OOIR: Observatory of International Research

Papers

(The H4-Index of Frontiers of Computer Science is 24. The table below lists those papers that are above that threshold based on CrossRef citation counts [max. 250 papers]. The publications cover those that have been published in the past four years, i.e., from 2021-11-01 to 2025-11-01.)

Article	Citations
Few-shot node classification via local adaptive discriminant structure learning	583
Towards practical data alignment in production federated learning	98
Exploiting comments information to improve legal public opinion news abstractive summarization	97
Top Pass: improve code generation by pass@k-maximized code ranking	91
Compressed page walk cache	89
Structure attack on full-round DBST	58
Sub-Nyquist sampling-based wideband spectrum sensing: a compressed power spectrum estimation approach	47
ReCSA: a dedicated sort accelerator using ReRAM-based content addressable memory	45
Self-corrected unsupervised domain adaptation	44
cKBET: assessing goodness of batch effect correction for single-cell RNA-seq	41
How graph convolutions amplify popularity bias for recommendation?	37
Model-based diagnosis with low-cost fault identification	37
Communication-robust multi-agent learning by adaptable auxiliary multi-agent adversary generation	35
Accountable attribute-based authentication with fine-grained access control and its application to crowdsourcing	35
Pusher: an augmented fuzzer based on the connection between input and comparison operand	33
Identifying useful learnwares via learnable specification	32
Trajectory prediction based on grouped spatial-temporal encoder	32
Revenue-maximizing online stable task assignment on taxi-dispatching platforms	32
Informative and diverse emotional conversation generation with variational recurrent pointer-generator	29
Minimizing the cost of periodically replicated systems via model and quantitative analysis	27
A lock-free approach to parallelizing personalized PageRank computations on GPU	27
An efficient atomic cross-chain commitment resisting fork fraud	27
Advanced persistent threat detection via mining long-term features in provenance graphs	26
MiMu: mitigating multiple shortcut learning behavior of transformers	24
Tool learning with large language models: a survey	24

ResLNet: deep residual LSTM network with longer input for action recognition	24
Debiasing vision-language models for vision tasks: a survey	24
Protein acetylation sites with complex-valued polynomial model	24