DARE-bench: Evaluating Modeling and Instruction Fidelity of LLMs in Data Science
Published in ICLR 2026
Fan Shu†, Yite Wang†, Ruofan Wu, Boyi Liu, Zhewei Yao, Yuxiong He, and Feng Yan.
Publications
† denotes equal contribution.
Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning
Published in arXiv preprint, 2026
Zhaoyang Wang, Canwen Xu, Boyi Liu, Yite Wang, Siwei Han, Zhewei Yao, Huaxiu Yao, and Yuxiong He.
Designing Large Foundation Models for Efficient Training and Inference: A Survey
Published in arXiv preprint, 2024
Dong Liu, Yanxuan Yu, Yite Wang, Jing Wu, Zhongwei Wan, Sina Alinejad, Benjamin Lengerich, and Ying Nian Wu.
Fullstack bench: Evaluating LLMs as full stack coder
Published in arXiv preprint, 2024
Seed-Foundation-Code Team, ByteDance.
LEMON: Lossless model expansion
Published in ICLR 2024, 2023
Yite Wang, Jiahao Su, Hanlin Lu, Cong Xie, Tianyi Liu, Jianbo Yuan, Haibin Lin, Ruoyu Sun, and Hongxia Yang.
NTK-SAP: Improving neural network pruning by aligning training dynamics
Published in ICLR 2023
Yite Wang, Dawei Li, and Ruoyu Sun.
Balanced Training for Sparse GANs
Published in NeurIPS 2023
Yite Wang†, Jing Wu†, Naira Hovakimyan, and Ruoyu Sun.
Global Convergence of MAML and Theory-Inspired Neural Architecture Search for Few-Shot Learning
Published in CVPR 2022
Haoxiang Wang†, Yite Wang†, Ruoyu Sun, and Bo Li.
Numerical investigation of convective transport in redox flow battery tanks: Using baffles to increase utilization
Published in Journal of Energy Storage, 2019
Yite Wang and Kyle Smith.