baseline comparison
Baseline comparison refers to the process of evaluating a new model against a standard baseline model or benchmark to gauge its performance. It provides a reference point to understand the efficacy and improvements of the proposed method.
- A Bayesian Fast-Slow Framework to Mitigate Interference in Non-Stationary Reinforcement Learning
- Advancing Interpretability of CLIP Representations with Concept Surrogate Model
- Efficient Utility-Preserving Machine Unlearning with Implicit Gradient Surgery
- FedFACT: A Provable Framework for Controllable Group-Fairness Calibration in Federated Learning
- Localized Data Shapley: Accelerating Valuation for Nearest Neighbor Algorithms
- MesaTask: Towards Task-Driven Tabletop Scene Generation via 3D Spatial Reasoning
- Meta-Learning Objectives for Preference Optimization
- Model Provenance Testing for Large Language Models
- NoPo-Avatar: Generalizable and Animatable Avatars from Sparse Inputs without Human Poses
- OCN: Effectively Utilizing Higher-Order Common Neighbors for Better Link Prediction
- R-KV: Redundancy-aware KV Cache Compression for Reasoning Models
- RePIC: Reinforced Post-Training for Personalizing Multi-Modal Language Models
- SpEx: A Spectral Approach to Explainable Clustering
- Weak-to-Strong Generalization under Distribution Shifts
- metaTextGrad: Automatically optimizing language model optimizers