| title | Injecting Distributional Awareness into MLLMs via Reinforcement Learning for Deep Imbalanced Regression |
|---|---|
| authors | Yao Du, Shanshan Song, Xiaomeng Li |
| date | 2026-05-11 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2605.01402 |
| upvotes | 1 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | Multimodal large language models (MLLMs) struggle with numerical regression under long-tailed 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 performance. We identify the lack of cross-sample relational supervision as a key limitation of existing MLLM training paradigms. To address it, we propose a distribution-aware reinforcement learning framework based on Group Relative Policy Optimization, which introduces batch-level comparison-based supervision via the Concordance Correlation Coefficient-based reward to align predicted and ground-truth distributions in terms of correlation, scale, and mean. The framework is plug-and-play, requiring no architectural modification. Experiments on a unified suite of long-tailed regression benchmarks show consistent improvements over SFT and existing MLLM regression methods, with particularly strong gains in medium- and few-shot regimes. |
cite
@misc{du2026injecting,
title={Injecting Distributional Awareness into MLLMs via Reinforcement Learning for Deep Imbalanced Regression},
author={Yao Du and Shanshan Song and Xiaomeng Li},
year={2026},
eprint={2605.01402},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2605.01402}
}