Dachuan Shi

28 papers A* 6B 1Misc 1Journal 17Unranked 3
YearRankTypeTitle / Venue / Authors
2026 J jnl
Behavior Knowledge Merge in Reinforced Agentic Models.
CoRR
Xiangchi Yuan, Dachuan Shi, Chunhui Zhang, Zheyuan Liu, Shenglong Yao, Soroush Vosoughi, Wenke Lee
2026 J jnl
Cognitive digital twins for capability matching toward reconfigurable manufacturing: Leveraging asset administration shells and large language models.
Robotics Comput. Integr. Manuf.
Dachuan Shi, Olga Meyer, Zhi Fan, Hao Wang, Thomas Bauernhansl
2026 J jnl
MetaState: Persistent Working Memory Enhances Reasoning in Discrete Diffusion Language Models.
CoRR
Kejing Xia, Mingzhe Li, Lixuan Wei, Zhenbang Du, Xiangchi Yuan, Dachuan Shi, Qirui Jin, Wenke Lee
2026 J jnl
Thinking in Uncertainty: Mitigating Hallucinations in MLRMs with Latent Entropy-Aware Decoding.
CoRR
Zhongxing Xu, Zhonghua Wang, Zhe Qian, Dachuan Shi, Feilong Tang, Ming Hu, Shiyan Su, Xiaocheng Zou, Wei Feng, Dwarikanath Mahapatra, Yifan Peng, Mingquan Lin, Zongyuan Ge
2025 J jnl
Dual data mapping with fine-tuned large language models and asset administration shells toward interoperable knowledge representation.
Robotics Comput. Integr. Manuf.
Dachuan Shi, Olga Meyer, Michael Oberle, Thomas Bauernhansl
2025 J jnl
Fine-tuning large language models with contrastive margin ranking loss for selective entity matching in product data integration.
Adv. Eng. Informatics
Qian Ruan, Dachuan Shi, Thomas Bauernhansl
2025 A* conf
LaCache: Ladder-Shaped KV Caching for Efficient Long-Context Modeling of Large Language Models.
ICML
Dachuan Shi, Yonggan Fu, Xiangchi Yuan, Zhongzhi Yu, Haoran You, Sixu Li, Xin Dong, Jan Kautz, Pavlo Molchanov, Yingyan Celine Lin
2025 J jnl
LaCache: Ladder-Shaped KV Caching for Efficient Long-Context Modeling of Large Language Models.
CoRR
Dachuan Shi, Yonggan Fu, Xiangchi Yuan, Zhongzhi Yu, Haoran You, Sixu Li, Xin Dong, Jan Kautz, Pavlo Molchanov, Yingyan Lin
2025 J jnl
Mitigating Forgetting Between Supervised and Reinforcement Learning Yields Stronger Reasoners.
CoRR
Xiangchi Yuan, Xiang Chen, Tong Yu, Dachuan Shi, Can Jin, Wenke Lee, Saayan Mitra
2025 A* conf
Superficial Self-Improved Reasoners Benefit from Model Merging.
EMNLP
Xiangchi Yuan, Chunhui Zhang, Zheyuan Liu, Dachuan Shi, Leyan Pan, Soroush Vosoughi, Wenke Lee
2025 J jnl
Superficial Self-Improved Reasoners Benefit from Model Merging.
CoRR
Xiangchi Yuan, Chunhui Zhang, Zheyuan Liu, Dachuan Shi, Soroush Vosoughi, Wenke Lee
2025 J jnl
SwiReasoning: Switch-Thinking in Latent and Explicit for Pareto-Superior Reasoning LLMs.
CoRR
Dachuan Shi, Abedelkadir Asi, Keying Li, Xiangchi Yuan, Leyan Pan, Wenke Lee, Wen Xiao
2024 A* conf
AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment.
NeurIPS
Yonggan Fu, Zhongzhi Yu, Junwei Li, Jiayi Qian, Yongan Zhang, Xiangchi Yuan, Dachuan Shi, Roman Yakunin, Yingyan (Celine) Lin
2024 J jnl
AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment.
CoRR
Yonggan Fu, Zhongzhi Yu, Junwei Li, Jiayi Qian, Yongan Zhang, Xiangchi Yuan, Dachuan Shi, Roman Yakunin, Yingyan Celine Lin
2024 A* conf
CrossGET: Cross-Guided Ensemble of Tokens for Accelerating Vision-Language Transformers.
ICML
Dachuan Shi, Chaofan Tao, Anyi Rao, Zhendong Yang, Chun Yuan, Jiaqi Wang
2023 — conf
Asset Adminstration Shell-based Flexible Manufacturing System.
ICPS
Zhi Fan, Dachuan Shi, Olga Meyer, Joachim Seidelmann, Hao Wang
2023 J jnl
CrossGET: Cross-Guided Ensemble of Tokens for Accelerating Vision-Language Transformers.
CoRR
Dachuan Shi, Chaofan Tao, Anyi Rao, Zhendong Yang, Chun Yuan, Jiaqi Wang
2023 A* conf
UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers.
ICML
Dachuan Shi, Chaofan Tao, Ying Jin, Zhendong Yang, Chun Yuan, Jiaqi Wang
2023 J jnl
UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers.
CoRR
Dachuan Shi, Chaofan Tao, Ying Jin, Zhendong Yang, Chun Yuan, Jiaqi Wang
2022 Misc conf
Heuristic Dropout: An Efficient Regularization Method for Medical Image Segmentation Models.
ICASSP
Dachuan Shi, Ruiyang Liu, Linmi Tao, Chun Yuan
2022 — conf
Masked Generative Distillation.
ECCV (11)
Zhendong Yang, Zhe Li, Mingqi Shao, Dachuan Shi, Zehuan Yuan, Chun Yuan
2022 J jnl
Masked Generative Distillation.
CoRR
Zhendong Yang, Zhe Li, Mingqi Shao, Dachuan Shi, Zehuan Yuan, Chun Yuan
2021 J jnl
Deep Learning based Virtual Point Tracking for Real-Time Target-less Dynamic Displacement Measurement in Railway Applications.
CoRR
Dachuan Shi, Eldar Sabanovic, Luca Rizzetto, Viktor Skrickij, Roberto Oliverio, Nadia Kaviani, Yunguang Ye, Gintautas Bureika, Stefano Ricci, Markus Hecht
2021 B conf
Multi-Encoder Parse-Decoder Network for Sequential Medical Image Segmentation.
ICIP
Dachuan Shi, Ruiyang Liu, Linmi Tao, Zuoxiang He, Li Huo
2021 A* conf
PTeacher: a Computer-Aided Personalized Pronunciation Training System with Exaggerated Audio-Visual Corrective Feedback.
CHI
Yaohua Bu, Tianyi Ma, Weijun Li, Hang Zhou, Jia Jia, Shengqi Chen, Kaiyuan Xu, Dachuan Shi, Haozhe Wu, Zhihan Yang, Kun Li, Zhiyong Wu, Yuanchun Shi, Xiaobo Lu, Ziwei Liu
2021 J jnl
PTeacher: a Computer-Aided Personalized Pronunciation Training System with Exaggerated Audio-Visual Corrective Feedback.
CoRR
Yaohua Bu, Tianyi Ma, Weijun Li, Hang Zhou, Jia Jia, Shengqi Chen, Kaiyuan Xu, Dachuan Shi, Haozhe Wu, Zhihan Yang, Kun Li, Zhiyong Wu, Yuanchun Shi, Xiaobo Lu, Ziwei Liu
2021 J jnl
Visual Measurement System for Wheel-Rail Lateral Position Evaluation.
Sensors
Viktor Skrickij, Eldar Sabanovic, Dachuan Shi, Stefano Ricci, Luca Rizzetto, Gintautas Bureika
2020 — conf
Empirical Study on Robustness of Machine Learning Approaches for Fault Diagnosis under Railway Operational Conditions.
ITSC
Dachuan Shi, Yunguang Ye, Marco Gillwald, Markus Hecht