Modality-Contrastive Preference Optimization (MCPO), a highly sample-efficient two-stage length-compression method that requires fewer than 900 training samples, and adopts a highly nonlinear odds-ratio formulation that provides steep gradients in the with-image context to reinforce length constraints for preferred tra...
Guang-Heng Yang, Zhen-Liang Ni, Zhen-Kai Wu et al.· 0 citations
A reinforcement-learning training set enriched with Chinese and adversarial instructions is constructed, which significantly improves model performance on MM-IFEval-Pro and transfers effectively to other mainstream multimodal benchmarks, demonstrating strong cross-task and cross-language generalization.
Chang-Ming Xiao, Zhen-Liang Ni, Jin-Hui He et al.· 0 citations
This work introduces an adaptive visual token selection strategy for VLMs that leverages average text-to-visual attention scores to assess the importance of visual tokens, removing redundant ones during pruning based on a set threshold, thereby optimizing the importance calculation.
Yaozhi Wen, Jialong Guo, Zhen-Liang Ni et al.· 0 citations
CapProbe is introduced, a full-scene dense QA benchmark that turns detailed caption evaluation into region-aligned factual checking and is cost-effective: by converting unconstrained scalar scoring into structured MCQ reading, it reduces open-ended scoring bias while remaining judge-conditioned and yields relatively st...
Mouxiao Huang, Qi Yan, Bo-Rui Jiang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
