid-gr… A single, sophisticated GNN model to achieve SoTA on recommendation. Deployed to many customers to generate huge (e.g., $100 million) additional sales. Check it out!