Modulating Merging Strengths via Joint Loss Estimation for LoRA-based Continual Learning
cs.LG
Submitted: 2026-11-03
Updated: 2026-11-03
Code: https://github.com/bbdeeer/M2LE_NeurIPS2026
Terminology
Sources
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- Sharpness-Aware Minimization for Efficiently Improving Generalization
- BECAME: BayEsian Continual Learning with Adaptive Model MErging
- From Isolation to Integration: Building an Adaptive Expert Forest for Pre-Trained Model-based Class-Incremental Learning
- Fine-Grained Visual Classification of Aircraft
- Train with Perturbation, Infer after Merging: A Two-Stage Framework for Continual Learning
- UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
- Model merging with SVD to tie the Knots
- Navigating Semantic Drift in Task-Agnostic Class-Incremental Learning
- SD-LoRA: Scalable Decoupled Low-Rank Adaptation for Class Incremental Learning
- Reasoning-Driven Multimodal LLM for Domain Generalization
- RobustMerge: Parameter-Efficient Model Merging for MLLMs with Direction Robustness
- Dual-Branch Cross-Projection Debiasing through Diffusion-based Disentanglement
- Revisiting Weight Regularization for Low-Rank Continual Learning
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