LIRA: A More Interpretable Dynamic Loss-Informed Rank Allocation for Low-Rank Adaptation
cs.LG, cs.AI
Submitted: 2026-11-03
Updated: 2026-11-03
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- RoBERTa: A Robustly Optimized BERT Pretraining Approach
- FIM-LoRA: Task-Informative Rank Allocation for LoRA via Calibration-Time Gradient-Variance Estimation
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis