Measure Less, Know More: Self-Supervised Test-Time Feature Acquisition
cs.LG, cs.AI
Submitted: 2026-10-02
Updated: 2026-10-02
Code: https://github.com/bunnelab/echo-k
Sources
- Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds
- Wasserstein Measure Coresets
- Selection via Proxy: Efficient Data Selection for Deep Learning
- Adversarial Active Learning for Deep Networks: a Margin Based Approach
- Estimating Conditional Mutual Information for Dynamic Feature Selection
- MMEarth-Bench: Global Model Adaptation via Multimodal Test-Time Training
- Revisiting Active Learning in the Era of Vision Foundation Models
- Information Templates: A New Paradigm for Intelligent Active Feature Acquisition
- A Closer Look at Invalid Action Masking in Policy Gradient Algorithms
- Opportunistic Learning: Budgeted Cost-Sensitive Learning from Data Streams
- Scaling Laws for Neural Language Models
- Learning-To-Measure: In-Context Active Feature Acquisition
- Towards a statistical theory of data selection under weak supervision
- Unsupervised Feature Selection Through Group Discovery
- Chernoff information of exponential families
- Stochastic Encodings for Active Feature Acquisition
- DINOv2: Learning Robust Visual Features without Supervision
- TabICL: A Tabular Foundation Model for In-Context Learning on Large Data
- A Survey on Active Feature Acquisition Strategies
- Proximal Policy Optimization Algorithms
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks