A dual-level confidence based framework (DuCoR) that achieves implicit self-refinement through iterative pseudo-supervised optimization that achieves superior performance and exhibits improved cross-domain generalization over fully supervised baseline.
DualRead builds on the insight that reliability can be read from the actor's internal states at critical moments in the answering process and improves correctness discrimination and calibration over verbalized confidence while preserving answer accuracy.
Yang-Yang Xie, Ke-Chun Hao, Jia-Qi Liu et al.· 0 citations
This work presents MedProb, a lightweight probing framework that predicts multiple-choice Med-VQA answers from frozen VLM representations without free-text generation, and shows the probe can be extended to open-ended generation via a rejection-sampling scoring procedure.
A novel training framework that enhances counterfactual contrastive learning for VQA and introduces a three-stage curriculum for stable multi-objective optimization, an enhanced Batch-Contrastive loss for more discriminative feature learning and two novel regularizers.
Truong-Binh Duong, T. Tran, Ngoc-Thao Nguyen et al.· 0 citations
A dual-branch frequency-domain fusion module that conditions spectral filtering on the input question, enabling adaptive selection of global low-frequency structure and fine-grained high-frequency detail before reconstructing the spatial representation for answer generation is introduced.
A simpler competing hypothesis on MedFrameQA is tested: methods that remain tightly aligned with the benchmark's final answer objective should be the strongest robust adaptation family once evaluation is controlled across fixed splits, matched budgets, repeated seeds, and calibration.
Site Li, Jianyi Hao, Xiaofeng Liu· arXiv.org· 0 citations
Consistent gains over DVD on LVBench, Video-MME, EgoSchema, and LongVideoBench suggest that option-aware evidence acquisition transfers beyond MMR-V, and proposes PACE (Progressive Acquisition of Critical Evidence), a factor-guided framework for long-video evidence acquisition.
Bai-Xuan Xu, Yinyui Xu, Tianshi ZHENG et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
