activity
20242026
collaborators

6 papers

cs.LG2026

Balancing the Reasoning Load: Difficulty-Differentiated Policy Optimization with Length Redistribution for Efficient and Robust Reinforcement Learning

Yinan Xia, Haotian Zhang, Huiming Wang

Large Reasoning Models (LRMs) have shown exceptional reasoning capabilities, but they also suffer from the issue of overthinking, often generating excessively long and redundant an…

cs.LG2026

From the Inside Out: Progressive Distribution Refinement for Confidence Calibration

Xizhong Yang, Yinan Xia, Huiming Wang +1

Leveraging the model's internal information as the self-reward signal in Reinforcement Learning (RL) has received extensive attention due to its label-free nature. While prior work…

cs.CV2025

Dream-IF: Dynamic Relative EnhAnceMent for Image Fusion

Xingxin Xu, Bing Cao, Dongdong Li +2

Image fusion aims to integrate comprehensive information from images acquired through multiple sources. However, images captured by diverse sensors often encounter various degradat…

cs.CV2025

MSR-Align: Policy-Grounded Multimodal Alignment for Safety-Aware Reasoning in Vision-Language Models

Yinan Xia, Yilei Jiang, Yingshui Tan +3

Vision-Language Models (VLMs) have achieved remarkable progress in multimodal reasoning tasks through enhanced chain-of-thought capabilities. However, this advancement also introdu…

cs.CV2024

Test-Time Dynamic Image Fusion

Bing Cao, Yinan Xia, Yi Ding +2

The inherent challenge of image fusion lies in capturing the correlation of multi-source images and comprehensively integrating effective information from different sources. Most e…

cs.CV2024

Predictive Dynamic Fusion

Bing Cao, Yinan Xia, Yi Ding +2

Multimodal fusion is crucial in joint decision-making systems for rendering holistic judgments. Since multimodal data changes in open environments, dynamic fusion has emerged and a…