← Learning Paradigms
Artificial Intelligence › Learning Paradigms ›

Meta-Learning

1524 directly classified papers

Papers per year

Papers

AgentRM: Enhancing Agent Generalization with Reward Modeling ACL 2025
MPO: Boosting LLM Agents with Meta Plan Optimization EMNLP 2025
Rethinking the Starting Point: Collaborative Pre-Training for Federated Downstream Tasks AAAI 2025
Improving Generalization in Meta-Learning via Meta-Gradient Augmentation IJCAI 2025
Capture the Key in Reasoning to Enhance CoT Distillation Generalization ACL 2025
Active Multimodal Distillation for Few-shot Action Recognition IJCAI 2025
Meta-Reasoning Improves Tool Use in Large Language Models NAACL 2025
DANCE: Resource-Efficient Neural Architecture Search with Data-Aware and Continuous Adaptation IJCAI 2025
SEE: Continual Fine-tuning with Sequential Ensemble of Experts ACL 2025
Data Poisoning for In-context Learning NAACL 2025
Real-Time Recurrent Reinforcement Learning AAAI 2025
The Geometry of Prompting: Unveiling Distinct Mechanisms of Task Adaptation in Language Models NAACL 2025
ThinkTuning: Instilling Cognitive Reflections without Distillation EMNLP 2025
First-Order Federated Bilevel Learning AAAI 2025
HyperNVD: Accelerating Neural Video Decomposition via Hypernetworks CVPR 2025
Enhancing Language Model Hypernetworks with Restart: A Study on Optimization NAACL 2025
LEMMA: Learning from Errors for MatheMatical Advancement in LLMs ACL 2025
Scale Down to Speed Up: Dynamic Data Selection for Reinforcement Learning EMNLP 2025
Generative Reviewer Agents: Scalable Simulacra of Peer Review EMNLP 2025
Continual Learning of Large Language Models EMNLP 2025
Vision-Language Models Can Self-Improve Reasoning via Reflection NAACL 2025
Inductive Link Prediction in N-ary Knowledge Graphs COLING 2025
MetaMixSpeech: Meta Task Augmentation for Low-Resource Speech Recognition EMNLP 2025
Learning vs Retrieval: The Role of In-Context Examples in Regression with Large Language Models NAACL 2025
Instruct-of-Reflection: Enhancing Large Language Models Iterative Reflection Capabilities via Dynamic-Meta Instruction NAACL 2025