7 papers
Towards Efficient LLMs Annealing with Principled Sample Selection
Yuanjian Xu, Jianing Hao, Wanbo Zhang +2
The annealing phase is a pivotal convergence stage in LLM pre-training that ultimately determines final model quality. However, effectively selecting training data during this phas…
D: Dynamic Directional Graph-Constrained Data Scheduling for LLM Training
Yuanjian Xu, Jianing Hao, Guang Zhang +1
Training data plays a central role in large language models (LLMs) optimization, motivating extensive research on data scheduling strategies. Most existing approaches concentrate o…
BizCompass: Benchmarking the Reasoning Capabilities of LLMs in Business Knowledge and Applications
Jianing Hao, Yuhe Wu, Yuanjian Xu +5
Large language models (LLMs) hold great promise for business applications, yet business analysis remains inherently complex, demanding rigorous reasoning and the integration of div…
Rethinking Data Mixing from the Perspective of Large Language Models
Yuanjian Xu, Tianze Sun, Changwei Xu +7
Data mixing strategy is essential for large language model (LLM) training. Empirical evidence shows that inappropriate strategies can significantly reduce generalization. Although…
HGAN-SDEs: Learning Neural Stochastic Differential Equations with Hermite-Guided Adversarial Training
Yuanjian Xu, Yuan Shuai, Jianing Hao +1
Neural Stochastic Differential Equations (Neural SDEs) provide a principled framework for modeling continuous-time stochastic processes and have been widely adopted in fields rangi…
Game-Theoretic Lens on LLM-based Multi-Agent Systems
Jianing Hao, Han Ding, Yuanjian Xu +5
Large language models (LLMs) have demonstrated strong reasoning, planning, and communication abilities, enabling them to operate as autonomous agents in open environments. While si…