Diversity-Enhanced Reasoning for Subjective Questions

Yumeng Wang*, Zhiyuan Fan*, Jiayu Liu*, May Fung

• We propose MultiRole-R1, a diversity-enhanced framework with multiple role perspectives, to improve the accuracy and diversity in subjective reasoning tasks. MultiRole-R1 features an unsupervised data construction pipeline that generates reasoning chains that incorporate diverse role perspectives. We further employ reinforcement learning via Group Relative Policy Optimization (GRPO) with reward shaping, by taking diversity as a reward signal in addition to the verifiable reward.

Unveiling the Lack of LVLM Robustness to Fundamental Visual Variations: Why and Path Forward

Zhiyuan Fan*, Yumeng Wang*, Sandeep Polisetty, May Fung

• Large Vision Language Models (LVLMs) excel in various vision-language tasks. Yet, their robustness to visual variations in position, scale, orientation, and context that objects in natural scenes inevitably exhibit due to changes in viewpoint and environment remains largely underexplored. To bridge this gap, we introduce V2R-Bench, a comprehensive benchmark framework for evaluating Visual Variation Robustness of LVLMs, which encompasses automated evaluation dataset generation and principled metrics for thorough robustness assessment.

CoKnowledge: Supporting Assimilation of Time-synced Collective Knowledge in Online Science Videos

Yuanhao Zhang, Yumeng Wang, Xiyuan Wang, Changyang He, Chenliang Huang, Xiaojuan Ma

• We propose a web demo to develop CoKnowledge – a tool incorporating a video abstract, knowledge graphs, and supplementary danmaku features to support viewers’ assimilation of collective knowledge in science videos.

CALM: Unleashing the Cross-Lingual Self-Aligning Ability of Language Model Question Answering

Yumeng Wang, Zhiyuan Fan, Qingyun Wang, May Fung, Heng Ji

Github

• We propose a self consistency based multilingual alignment algorithm to bridge the knowledge gap across different languages. We evaluate this method under both zero-shot chain-of-thought and retrieval augmented setting.

DoNet: Deep De-Overlapping Network for Cytology Instance Segmentation

Hao Jiang*, Rushan Zhang*, Yanning Zhou, Yumeng Wang, Hao Chen

Google Scholar | Paper | Code |

• In this work, we proposed a De-overlapping Network (DoNet) in a decompose-and-recombined strategy. A Dual-path Region Segmentation Module (DRM) explicitly decomposes the cell clusters into intersection and complement regions, followed by a Semantic Consistency-guided Recombination Module (CRM) for integration. To further introduce the containment relationship of the nucleus in the cytoplasm, we design a Mask-guided Region Proposal Strategy (MRP) that integrates the cell attention maps for inner-cell instance prediction.