CAMERA: Multi-Matrix Joint Compression for MoE Models via Micro-Expert Redundancy Analysis

arXiv preprint arXiv:2508.02322, 2025.

Xu, Yuzhuang and Han, Xu and Zhang, Yuanchi and Wang, Yixuan and Liu, Yijun and Ji, Shiyu and Zhu, Qingfu and Che, Wanxiang

CAMERA: Multi-Matrix Joint Compression for MoE Models via Micro-Expert Redundancy Analysis

arXiv preprint arXiv:2508.02322, 2025.

Xu, Yuzhuang and Han, Xu and Zhang, Yuanchi and Wang, Yixuan and Liu, Yijun and Ji, Shiyu and Zhu, Qingfu and Che, Wanxiang

Judge Q: Trainable Queries for Optimized Information Retention in KV Cache Eviction

arXiv preprint arXiv:2509.10798, 2025.

Liu, Yijun and Wang, Yixuan and Xu, Yuzhuang and Ji, Shiyu and Xu, Yang and Zhu, Qingfu and Che, Wanxiang

Judge Q: Trainable Queries for Optimized Information Retention in KV Cache Eviction

arXiv preprint arXiv:2509.10798, 2025.

Liu, Yijun and Wang, Yixuan and Xu, Yuzhuang and Ji, Shiyu and Xu, Yang and Zhu, Qingfu and Che, Wanxiang

Lookahead Q-Cache: Achieving More Consistent KV Cache Eviction via Pseudo Query

Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 34146--34162, 2025.

Wang, Yixuan and Ji, Shiyu and Liu, Yijun and Xu, Yuzhuang and Xu, Yang and Zhu, Qingfu and Che, Wanxiang

Lookahead Q-Cache: Achieving More Consistent KV Cache Eviction via Pseudo Query

Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 34146--34162, 2025.

Wang, Yixuan and Ji, Shiyu and Liu, Yijun and Xu, Yuzhuang and Xu, Yang and Zhu, Qingfu and Che, Wanxiang

Improving Grammatical Error Correction via Contextual Data Augmentation

Findings of the Association for Computational Linguistics: ACL 2024, 10898--10910, 2024.

Wang, Yixuan and Wang, Baoxin and Liu, Yijun and Zhu, Qingfu and Wu, Dayong and Che, Wanxiang

Improving Grammatical Error Correction via Contextual Data Augmentation

Findings of the Association for Computational Linguistics: ACL 2024, 10898--10910, 2024.

Wang, Yixuan and Wang, Baoxin and Liu, Yijun and Zhu, Qingfu and Wu, Dayong and Che, Wanxiang

LM-Combiner: A Contextual Rewriting Model for Chinese Grammatical Error Correction

Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), 10675--10685, 2024.

Wang, Yixuan and Wang, Baoxin and Liu, Yijun and Wu, Dayong and Che, Wanxiang

LM-Combiner: A Contextual Rewriting Model for Chinese Grammatical Error Correction

Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), 10675--10685, 2024.

Wang, Yixuan and Wang, Baoxin and Liu, Yijun and Wu, Dayong and Che, Wanxiang

Make Some Noise: Unlocking Language Model Parallel Inference Capability through Noisy Training

Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 12914--12926, 2024.

Wang, Yixuan and Luo, Xianzhen and Wei, Fuxuan and Liu, Yijun and Zhu, Qingfu and Zhang, Xuanyu and Yang, Qing and Xu, Dongliang and Che, Wanxiang

Make Some Noise: Unlocking Language Model Parallel Inference Capability through Noisy Training

Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 12914--12926, 2024.

Wang, Yixuan and Luo, Xianzhen and Wei, Fuxuan and Liu, Yijun and Zhu, Qingfu and Zhang, Xuanyu and Yang, Qing and Xu, Dongliang and Che, Wanxiang