Special Topic: Large Multimodal Models (2026)
RESEARCH PAPER Webpage Webpage-cn SpringerLink Google Scholar

Motion-aware generative frame interpolation
Zhang G Z, Zhu Y H, Cui Y T, et al
Sci China Inf Sci, 2026, 69(5): 150101
Keywords: video generation; diffusion model; video frame interpolation; optical flow; temporal modeling; motion guidance; latent diffusion
Cite as: Zhang G Z, Zhu Y H, Cui Y T, et al. Motion-aware generative frame interpolation. Sci China Inf Sci, 2026, 69: 150101, doi: 10.1007/s11432-025-4920-3

Special Topic: Large Multimodal Models (2026)
RESEARCH PAPER Supplementary Webpage Webpage-cn SpringerLink Google Scholar

Gelm: graph-based Tanimoto similarity grouping pretraining and entropy-guided conformer selection finetuning for large language models
Chen Z, Wang S H, Chen L J, et al
Sci China Inf Sci, 2026, 69(5): 150102
Keywords: molecular relationship learning; multimodal large language model; pretraining; information entropy; DDI prediction
Cite as: Chen Z, Wang S H, Chen L J, et al. Gelm: graph-based Tanimoto similarity grouping pretraining and entropy-guided conformer selection finetuning for large language models. Sci China Inf Sci, 2026, 69: 150102, doi: 10.1007/s11432-025-4913-5

Special Topic: Large Multimodal Models (2026)
RESEARCH PAPER Webpage Webpage-cn SpringerLink Google Scholar

Shenbi: accelerating video diffusion models with INT8-attention
Fan H S, Lv A, Yan G H
Sci China Inf Sci, 2026, 69(5): 150103
Keywords: video diffusion model; model quantization; INT8 attention; GPU acceleration; large multimodal models
Cite as: Fan H S, Lv A, Yan G H. Shenbi: accelerating video diffusion models with INT8-attention. Sci China Inf Sci, 2026, 69: 150103, doi: 10.1007/s11432-025-4915-9

Special Topic: Large Multimodal Models (2026)
SCIS Selected Articles on Large Language Models (LLM)
RESEARCH PAPER Webpage Webpage-cn SpringerLink Google Scholar

MNAFT: modality neuron-aware fine-tuning of multimodal large language models for image translation
Li B, Deng N Y, Dong T Y, et al
Sci China Inf Sci, 2026, 69(5): 150104
Keywords: vision-language models; multilingual image translation; large language models
Cite as: Li B, Deng N Y, Dong T Y, et al. MNAFT: modality neuron-aware fine-tuning of multimodal large language models for image translation. Sci China Inf Sci, 2026, 69: 150104, doi: 10.1007/s11432-025-4914-1

Special Topic: Large Multimodal Models (2026)
RESEARCH PAPER Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 0

Multimodal prior-augmented text-driven 3D human-object interaction generation
Wang, Yin; Zhang, Ziyao; Leng, Zhiying; Liu, Haitian; Li, Frederick W. B.; Li, Mu; Liang, Xiaohui
Sci China Inf Sci, 2026, 69(5): 150105
Keywords: text-driven motion generation; human-object interaction; multimodal models; diffusion model
Cite as: Wang Y, Zhang Z Y, Leng Z Y, et al. Multimodal prior-augmented text-driven 3D human-object interaction generation. Sci China Inf Sci, 2026, 69: 150105, doi: 10.1007/s11432-025-4809-7

Special Topic: Large Multimodal Models (2026)
RESEARCH PAPER Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 0

Multimodal 3D object detection for autonomous driving under vision-language supervision: a contrastive-learning perspective
Lin, Chunmian; Zhang, Wenze; Chen, Yanyan; Yang, Lei; Jiang, Han; Tian, Daxin; Duan, Xuting; Zhou, Jianshan; Cao, Dongpu
Sci China Inf Sci, 2026, 69(5): 150106
Keywords: multimodal 3D detection; vision-language model; autonomous driving; contrastive learning; adapter
Cite as: Lin C M, Zhang W Z, Chen Y Y, et al. Multimodal 3D object detection for autonomous driving under vision-language supervision: a contrastive-learning perspective. Sci China Inf Sci, 2026, 69: 150106, doi: 10.1007/s11432-025-4853-5

Special Topic: Large Multimodal Models (2026)
SCIS Selected Articles on Large Language Models (LLM)
RESEARCH PAPER Webpage Webpage-cn SpringerLink Google Scholar

CT-Agent: a multimodal-LLM agent for 3D CT radiology question answering
Mao Y R, Xu W Y, Qin Y Y, et al
Sci China Inf Sci, 2026, 69(5): 150107
Keywords: LLM agent; CT radiology question answering; visual question answering; token compression; LoRA fine-tuning
Cite as: Mao Y R, Xu W Y, Qin Y Y, et al. CT-Agent: a multimodal-LLM agent for 3D CT radiology question answering. Sci China Inf Sci, 2026, 69: 150107, doi: 10.1007/s11432-025-4818-7