This is LCM-Lab, an open-source research team within the OpenNLG Group that focuses on long sequence modeling and optimization. Below is a list of our work—please feel free to explore!
If you have any questions about the code or paper details, please don’t hesitate to open an issue or contact this email zecheng.tang@foxmail.com.
-
LongRM: Pushing the limits of reward modeling beyond 128K tokens
Zecheng Tang, Baibei Ji, Quantong Qiu, Haitian Wang, Xiaobo Liang, Juntao Li, Min Zhang.
-
MemoryRewardBench (EMNLP 2026): Benchmarking Reward Models for Long-Term Memory Management in Large Language Models
Zecheng Tang, Baibei Ji, Ruoxi Sun, Haitian Wang, WangJie You, Zhang Yijun, Wenpeng Zhu, Ji Qi, Juntao Li, Min Zhang.
-
LOOM-Eval: A comprehensive and efficient framework for long-context model evaluation
Zecheng Tang, Haitian Wang, Quantong Qiu, Baibei Ji, Ruoxi Sun, Keyan Zhou, Juntao Li, Min Zhang .
-
L-CiteEval (ACL 2025): A faithfulness-oriented benchmark for long-context citation
Zecheng Tang, Keyan Zhou, Juntao Li, Baibei Ji, Jianye Hou, Min Zhang.
-
MMLongCite: A Benchmark for Evaluating Fidelity of Long-Context Vision-Language Models
Keyan Zhou, Zecheng Tang, Lingfeng Ming, Guanghao Zhou, Qiguang Chen, Dan Qiao, Zheming Yang, Libo Qin, Minghui Qiu, Juntao Li, Min Zhang.
-
Elastic Attention: Test-time Adaptive Sparsity Ratios for Efficient Transformers
Zecheng Tang, Quantong Qiu, Yi Yang, Zhiyi Hong, Haiya Xiang, Kebin Liu, Qingqing Dang, Juntao Li, Min Zhang.
-
CDT (ICLR 2026): Context Denoising Training for Long-Context Modeling
Zecheng Tang, Baibei Ji, Juntao Li, Lijun Wu, Haijia Gui, Min Zhang.
-
LOGO (ICML 2025): Long cOntext aliGnment via efficient preference Optimization
Zecheng Tang, Zechen Sun, Juntao Li, Qiaoming Zhu, Min Zhang.
-
Global-Mamba (ACL 2025): Efficient long-context modeling architecture
Wangjie You, Zecheng Tang, Juntao Li, Lili Yao, Min Zhang.
