TrustMix: Graceful Degradation for Pretrained Models under Distribution Shift
cs.LG
Submitted: 2026-11-04
Updated: 2026-11-04
Code: https://github.com/jniimi/tripadvisor_dataset
Terminology
Sources
- A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantification
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- Benchmarking Neural Network Robustness to Common Corruptions and Perturbations
- A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks
- Shifts: A Dataset of Real Distributional Shift Across Multiple Large-Scale Tasks
- Shifts 2.0: Extending The Dataset of Real Distributional Shifts
- Rethinking Approximate Gaussian Inference in Classification
- Detecting Out-of-Distribution Inputs to Deep Generative Models Using Typicality
- DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- On Feature Collapse and Deep Kernel Learning for Single Forward Pass Uncertainty
- Wide Residual Networks
- Just One Layer Norm Guarantees Stable Extrapolation
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis