Learning to Predict Distributions over Weight Updates for Test-Time Adaptation
cs.LG
Submitted: 2026-10-01
Updated: 2026-10-01
Terminology
Sources
- LoRA: Low-Rank Adaptation of Large Language Models
- HyperNetworks
- Text-to-LoRA: Instant Transformer Adaption
- SHINE: A Scalable In-Context Hypernetwork for Mapping Context to LoRA in a Single Pass
- Doc-to-LoRA: Learning to Instantly Internalize Contexts
- Tent: Fully Test-time Adaptation by Entropy Minimization
- Test-Time Learning for Large Language Models
- SLOT: Sample-specific Language Model Optimization at Test-time
- End-to-End Test-Time Training for Long Context
- Bayesian Hypernetworks
- Implicit Weight Uncertainty in Neural Networks
- HyperGAN: A Generative Model for Diverse, Performant Neural Networks
- In-Context Meta LoRA Generation
- DiffLoRA: Generating Personalized Low-Rank Adaptation Weights with Diffusion
- Bayesian Low-rank Adaptation for Large Language Models
- BLoB: Bayesian Low-Rank Adaptation by Backpropagation for Large Language Models
- LoRA ensembles for large language model fine-tuning
- Neural Thickets: Diverse Task Experts Are Dense Around Pretrained Weights
- Auto-Encoding Variational Bayes
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
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