Shanghai Artificial Intelligence Laboratory

Recent papers from Shanghai Artificial Intelligence Laboratory

1. AnyStitch: Generative Large Parallax Image StitchingACM Transactions on Graphics · 2026
2. SwiftFusion: Towards Motion-Robust and Efficient 4K HDR FusionACM Transactions on Graphics · 2026
3. A Comprehensive Survey on Graph-Structured Small-Molecule Drug Discovery and Development with Deep LearningTransactions on Graph Intelligence and Network Applications · 2026
4. NeuroPack: Advanced Learnable Packaging Toolkit Towards Ultra-High Compression Ratio for Volumetric Neuroimaging2026
5. Data-Driven Approach for Predicting Long-Time Anomalous Transport from Short TrajectoriesJournal of Chemical Theory and Computation · 2026
6. Paired-Isotopologue Hessian Benchmarking for Second-Order Validation of Machine-Learned Water PotentialsJournal of Chemical Theory and Computation · 2026
7. HaVen-Agent: Enhancing Hallucination-Mitigated Verilog Code Generation Aligned with HDL Engineers through Code Repair and Multi-Agent OrchestrationACM Transactions on Design Automation of Electronic Systems · 2026
8. Scaling genetic discovery through automated post-GWAS interpretation2026
9. Protein resource allocation across subcellular compartments revealed by large-scale absolute quantitative proteomics in yeastProceedings of the National Academy of Sciences · 2026
10. Disease-associated NK-cell state remodeling reveals transcriptional profiles predictive of clinical phenotypes2026
11. Detecting symmetry-resolved entanglement: A quantum Monte Carlo approachSciPost Physics · 2026
12. Teaching PPG How not Who: Fixed-Effects Distillation from ECG2026
13. Multi-modal parameter-efficient fine-tuning via hypergraph adaptersComplex & Intelligent Systems · 2026
14. NeuroChrono: Dissociated Neural Encoding with ChronoGate for Brain-to-Video Diffusion2026
15. A Generalizable Multimodal Model for Treatment‐Stratified Risk and Survival Assessment under Real‐World Constraints: A Multi‐Center Study of Colorectal CancerAdvanced Science · 2026
16. Efficient Multimodal Instruction Tuning Through Iterative Data Selection and Augmentation Under Fixed Data BudgetsElectronics · 2026
17. MKE: A Lightweight Framework for Multimodal Knowledge Extraction via Knowledge DistillationElectronics · 2026
18. Efficient physics-interpretable deep learning for skillful tropical stratosphere dynamics modelingnpj Artificial Intelligence · 2026
19. Revisiting the broken symmetry phase of solid hydrogen: A neural network variational Monte Carlo studyPhysical review. B./Physical review. B · 2026
20. Interpretable multi-modal hierarchical framework to support cytomorphological analysis of hematologic cancersnpj Digital Medicine · 2026