5 citations · 5 across the 2 of their papers we have counts for
7 papers · 1 filter
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…
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…
LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget
Changhai Zhou, Kieran Liu, Yuhua Zhou +17
Long-context RL post-training is constrained by the lifetime of state and gradients, not attention cost alone. In GRPO, one multi-million-token prompt must serve old-policy and ref…
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…
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…
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…