Min Cai
About Blog Project CV ↗

Projects

  • REPL-based Long-context Reasoning

    Reproducing and extending Recursive Language Models (RLM) — offloading long contexts into a REPL — plus an iterative (ILM) and runtime-assisted DP-ILM variant. Evaluated on OOLONG, LongBench v2, and CodeQA with DeepSeek v3.2 and Kimi K2.

    🔒 WIP
    Jun 28, 2026
© 2026 Min Cai · GitHub · Google Scholar · ORCID · visit counter