Mind Lab

company

https://macaron.im/mindlab

Macaron0fficial

MindLab-Research

mindlab-mindverse

AI & ML interests

agent model, recursive self-improvement, continual learning and collective intelligence.

Recent Activity

mindlab-bot new activity about 7 hours ago

mindlab-research/Macaron-V1-Coding-Venti:Fix eval results task IDs for unregistered benchmarks

mindlab-bot new activity about 7 hours ago

mindlab-research/Macaron-V1-Tall:Fix eval results task IDs for unregistered benchmarks

mindlab-bot new activity about 7 hours ago

mindlab-research/Macaron-V1-Venti:Fix eval results task IDs for unregistered benchmarks

View all activity

Papers

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA

LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget

View all Papers

mindlab-research 's papers 6

Submitted by

Andrew Chen

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA

mindlab-research

Submitted by

Xiaoteng Ma

LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget

mindlab-research

Submitted by

Andrew Chen

On the Scaling of PEFT: Towards Million Personal Models of Trillion Parameters

mindlab-research

4

Submitted by

Andrew Chen

Macaron-A2UI: A Model for Generative UI in Personal Agents

mindlab-research

5

Submitted by

Andrew Chen

MinT: Managed Infrastructure for Training and Serving Millions of LLMs

mindlab-research

Submitted by

taesiri

δ-mem: Efficient Online Memory for Large Language Models

mindlab-research