Pragmatic competence remains a vital yet often overlooked area in instructed second language learning, particularly in the domain of refusal speech acts. This quasi-experimental study investigated the effect of VR-mediated explicit pragmatics instruction on L2 learners’ refusal strategies. Fifty-two intermediate-leve...
Selin Demir, D. Atay· RELC Journal : A Journal of...· 0 citations
Background: Reliable access to postoperative guidance between clinic visits remains inconsistent, and the usefulness of large language models depends on how clinical knowledge is structured and retrieved. Knowledge graph-only (KG-only), vector retrieval-augmented generation (RAG-only), and hybrid graph-retrieval (Graph...
Srinivagasam Prabha, B. Collaço, Carina Rosa Malena et al.· Bioengineering· 0 citations
ANI-Gamut is presented, a reproducible, open-source playground that exposes the same task at several levels on a single, densely populated brownfield substrate, where many coexisting services share resources and collateral damage actually arises.
Lorenzo Bracciale, P. Loreti, A. Mayer et al.· 0 citations
MaskVLA, a masking-based fine-tuning strategy that randomly masking a small portion of the main camera's visual information leads to the emergence of robust policies, thereby enhancing the model's capability to tackle complex manipulation tasks and improving its generalization performance.
Yuxuan Jiang, Jia-Ying Huang, Ge Wang et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
TravPro, which converts standard annotations into ordered region pairs and fits a small readout on frozen vision--language model (VLM) patch tokens to these pairs, producing an ordering sensitive to surface condition that a per-class value cannot represent.
Ji-Hoon Hwang, Jisung Bae, E-In Son et al.· 0 citations
A central problem in nonlinear elasto-plasticity theory is to formulate a geometrically nonlinear, large-strain model of elasto-plasticity in single crystals in which plastic flow is driven directly by the motion of dislocations and which allows for a homogenization procedure from discrete dislocation lines to dislocat...
The results show that lightweight detection, structured spatial-semantic decoding, and deeply integrated vision-language priors can be blended into a single efficient HOI pipeline.
SPHQuant is a rotation-free spherical weight-only quantization framework for VLMs that isolates outlier magnitude into the radius while keeping directions bounded and statistically regular and designs a hardware-friendly GEMV kernel that keeps the direction codebook small enough for shared-memory lookup and packs radia...
Ke-Wei Zhang, Zheng Chen, Hao-Tong Qin et al.· 0 citations
The results show that combining a large zero-shot model with a smaller adapted model provides a practical framework for multilingual and fine-grained hallucination localization, while also highlighting the difficulty of transferring development-set improvements to hidden test data.
Ali Athar, Imran Ahsan, Joon-Yong Jung· 0 citations
DocMIDE is introduced, a fine-tuning framework that trains compact vision-language models to retrieve visual evidence explicitly before deriving an answer, and constrains generation to a plan-retrieve-derive structure and optimizes it with Group Relative Policy Optimization under a four-component, rule-based reward.
Jeremy Cerwin Wang, Wai-Kit Wong, Jeff Tang· 0 citations
Across seven benchmarks and four base VLMs, VLM-in-Sandbox achieves the highest sample-weighted average accuracy among Vanilla VLM, Append-only Sandbox, and the proposed method, and is identified as a central abstraction for sandboxed VLM agents.
He-Xiong Yang, Ming-Rui Chen, Jie Cao et al.· 0 citations
ConSynth-X, a paired synthetic construction-site image dataset containing 34,199 images derived from 3,109 real-world source scenes, is presented, providing a structured resource for evaluating and improving the robustness of construction vision and vision-language models under challenging field conditions.
Viet Huy Duong, Ruoxin Xiong, Md Abdullah Al Forhad et al.· 0 citations
StudentSim is a research system for evaluating and improving AI tutoring tools before they are tested with learners. It models how individuals may engage with tutors, giving feedback to improve tutor performance across subjects like chess, writing, and mathematics. The post Simulating student learning for better AI tutoring appeared first on Microsoft Research.
