LARC: Low-Rank Adaptive Residual Connections for Learning in Frozen Models
cs.LG, cs.CL
Submitted: 2026-09-30
Updated: 2026-09-30
Terminology
Sources
- Using Fast Weights to Attend to the Recent Past
- ReZero is All You Need: Fast Convergence at Large Depth
- Titans: Learning to Memorize at Test Time
- Provable Meta-Learning with Low-Rank Adaptations
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- Deep Residual Learning for Image Recognition
- Parameter-Efficient Transfer Learning for NLP
- LoRA: Low-Rank Adaptation of Large Language Models
- Decoupled Weight Decay Regularization
- On First-Order Meta-Learning Algorithms
- Learning to (Learn at Test Time): RNNs with Expressive Hidden States
- Test-Time Training with Self-Supervision for Generalization under Distribution Shifts
- Meta-Learning at Scale for Large Language Models via Low-Rank Amortized Bayesian Meta-Learning
- MMLA: Memory-Mediated Learning Architecture for Predictive Dual-State Adaptation
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