Papers Meta-Learning
“Meta-Learning” 태그가 달린 논문 3,569편 · 필터 해제
Distributionally robust minimization in meta-learning for system identification
Meta learning aims at learning how to solve tasks, and thus it allows to estimate models that can be quickly adapted to new scenarios. This work explores distributionally robust minimization in meta learning for system i…
Meta-LearningEpisode-specific Fine-tuning for Metric-based Few-shot Learners with Optimization-based Training
In few-shot classification tasks (so-called episodes), a small set of labeled support samples is provided during inference to aid the classification of unlabeled query samples. Metric-based models typically operate by co…
Meta-LearningSelf-supervised Feature Extraction for Enhanced Ball Detection on Soccer Robots
Robust and accurate ball detection is a critical component for autonomous humanoid soccer robots, particularly in dynamic and challenging environments such as RoboCup outdoor fields. However, traditional supervised appro…
ColorizationEdge DetectionMeta-LearningSelf-Supervised Learning+1MetaQAP -- A Meta-Learning Approach for Quality-Aware Pretraining in Image Quality Assessment
Image Quality Assessment (IQA) is a critical task in a wide range of applications but remains challenging due to the subjective nature of human perception and the complexity of real-world image distortions. This study pr…
Image Quality AssessmentMeta-LearningIn-Context Learning for Gradient-Free Receiver Adaptation: Principles, Applications, and Theory
In recent years, deep learning has facilitated the creation of wireless receivers capable of functioning effectively in conditions that challenge traditional model-based designs. Leveraging programmable hardware architec…
In-Context LearningMeta-LearningState Space ModelsMeta-SurDiff: Classification Diffusion Model Optimized by Meta Learning is Reliable for Online Surgical Phase Recognition
Online surgical phase recognition has drawn great attention most recently due to its potential downstream applications closely related to human life and health. Despite deep models have made significant advances in captu…
Meta-LearningOnline surgical phase recognitionSurgical phase recognitionSocratic RL: A Novel Framework for Efficient Knowledge Acquisition through Iterative Reflection and Viewpoint Distillation
Current Reinforcement Learning (RL) methodologies for Large Language Models (LLMs) often rely on simplistic, outcome-based reward signals (e.g., final answer correctness), which limits the depth of learning from each int…
Meta-Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)Few-Shot Learning for Industrial Time Series: A Comparative Analysis Using the Example of Screw-Fastening Process Monitoring
Few-shot learning (FSL) has shown promise in vision but remains largely unexplored for \emph{industrial} time-series data, where annotating every new defect is prohibitively expensive. We present a systematic FSL study o…
BenchmarkingFew-Shot LearningMeta-LearningMetric Learning+1Meta-learning how to Share Credit among Macro-Actions
One proposed mechanism to improve exploration in reinforcement learning is through the use of macro-actions. Paradoxically though, in many scenarios the naive addition of macro-actions does not lead to better exploration…
Atari GamesMeta-LearningLatent Representation Learning of Multi-scale Thermophysics: Application to Dynamics in Shocked Porous Energetic Material
Coupling of physics across length and time scales plays an important role in the response of microstructured materials to external loads. In a multi-scale framework, unresolved (subgrid) meso-scale dynamics is upscaled t…
Meta-LearningRepresentation LearningDifferentially Private Bilevel Optimization: Efficient Algorithms with Near-Optimal Rates
Bilevel optimization, in which one optimization problem is nested inside another, underlies many machine learning applications with a hierarchical structure -- such as meta-learning and hyperparameter optimization. Such …
Bilevel OptimizationHyperparameter OptimizationMeta-LearningPDEfuncta: Spectrally-Aware Neural Representation for PDE Solution Modeling
Scientific machine learning often involves representing complex solution fields that exhibit high-frequency features such as sharp transitions, fine-scale oscillations, and localized structures. While implicit neural rep…
Meta-LearningHybrid Meta-Learning Framework for Anomaly Forecasting in Nonlinear Dynamical Systems via Physics-Inspired Simulation and Deep Ensembles
We propose a hybrid meta-learning framework for forecasting and anomaly detection in nonlinear dynamical systems characterized by nonstationary and stochastic behavior. The approach integrates a physics-inspired simulato…
Anomaly DetectionAnomaly ForecastingAnomaly LocalizationMeta-Learning+1A Gradient Meta-Learning Joint Optimization for Beamforming and Antenna Position in Pinching-Antenna Systems
In this paper, we consider a novel optimization design for multi-waveguide pinching-antenna systems, aiming to maximize the weighted sum rate (WSR) by jointly optimizing beamforming coefficients and antenna position. To …
Meta-LearningPositionRobust LLM Unlearning with MUDMAN: Meta-Unlearning with Disruption Masking And Normalization
Language models can retain dangerous knowledge and skills even after extensive safety fine-tuning, posing both misuse and misalignment risks. Recent studies show that even specialized unlearning methods can be easily rev…
Meta-LearningTARRobust Molecular Property Prediction via Densifying Scarce Labeled Data
A widely recognized limitation of molecular prediction models is their reliance on structures observed in the training data, resulting in poor generalization to out-of-distribution compounds. Yet in drug discovery, the c…
Drug DiscoveryMeta-LearningMolecular Property PredictionProperty PredictionDetecting Sockpuppetry on Wikipedia Using Meta-Learning
Malicious sockpuppet detection on Wikipedia is critical to preserving access to reliable information on the internet and preventing the spread of disinformation. Prior machine learning approaches rely on stylistic and me…
Meta-LearningMeta-learning Representations for Learning from Multiple Annotators
We propose a meta-learning method for learning from multiple noisy annotators. In many applications such as crowdsourcing services, labels for supervised learning are given by multiple annotators. Since the annotators ha…
Meta-LearningTest-Time Adaptation for Generalizable Task Progress Estimation
We propose a test-time adaptation method that enables a progress estimation model to adapt online to the visual and temporal context of test trajectories by optimizing a learned self-supervised objective. To this end, we…
In-Context LearningMeta-LearningTest-time AdaptationTowards Efficient and Effective Alignment of Large Language Models
Large language models (LLMs) exhibit remarkable capabilities across diverse tasks, yet aligning them efficiently and effectively with human expectations remains a critical challenge. This thesis advances LLM alignment by…
Mathematical ReasoningMeta-Learning