supervised learning
A type of machine learning where models are trained on labeled datasets, learning to predict outputs from given inputs. It requires a predefined dataset with input-output pairs to guide the learning process.
- A Closer Look to Positive-Unlabeled Learning from Fine-grained Perspectives: An Empirical Study
- A High-Dimensional Statistical Method for Optimizing Transfer Quantities in Multi-Source Transfer Learning
- ACT as Human: Multimodal Large Language Model Data Annotation with Critical Thinking
- AMBER: Adaptive Mesh Generation by Iterative Mesh Resolution Prediction
- Adaptive Surrogate Gradients for Sequential Reinforcement Learning in Spiking Neural Networks
- Adaptive Surrogate Gradients for Sequential Reinforcement Learning in Spiking Neural Networks
- Asymptotically Stable Quaternion-valued Hopfield-structured Neural Network with Periodic Projection-based Supervised Learning Rules
- CaMiT: A Time-Aware Car Model Dataset for Classification and Generation
- CamEdit: Continuous Camera Parameter Control for Photorealistic Image Editing
- Can Large Language Models Master Complex Card Games?
- CoT Information: Improved Sample Complexity under Chain-of-Thought Supervision
- CoUn: Empowering Machine Unlearning via Contrastive Learning
- Computational Efficiency under Covariate Shift in Kernel Ridge Regression
- Compute-Optimal Scaling for Value-Based Deep RL
- Consistent Supervised-Unsupervised Alignment for Generalized Category Discovery
- Contribution of task-irrelevant stimuli to drift of neural representations
- Deferring Concept Bottleneck Models: Learning to Defer Interventions to Inaccurate Experts
- Learning Juntas under Markov Random Fields
- Learning to Condition: A Neural Heuristic for Scalable MPE Inference
- Learning to Flow from Generative Pretext Tasks for Neural Architecture Encoding
- Solving Continuous Mean Field Games: Deep Reinforcement Learning for Non-Stationary Dynamics
- Storyboard-guided Alignment for Fine-grained Video Action Recognition
- The Power of Iterative Filtering for Supervised Learning with (Heavy) Contamination
- UGM2N: An Unsupervised and Generalizable Mesh Movement Network via M-Uniform Loss