Meta-Learning

Towards Automated Knowledge Integration From Human-Interpretable Representations ICLR 2025 Towards Higher Effective Rank in Parameter-Efficient Fine-tuning using Khatri-Rao Product ICCV 2025 Transformers Can Learn Temporal Difference Methods for In-Context Reinforcement Learning ICLR 2025 Transformer-Squared: Self-adaptive LLMs ICLR 2025 Understanding the Thinking Process of Reasoning Models: A Perspective from Schoenfeld’s Episode Theory EMNLP 2025 UniFORM: Towards Unified Framework for Anomaly Detection on Graphs AAAI 2025 Unlocking the Potential of Black-box Pre-trained GNNs for Graph Few-shot Learning AAAI 2025 Unlocking the Power of Function Vectors for Characterizing and Mitigating Catastrophic Forgetting in Continual Instruction Tuning ICLR 2025 Unsupervised Meta-Learning via In-Context Learning ICLR 2025 VideoScene: Distilling Video Diffusion Model to Generate 3D Scenes in One Step CVPR 2025 Vision-Language Models Can Self-Improve Reasoning via Reflection NAACL 2025 Visualising Policy-Reward Interplay to Inform Zeroth-Order Preference Optimisation of Large Language Models ACL 2025 WebEvolver: Enhancing Web Agent Self-Improvement with Co-evolving World Model EMNLP 2025 Why In-Context Learning Models are Good Few-Shot Learners? ICLR 2025 World Models with Hints of Large Language Models for Goal Achieving NAACL 2025 XAutoLM: Efficient Fine-Tuning of Language Models via Meta-Learning and AutoML EMNLP 2025 Zero-cost Proxy for Adversarial Robustness Evaluation ICLR 2025 ACCEPT: Adaptive Codebook for Composite and Efficient Prompt Tuning EMNLP 2024 AcKnowledge: Acquired Knowledge Representation by Small Language Model Without Pre-training ACL 2024 ADaPT: As-Needed Decomposition and Planning with Language Models NAACL 2024 Adaptive Meta-Learning Probabilistic Inference Framework for Long Sequence Prediction AAAI 2024 Addressing Hidden Confounding with Heterogeneous Observational Datasets for Recommendation NeurIPS 2024 A Good Learner can Teach Better: Teacher-Student Collaborative Knowledge Distillation ICLR 2024 All in One: Multi-task Prompting for Graph Neural Networks (Extended Abstract) IJCAI 2024 AMAGO-2: Breaking the Multi-Task Barrier in Meta-Reinforcement Learning with Transformers NeurIPS 2024