model training
Model training is the process of optimizing a model's parameters using labeled data, effectively teaching it to identify patterns and make predictions or classifications. This typically involves iterating through data to minimize error rates.
- A Theory for Worst-Case vs. Average-Case Guarantees for LLMs
- BMW: Bidirectionally Memory bank reWriting for Unsupervised Person Re-Identification
- Conformal Risk Training: End-to-End Optimization of Conformal Risk Control
- Continual Release Moment Estimation with Differential Privacy
- Differentially Private Relational Learning with Entity-level Privacy Guarantees
- EvolvedGRPO: Unlocking Reasoning in LVLMs via Progressive Instruction Evolution
- Incremental Sequence Classification with Temporal Consistency
- Information-Theoretic Reward Decomposition for Generalizable RLHF
- Inpainting the Neural Picture: Inferring Unrecorded Brain Area Dynamics from Multi-Animal Datasets
- InternScenes: A Large-scale Simulatable Indoor Scene Dataset with Realistic Layouts
- Investigating and Mitigating Catastrophic Forgetting in Medical Knowledge Injection through Internal Knowledge Augmentation Learning
- LLM-Driven Treatment Effect Estimation Under Inference Time Text Confounding
- Lie Detector: Unified Backdoor Detection via Cross-Examination Framework
- MARS: A Malignity-Aware Backdoor Defense in Federated Learning
- Mitra: Mixed Synthetic Priors for Enhancing Tabular Foundation Models
- Prediction-Powered Semi-Supervised Learning with Online Power Tuning
- SD-VLM: Spatial Measuring and Understanding with Depth-Encoded Vision-Language Models
- Scalable Evaluation and Neural Models for Compositional Generalization
- Scaling Embedding Layers in Language Models
- Scaling Physical Reasoning with the PHYSICS Dataset
- ShotBench: Expert-Level Cinematic Understanding in Vision-Language Models
- Synthesize Privacy-Preserving High-Resolution Images via Private Textual Intermediaries
- Toward Artificial Palpation: Representation Learning of Touch on Soft Bodies