5 papers
CrystalDiT: A Diffusion Transformer for Crystal Generation
Xiaohan Yi, Guikun Xu, Xi Xiao +4
We present CrystalDiT, a diffusion transformer for crystal structure generation that achieves state-of-the-art performance by challenging the trend of architectural complexity. Ins…
Multi-Task Vehicle Routing Solver via Mixture of Specialized Experts under State-Decomposable MDP
Yuxin Pan, Zhiguang Cao, Chengyang Gu +4
Existing neural methods for multi-task vehicle routing problems (VRPs) typically learn unified solvers to handle multiple constraints simultaneously. However, they often underutili…
Principled Data Selection for Alignment: The Hidden Risks of Difficult Examples
Chengqian Gao, Haonan Li, Liu Liu +3
The alignment of large language models (LLMs) often assumes that using more clean data yields better outcomes, overlooking the match between model capacity and example difficulty.…
Injecting Imbalance Sensitivity for Multi-Task Learning
Zhipeng Zhou, Liu Liu, Peilin Zhao +1
Multi-task learning (MTL) has emerged as a promising approach for deploying deep learning models in real-life applications. Recent studies have proposed optimization-based learning…
HDT: Hierarchical Discrete Transformer for Multivariate Time Series Forecasting
Shibo Feng, Peilin Zhao, Liu Liu +2
Generative models have gained significant attention in multivariate time series forecasting (MTS), particularly due to their ability to generate high-fidelity samples. Forecasting…