AI Paper Atlas

Research map / Reinforcement learning / RL from feedback

Injecting Distributional Awareness into MLLMs via Reinforcement Learning for Deep Imbalanced Regression

Yao DU, Shanshan Song, Xiaomeng Li

ICML 2026 · Reinforcement learning › RL from feedback · approach: RL for LLM reasoning · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add CCC batch-level reward to a pairwise rank reward (ablation)GRPO · AgeDB-DIR (Qwen2.5-VL-3B)MAE (all): 9.35 -> 5.57Improved
add CCC reward on top of regression MAE reward (ablation)GRPO · AgeDB-DIR (Qwen2.5-VL-3B)MAE (all): 5.85 -> 5.61Improved
add CCC reward on top of Spearman correlation reward (ablation)GRPO · AgeDB-DIR (Qwen2.5-VL-3B)MAE (all): 6.81 -> 5.68Improved
add CCC reward on top of Spearman reward (ablation)GRPO · AgeDB-DIR (Qwen2.5-VL-3B)GM (few-shot): 3.40 -> 4.18Hurt
use CCC reward instead of per-sample DISCO MAE reward (ablation)GRPO · AgeDB-DIR (Qwen2.5-VL-3B)MAE (all): 5.95 -> 5.52Improved
use CCC-GRPO instead of SFTQwen2.5-VL-3B · IMDB-Movie-DIRMAE (few-shot): 21.51 -> 16.35Improved
use CCC-GRPO instead of SFTQwen2.5-VL-3B · IMDB-Movie-DIRMAE (medium-shot): 11.21 -> 8.12Improved
use CCC-GRPO instead of SFTQwen2.5-VL-7B · BoneAge-DIRMAE (all): 17.09 -> 13.35Improved
use DrGRPO instead of GRPO with CCC reward (ablation)CCC-GRPO · AgeDB-DIR (Qwen2.5-VL-3B)MAE (all): 5.52 -> 5.73No clear effect
use RegGRPO instead of GRPO with CCC reward (ablation)CCC-GRPO · AgeDB-DIR (Qwen2.5-VL-3B)MAE (all): 5.52 -> 5.56No clear effect
increase generations from 4 to 8 (ablation)CCC-GRPO · AgeDB-DIR (Qwen2.5-VL-3B)MAE (all): 5.52 -> 5.53No clear effect
increase batch size from 16 to 32 (ablation)CCC-GRPO · AgeDB-DIR (Qwen2.5-VL-3B)MAE (all): 5.52 -> 5.56No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy