OOIR: Observatory of International Research

Papers

(The H4-Index of Frontiers of Computer Science is 26. 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 2022-01-01 to 2026-01-01.)

Article	Citations
Towards practical data alignment in production federated learning	689
Communication-robust multi-agent learning by adaptable auxiliary multi-agent adversary generation	127
Structure attack on full-round DBST	96
Sub-Nyquist sampling-based wideband spectrum sensing: a compressed power spectrum estimation approach	91
cKBET: assessing goodness of batch effect correction for single-cell RNA-seq	64
Model-based diagnosis with low-cost fault identification	58
ReCSA: a dedicated sort accelerator using ReRAM-based content addressable memory	53
Data quality matters: towards trajectory data collection under local differential privacy	52
Exploiting comments information to improve legal public opinion news abstractive summarization	46
Top Pass: improve code generation by pass@k-maximized code ranking	43
Few-shot node classification via local adaptive discriminant structure learning	42
How graph convolutions amplify popularity bias for recommendation?	42
Accountable attribute-based authentication with fine-grained access control and its application to crowdsourcing	42
Identifying useful learnwares via learnable specification	40
Debiasing vision-language models for vision tasks: a survey	39
Trajectory prediction based on grouped spatial-temporal encoder	39
Informative and diverse emotional conversation generation with variational recurrent pointer-generator	36
A lock-free approach to parallelizing personalized PageRank computations on GPU	35
RE2: improving Chinese grammatical error correction via retrieving appropriate examples with explanation	32
MiMu: mitigating multiple shortcut learning behavior of transformers	29
Advanced persistent threat detection via mining long-term features in provenance graphs	28
An efficient atomic cross-chain commitment resisting fork fraud	27
Minimizing the cost of periodically replicated systems via model and quantitative analysis	27
Revenue-maximizing online stable task assignment on taxi-dispatching platforms	27
Protein acetylation sites with complex-valued polynomial model	26

ResLNet: deep residual LSTM network with longer input for action recognition	26
A comprehensive survey on graph neural network accelerators	26
Tool learning with large language models: a survey	26