activity
20242026
collaborators

5 papers

cs.LG2026

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

Mind Lab, :, Vin Bo +80

Macaron-V1 is an open agent-model family for experiential intelligence: learning from experience in real environments and continuing to learn after deployment. It is organized arou…

cs.LG2026

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

Mind Lab, :, Vin Bo +64

Parameter-efficient fine-tuning (PEFT) is usually treated as a cheaper alternative to full fine-tuning. We study a broader role: small trainable adapters as persistent local state…

cs.AI2026

SelfBudgeter: Adaptive Token Allocation for Efficient LLM Reasoning

Zheng Li, Qingxiu Dong, Jingyuan Ma +3

Recently, large reasoning models demonstrate exceptional performance on various tasks. However, reasoning models always consume excessive tokens even for simple queries, leading to…

cs.CL2025

Be a Multitude to Itself: A Prompt Evolution Framework for Red Teaming

Rui Li, Peiyi Wang, Jingyuan Ma +3

Large Language Models (LLMs) have gained increasing attention for their remarkable capacity, alongside concerns about safety arising from their potential to produce harmful content…

cs.CL2024

ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors

Zhexin Zhang, Yida Lu, Jingyuan Ma +8

The safety of Large Language Models (LLMs) has gained increasing attention in recent years, but there still lacks a comprehensive approach for detecting safety issues within LLMs'…