CX Research Group

About

CX Research Group focuses on foundation and large language models.

Led by Professor Chenyan Xiong at the Language Technologies Institute, Carnegie Mellon University. Our recent work focuses on improving the speed–quality trade-offs in pretraining, exploring new scaling frontiers, and enabling new capabilities for next-generation GenAI applications.

Members of the CX Research Group, photographed in front of the Fence at Carnegie Mellon University, April 2024.
The group, taken April 2024 in front of the Fence @ CMU.

Research areas

Our research spans three directions.

Foundation Model Science
  • Advancing the Pareto frontier of scaling laws (speed–quality) through data-centric strategies, new architectures, and model–infrastructure co-design.
  • Exploring scaling frontiers with synthetic data, innovative training methods, and feedback-driven learning.
  • Developing foundation models with new capabilities for emerging applications in multimodality, vision–language–action, and model-as-agents.
GenAI-Native Information Retrieval
  • Building agentic search and recommendation systems leveraging the new capabilities of foundation models.
  • Exploring the ecosystem of the agentic web, including new organization of the digital world, new economic models, and fair revenue sharing.
  • Supporting community research on agentic information systems with retrieval and large-scale training infrastructures.
New GenAI-Enabled Scenarios
  • Designing healthcare foundation models to support clinical applications.
  • Developing new context learning paradigms for agent and test-time scaling.
  • Adapting foundation models to verticals such as finance, robotics, and sports.

Recent publications

See all →
  1. 2025

    Craw4LLM: Efficient Web Crawling for LLM Pretraining

    ACL 2025 (Findings)

  2. 2025

    Aligning Web Query Generation with Ranking Objectives via Direct Preference Optimization

    Association for Computing Machinery, Inc.

  3. 2025

    Intercept Cancer: Cancer Pre-Screening with Large Scale Healthcare Foundation Models

    arXiv preprint

  4. 2025

    FLAME-MoE: A Transparent End-to-End Research Platform for Mixture-of-Experts Language Models

    arXiv

  5. 2025

    Fact-Aware Multimodal Retrieval Augmentation for Accurate Medical Radiology Report Generation

    Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL)