Special Topic: Enabling Techniques and Cutting-Edge Applications of Foundation Models
EDITORIAL Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 0

Special topic on enabling techniques and cutting-edge applications of foundation models
Jing, Liping; Liu, Qi; Zhang, Min-Ling
Sci China Inf Sci, 2025, 68(6): 160100
Cite as: Jing L P, Liu Q, Zhang M-L. Special topic on enabling techniques and cutting-edge applications of foundation models. Sci China Inf Sci, 2025, 68(6): 160100, doi: 10.1007/s11432-025-4448-4

Special Topic: Enabling Techniques and Cutting-Edge Applications of Foundation Models
RESEARCH PAPER Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 0

Agent4Vul: multimodal LLM agents for smart contract vulnerability detection
Jie, Wanqing; Qiu, Wangjie; Yang, Haofu; Guo, Muyuan; Huang, Xinpeng; Lei, Tianyu; Zhang, Qinnan; Zheng, Hongwei; Zheng, Zhiming
Sci China Inf Sci, 2025, 68(6): 160101
Keywords: smart contract; vulnerability detection; LLM; agent; multimodal learning
Cite as: Jie W Q, Qiu W J, Yang H F, et al. Agent4Vul: multimodal LLM agents for smart contract vulnerability detection. Sci China Inf Sci, 2025, 68(6): 160101, doi: 10.1007/s11432-024-4402-2

Special Topic: Enabling Techniques and Cutting-Edge Applications of Foundation Models
RESEARCH PAPER Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 0

RAG-leaks: difficulty-calibrated membership inference attacks on retrieval-augmented generation
Wang, Guangshuo; He, Jiajun; Li, Hao; Zhang, Min; Feng, Dengguo
Sci China Inf Sci, 2025, 68(6): 160102
Keywords: large language models; retrieval-augmented generation; membership inference; privacy risk; difficulty calibration
Cite as: Wang G S, He J J, Li H, et al. RAG-leaks: difficulty-calibrated membership inference attacks on retrieval-augmented generation. Sci China Inf Sci, 2025, 68(6): 160102, doi: 10.1007/s11432-024-4441-4

Special Topic: Enabling Techniques and Cutting-Edge Applications of Foundation Models
RESEARCH PAPER Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 0

DiagLLM: multimodal reasoning with large language model for explainable bearing fault diagnosis
Wang, Jie; Li, Tianrui; Yang, Yan; Chen, Shiqian; Zhai, Wanming
Sci China Inf Sci, 2025, 68(6): 160103
Keywords: large language model; fault diagnosis; cross-dataset generalization; multimodal learning; multimodal fusion
Cite as: Wang J, Li T R, Yang Y, et al. DiagLLM: multimodal reasoning with large language model for explainable bearing fault diagnosis. Sci China Inf Sci, 2025, 68(6): 160103, doi: 10.1007/s11432-024-4333-7

Special Topic: Enabling Techniques and Cutting-Edge Applications of Foundation Models
RESEARCH PAPER Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 0

On the encryption for graph foundation model inference of sparse graph
Yuan, Man-Jie; Bai, Xue-Tong; Zhang, Kai-Ran; Gao, Wei
Sci China Inf Sci, 2025, 68(6): 160104
Keywords: graph foundation model; graph prompt; privacy-preserving machine learning; graph encryption; data encryption
Cite as: Yuan M-J, Bai X-T, Zhang K-R, et al. On the encryption for graph foundation model inference of sparse graph. Sci China Inf Sci, 2025, 68(6): 160104, doi: 10.1007/s11432-024-4439-1

Special Topic: Enabling Techniques and Cutting-Edge Applications of Foundation Models
RESEARCH PAPER Supplementary Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 0

MindScore: quantifying human preference for text-to-image generation through multi-view lens
Tong, Yiqi; Zhang, Jiarui; Wei, Shaohang; Guo, Wei; Zhuang, Fuzhen; Wang, Deqing; Yang, Xi; Xuan, Richeng
Sci China Inf Sci, 2025, 68(6): 160105
Keywords: text-to-image generation; foundation models; human preference evaluation; multi-view assessment; language and vision
Cite as: Tong Y Q, Zhang J R, Wei S H, et al. MindScore: quantifying human preference for text-to-image generation through multi-view lens. Sci China Inf Sci, 2025, 68(6): 160105, doi: 10.1007/s11432-024-4401-y

Special Topic: Enabling Techniques and Cutting-Edge Applications of Foundation Models
RESEARCH PAPER Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 0

LEDNet: a multimodal foundation model for robust deepfake detection
Tao, Renshuai; Tang, Shijie; Qin, Haotong; Wang, Wei; Wei, Yunchao; Zhao, Yao
Sci China Inf Sci, 2025, 68(6): 160106
Keywords: computer vision; multimodel foundation model; deepfake detection
Cite as: Tao R S, Tang S J, Qin H T, et al. LEDNet: a multimodal foundation model for robust deepfake detection. Sci China Inf Sci, 2025, 68(6): 160106, doi: 10.1007/s11432-024-4400-8

Special Topic: Enabling Techniques and Cutting-Edge Applications of Foundation Models
POSITION PAPER Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 0

The superalignment of superhuman intelligence with large language models
Huang, Minlie; Wang, Yingkang; Cui, Shiyao; Ke, Pei; Tang, Jie
Sci China Inf Sci, 2025, 68(6): 160107
Keywords: superalignment; superhuman intelligence; large language models; scalable feedback; weak-to-strong generalization
Cite as: Huang M L, Wang Y K, Cui S Y, et al. The superalignment of superhuman intelligence with large language models. Sci China Inf Sci, 2025, 68(6): 160107, doi: 10.1007/s11432-024-4348-6

Special Topic: Enabling Techniques and Cutting-Edge Applications of Foundation Models
LETTER Supplementary Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 0

Trustworthy forgery detection with causal inference
Duan, Junxian; Ji, Fan; Li, Yi; Sun, Hao; He, Ran
Sci China Inf Sci, 2025, 68(6): 160108
Keywords: forgery detection; causal inference; visual media forgery detection; structural causal model; plug-and-play
Cite as: Duan J X, Ji F, Li Y, et al. Trustworthy forgery detection with causal inference. Sci China Inf Sci, 2025, 68(6): 160108, doi: 10.1007/s11432-024-4347-6

Special Topic: Enabling Techniques and Cutting-Edge Applications of Foundation Models
LETTER Supplementary Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 0

Dynamic prompt allocation and tuning for continual test-time adaptation
Cui, Chaoran; Zhen, Yongrui; Gong, Shuai; Zhang, Chunyun; Liu, Hui; Yin, Yilong
Sci China Inf Sci, 2025, 68(6): 160109
Keywords: test-time adaptation; continual learning; catastrophic forgetting; prompt tuning; parameter disentanglement
Cite as: Cui C R, Zhen Y R, Gong S, et al. Dynamic prompt allocation and tuning for continual test-time adaptation. Sci China Inf Sci, 2025, 68(6): 160109, doi: 10.1007/s11432-024-4379-8

Special Topic: Enabling Techniques and Cutting-Edge Applications of Foundation Models
LETTER Supplementary Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 0

Visual and text prompt learning for multi-modal brain disease diagnosis
Zhao, Yumiao; Jiang, Bo; Ding, Yuhe; Wan, Xixi; Tang, Jin
Sci China Inf Sci, 2025, 68(6): 160110
Keywords: brain disease diagnosis; 3D multi-modal fusion; foundation model; local feature representation; expert knowledge
Cite as: Zhao Y M, Jiang B, Ding Y H, et al. Visual and text prompt learning for multi-modal brain disease diagnosis. Sci China Inf Sci, 2025, 68(6): 160110, doi: 10.1007/s11432-024-4399-9