A neurosymbolic model augments Swin Transformers with focal sets and fuzzy logic to produce calibrated hierarchical image classifications that respect logical constraints.
Title resolution pending
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4representative citing papers
MP-IB uses an 8x information asymmetry via FP16 trait heads and INT4 state heads to disentangle speaker identity from agitation in voice biomarkers, outperforming larger models on edge devices with low latency and suppressed identity leakage.
Unsupervised single-generation confidence calibration for reasoning LLMs via offline self-consistency proxy distillation outperforms baselines on math and QA tasks and improves selective prediction.
A comprehensive public dataset of simulated Ariel exoplanet transmission spectra is released to benchmark detrending algorithms, with an ML baseline highlighting dataset shift risks.
citing papers explorer
-
A neurosymbolic Approach with Epistemic Deep Learning for Hierarchical Image Classification
A neurosymbolic model augments Swin Transformers with focal sets and fuzzy logic to produce calibrated hierarchical image classifications that respect logical constraints.
-
Mixed-Precision Information Bottlenecks for On-Device Trait-State Disentanglement in Bipolar Agitation Detection
MP-IB uses an 8x information asymmetry via FP16 trait heads and INT4 state heads to disentangle speaker identity from agitation in voice biomarkers, outperforming larger models on edge devices with low latency and suppressed identity leakage.
-
Unsupervised Confidence Calibration for Reasoning LLMs from a Single Generation
Unsupervised single-generation confidence calibration for reasoning LLMs via offline self-consistency proxy distillation outperforms baselines on math and QA tasks and improves selective prediction.
-
A public dataset of Ariel simulated observations for developing exoplanetary atmosphere data reduction pipelines
A comprehensive public dataset of simulated Ariel exoplanet transmission spectra is released to benchmark detrending algorithms, with an ML baseline highlighting dataset shift risks.