training samples
Training samples are the individual data points used to train a machine learning model, consisting of input features and corresponding target outputs that help the model learn patterns and relationships in the data.
- A solvable model of learning generative diffusion: theory and insights
- Adaptive Batch-Wise Sample Scheduling for Direct Preference Optimization
- Algorithm- and Data-Dependent Generalization Bounds for Diffusion Models
- Emergence and scaling laws in SGD learning of shallow neural networks
- LOMIA: Label-Only Membership Inference Attacks against Pre-trained Large Vision-Language Models
- On Traceability in $\ell_p$ Stochastic Convex Optimization
- SAM-R1: Leveraging SAM for Reward Feedback in Multimodal Segmentation via Reinforcement Learning
- SE-GUI: Enhancing Visual Grounding for GUI Agents via Self-Evolutionary Reinforcement Learning
- Temporal In‑Context Fine‑Tuning for Versatile Control of Video Diffusion Models