1. X
  2. Maojun SUN
EntraRegistra't
Maojun SUN
13 posts
user avatar
Maojun SUN
@Stephen_MJSUN
AI Researcher & Developer PhD Student@HK PolyU
Hong Kong
stephen-smj.tech
Data d'incorporació: July 2024
35
Seguint
6
Seguidors
RespostesRespostesContingutsContinguts

Log in or sign up for X

See what’s happening and join the conversation

Continue with phone
or
Log in with username or email
Terms·Privacy·Cookies·Accessibilitat·Ads Info·© 2026 X Corp.
  • user avatar
    Maojun SUN
    @Stephen_MJSUN
    1 d’abr.
    Introducing open-cc — an open-source terminal AI coding assistant. ▌ OpenAI-compatible. One-line install. Built with React + Ink. Ships with 6 tools (Read, Edit, Bash, Glob, Grep, Write). ▌ curl -fsSL raw.githubusercontent.com/Stephen-SMJ/op… | bash ⭐️ on GitHub: github.com/Stephen-SMJ/op…
    136
  • user avatar
    Maojun SUN
    @Stephen_MJSUN
    6 de març
    Out DARE is online! We introduce DARE, an embedding model for improving LLM Agents on R package retrieval and downstream statistical analysis tasks. Paper: arxiv.org/abs/2603.04743 Website: ama-cmfai.github.io/DARE_webpage/
    79
  • user avatar
    Maojun SUN
    @Stephen_MJSUN
    6 de març
    arxiv.org/abs/2603.04743 Out DARE is online! We introduce DARE, an embedding model for Improving LLM Agents on R package retrieval and down stream statistical analysis ttask. We achieve 93.47% NDCG@10 and outperform strong open-source embeddings models.
    arXiv logo
    arxiv.org
    DARE: Aligning LLM Agents with the R Statistical Ecosystem via...
    Large Language Model (LLM) agents can automate data-science workflows, but many rigorous statistical methods implemented in R remain underused because LLMs struggle with statistical knowledge and...
    62
  • user avatar
    Maojun SUN
    @Stephen_MJSUN
    22 de gen.
    Excited to share our new benchmark: DSAEval (Data Science Agent Evaluation), a comprehensive benchmark designed for evaluating LLM-driven data science agents on real-world tasks. 📄 Paper: arxiv.org/pdf/2601.13591 🌐 Homepage: dsaeval.github.io/DSAEval/ #AI #LLM #AgenticAI
    80
  • user avatar
    Maojun SUN
    @Stephen_MJSUN
    27 de jul. del 2024
    This is our recent work. Welcome to discuss with us.
    user avatar
    AK
    @_akhaliq
    26 de jul. del 2024
    LAMBDA A Large Model Based Data Agent We introduce ``LAMBDA," a novel open-source, code-free multi-agent data analysis system that that harnesses the power of large models. LAMBDA is designed to address data analysis challenges in complex data-driven applications through the
    134