
Research Scientist @GoogleDeepMind | Prev: CS PhD @EmoryUniversity | Gemini Agentic Post-training | CyberSecurity
Mountain View, CA
Joined September 2022
- Tweets58
- Following318
- Followers741
- Likes74
Wonder is here, and it's looking Wonder Full! 🍉
We've worked hard to push its intelligence and real-world usefulness, especially for coding, agentic and personal superintelligence.
Proud to be part of this journey. More wonders ahead!
Ran Xu retweeted
Today, we announced Gemini 4 Argon, our next generation model and a cybersecurity powerhouse equipping defenders for the next era of cyberattack.
On the Gray Swan IPI Benchmark, Gemini 4 Argon leads in prompt injection robustness. @GoogleDeepMind
Ran Xu retweeted
Today we’re launching Gemini 3.8 Flash Cyber and Gemini 3.8 Flash. ⚡️🛡️
3.8 Flash Cyber is our most capable cybersecurity model for finding and fixing vulnerabilities. It sits on the Pareto Frontier on CWE-Bench for patching. Available to trusted defenders through our new Fairwind Program.
Ran Xu retweeted
Introducing Gemini 3.8 Flash, another upgrade in under a month! And the new 3.8 Flash Cyber pushes the frontier of cyber defense. Relentless progress 🚀 More on the models & our cyber security work in the blog - happy building! blog.google/innovation-and-a…
Ran Xu retweeted
Excited to announce Gemini 3.8 Flash and 3.8 Flash Cyber @google blog.google/innovation-and-a…
Our cyber model has frontier capabilities being competitive on finding and patching benchmarks with much larger models, at a cheaper cost.
@GoogleDeepMind
Muse Spark 1.2 and MuseCode are out—less than a month after Muse Spark 1.1! 🚀
Excited to join the journey and see the pace of progress. Give it a try and let us know what you build!
curl -fsS dev.meta.ai/install.sh | bash
muse code in beta is live. first coding agent from msl, built on muse spark 1.2.
install: curl -fsS dev.meta.ai/install.sh | bash
here's what you should know:
Muse Spark 1.1 🥑 is out! with lot of improvements on agents / reasoning / coding.
Scaling RL has been tiring, rewarding, and full of lessons.
Try it on dev.meta.ai and please send feedback + failure cases. They help make the model better.
More to come!
Ran Xu retweeted
This Monday, Wenqi Shi from UT Southwestern Medical Center will be joining us to talk about their work on training LLM agents for code-based medical reasoning at scale. Catch it at 1-2pm PT this Monday on Zoom! Subscribe to mailman.stanford.edu/mailman… #ML #AI #medicine #healthcare
Ran Xu retweeted
🤔 How can we systematically enhance LLMs for complex medical coding tasks?
🚀 Introducing MedAgentGym, an interactive gym-style platform designed specifically for training LLM agents in coding-based medical reasoning! 🧬💻
🎯 Comprehensive Code-based Medical Reasoning Benchmark:
- 📌 72,000+ coding tasks across 129 diverse categories
- 🌐 12 authentic, real-world biomedical scenarios
- 🛠️ Supports structured and open-ended coding challenges
⚙️ Robust & Scalable Infrastructure:
- 🚧 Task-specific Docker environments for isolated, reproducible execution
- 🚦 Multi-threaded, parallel execution and sequential sampling
- 📊 Efficient trajectory collection tailored for diverse agent training
🔗 Explore more:
📖 Paper: arxiv.org/abs/2506.04405
📚 Doc: wshi83.github.io/MedAgentGym…
💻 Code: github.com/wshi83/MedAgentGy…
🤗 Model & Data: huggingface.co/MedAgentGym
#AI #MachineLearning #Bioinformatics #MedicalAI #LLM #DeepLearning #HealthTech #OpenSource #Healthcare #DataScience #MedTech #NLP #GenerativeAI #Coding #Benchmark
Ran Xu retweeted
🔍 Reward modeling is a reasoning task—can self-generated CoT-style critiques help?
🚀 Check out my intern work at Llama Team @AIatMeta, 3.7-7.3% gains on RewardBench vs. RM & LLM judge baselines, with better generalization & data efficiency!
arxiv.org/abs/2411.16646
#rlhf #LLM
Ran Xu retweeted
After going through 100s of AI papers in the past couple of weeks, I am noticing the deeper integration of ideas (e.g., Mixture of Million Experts and Internet of Agents) and the utility of simple yet very effective methods (e.g., RouteLLM and RankRAG).
If you are looking for some weekend reads, here are a few notable AI papers I read this week:
- RankRAG: introduces a new instruction fine-tuning framework to perform effective context ranking and answering generation to enhance an LLM’s RAG capabilities. It leverages a small ranking dataset to outperform existing expert ranking models. Shows that a Llama3-RankRAG significantly outperforms Llama3-ChatQA-1.5 and GPT-4 models on nine knowledge-intensive benchmarks. arxiv.org/abs/2407.02485v1
- Mixture of A Million Experts: introduces a parameter-efficient expert retrieval mechanism that leverages the product key technique for sparse retrieval from a million tiny experts. It attempts to decouple computational cost from parameter count by efficiently routing to a very large number of tiny experts through a learned index structure used for routing. arxiv.org/abs/2407.04153
- Contextual Hallucinations Mitigation in LLMs: proposes a new method that detects and significantly reduces contextual hallucinations in LLMs (e.g., reduces by 10% in the XSum summarization task). Builds a hallucination detection model based on input features given by the ratio of attention weights on the context vs. newly generated tokens (for each attention head). The hypothesis is that contextual hallucinations are related to the extent to which an LLM attends to the provided contextual information. arxiv.org/abs/2407.07071
- RouteLLM: proposes efficient router models to dynamically select between stronger and weak LLMs during inference to achieve a balance between cost and performance. The training framework leverages human preference data and data augmentation techniques to boost performance. Shows to significantly reduce costs by over 2x in certain cases while maintaining the quality of responses. arxiv.org/abs/2406.18665v2
- Internet of Agents: a new framework to address several limitations in multi-agent frameworks such as integrating diverse third-party agents and adaptability to dynamic task requirements. Introduces an agent integration protocol, instant messaging architecture design, and dynamic mechanisms for effective collaboration among heterogeneous agents. arxiv.org/abs/2407.07061v2
There are a few more exciting papers that I will be highlighting tomorrow in the Top ML Papers of the Week @dair_ai. Stay tuned!
Ran Xu retweeted
Introducing RankRAG, a novel RAG framework that instruction-tunes a single LLM for the dual purposes of top-k context ranking and answer generation in RAG.
For context ranking, it performs exceptionally well by incorporating a small fraction of ranking data into the training blend, surpassing existing expert ranking models, including the same LLM exclusively fine-tuned on a large amount of ranking data.
For retrieval-augmented generation, the RankRAG models significantly outperform GPT-4-0613, GPT-4-turbo-2024-0409, and ChatQA-1.5 on nine knowledge-intensive benchmarks. It has also demonstrated superb capability for generalization to new domains, such as biomedical tasks.
Paper: arxiv.org/abs/2407.02485
Model weights: will be released later.
Ran Xu retweeted
🤖 Introducing EHRAgent: Tackling Complex Multi-Tabular Reasoning on Electronic Health Records just got smarter with #EHRAgent!
✨👩🔬 We propose EHRAgent, an LLM agent 🧠 empowered with a code interface 💻, to autonomously generate and execute code 🔄 for complex clinical tasks within EHRs 📈🏥. (1/N)
🔗 Explore our work:
📄 paper: arxiv.org/abs/2401.07128
💻 code: github.com/wshi83/EhrAgent
#MedicalAI #HealthcareTech #EHR #Agent #LLM 🌐💊🔬🩺
Ran Xu retweeted
#AcademicJobs #FacultyHiring Emory University's CS Department seeks passionate and innovative individuals to join our faculty team! We're inviting applications for positions at all ranks. Retweet appreciated!
Discover more about the application process: cra.org/job/emory-university…
Ran Xu retweeted
🚀 Checkout our new preprint!
🔍 LLM-as-training-data-generator is a recent paradigm for zero-shot learning. We design attributed prompts to generate diverse training data from #LLMs automatically. 1/n
Link: arxiv.org/abs/2306.15895
Code: shorturl.at/amBV8
Ran Xu retweeted
Excited to share that our work received an outstanding paper award at ML4H 2022. This was spearheaded by Emory CSI PhD student Ran Xu and GT PhD student Yue Yu and includes collaborations with @chaozhangcs, @yangji9181, and @mkali_twindad.






































