Audit Before You Merge: Provenance, Probing, and Continual LoRA Composition
cs.AI, cs.CR, cs.LG
Submitted: 2026-11-07
Updated: 2026-11-07
Code: https://github.com/LennyAharon/audit_continual_learning
Terminology
Sources
- Few-Shot Speech Deepfake Detection Adaptation with Gaussian Processes
- STABLE: Gated Continual Learning for Large Language Models
- Editing Models with Task Arithmetic
- Preference-Aligned LoRA Merging: Preserving Subspace Coverage and Addressing Directional Anisotropy
- The Appeal and Reality of Recycling LoRAs with Adaptive Merging
- Closed-form merging of parameter-efficient modules for Federated Continual Learning
- K-Merge: Online Continual Merging of Adapters for On-device Large Language Models
- Understanding Layer Significance in LLM Alignment
- Merging Models on the Fly Without Retraining: A Sequential Approach to Scalable Continual Model Merging
- Crowded in B-Space: Calibrating Shared Directions for LoRA Merging
- A Survey on Model MoErging: Recycling and Routing Among Specialized Experts for Collaborative Learning
- LoRI: Reducing Cross-Task Interference in Multi-Task Low-Rank Adaptation
- Merging LoRAs like Playing LEGO: Pushing the Modularity of LoRA to Extremes Through Rank-Wise Clustering
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents