This work examines whether Large Language Models (LLMs) can serve as explanation layers that translate post-hoc explanation artefacts into stakeholder-appropriate risk narratives and discusses implications for the governance of risk models, including deployment considerations and the value of domain-aligned LLMs in regulated credit settings.
Sahab Zandi, Noah Kostesku, Christophe Mues et al.· 0 citations
This work integrates SmoothQuant into TorchAO and optimize the resulting inference path for Intel Xeon CPUs through graph-level fusion in TorchInductor and efficient INT8 GEMM kernel selection across oneDNN-, AVX512_VNNI-, and AMX-based implementations.
OVIP-SG is presented, a unified framework for instance-preserving semantic mapping, functional scene partitioning, and language-guided small, fine-grained object retrieval that outperforms ConceptGraphs under a unified evaluation protocol on Replica.
Tianjing Hao, Hai-Yu Lan, Ang Li et al.· 0 citations
The findings indicate that anchoring experiential loops within a scannable digital format systematically drives uniform cognitive gains, offering a robust pedagogical vehicle for vocational mathematics education.
A. Yuliani, Aflich Yusnita Fitrianna, Norma Alias· Riemann: Research of Mathema...· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
This paper evaluates training-free vision language model (VLM) localization on two datasets representing same-section high-correspondence and adjacent-section low-correspondence imaging and tests unconstrained and metadata-constrained search and VLMs with geometric controls, classical template matching, and two alternative training-free approaches.
Xiangyu Yin, T. Paunesku, Letonia Copeland-Hardin et al.· 0 citations
This work proposes CounterfactualLVLM, a training-free and plug-and-play framework that mitigates object hallucinations via small-model-assisted counterfactual reasoning and highlights the power of counterfactual guidance as a simple yet effective paradigm for enhancing factual grounding in LVLM-based multi-modal reasoning.
Xilin Li, Boyue Wang, Xiaoqian Ju et al.· Multimedia Systems· 0 citations
This perspective examines recent developments in AI for PV and introduces a conceptual framework of “computable PV,” in which tasks are evaluated based on their computational tractability and suitability for automation.
Leihong Wu, Joshua Xu, Oanh Dang et al.· Frontiers in Drug Safety and...· 0 citations
Two language-model-based strategies are proposed for semantic code document segmentation, including a line-by-line approach that classifies each line of code separately before grouping the results into functional units, and a range-based approach that aims to directly determine groups of code lines from the input.
Abdelhalim Hafedh Dahou, A. Scherp, Sebastian Kurten et al.· Proceedings of the 2026 ACM...· 0 citations
This paper proposes the Evaluation Context Protocol (ECP), an early-stage, vendor-neutral framework intended to act as a portable evaluation contract layer for agentic systems and describes an open-source reference implementation that includes adapters for LangChain, LlamaIndex, CrewAI, and PydanticAI.
Small language models can grade open-ended examination answers as reliably as substantially more expensive models when they grade against an explicit rubric. We test this claim as the design principle behind any-to-bench: a frontier model reads source documents once, at ingestion, to extract each question and its rubric; lower-cost models then perform all repeated grading work. We evaluate six cost-efficient model configurations from two model families at three reasoning-effort levels. Each configuration answers 24 open-ended examination questions, and each also grades every answer sheet three times, yielding 3,456 per-question grades. Scores depend overwhelmingly on the answer being graded: answer identity explains 95.6% of score variance, whereas judge identity explains only 0.2%. Raising a writer's reasoning effort moves earned scores by as much as 0.143 of full marks, while raising a judge's reasoning effort moves assigned scores by at most 0.006. Six frontier-tier judges, added as a check, reproduce these scores and are no more reliable as a panel. Two ablations then decompose the rubric on the same questions and answers. Removing its criteria and levels while keeping the official answer changes nothing measurable. Removing the official answer as well collapses reliability (ICC 0.888 to 0.628), inflates scores, and makes judge reasoning effort matter again. The rubric is what decouples grading from judge intelligence, and within the rubric the official answer does nearly all the work. We find no evidence of length preference or same-family preference under rubric-anchored grading.
This work mathematically formalizes how transformers execute abstract reasoning and provides a novel, strictly geometric signature for evaluating factual reliability, proving that deep LLM latent spaces natively organize into Small-World networks.
An augmented reality learning medium integrated with a deep-learning-oriented pedagogy for the Solar System topic supports the feasibility and educational promise of combining interactive AR visualization with cognitively engaging pedagogy.
Bagas Brilian Ramadhan, Meida Wulan Sari, S. Yamtinah et al.· Kognisi: Jurnal Ilmu Kegurua...· 0 citations
