Event-level MAE embeddings plus UMAP/HDBSCAN or K-Means clustering recover 15 hydroacoustic classes from multi-year Mayotte data with ~1 hour of annotation and detector-comparable F1.
Human-in-the-loop machine learning: a state of the art
8 Pith papers cite this work, alongside 738 external citations. Polarity classification is still indexing.
8
Pith papers citing it
738
external citations · Crossref
citation-role summary
background 1
citation-polarity summary
years
2026 8roles
background 1polarities
background 1representative citing papers
LLM reframing of liberal headlines boosts conservative readers' trust and engagement, but LLM simulations overestimate these effects and misidentify which readers will respond.
AI improves brainstorming quality for general-purpose impact assessment but not specialized applications when it offers hints early and structures ideas later, based on workshop evaluations with 54 participants.
A conceptual model proposes representing LLM workflow definitions, instances, and inference records as persistent typed objects in a shared knowledge substrate, distinguishing deterministic derive from LLM-mediated infer.
RocketSmith is an LLM-based agentic system that designs four high-powered rockets via additive manufacturing, with two achieving stable launches and recovery after reaching 80% of simulated apogee.
TRACE is a metrologically-grounded four-layer engineering framework for trustworthy agentic AI that enforces an ML-LLM split, stateful policies, human supervision, and a parsimony metric across critical domains.
CoLLM unifies FL PEFT and inference on shared edge replicas via intra-replica model sharing and two-timescale inter-replica coordination, achieving up to 3x higher goodput than prior LLM systems.
AI to Learn 2.0 is a deliverable-oriented framework with a seven-dimension maturity rubric and capability-evidence ladder that permits opaque AI for exploration but requires final outputs to be auditable, transferable, and supported by human-attributable evidence.
citing papers explorer
-
A Self-Supervised Approach for Minimal-Annotation Hydroacoustic Data Exploration
Event-level MAE embeddings plus UMAP/HDBSCAN or K-Means clustering recover 15 hydroacoustic classes from multi-year Mayotte data with ~1 hour of annotation and detector-comparable F1.
-
Can AI Debias the News? LLM Interventions Improve Cross-Partisan Receptivity but LLMs Overestimate Their Own Effectiveness
LLM reframing of liberal headlines boosts conservative readers' trust and engagement, but LLM simulations overestimate these effects and misidentify which readers will respond.
-
When and How AI Should Assist Brainstorming for AI Impact Assessment
AI improves brainstorming quality for general-purpose impact assessment but not specialized applications when it offers hints early and structures ideas later, based on workshop evaluations with 54 participants.
-
Workflow as Knowledge: Semantic Persistence for LLM-Mediated Workflows
A conceptual model proposes representing LLM workflow definitions, instances, and inference records as persistent typed objects in a shared knowledge substrate, distinguishing deterministic derive from LLM-mediated infer.
-
RocketSmith: Agentic Additive Manufacturing of High-Powered Rockets
RocketSmith is an LLM-based agentic system that designs four high-powered rockets via additive manufacturing, with two achieving stable launches and recovery after reaching 80% of simulated apogee.
-
TRACE: A Metrologically-Grounded Engineering Framework for Trustworthy Agentic AI Systems in Operationally Critical Domains
TRACE is a metrologically-grounded four-layer engineering framework for trustworthy agentic AI that enforces an ML-LLM split, stateful policies, human supervision, and a parsimony metric across critical domains.
-
CoLLM: Continuous Adaptation for SLO-Aware LLM Serving on Shared GPU Clusters
CoLLM unifies FL PEFT and inference on shared edge replicas via intra-replica model sharing and two-timescale inter-replica coordination, achieving up to 3x higher goodput than prior LLM systems.
-
AI to Learn 2.0: A Deliverable-Oriented Governance Framework and Maturity Rubric for Opaque AI in Learning-Intensive Domains
AI to Learn 2.0 is a deliverable-oriented framework with a seven-dimension maturity rubric and capability-evidence ladder that permits opaque AI for exploration but requires final outputs to be auditable, transferable, and supported by human-attributable evidence.