Dense retrievers have made significant progress on text and image corpora, but whether these capabilities extend reliably to mixed corpora containing text, image, and fused text-image documents remains unclear. In this paper, we systematically examine retrievers across architectures and find that their performance is h...
Yu-Bo Sun, Chun-Yi Peng, Yu-Kun Yan et al.· 0 citations
ConceptFormer models query-relevant evidence as continuous, query-conditioned latent concepts that explicitly bridge localized visual evidence and semantic relevance, without requiring either textual intermediate representations or direct reliance on raw visual annotations.
Chunyi Peng, Zhi-Peng Xu, Yu-Kun Yan et al.· 0 citations
HiEviDR-Bench is introduced, a benchmark for evaluating Hierarchical Evidence Aggregation in Deep Research and a traceability-oriented evaluation framework with five dimensions: report quality, evidence traceability, citation accuracy, claim verification, and answer correctness, together with a progressive gating mecha...
Yu-Bo Sun, Chunyi Peng, Yu-Kun Yan et al.· arXiv.org· 0 citations
REFACT is an adaptive fact-restatement citation framework that enables LLMs to determine when contextual grounding is needed and selectively restate source facts at appropriate levels of detail for reliable reasoning.
Zhensheng Jin, Xin Dai, Zhenghao Liu et al.· arXiv.org· 0 citations
MemoryCard is a video-memory-based augmentation framework that organizes long videos into self-contained Memory Cards, each corresponding to a distinct topic or event, and consistently improves long-video QA performance under comparable visual-token budgets.
Qing Yang, Pengcheng Huang, Xinze Li et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
