7 papers
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…
ChestX-Reasoner: Advancing Radiology Foundation Models with Reasoning through Step-by-Step Verification
Ziqing Fan, Cheng Liang, Chaoyi Wu +3
Recent advances in reasoning-enhanced large language models (LLMs) and multimodal LLMs (MLLMs) have significantly improved performance in complex tasks, yet medical AI models often…
Combatting Dimensional Collapse in LLM Pre-Training Data via Diversified File Selection
Ziqing Fan, Siyuan Du, Shengchao Hu +5
Selecting high-quality pre-training data for large language models (LLMs) is crucial for enhancing their overall performance under limited computation budget, improving both traini…
Continual Task Learning through Adaptive Policy Self-Composition
Shengchao Hu, Yuhang Zhou, Ziqing Fan +4
Training a generalizable agent to continually learn a sequence of tasks from offline trajectories is a natural requirement for long-lived agents, yet remains a significant challeng…
Prompt Tuning with Diffusion for Few-Shot Pre-trained Policy Generalization
Shengchao Hu, Wanru Zhao, Weixiong Lin +3
Offline reinforcement learning (RL) methods harness previous experiences to derive an optimal policy, forming the foundation for pre-trained large-scale models (PLMs). When encount…
Task-Aware Harmony Multi-Task Decision Transformer for Offline Reinforcement Learning
Ziqing Fan, Shengchao Hu, Yuhang Zhou +4
The purpose of offline multi-task reinforcement learning (MTRL) is to develop a unified policy applicable to diverse tasks without the need for online environmental interaction. Re…