Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up
Mark's picture

Mark

Makrrr
2 13 4
·
https://makr-xie.github.io/

AI & ML interests

RL, Agent Memory, RAG

Recent Activity

upvoted a paper 11 days ago
MemComposer: Learning to Assemble Memories for LLM Agents via Reinforcement Learning
updated a collection 11 days ago
MemComposer
upvoted a paper 11 days ago
Retrieval is Cheap, Show Me the Code: Executable Multi-Hop Reasoning for Retrieval-Augmented Generation
View all activity

Organizations

University of Illinois at Urbana-Champaign's profile picture Tako AI's profile picture CL-From-Nothing's profile picture

Makrrr 's collections 1

MemComposer
Memory banks, training data and trained LoRA selectors for MemComposer (arXiv:2610.21091).
  • Makrrr/MemComposer

    Reinforcement Learning • Updated 12 days ago
  • Makrrr/MemComposer-data

    Viewer • Updated 12 days ago • 2.58k • 103
  • MemComposer: Learning to Assemble Memories for LLM Agents via Reinforcement Learning

    Paper • 2610.21091 • Published 20 days ago • 4
MemComposer
Memory banks, training data and trained LoRA selectors for MemComposer (arXiv:2610.21091).
  • Makrrr/MemComposer

    Reinforcement Learning • Updated 12 days ago
  • Makrrr/MemComposer-data

    Viewer • Updated 12 days ago • 2.58k • 103
  • MemComposer: Learning to Assemble Memories for LLM Agents via Reinforcement Learning

    Paper • 2610.21091 • Published 20 days ago • 4
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs