#DuanYu
「📸 | O drama #GoBackLover, estrelado por #LiYunrui, #XuRuohan, #RenShihao, #WangYijin, #XiaHaoran, #DuanYu, #LiuHaikuan e #XuShixin atingiu 300.000 de reservas antes da sua estreia na WeTV e YOUKU 💕
October 8, 2024 at 3:42 AM
「📸 | O drama moderno #GoBackLover, liberou novo pôster do casal secundário com #DuanYu e #XiaHaoran antes da estreia em 08 de Outubro na WeTV/ Tencent 💛

—Love é um guarda-chuva inclinado que resiste ao vento e à chuva e dá origem ao romance.
October 5, 2024 at 2:45 AM
March 2, 2026 at 4:01 AM
Youcheng Huang, Chen Huang, Duanyu Feng, Wenqiang Lei, Jiancheng Lv
Cross-model Transferability among Large Language Models on the Platonic Representations of Concepts
https://arxiv.org/abs/2501.02009
January 7, 2025 at 10:46 AM
「📸 | O drama moderno #GoBackLover, estrelado por #LiYunrui, #XuRuohan, #RenShihao, #WangYijin, #XiaHaoran, #DuanYu, #LiuHaikuan e #XuShixin liberou novo pôster ❤️
October 22, 2024 at 2:05 AM
An on-chip programmable mechano-quantum transducer
https://arxiv.org/pdf/2607.21487
Xinrui Zhang, Wei Liu, Duanyu Ma, Lin-Ke Xie, Nai-Jie Guo, Zhongtao Gou, Yifan Wang, Jianxin Xu, Xiaoguang Luo, Zhao Mu, Honglong Chang, Weizheng Yuan, Jian-Shun Tang, Chuan-Feng Li, Guangcan Guo, Tao Ye.
https://arxiv.org/abs/2607.21487
arXiv abstract link
arxiv.org
July 24, 2026 at 4:12 AM
MicroEvoEval: A Systematic Evaluation Framework for Image-Based Microstructure Evolution Prediction
https://arxiv.org/pdf/2511.08955
Qinyi Zhang, Duanyu Feng, Ronghui Han, Yangshuai Wang, Hao Wang.
https://arxiv.org/abs/2511.08955
arXiv abstract link
arxiv.org
November 13, 2025 at 6:19 AM
Shuai Li, Chen Huang, Duanyu Feng, Wenqiang Lei, See-Kiong Ng: STAR: Semantic-Tuned and Tail-Adaptive Retriever for Graph-Augmented Generation https://arxiv.org/abs/2605.18765 https://arxiv.org/pdf/2605.18765 https://arxiv.org/html/2605.18765
May 20, 2026 at 6:41 AM
Li Ding, Duanyu Feng, Chen Huang, Yangshuai Wang, Yang Li, Wenqiang Lei, See-Kiong Ng: Unlocking Biological Workflows for Robust Protein-Text Question Answering: A Dual-Dimensional RAG Framework https://arxiv.org/abs/2605.17261 https://arxiv.org/pdf/2605.17261 https://arxiv.org/html/2605.17261
May 19, 2026 at 6:43 AM
Duanyu Chen, Xiangxin Liu, Lisa Hui Sun: Double-sum Rogers-Ramanujan type identities https://arxiv.org/abs/2605.06248 https://arxiv.org/pdf/2605.06248 https://arxiv.org/html/2605.06248
May 8, 2026 at 6:47 AM
STAR: Semantic-Tuned and Tail-Adaptive Retriever for Graph-Augmented Generation
tech_blogs_arxiv | Author: Shuai Li, Chen Huang, Duanyu Feng, Wenqiang Lei, See-Kiong Ng
STAR: Semantic-Tuned and Tail-Adaptive Retriever for Graph-Augmented Generation
To augment Large Language Models (LLMs) for multi-hop question answering, a mainstream solution within Graph Retrieval Augmented Generation (GraphRAG) leverages lightweight retrievers to efficiently extract information from a given Knowledge Graph (KG). However, existing methods often overlook th...
arxiv.org
May 20, 2026 at 4:01 AM
DRfold2 is a deep learning-based tool that enables efficient and accurate RNA structure prediction @PLOSBiology.org
DRfold2 is a deep learning-based tool that enables efficient and accurate RNA structure prediction
by Yang Li, Chenjie Feng, Xi Zhang, Sho Tsukiyama, Duanyu Feng, Yang Zhang RNA structures are essential for understanding their biological functions and developing RNA-targeted therapeutics. However, accurate RNA structure prediction from sequence remains a crucial challenge. We introduce DRfold2, a deep learning framework that integrates a novel pre-trained RNA Composite Language Model (RCLM) with a denoising structure module for end-to-end RNA structure prediction. Based solely on single sequence, DRfold2 achieves superior performance in both global topology and secondary structure predictions over other state-of-the-art approaches across multiple benchmark tests from diverse species. Detailed analyses reveal that the improvements primarily stem from the RCLM’s ability to capture co-evolutionary pattern and the effective denoising process, with a more than 100% increase in contact prediction precision compared to existing methods. Furthermore, DRfold2 demonstrates high complementarity with AlphaFold3, achieving statistically significant accuracy gains when integrated into our optimization framework. By uniquely combining composite language modeling, denoising-based end-to-end learning, and deep learning-guided post-optimization, DRfold2 establishes a distinct direction for advancing ab initio RNA structure prediction.
dlvr.it
February 26, 2026 at 6:53 PM
DRfold2 is a deep learning-based tool that enables efficient and accurate RNA structure prediction @PLOSBiology.org
DRfold2 is a deep learning-based tool that enables efficient and accurate RNA structure prediction
by Yang Li, Chenjie Feng, Xi Zhang, Sho Tsukiyama, Duanyu Feng, Yang Zhang RNA structures are essential for understanding their biological functions and developing RNA-targeted therapeutics. However, accurate RNA structure prediction from sequence remains a crucial challenge. We introduce DRfold2, a deep learning framework that integrates a novel pre-trained RNA Composite Language Model (RCLM) with a denoising structure module for end-to-end RNA structure prediction. Based solely on single sequence, DRfold2 achieves superior performance in both global topology and secondary structure predictions over other state-of-the-art approaches across multiple benchmark tests from diverse species. Detailed analyses reveal that the improvements primarily stem from the RCLM’s ability to capture co-evolutionary pattern and the effective denoising process, with a more than 100% increase in contact prediction precision compared to existing methods. Furthermore, DRfold2 demonstrates high complementarity with AlphaFold3, achieving statistically significant accuracy gains when integrated into our optimization framework. By uniquely combining composite language modeling, denoising-based end-to-end learning, and deep learning-guided post-optimization, DRfold2 establishes a distinct direction for advancing ab initio RNA structure prediction.
dlvr.it
February 24, 2026 at 12:52 PM
DRfold2 is a deep learning-based tool that enables efficient and accurate RNA structure prediction @PLOSBiology.org
DRfold2 is a deep learning-based tool that enables efficient and accurate RNA structure prediction
by Yang Li, Chenjie Feng, Xi Zhang, Sho Tsukiyama, Duanyu Feng, Yang Zhang RNA structures are essential for understanding their biological functions and developing RNA-targeted therapeutics. However, accurate RNA structure prediction from sequence remains a crucial challenge. We introduce DRfold2, a deep learning framework that integrates a novel pre-trained RNA Composite Language Model (RCLM) with a denoising structure module for end-to-end RNA structure prediction. Based solely on single sequence, DRfold2 achieves superior performance in both global topology and secondary structure predictions over other state-of-the-art approaches across multiple benchmark tests from diverse species. Detailed analyses reveal that the improvements primarily stem from the RCLM’s ability to capture co-evolutionary pattern and the effective denoising process, with a more than 100% increase in contact prediction precision compared to existing methods. Furthermore, DRfold2 demonstrates high complementarity with AlphaFold3, achieving statistically significant accuracy gains when integrated into our optimization framework. By uniquely combining composite language modeling, denoising-based end-to-end learning, and deep learning-guided post-optimization, DRfold2 establishes a distinct direction for advancing ab initio RNA structure prediction.
dlvr.it
February 23, 2026 at 4:51 AM
Qinyi Zhang, Duanyu Feng, Ronghui Han, Yangshuai Wang, Hao Wang: MicroEvoEval: A Systematic Evaluation Framework for Image-Based Microstructure Evolution Prediction https://arxiv.org/abs/2511.08955 https://arxiv.org/pdf/2511.08955 https://arxiv.org/html/2511.08955
November 13, 2025 at 6:42 AM
Ruibo Deng, Duanyu Feng, Wenqiang Lei
AMaPO: Adaptive Margin-attached Preference Optimization for Language Model Alignment
https://arxiv.org/abs/2511.09385
November 13, 2025 at 5:34 AM
Qianqian Xie, Weiguang Han, Zhengyu Chen, Ruoyu Xiang, Xiao Zhang, Yueru He, Mengxi Xiao, Dong Li, Yongfu Dai, Duanyu Feng, Yijing Xu, Haoqiang Kang, Ziyan Kuang, Chenhan Yuan, Kailai Yang,...
FinBen: A Holistic Financial Benchmark for Large Language Models
https://arxiv.org/abs/2402.12659
June 21, 2024 at 11:02 PM
Duanyu Feng, Bowen Qin, Chen Huang, Youcheng Huang, Zheng Zhang, Wenqiang Lei
Legend: Leveraging Representation Engineering to Annotate Safety Margin for Preference Datasets
https://arxiv.org/abs/2406.08124
June 13, 2024 at 7:31 AM
Youcheng Huang, Jingkun Tang, Duanyu Feng, Zheng Zhang, Wenqiang Lei, Jiancheng Lv, Anthony G. Cohn
Dishonesty in Helpful and Harmless Alignment
https://arxiv.org/abs/2406.01931
June 5, 2024 at 4:41 AM
Youcheng Huang, Jingkun Tang, Duanyu Feng, Zheng Zhang, Wenqiang Lei, Jiancheng Lv, Anthony G. Cohn
Dishonesty in Helpful and Harmless Alignment
https://arxiv.org/abs/2406.01931
June 5, 2024 at 4:40 AM
Duanyu Feng, Bowen Qin, Chen Huang, Zheng Zhang, Wenqiang Lei
Towards Analyzing and Understanding the Limitations of DPO: A Theoretical Perspective
https://arxiv.org/abs/2404.04626
April 9, 2024 at 4:15 AM
Qianqian Xie, Weiguang Han, Zhengyu Chen, Ruoyu Xiang, Xiao Zhang, Yueru He, Mengxi Xiao, Dong Li, Yongfu Dai, Duanyu Feng, Yijing Xu, Haoqiang Kang, Ziyan Kuang, Chenhan Yuan, Kailai ...
The FinBen: An Holistic Financial Benchmark for Large Language Models
https://arxiv.org/abs/2402.12659
February 21, 2024 at 7:03 AM
Yongfu Dai, Duanyu Feng, Jimin Huang, Haochen Jia, Qianqian Xie, Yifang Zhang, Weiguang Han, Wei Tian, Hao Wang
LAiW: A Chinese Legal Large Language Models Benchmark
https://arxiv.org/abs/2310.05620
February 20, 2024 at 9:14 AM
Xiao Zhang, Ruoyu Xiang, Chenhan Yuan, Duanyu Feng, Weiguang Han, Alejandro Lopez-Lira, Xiao-Yang Liu, Sophia Ananiadou, Min Peng, Jimin Huang, Qianqian Xie
D\'olares or Dollars? Unraveling the Bilingual Prowess of Financial LLMs Between Spanish and English
https://arxiv.org/abs/2402.07405
February 14, 2024 at 4:00 AM
Xiao Zhang, Ruoyu Xiang, Chenhan Yuan, Duanyu Feng, Weiguang Han, Alejandro Lopez-Lira, Xiao-Yang Liu, Sophia Ananiadou, Min Peng, Jimin Huang, Qianqian Xie
D\'olares or Dollars? Unraveling the Bilingual Prowess of Financial LLMs Between Spanish and English
https://arxiv.org/abs/2402.07405
February 13, 2024 at 1:00 PM