On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,051 papers · 148 categories

Trend · papers per month

count % of corpus

6 results for “many-shot”

From Few to Many: Self-Improving Many-Shot Reasoners Through Iterative Optimization and Generationcs.LG

Improves many-shot learning by optimizing and generating influential examples.

problem Limited performance in many-shot in-context learning (ICL).

method Iterative optimization and generation of influential examples.

result Significant improvements across various tasks using BRIDGE.

many-shot learning in-context learning Bayesian optimization generative models language models

2025-02-01abs ↗pdf ↗

A Meta-Learning Approach for Custom Model Trainingcs.LG

Improved model training for few-class, few-shot tasks.

problem Meta-learning algorithms struggle in many-shot and many-class settings.

method Joint training approach combining transfer-learning and meta-learning.

result Improved generalization performance on unseen tasks.

meta-learning transfer-learning few-shot few-class many-shot

2018-09-21abs ↗pdf ↗

Meta-Learning Initializations for Image Segmentationcs.LG

Meta-learning improves image segmentation performance.

problem Improving image segmentation accuracy using meta-learning.

method Extending FOMAML and Reptile to image segmentation, using EfficientLab architecture, and leveraging test error definition.

result Meta-learned initializations provide value for few-shot image segmentation but are quickly matched by conventional transfer learning.

meta-learning image segmentation few-shot learning transfer learning Bayesian optimization

2019-12-13abs ↗pdf ↗

Belief Dynamics Reveal the Dual Nature of In-Context Learning and Activation Steeringcs.LG

Unified Bayesian model explains in-context learning and activation steering in LLMs.

problem Understanding and controlling the behavior of large language models (LLMs) through prompts and activations.

method Developed a Bayesian model to explain and predict the effects of in-context learning and activation steering.

result Unified model predicts distinct phases and sudden shifts in LLM behavior, explaining prior empirical phenomena.

Bayesian model LLMs in-context learning activation steering prompt control

2025-11-01abs ↗pdf ↗

Learning to Propagate for Graph Meta-Learningcs.LG

Meta-learning improves few-shot learning by propagating knowledge across related classes on a graph.

problem Few-shot learning suffers from insufficient training data.

method Developed a Gated Propagation Network (GPN) that learns to propagate messages between prototypes of different classes on a graph.

result GPN outperforms recent meta-learning methods on benchmark datasets.

meta-learning few-shot learning graph-based meta-learning prototype-based classification attention mechanism

2019-09-11abs ↗pdf ↗

Many-Class Few-Shot Learning on Multi-Granularity Class Hierarchycs.LG

Paper tackles many-class few-shot learning with class hierarchy, improving accuracy.

problem Many-class few-shot learning problem in practical applications.

method Leverages class hierarchy to train a coarse-to-fine classifier using memory-augmented hierarchical-classification network (MahiNet).

result MahiNet outperforms state-of-the-art models on MCFS problems in both supervised and meta-learning settings.

few-shot learning class hierarchy meta-learning convolutional neural network memory-augmented attention

2020-06-28abs ↗pdf ↗