6 papers
LazyTrain: Limited-resource Allocation toward Zero-waste Yield Optimization in Large Language Model Training
Xiaojun Wu, Cehao Yang, Honghao Liu +5
Training large language models on limited hardware is increasingly a scheduling problem across GPU compute, host memory, PCIe transfer, and storage bandwidth. Existing offloading s…
Bayesian-Agent: Posterior-Guided Skill Evolution Across LLM Agent Harnesses
Xiaojun Wu, Cehao Yang, Honghao Liu +7
LLM agents increasingly rely on prompts, tools, memory, SOPs, skills, and harness feedback, yet current self-evolution pipelines often update these assets through heuristic reflect…
Conflicts Make Large Reasoning Models Vulnerable to Attacks
Honghao Liu, Chengjin Xu, Xuhui Jiang +5
Large Reasoning Models (LRMs) have achieved remarkable performance across diverse domains, yet their decision-making under conflicting objectives remains insufficiently understood.…
Continual Pretraining on Encrypted Synthetic Data for Privacy-Preserving LLMs
Honghao Liu, Xuhui Jiang, Chengjin Xu +4
Preserving privacy in sensitive data while pretraining large language models on small, domain-specific corpora presents a significant challenge. In this work, we take an explorator…
Select2Reason: Efficient Instruction-Tuning Data Selection for Long-CoT Reasoning
Cehao Yang, Xueyuan Lin, Xiaojun Wu +5
A practical approach to activate long chain-of-thoughts reasoning ability in pre-trained large language models is to perform supervised fine-tuning on instruction datasets synthesi…
A Survey on LLM-as-a-Judge
Jiawei Gu, Xuhui Jiang, Zhichao Shi +13
Accurate and consistent evaluation is crucial for decision-making across numerous fields, yet it remains a challenging task due to inherent subjectivity, variability, and scale. La…