Focus on Likely Classes for Test-Time Prediction
cs.LG, cs.AI
Submitted: 2025-05-02
Updated: 2026-09-27
Code: https://github.com/hzcar/ReCAP
Project page: http://skylion007.github.io/OpenWebTextCorpus
Terminology
Sources
- Stable LM 2 1.6B Technical Report
- Qwen2.5-Coder Technical Report
- Test-Time Training on Nearest Neighbors for Large Language Models
- Fox-1: Open Small Language Model for Cloud and Edge
- Efficiently Learning at Test-Time: Active Fine-Tuning of LLMs
- Efficient Estimation of Word Representations in Vector Space
- Test-Time Adaptation to Distribution Shift by Confidence Maximization and Input Transformation
- Towards Stable Test-Time Adaptation in Dynamic Wild World
- Generative to Agentic AI: Survey, Conceptualization, and Challenges
- Learning to (Learn at Test Time): RNNs with Expressive Hidden States
- Locating and Editing Factual Associations in Mamba
- The Llama 3 Herd of Models
- Tent: Fully Test-time Adaptation by Entropy Minimization
- Calibrating Language Models with Adaptive Temperature Scaling
- Evaluation of OpenAI o1: Opportunities and Challenges of AGI
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