This work introduces the Epistemic Honesty Quotient (EHQ), which reports three observable sub-scores across two operational axes (epistemic restraint and substantive-answer calibration), and constructs EHQ-3000, a 3,000-question benchmark spanning Fabricated Entity, Post-Cutoff Event, Hyper-Niche True, and Context-Cond...
The multi-view text-guided multimodal fusion adapter (MVFA) is proposed, a parameter-efficient framework that augments frozen LLMs with strong multimodal reasoning capability and achieves state-of-the-art performance on key metrics while updating only a small fraction of parameters.
Peng-Fei Shao, Ji-Sheng Dang, Jia-Wen Fang et al.· 0 citations
Serving optimizations cut orchestrator P90 latency from 3.87s to 2.24s on a GPU footprint reduced by roughly one-third, and self-hosting reduces estimated annual model-serving cost by more than an order of magnitude.
Cen-Mia Zhao, Peng Wang, Chuan Shi et al.· 0 citations
The results provide evidence that output embeddings encode signals relevant to time and space, while also offering a practical tool for interpretability and for downstream temporal and geographic information retrieval tasks, such as temporal ordering, geographic ranking, and tagging.
Esteban Feuerstein, Victoria Klimkowski, J. O. D. de Zarate et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
CUSP (Collective Uncertainty through Semantic Opinion Pooling), a training-free uncertainty quantification framework that maps multiple VLM responses to a shared semantic response space, pools them into a pooled semantic opinion, and reports two complementary system-level signals.
C. Yu, David Garcia, Brian Jalaian et al.· 0 citations
This project seeks to create the infrastructure needed to make legal citation in OpenJustice rigorous and transparent through various enhancements to the extraction and connection of case metadata, and fully integrating the resulting citation graph into the reranker, maximizing LLM reasoning capabilities.
Abstract:This article investigates how admission category and geographic location shape the utilization of language training and employment-related settlement services among immigrants in Canada. Using administrative data from the Longitudinal Immigration Database (IMDB) linked with the Immigration Contribution Agreeme...
Unknown authors· Canadian Ethnic Studies· 0 citations
This work introduces Latent Semantic Scaffolding (LSS), an auxiliary loss applied during human-demonstration pretraining that aligns a VLA's action-token representations to text embeddings of physical-reasoning rationales through a small projection head.
A. Li, Zhuo Li, Zhe-Lin Yang et al.· Cyber ..· 3 citations
Morphological analysis of the flow–volume curve represents a promising approach to complement conventional spirometry in the identification and characterization of fixed airflow obstruction and may provide additional information regarding airflow limitation, non-uniform lung emptying, emphysema, small airway disease, h...
A. Bastidas-Goyes, L. Giraldo-Cadavid, Eduardo Tuta-Quintero et al.· Advances in Respiratory Medi...· 0 citations
The strongest evidence came from narrowly defined tasks with explicit reference standards, including motor-skill assessment, biomechanical estimation, markerless motion capture, and athlete tracking, while evidence for injury prediction, wearable systems, generative AI, and athlete digital twins was less mature.
A. S· International Journal of Phy...· 0 citations
This study investigates whether Guangzhou Cantonese ABB ideophones exhibit iconic-systematicity, the statistical association between speech sounds and sensory meanings that is grounded in perceived resemblance. While such systematic sound-meaning correspondences have been widely documented in Indo-European languages, i...
Dan-Rui Li· Journal of Artificial Intell...· 0 citations
Analysis of word associations generated by humans and large language models indicate that latent semantic representations of human word associations are better integrated than that of the LLMs, illustrating how cross-comparisons with LLM-generated data can provide insights into the nature of human semantic representati...
Cynthia S. Q. Siew· Quarterly Journal of Experim...· 0 citations
