MPD²-Router is a dual-head deferral router that uses mask-aware Gumbel-sigmoid gating, asymmetric cost-sensitive training, and rank-majorization regularization to lower clinical cost and raise MCC versus AI-only baselines while balancing expert utilization across three glaucoma cohorts.
MPD 2-Router largely recovers this region, leaving residual errors sparse rather than spatially clustered
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
verdicts
UNVERDICTED 7representative citing papers
A code-and-comment analysis method detects semantic clones in Solidity functions with 59% overall precision (84% for same-name functions) and 97% recall on 300k contracts, plus LLM summaries for uncommented code.
A closed-loop framework jointly optimizes molecular composition and geometry in multi-component systems, demonstrated by a 30% reduction in activation barrier for a Claisen rearrangement via post-hoc validation.
In XX spin chains with open boundaries, a local quench via a single-spin impurity prevents thermalization and produces a strong violation of the eigenstate thermalization hypothesis, including its weak version.
A generalized approach to automatically generate atomic consistency preserving search operators (aCPSOs) for search-based model engineering that perform comparably or better than manual operators in case studies.
Feedback Former improves cell image segmentation accuracy by feeding detailed feature maps back from near the output to lower transformer layers, outperforming non-feedback baselines with lower computational cost on three datasets.
A new 'Artificial Special Intelligence' method is claimed to enable error-free training of classification models to 100% accuracy on 15 of 18 MedMNIST biomedical datasets.
citing papers explorer
-
MPD$^2$-Router: Mask-aware Multi-expert Prior-regularized Dual-head Deferral Router in Glaucoma Screening and Diagnosis
MPD²-Router is a dual-head deferral router that uses mask-aware Gumbel-sigmoid gating, asymmetric cost-sensitive training, and rank-majorization regularization to lower clinical cost and raise MCC versus AI-only baselines while balancing expert utilization across three glaucoma cohorts.
-
Identifying and Characterizing Semantic Clones of Solidity Functions
A code-and-comment analysis method detects semantic clones in Solidity functions with 59% overall precision (84% for same-name functions) and 97% recall on 300k contracts, plus LLM summaries for uncommented code.
-
Hierarchical generative modeling for the design of multi-component systems
A closed-loop framework jointly optimizes molecular composition and geometry in multi-component systems, demonstrated by a 30% reduction in activation barrier for a Claisen rearrangement via post-hoc validation.
-
Absence of thermalization after a local quench and strong violation of the eigenstate thermalization hypothesis
In XX spin chains with open boundaries, a local quench via a single-spin impurity prevents thermalization and produces a strong violation of the eigenstate thermalization hypothesis, including its weak version.
-
Automatic Generation of Atomic Consistency Preserving Search Operators for Search-Based Model Engineering
A generalized approach to automatically generate atomic consistency preserving search operators (aCPSOs) for search-based model engineering that perform comparably or better than manual operators in case studies.
-
Accuracy Improvement of Cell Image Segmentation Using Feedback Former
Feedback Former improves cell image segmentation accuracy by feeding detailed feature maps back from near the output to lower transformer layers, outperforming non-feedback baselines with lower computational cost on three datasets.
-
Benchmarking PNW Model for MedMNIST to 100% Accuracy
A new 'Artificial Special Intelligence' method is claimed to enable error-free training of classification models to 100% accuracy on 15 of 18 MedMNIST biomedical datasets.