News | Xi Zhang

✨ Joining ANative Lab as Chief Scientist

Tue, 25 Aug 2026 00:00:00 +0000

A new chapter. Excited to join ANative Lab as Chief Scientist — and continue building the next generation of self-evolving scientific research. 🎉

ANative Lab is a research lab for AI-native & agent-native intelligence, advancing self-evolving agents and autonomous scientific discovery.

Alongside the lab, I continue to lead EvoScientist — your self-evolving AI scientist: a multi-agent system for end-to-end scientific discovery.

🌐 ANative.ai · 💻 github.com/ANative-Lab · 📣 Announcement on X

⭐ EvoScientist Crosses 4.5k GitHub Stars!

Fri, 31 Jul 2026 00:00:00 +0000

Today we crossed 4.5k GitHub stars. 🚀🚀🚀

Thanks to everyone who’s been part of the journey — more to come.

Github: EvoScientist

⭐ Star it / 🍴 Fork it / 👀 Watch it 👆

Star History

🎤 Talk at Glasgow AI4BioMed Lab!

Wed, 17 Jun 2026 00:00:00 +0000

💡 Talk Title

“CCS: Clinical Consensus Selection for Radiology Report Generation”

🖇️ Abstract

Radiology report generation (RRG) is commonly framed as a single-path task, where a multimodal large language model (MLLM) produces one decoded report as the final output. While progress has largely come from scaling training data, model capacity, and retrieval mechanisms, improving report quality at inference time remains underexplored. We observe that fixed radiology MLLMs often generate clinically stronger reports elsewhere in their candidate pool than the one selected by default decoding, suggesting that inference-time decision making is an overlooked bottleneck. To address this, we propose Clinical Consensus Selection (CCS), a decoder-agnostic inference-time selection framework that samples multiple candidate reports and selects the one with the highest clinical consensus across the rollout pool. CCS combines text-based utilities with a radiology-adapted utility computed by an image–report-trained multimodal embedder, measuring agreement beyond surface-level textual similarity. Across three datasets and multiple radiology MLLMs, CCS consistently improves inference-time performance over single-path decoding and generic Best-of-N baselines, with especially clear gains on clinical metrics. Further analysis shows that image-grounded utility forms a selection axis distinct from textual consensus, and that substantial headroom remains for improving RRG at inference time.

🔗 Project Website: https://x-izhang.github.io/CCS/

📺 Slides

📍 Glasgow AI4BioMed Lab — An interdisciplinary research lab focusing on AI applications in biomedical sciences, based in Glasgow.

📅

When: Wednesday, June 17, 2026 at 2pm
Where: F121

See you there!

🚨 Preprint out — Clinical Consensus Selection！

Fri, 29 May 2026 00:00:00 +0000

“CCS: Clinical Consensus Selection for Radiology Report Generation”. The preprint is now available.

For detailed model information and source code, please visit our Project Page: CCS

Overview

Radiology report generation (RRG) is usually treated as a single-path task: a multimodal large language model (MLLM) emits one decoded report and commits to it. Yet a fixed model often places clinically stronger reports elsewhere in its candidate pool than the one chosen by default decoding—so inference-time decision making remains an overlooked bottleneck. We introduce Clinical Consensus Selection (CCS), a decoder-agnostic, reference-free framework that samples multiple candidate reports and selects the one with the highest clinical consensus across the rollout pool. CCS unifies text-based utilities with a radiology-adapted utility from an image–report-trained multimodal embedder, measuring candidate agreement beyond surface-level text. Across three datasets and multiple radiology MLLMs, CCS consistently improves over single-path decoding and generic Best-of-N baselines, with particularly clear gains on clinical metrics.

Key Resources

GitHub Repository — Explore the CCS project on GitHub

✒️ Invited as Reviewer for NeurIPS 2026

Thu, 23 Apr 2026 00:00:00 +0000

I have been invited to serve as a reviewer for NeurIPS 2026, the 40th Annual Conference on Neural Information Processing Systems. Looking forward to contributing to the review process and supporting high-quality research in machine learning and AI.

🎉 Paper Accepted — See You at ACL 2026!

Mon, 06 Apr 2026 00:00:00 +0000

“CCD: Mitigating Hallucinations in Radiology MLLMs via Clinical Contrastive Decoding” has been accepted to ACL 2026!

📍 ACL 2026 — The 64th Annual Meeting of the Association for Computational Linguistics will take place in San Diego, California, July 2026

See you there!

🪧 Poster

🎤 Invited Talk at EvoAgentX Community!

Wed, 01 Apr 2026 00:00:00 +0000

Honoured to be invited by the EvoAgentX community to present our latest project at this week’s EvoAgentX Talk! As a core contributor to the EvoAgentX community, I shared the design and progress behind EvoScientist — an open-source, long-horizon agent system for autonomous scientific discovery.

💡 Talk Title

EvoScientist: Toward Long-Horizon Agent Systems for Scientific Discovery

🖇️ Abstract

AI is rapidly shifting from dialogue models to agent systems. Platforms like OpenClaw have already demonstrated that AI can execute real-world tasks beyond simple Q&A. However, when we move to the scientific research domain, the challenges multiply dramatically. Research tasks are inherently long-horizon, multi-stage, strongly interdependent, and continuously iterative — far from a single-turn reasoning problem, they demand sustained decision-making and an evolving system architecture.

EvoScientist explores a long-horizon agent design paradigm tailored to research scenarios. Through multi-agent collaboration, the system progressively completes the full pipeline from idea generation to experiment execution to result summarization — an approach we call Vibe Research. Unlike many agent systems that remain at the demo stage, EvoScientist emphasizes executability in complex tasks and the ability to continuously evolve in real-world settings.

In this talk, I address three key questions: why current agent systems fall short in research scenarios, what the core design philosophy of EvoScientist is, and whether we truly need a new long-horizon agent paradigm to support increasingly complex task systems in the future.

📺 Slides

This talk was presented to the Chinese-speaking community, so the slides below are in Chinese. An English version will be shared in a future community session.

🔗 Project Link

EvoScientist — Harness Vibe Research with Self-evolving AI Scientists

EvoScientist aims to harness vibe research by enabling self-evolving AI scientists that autonomously explore, generate insights, and iteratively improve. It is designed to be opinionated and ready to use out of the box, offering a living research system that grows alongside evolving agent skills, toolsets, and memory bases. Moving beyond traditional human-in-the-loop systems, EvoScientist adopts a human-on-the-loop paradigm — AI acts as a research buddy that co-evolves with human researchers and internalizes scholarly taste and scientific judgment.

🚀 EvoScientist Debuts!

Fri, 13 Mar 2026 00:00:00 +0000

See what’s new on Github: EvoScientist

⭐ Star it / 🍴 Fork it / 👀 Watch it 👆

🧬 If AI agents must be Self-Evolving, then AI Scientists should lead the way.

EvoScientist aims to harness vibe research by enabling self-evolving AI scientists that autonomously explore, generate insights, and iteratively improve. Moving beyond traditional human-in-the-loop systems, EvoScientist adopts a human-on-the-loop paradigm — AI acts as a research buddy that co-evolves with human researchers and internalizes scholarly taste and scientific judgment.

Why vibe research matters and how it drives EvoScientist: Harness Vibe Research 📟

🔬 End-to-End Scientific Workflow

🚀 Quick Start Demo

🏆 Awards & Recognition

🥇 #1 on DeepResearch Bench II
🥇 #1 on AstaBench Code & Execution
🥇 #1 on AstaBench Data Analysis
🏆 Best Paper & AI Reviewer’s Appraisal Award at ICAIS 2025

🪧 Join Our Community!

We’re building a community of researchers, developers, and visionaries dedicated to harnessing vibe research and self-evolving AI scientists. Together, we’re redefining autonomous scientific discovery.

Discord — Chat, discuss, and collaborate in real-time
GitHub — Source code and documentation
WeChat — Connect with our Chinese community

📝 New Blog Just Dropped!

Wed, 04 Mar 2026 00:00:00 +0000

🧠 TL;DR

Full research autonomy will happen — but it won’t come from a pre-built product. It will emerge from your own harness: a system that absorbs your judgment, encodes your taste, and compounds with every run. The question is not whether this shift is coming. The question is whether you are building the harness to grow with it.

Dive deeper in the full post: Harness Vibe Research 📟

Opinions on my own

✒️ Invited as Reviewer for ACM HEALTH

Sun, 15 Feb 2026 00:00:00 +0000

I have been invited to serve as a reviewer for ACM Transactions on Computing for Healthcare (ACM HEALTH). Looking forward to contributing to the review process and supporting high-quality research in computing for healthcare.

🎤 Talk at Glasgow AI4BioMed Lab!

Wed, 28 Jan 2026 00:00:00 +0000

💡 Talk Title

“CCD: Mitigating Hallucinations in Radiology MLLMs via Clinical Contrastive Decoding”

🖇️ Abstract

Radiology multimodal large language models (MLLMs) often generate clinically unsupported descriptions, posing serious risks in medical applications. We introduce Clinical Contrastive Decoding (CCD), a training-free inference framework that integrates structured clinical signals from radiology expert models to mitigate hallucinations. CCD refines token-level logits during generation through a dual-stage contrastive mechanism, enhancing clinical fidelity without modifying the base MLLM. On the MIMIC-CXR dataset,CCD yields up to 17% improvement in RadGraph-F1, providing a lightweight solution for bridging expert models and MLLMs in radiology.

🔗 Project Website: https://x-izhang.github.io/CCD/

📺 Slides

📍 Glasgow AI4BioMed Lab — An interdisciplinary research lab focusing on AI applications in biomedical sciences, based in Glasgow.

📅

When: Wednesday, January 28, 2026 at 2pm
Where: F121

See you there!

🎉 Paper Accepted at PSB 2026!

Mon, 22 Dec 2025 00:00:00 +0000

Automated Chest X-ray Report Generation Remains Unsolved has been accepted to Pacific Symposium on Biocomputing 2026!

For the 🏆 Chest X-ray Interpretation Leaderboard 🏆, please visit ReXrank.

📍 PSB 2026 - The Pacific Symposium on Biocomputing 2026 will be held in Hawaii, USA, from January 3-7, 2026.

🪧 Poster

🎤 Invited Talk at DICTA 2025!

Tue, 25 Nov 2025 00:00:00 +0000

💡 Talk Title

Multimodal Medical Models: Cross-modal Alignment and Consistency

🖇️ Abstract

This talk provides an overview of recent developments in medical vision–language modelling and examines key sources of misalignment that lead to hallucinations. Emerging strategies to enhance visual, semantic, and temporal consistency will also be discussed, highlighting pathways toward safer and more trustworthy clinical AI systems.

📺 Slides

📍 DICTA 2025 — The 26th International Conference on Digital Image Computing: Techniques and Applications will take place in Adelaide, Australia, from 3–5 December 2025.

🏥 MedAI-CHAS — A workshop focusing on Challenges, Hallucinations, and Solutions for Advancing Clinical Utility in Medical AI.

See you there!

🎤 Invited Talk at MLiS!

Sat, 22 Nov 2025 00:00:00 +0000

💡 Talk Title

Leveraging Temporal Images for Biomedical Radiology Analysisy

🖇️ Abstract

A temporal-aware multimodal method for radiology report generation that leverages paired chest X-rays to understand disease progression and address key challenges in medical AI.

📹 Talk

📺 Slides

⏰ Time

📍 MLiS — Machine Learning in Science Colloquium, an interdisciplinary University of Glasgow-based research community fostered around the use of machine learning.

See you there!

🎉 Paper Accepted — See You at ICAIS 2025!

Sat, 15 Nov 2025 00:00:00 +0000

We are thrilled to announce that 6 papers from our team have been accepted to present at the upcoming ICAIS 2025 conference!

At the same time, we are honoured to have received both the Best Paper Award and The AI Reviewer’s Appraisal Award in the AI Scientist Track.

🏆 Awards

💬 Talk with Prof. James J. Heckman

Nobel Laureate in Economic Sciences (2000)

🪧 Papers

This inaugural conference brings together leading researchers exploring the future of automated scientific discovery, including AI scientists, autonomous research agents, and next-generation AI-driven workflows.

📍 ICAIS 2025 — the 1st International Conference on AI Scientists will take place in Zhongguancun, Beijing, China, November 23–25, 2025

See you there!

🚨 Preprint out — Clinical Contrastive Decoding！

Sat, 27 Sep 2025 00:00:00 +0000

“CCD: Mitigating Hallucinations in Radiology MLLMs via Clinical Contrastive Decoding”. The preprint is now available.

For detailed model information and source code, please visit our Project Page: CCD

Overview

Multimodal large language models (MLLMs) have advanced radiology tasks by combining image and text understanding, but can sometimes produce inaccurate or unsupported clinical statements—so-called medical hallucinations. We introduce Clinical Contrastive Decoding (CCD), an inference-time method that leverages structured clinical signals (for example, symptom-level probabilities from specialist classifiers) to refine token-level logits during generation. CCD is designed to be applied without modifying base model weights or requiring external retrieval. In our evaluations on datasets such as MIMIC-CXR and IU-Xray, CCD yields consistent improvements in clinical metrics (for example, up to +17% RadGraph-F1 on MIMIC-CXR), reducing unsupported mentions while preserving overall fluency.

Key Resources

Interactive Demo — Try CCD online
GitHub Repository — Explore the CCD project on GitHub

🎉 Paper Accepted — See You at EMNLP 2025!

Tue, 09 Sep 2025 00:00:00 +0000

“RadEval: A framework for radiology text evaluation”, has been accepted for system demonstration at EMNLP 2025 with Oral Presentation!

For detailed model information and source code, please visit our GitHub repository: RadEval

PyPI Package — Install RadEval with pip
HuggingFace Model — Access our domain-adapted evaluation model
Interactive Demo — Try RadEval online
Research Paper — Read our detailed research paper

📍 EMNLP 2025 - The 2025 Conference on Empirical Methods in Natural Language Processing will be held in Suzhou, China, from November 4 - 9, 2025.

🤖 New Preprint Out — Self-Evolving AI Agents!

Tue, 12 Aug 2025 00:00:00 +0000

A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems

In our latest survey, we outline a clear roadmap for moving from static configurations to lifelong, self-evolving agentic systems, built on a unified Self-Evolving Feedback Loop.

📄 Paper

A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems

💻 Project

Awesome Self-Evolving Agents

I’ve jotted down some musings on the thinking behind the Three Laws: The Law of AI Agents 🏛️

📝 New Blog Is Here!

Sat, 26 Jul 2025 00:00:00 +0000

🧠 TL;DR

Today’s AI agents are human proxies. AI’s own agents don’t exist — yet.
Like early blockchain, consensus will outpace capability — awkward years ahead.
Tools (MCPs et al.) are primitive production materials, not motives. The surplus value of AI labour is still unclaimed.

Dive deeper in the full post: AI Agents Are Not AI’s Agents 🧩

Opinions on my own

🩺 RadEval Debuts！

Mon, 14 Jul 2025 00:00:00 +0000

🩺 Revolutionizing Radiology Text Evaluation with AI-Powered Metrics

Imagine having a comprehensive evaluation framework that doesn’t just measure surface-level text similarity, but truly understands clinical accuracy and medical semantics in radiology reports. This vision is now a reality with RadEval, a groundbreaking, open-source evaluation toolkit designed specifically for AI-generated radiology text.

📊 All-in-one metrics for evaluating AI-generated radiology text

From traditional n-gram metrics to advanced LLM-based evaluations, RadEval provides 11+ different evaluation metrics in one unified framework, enabling researchers to thoroughly assess their radiology text generation models with domain-specific medical knowledge integration.

For detailed handbook, please visit our GitHub repository:

🚀 Quick Start Demo

Try RadEval instantly with our interactive Gradio demo:

💡 Key Features

RadEval stands out with its comprehensive approach to radiology text evaluation:

🎯 Domain-Specific: Tailored for radiology with medical knowledge integration
📈 Multi-Metric: Supports lexical, semantic, clinical, and temporal evaluations
⚡ Easy to Use: Simple API with flexible configuration options
🔬 Research-Ready: Built-in statistical testing for system comparison
📦 PyPI Available: Install with a simple pip install RadEval

🏥 Advancing Radiology AI Research Community

We are committed to building a standardized and reproducible toolkit for researchers, clinicians, and developers dedicated to advancing AI evaluation in medical imaging and radiology. Together, we’re setting new standards for clinical AI assessment.

PyPI Package — Install RadEval with pip
HuggingFace Model — Access our domain-adapted evaluation model
Interactive Demo — Try RadEval online
Research Paper — Read our detailed research paper

🚀 EvoAgentX Released!

Fri, 16 May 2025 00:00:00 +0000

See what’s new on Github: EvoAgentX

⭐ Star it / 🍴 Fork it / 👀 Watch it 👆

🧠 If AI is entering its Second-Half, then AI agents must be Self-Evolving.

Imagine an AI system that doesn’t just execute predefined tasks, but continuously evolves on its own—adapting dynamically and optimizing itself in real-time, without constant human oversight. This vision is now a reality with EvoAgentX, a groundbreaking, open-source AI framework designed specifically for autonomous evolution.

🔗 An automated framework for evaluating and evolving agentic workflows.

📺 Workflow Generation Demo

🪧 Join Our Community!

We’re building a vibrant community of researchers, developers, and visionaries dedicated to exploring the limitless potential of self-evolving AI systems. Together, we’ll redefine what’s possible with AI.

Discord — Chat, discuss, and collaborate in real-time.
X (formerly Twitter) — Follow us for news, updates, and insights.
WeChat — Connect with our Chinese community.

🎉 Paper Accepted — See You at ACL 2025!

Thu, 15 May 2025 00:00:00 +0000

“Libra: Leveraging Temporal Images for Biomedical Radiology Analysis” has been accepted to ACL 2025!

Explore the critical role of temporal information in radiology diagnostics and how the Libra model applies it in detail at blog: Libra - Temporal Insight 🕰️.

Dive into how model architecture shapes temporal reasoning capabilities in radiology imaging analysis at blog: Libra – Structural Logic 🧠.

Look ahead to future directions in radiology AI, moving beyond temporal comparison at blog: Libra – What about next? 🛸.

📍 ACL 2025 — The 63rd Annual Meeting of the Association for Computational Linguistics will take place in Vienna, Austria, July 27–August 1st, 2025

See you there!

📺 Talk

🪧 Poster

🎤 Talk & Poster at HealTAC 2025!

Tue, 22 Apr 2025 00:00:00 +0000

We’re excited to share that we’ve been invited to present our recent research — “Towards Temporal-Aware Multimodal Large Language Models for Improved Radiology Report Generation” — as a lightning talk and poster presentation at the PhD Forum of HealTAC 2025!

📍 HealTAC 2025 — The 8th Healthcare Text Analytics Conference will take place in Glasgow, 16–18 June 2025.

See you there!

📍 See You at SICSA 2025!

Wed, 26 Mar 2025 00:00:00 +0000

🗓️ I’ll be attending the SICSA 2025 PhD Conference on 25–26 June at Edinburgh Napier University’s Craighlockhart Campus — two days of networking and researcher training with a focus on interdisciplinary collaboration.

Grateful to be supported by the University of Glasgow for this trip.

See you there!

🎉 Paper Accepted — See You at ACL 2024!

Sat, 20 Jul 2024 00:00:00 +0000

“Gla-AI4BioMed at RRG24: Visual Instruction-tuned Adaptation for Radiology Report Generation” has been accepted to BioNLP @ ACL 2024!

For detailed model information and source code, please visit our GitHub repository: RRG-BioNLP-ACL2024