Jev: System One models for Prod, not God — with Diogo Almeida, CEO, TypeSafe AI
4 sources 15 min
What Is RLCD? The Secret Behind Jev
15 min
Nokia Open-Sources AnyJev: A Training-Free Layer That Turns Any Open LLM Into a Calibrated Decision Model
4 min
Calibration as a First-Class Criterion in LLM Evaluation
Pinocchio: Fast Uncertainty Estimates for Black-Box Language Models
Laya the open source version of Jev
10 min1
Available Guardrails: Certifying Selective Prediction across ML Systems
Moral Entropy: Auditing Bias and Uncertainty in Moral Judgment
When Should a Failing Robot Ask? Initiating Corrective Human-Robot Dialogue from Audited Sensor Evidence
convaiinnovations/laya — new model trending #30 on Hugging Face
6 min
Calibrated RF-Fingerprinting Under Interference With Heterogeneous Transmission Protocols
LLM Classification Is Feature Engineering
15 min1
When Should LLMs Abstain? Chain-of-Self-Questioning for Selective Risk Control
1
ENCP: Episode-Normalized Conformal Prediction for Vision-and-Language Navigation
Bridging the Confidence Gap: Temperature Scaling for Calibrating Test-Time Prompt Tuning
1
Confidence Comes from Experience: Experiential Confidence Estimation from Reasoning to Agents
A Ranking Approach for Measuring Calibration
1
Domain-Specific Hallucination Detection in Large Language Models
1
Target leakage, not model class, explains reported accuracy in survey-based cardiovascular screening: a leakage-tiered audit of glass-box and tabular foundation models
1
Competence-Gated Pooling of Language Models and Priors for Event Forecasting
1
Bag of Tricks or Bag of Myths? Reducing Modeling Complexity with Task Knowledge in Explainable Suicide Risk Assessment
Train Smarter, Not Harder: Switching Signal-Guided Training in Active Learning
MLLMs Hallucinate when Information Distribution Drifts in Synergy Heads
