2026
Injecting Distributional Awareness into MLLMs via Reinforcement Learning for Deep Imbalanced Regression
ICML 2026poster
Multimodal large language models (MLLMs) struggle with numerical regression under longtailed target distributions. Token-level supervised fine-tuning (SFT) and point-wise regression rewards bias learning toward high-density regions, leading to regression-to-the-mean behavior and poor tail performanc…