Reassessing Global Gradient-Norm Imbalance in BLIP Fine-Tuning Across Physical Domains

arXiv:2609.23655 · cs.CV · Submitted 2026-09-20 · Read on arXiv

cs.CV

Submitted: 2026-09-20

Updated: 2026-09-20

Code: https://github.com/KiranNaseer-AI/multimodal-domain-shift-vlm

Terminology

• Fine-Tuning — 40× in this paper · explained in 5 episodes
• Adaptation — 9× in this paper · explained in 1 episode
• Domain Shift — 9× in this paper · explained in 4 episodes
• Computer Vision and Pattern Recognition — 4× in this paper
• Decoupling — 4× in this paper · explained in 2 episodes
• Multimodal Learning — 4× in this paper · explained in 2 episodes
• Ablation — 3× in this paper · explained in 1 episode
• International Conference on Learning Representations — 3× in this paper
• International Conference on Machine Learning — 3× in this paper
• Consistency — 2× in this paper · explained in 3 episodes
• Quantization — 2× in this paper · explained in 12 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Underwater Image Captioning Dataset — 2× in this paper
• Adaptive Reweighting — 1× in this paper · explained in 1 episode
• Association for Computational Linguistics — 1× in this paper
• Benchmark — 1× in this paper · explained in 2 episodes
• Distribution Shift — 1× in this paper · explained in 6 episodes
• Gradient Flow — 1× in this paper · explained in 2 episodes
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• International Conference on Computer Vision — 1× in this paper
• LoRA Adapters — 1× in this paper · explained in 3 episodes
• Multi-objective Optimization — 1× in this paper · explained in 4 episodes
• Pairwise Comparisons — 1× in this paper · explained in 2 episodes
• Parameter-Efficient Fine-Tuning — 1× in this paper · explained in 2 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Robustness — 1× in this paper · explained in 5 episodes

Sources

• Pareto LoRA: Mitigating Modality Imbalance in Unified Multimodal Models via Pareto-Optimal Gradient Integration
• On-the-fly Modulation for Balanced Multimodal Learning
• PLoP: Precise LoRA Placement for Efficient Finetuning of Large Models
• BalanceBenchmark: A Survey for Multimodal Imbalance Learning
• Improving Stability of Fine-Tuning Pretrained Language Models via Component-Wise Gradient Norm Clipping
• Microsoft COCO Captions: Data Collection and Evaluation Server

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models