CACM improves language-based drug discovery agents by 36.4% via protocol auditing, a grounded diagnostician, and compressed static/dynamic/corrective memory channels that localize failures and bias corrections.
hub
From Local Explanations to Global Understanding with Explainable AI for Trees
14 Pith papers cite this work. Polarity classification is still indexing.
14
Pith papers citing it
hub tools
citation-role summary
background 4
citation-polarity summary
roles
background 4polarities
background 4representative citing papers
DSINet uses a selective spatial state unit (S3U) from Mamba and concentration-balanced distillation (CBD) to keep spatial change representations stable across incremental domains while preserving linear efficiency.
Using a corpus of 5542 fault-injected traces from 38 DL programs, the study finds a 0.19 balanced accuracy gap in fault diagnosis between within-program and cross-program evaluation caused by program-specific feature structures.
R3LM trains LLMs via two-stage reasoning-then-regression on a new dataset CRE-ReasonBench with mechanistic traces, achieving SOTA enhancer activity prediction across three cell types with interpretable outputs.
Teachers' views on AI benefits and risks vary widely across 55 countries, but LLMs compress these differences, overestimate both sides, and show little improvement from country prompting or better reasoning.
Pact is a choreographic language extended with game-theoretic operations that maps every protocol to a formal game for reasoning about agent decisions and solving for decision policies.
This paper reconstructs Toegye Yi Hwang's philosophy into a five-stage EEFS architecture with design principles, scenario classifications, and an evaluation instrument for ethical emotion regulation in agentic AI.
SAL is a spike-timing-based local learning rule that aligns feedback weights to forward weights in spiking networks by exploiting noise and Hebbian/anti-Hebbian plasticity to recover the true gradient.
Learning-induced spectral structure in hybrid quantum models is diagnosed by edge-resolved two-boson interference correlated with Fiedler cuts and by absolute Bloch drift that separates anomalies from benign states.
Workshops with over 100 creative writers produced metaphors and four themes for language model governance that favor consent-driven, smaller open models encoding community values.
Insider action research in an AI startup identifies three patterns of how practitioners view regulatory requirements and proposes internal expert collaboration as a way to turn external governance rules into shared, practical ownership.
The UPDP pipeline filters privacy terms and generates de-identified radiology images that preserve diagnostic pathology information, enabling models with competitive disease detection accuracy but reduced identity leakage and improved cross-hospital performance.
ICA and VEIL enable privacy-preserving supervised ML by producing structurally non-invertible encodings aligned with downstream tasks while maintaining predictive utility.
The paper develops a transparent data-driven fault detection system for manufacturing that integrates supervised ML classification, SHAP explanations, and operator-focused visualizations, reporting 95.9% accuracy on univariate crimping time series data.
citing papers explorer
-
Constraint-Aware Corrective Memory for Language-Based Drug Discovery Agents
CACM improves language-based drug discovery agents by 36.4% via protocol auditing, a grounded diagnostician, and compressed static/dynamic/corrective memory channels that localize failures and bias corrections.
-
Dual-Selective Network for Domain-Incremental Change Detection
DSINet uses a selective spatial state unit (S3U) from Mamba and concentration-balanced distillation (CBD) to keep spatial change representations stable across incremental domains while preserving linear efficiency.
-
Evaluation-Strategy Gap in Fault Diagnosis of Deep Learning Programs
Using a corpus of 5542 fault-injected traces from 38 DL programs, the study finds a 0.19 balanced accuracy gap in fault diagnosis between within-program and cross-program evaluation caused by program-specific feature structures.
-
Biological Reasoning-Informed Regression for Interpretable Regulatory DNA Activity Prediction
R3LM trains LLMs via two-stage reasoning-then-regression on a new dataset CRE-ReasonBench with mechanistic traces, achieving SOTA enhancer activity prediction across three cell types with interpretable outputs.
-
Teachers' Perceived Benefits and Risks of AI Across Fifty-Five Countries: An Audit of LLM Alignment and Steerability
Teachers' views on AI benefits and risks vary widely across 55 countries, but LLMs compress these differences, overestimate both sides, and show little improvement from country prompting or better reasoning.
-
Pact: A Choreographic Language for Agentic Ecosystems
Pact is a choreographic language extended with game-theoretic operations that maps every protocol to a formal game for reasoning about agent decisions and solving for decision policies.
-
Designing Ethical Learning for Agentic AI: Toegye Yi Hwang's Ethical Emotion Regulation Framework
This paper reconstructs Toegye Yi Hwang's philosophy into a five-stage EEFS architecture with design principles, scenario classifications, and an evaluation instrument for ethical emotion regulation in agentic AI.
-
Spike-based alignment learning solves the weight transport problem
SAL is a spike-timing-based local learning rule that aligns feedback weights to forward weights in spiking networks by exploiting noise and Hebbian/anti-Hebbian plasticity to recover the true gradient.
-
Spectral Geometry and Bosonic-Bloch Probes: Explorations in Quantum Learning
Learning-induced spectral structure in hybrid quantum models is diagnosed by edge-resolved two-boson interference correlated with Fiedler cuts and by absolute Bloch drift that separates anomalies from benign states.
-
Seed Bank, Co-op, Stoop Swap: Metaphors for Governing Language Model Data for Creative Writing
Workshops with over 100 creative writers produced metaphors and four themes for language model governance that favor consent-driven, smaller open models encoding community values.
-
Engaged AI Governance: Addressing the Last Mile Challenge Through Internal Expert Collaboration
Insider action research in an AI startup identifies three patterns of how practitioners view regulatory requirements and proposes internal expert collaboration as a way to turn external governance rules into shared, practical ownership.
-
A Utility-preserving De-identification Pipeline for Cross-hospital Radiology Data Sharing
The UPDP pipeline filters privacy terms and generates de-identified radiology images that preserve diagnostic pathology information, enabling models with competitive disease detection accuracy but reduced identity leakage and improved cross-hospital performance.
-
Informationally Compressive Anonymization: Non-Degrading Sensitive Input Protection for Privacy-Preserving Supervised Machine Learning
ICA and VEIL enable privacy-preserving supervised ML by producing structurally non-invertible encodings aligned with downstream tasks while maintaining predictive utility.
-
Towards transparent and data-driven fault detection in manufacturing: A case study on univariate, discrete time series
The paper develops a transparent data-driven fault detection system for manufacturing that integrates supervised ML classification, SHAP explanations, and operator-focused visualizations, reporting 95.9% accuracy on univariate crimping time series data.