Xi Zhang
@_xizhang
Incoming R&D Intern @huawei | CS PhD @UofGlasgow (@ir_glasgow / https://ai4biomed.org/) | Alumni of @Sydney_Uni & DUT | Interests: AI4Health, AI Agents, Web3
🎉 Excited to share that our paper "Libra: Leveraging Temporal Images for Biomedical Radiology Analysis" (w/@mengzaiqiao, @jakelever0 & @EdmondSLHo) is accepted at #ACL2025! 🧠 TL;DR: We present Libra, a temporally-aware MLLM — inspired by "structure determines function" — to…
📢 Come by Poster #130 right now at #ACL2025NLP ! @mengzaiqiao is here! KiRAG: Knowledge-Driven Iterative Retriever for Enhancing Retrieval-Augmented Generation 🔁📚 w/ @JinyuanF and @craig_macdonald — don’t miss the deep dive into knowledge-grounded retrieval! @ir_glasgow…
Heading to #ACL2025 this weekend — Vienna, here we come! 🇦🇹 Excited to share that the AI4BioMed Lab (led by @mengzaiqiao & @jakelever0) has three papers accepted this year! 🎉 Come chat with us at the conference 👋 w/ @JinyuanF, @_xizhang, and @JavierSanzCruza 💬 📮 Also, I'll…
🎉 Excited to share that the Glasgow AI4BioMed Lab (ai4biomed.org) is presenting at #HealTAC2025 this Thursday! 📍 Join us at the PhD Forum in the Debates Chamber at Glasgow Uni! 💬 w/ @XinhaoYi, @Zhaohan_Meng, @_xizhang, Hana Elsherbeny 🙌 Advised by @mengzaiqiao &…
❓Which retrieval library should you use for RAG? Which agent library? Where do you get datasets? We made PyTerrier RAG to stop your headaches! Led by @craig_macdonald /w (@JinyuanF , me and @mengzaiqiao )! 🧵 ⬇️
Pleased to share that Libra is now ranked at Top 3 on ReXrank (rexrank.ai), a public leaderboard for chest X-ray image interpretation. Well done @_xizhang! @ir_glasgow @IDAglasgow @GlasgowCS
🎉 Excited to share that our paper "Libra: Leveraging Temporal Images for Biomedical Radiology Analysis" (w/@mengzaiqiao, @jakelever0 & @EdmondSLHo) is accepted at #ACL2025! 🧠 TL;DR: We present Libra, a temporally-aware MLLM — inspired by "structure determines function" — to…
🚨 New Pre-Print! We show that in-context learning can steer LLM rankers to satisfy multiple objectives at once, relevance and fairness/diversity, without any parameter updates. Work done jointly with @nilanjansb from IIT Kharagpur and @debforit. 🧵 Below!
💡One of the most exciting projects I’ve ever worked on. 👏 Let’s embrace this new wave of autonomous AI Agents — come explore, contribute, and shape the future with us. 😎 Come poke around. You might just get hooked. #EvoAgentX #AI #OpenSource
🎉 An open-source AI Agent project, EvoAgentX, led by @GlasgowCS PhD students, has received ⭐️ 260+ stars on GitHub in just 5 DAYS! 🤖 The project aims to build a Self-Evolving Ecosystem of AI Agents — redefining autonomous AI. @ir_glasgow @UofGlasgow @IDAglasgow #AI #EvoAgentX
🚨 EvoAgentX Surpasses 100 Stars! Introducing EvoAgentX: the world’s first self-evolving AI agent framework 🧠⚙️ ✅ Automated Prompt Optimization ✅ Continuous Self-Improvement ⭐️ Star / 🍴 Fork / 👀 Watch Your ⭐️ boosts visibility. #AI #LLM #OpenSource #EvoAgentX #DevTools
🎉 Glad to share that our paper "KiRAG: Knowledge-Driven Iterative Retriever for Enhancing Retrieval-Augmented Generation" (w/ @mengzaiqiao and @craig_macdonald) has been accepted at #ACL2025 as a main conference paper!
Just uploaded our paper KiRAG to Arxiv! 🚀 KiRAG integrates reasoning into retrieval, dynamically identifying and retrieving knowledge to bridge information gaps. We leverage KGs to enhance the retrieval process of iRAG. 📄:arxiv.org/abs/2502.18397 💻: github.com/jyfang6/kirag