active learning
PulseAugur coverage of active learning — every cluster mentioning active learning across labs, papers, and developer communities, ranked by signal.
5 day(s) with sentiment data
-
Active learning refines Bayesian optimization for faster materials discovery
Researchers have developed a new framework that combines active learning with multi-objective Bayesian optimization to improve the efficiency of materials discovery. This approach refines the design space by adaptively …
-
New framework optimizes active learning for medical image classification
Researchers have developed ALDA, an Active Learning Deployment Advisor, to optimize the selection of active learning strategies for medical image classification. ALDA uses a pilot annotation phase to model the learning …
-
New adaptive technique reconstructs bosonic quantum states efficiently
Researchers have developed an adaptive reconstruction technique to more efficiently characterize bosonic quantum states. This method uses Bayesian inference, bootstrap, and active learning to select optimal measurement …
-
LLM Uncertainty Quantification: Blackbox vs. Whitebox Methods Compared
Researchers are exploring methods for Large Language Models (LLMs) to quantify their own uncertainties, a capability crucial for applications like active learning and safety classification. Current approaches are divide…
-
Human-in-the-Loop ML for Safer Autonomous Vehicles Explored
A new arXiv paper explores the integration of Human-in-the-Loop Machine Learning (HITL-ML) techniques to enhance the safety and ethical considerations of autonomous vehicles (AVs). The paper details how human input, thr…
-
New Active Learning Framework Slashes Histopathology Annotation Costs
Researchers have developed SHAL (Slide-level Hybrid Active Learning), a novel framework designed to significantly reduce the annotation burden in deep learning models for histopathology image segmentation. This patient-…
-
New active learning algorithm tackles adversarial graph corruption
Researchers have developed a new active learning algorithm designed to identify corrupted vertices within graphs, even when adversaries tamper with network structures. The algorithm aims to efficiently find these hidden…
-
New framework boosts unsupervised anomaly detection with active learning
Researchers have developed a new framework to improve unsupervised time series anomaly detection by incorporating active learning. This method uses a masked time-series reconstruction feedback strategy and a minimax lea…
-
Transformer models boost vaccine epitope selection efficiency
Researchers have developed a transformer-based active learning approach to improve the efficiency of selecting vaccine epitopes. This method significantly enhances the accuracy of identifying high-affinity binding epito…
-
New warm-start strategies accelerate Gaussian Process inference
Researchers have developed new warm-start strategies to accelerate Gaussian Process (GP) inference, a critical component for tasks like active learning and Bayesian optimization. These methods leverage solutions from sm…
-
New RL Method Enhances LLM Uncertainty Expression and Trustworthiness
Researchers have developed a new method called Reinforcement Learning with Metacognitive Feedback (RLMF) to improve how Large Language Models (LLMs) express their uncertainty. This approach uses the model's self-assessm…
-
In-context learning may enable intrinsic curiosity in machine learning
A new research paper explores whether in-context learning (ICL) capabilities of large sequence models can support intrinsic curiosity in machine learning. The study investigates if an exploration policy can be trained t…
-
In-Context Learning Explored for AI Intrinsic Curiosity
Researchers have explored whether in-context learning (ICL) capabilities of sequence models can support intrinsic curiosity in machine learning. While traditional methods for automated data selection, or "intrinsic curi…
-
LLM annotation rivals human labels for hostility detection at lower cost
A new arXiv paper investigates the efficacy of Large Language Models (LLMs) in annotating data for active learning, specifically for hostility detection in online comments. The study found that LLMs, particularly GPT-5.…
-
New active learning framework tackles imbalanced data with foundation models
Researchers have developed a new active learning framework designed to improve model performance on datasets with imbalanced class distributions and noisy annotations. This approach leverages foundation model priors to …
-
Review details AI models for inverse materials design
A new review paper details advancements in using generative models and multimodal learning for inverse materials design. It covers various generative model classes like VAEs, normalizing flows, and diffusion models, emp…
-
New AI Methods Tackle Evolving Android Malware Detection
Researchers have developed new methods to combat concept drift in Android malware detection systems, a problem where model performance degrades over time due to evolving malware characteristics. One approach, "Concept D…
-
New CAML framework boosts ML model robustness against spurious correlations
Researchers have developed a new active learning framework called Cumulative Active Meta-Learning (CAML) to improve the robustness of machine learning models against spurious correlations. CAML treats each active learni…
-
New PFNs method separates epistemic and aleatoric uncertainty for better decision-making
Researchers have developed a new method called Decoupled PFNs to better distinguish between epistemic uncertainty (uncertainty about the model's knowledge) and aleatoric uncertainty (inherent noise in the data). This is…