works on

From the 1 of 7 linked papers with an AI index.

collaborators

7 papers

cs.LG2026

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

Mind Lab, :, Vin Bo +74

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

Beyond Isolation: Unlocking Reinforcement Learning Component Synergy for Sample-Efficient Continuous Control

Qi Zhao, Guozheng Ma, Yilun Kong +9

Reinforcement learning systems are significantly more complex than other machine learning paradigms due to inherent properties, causing RL system design to jointly account for many…

cs.LG2026

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

Changhai Zhou, Kieran Liu, Yuhua Zhou +17

LongStraw introduces an execution framework that enables reinforcement‑learning post‑training on million‑token prompts using a fixed GPU budget by separating prompt evaluation from…

cs.LG2026

Beyond One-Size-Fits-All: Diagnosis-Driven Online Reinforcement Learning with Offline Priors

Guozheng Ma, Lu Li, Zilin Wang +2

Online reinforcement learning (RL) agents increasingly depend on knowledge acquired offline to achieve practical efficiency. Originally studied in offline-to-online RL, this paradi…

cs.LG2026

MinT: Managed Infrastructure for Training and Serving Millions of LLMs

Mind Lab, :, Song Cao +60

We present MindLab Toolkit (MinT), a managed infrastructure system for Low-Rank Adaptation (LoRA) post-training and online serving. MinT targets a setting where many trained polici…

cs.LG2026

Rotation-Preserving Supervised Fine-Tuning

Hangzhan Jin, Tianwei Ni, Lu Li +3

Supervised fine-tuning (SFT) improves in-domain performance but can degrade out-of-domain (OOD) generalization. Prior work suggests that this degradation is related to changes in d…