When Less Compute Is More: Adaptive Early Exit Improves Pretrained Outlier Detection
cs.LG, cs.AI
Submitted: 2026-09-26
Updated: 2026-09-26
Terminology
Sources
- VIP-COP: Context Optimization for Tabular Foundation Models
- Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach
- TabPFN-3: Technical Report
- DiScoFormer: Plug-In Density and Score Estimation with Transformers
- Scaling Laws for Neural Language Models
- Skip a Layer or Loop It? Learning Program-of-Layers in LLMs
- In-Context Data Distillation with TabPFN
- TabDPT: Scaling Tabular Foundation Models on Real Data
- TACTIC for Navigating the Unknown: Tabular Anomaly deteCTion via In-Context inference
- In-context Learning and Induction Heads
- TabICL: A Tabular Foundation Model for In-Context Learning on Large Data
- TabICLv2: A better, faster, scalable, and open tabular foundation model
- Sparse Attention as Compact Kernel Regression
- ICLAD: In-Context Learning for Unified Tabular Anomaly Detection Across Supervision Regimes
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: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks