**CRAFT** (Consensus Reasoning knowledge graph Aggregation for Flaw-aware Trace synthesis), which aggregates the consensus components shared across multiple candidate reasoning traces to synthesize improved ones, consistently improves label-prediction accuracy on both logical and mathematical reasoning benchmarks.
Zi-Peng Ling, Shuliang Liu, Sheng-Hong Fu et al.· arXiv.org· 1 citation
This paper surveys the VDR landscape as a retrieval problem in its own right, rather than as the front end of a generation pipeline, and does so specifically through the lens of the Multimodal Large Language Model (MLLM) era, and dives into the methodological evolution along two orthogonal axes.
This work introduces AnchorFold, a training-free focus-then-fold framework for document-side index compression, which consistently outperforms all evaluated training-free baselines at $\gamma \leq 0.20$.
EviAnchor is proposed, a training-free and single-branch inference framework that preserves and reactivates visual evidence throughout generation in large vision-language models and demonstrates consistent improvements in visual grounding.
Sihang Jia, Shuliang Liu, Song-Bo Yang et al.· 0 citations
This work starts from an empirical observation: when query-relevant visual evidence is explicitly strengthened using the model's own attention, generation becomes more accurate, suggesting that many failures do not arise solely from missing perception, but from an insufficient tendency to trust the evidence the model h...
Xin Zou, Hao Deng, Yibo Yan 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.
