Nepali is a low resource language for speech technology and there is very little open text-to-speech support for it. Most high quality neural TTS models are too large to run in real time on the low end machines that are common in Nepal, and the usual answer to that problem is knowledge distillation, where a large teach...
Yagya Raj Sharma· Zenodo (CERN European Organi...· 0 citations
These findings describe concurrent adjusted associations rather than temporal or causal pathways and should be interpreted in light of the weak measurement structure of the AI-literacy instrument in this sample.
Şaziye Seçkin Yılmaz, N. Birol· BMC Medical Education· 0 citations
Nepali is a low resource language for speech technology and there is very little open text-to-speech support for it. Most high quality neural TTS models are too large to run in real time on the low end machines that are common in Nepal, and the usual answer to that problem is knowledge distillation, where a large teach...
Yagya Raj Sharma· Zenodo (CERN European Organi...· 0 citations
This study shows that sequential sampling has a higher performance ceiling, providing a more diverse and effective pool of samples, particularly under smaller sampling budgets, and suggests an explanation of the mechanism through which sequential scaling improves machine translation.
Di Wu, S. Troshin, C. Monz et al.· 1 citation
Reach audiences
Advertise in front of researchers, engineers, and readers.
A general framework for synthetic-augmented inference across a population of related tasks is developed, which characterizes synthetic augmentation by the number of synthetic observations and their weight and specifies a size-weight frontier that specifies, for each weight, the largest synthetic sample size for which a...
An Anatomy-Routed Contrastive Learning for 3D Chest CT (ARC-CT), a region-aware framework that addresses limitations using only reports extracted from reports by an LLM, with no manual annotations or bounding boxes, outperforms both comparable efficient baselines and larger transformer models.
H. Isik, Mehmet Alp Ozaydin, S. Kurugol et al.· 1 citation
Regression analyses show that distributional properties of confidence scores explain much of the observed alignment pattern, with model metadata playing a smaller role after controls, and support a lossy-channel view of linguistic confidence.
Hefan Zhang, Bing-Quan Zhang, Ming Cheng et al.· 2 citations
SentiLLM is proposed, a unified framework that leverages Semantic-Aligned Structural Abstraction to distill continuous raw signals into compact, semantically meaningful tokens and significantly improves discriminative performance with only a small number of trainable parameters.
Wei Chen, Jun-Kai Li, Tongguan Wang et al.· arXiv.org· 0 citations
It is suggested that imitating full trajectories helps with playability, while turn-level and teacher-guided training usually improve decision-making and increase the overall score, and small models are performant simply by using careful curation strategies rather than aggressive changes.
On a 740-instance healthcare API routing task with a 1.5B Qwen student and a 20B teacher, eight KD variants are compared against supervised cross-entropy, finding single-seed evaluation is unable to detect central failure modes in small-model KD.
Dipto Sumit, Sakib Ul Haque, Farig Sadeque· 0 citations
DAMP uses both quantization-error energy and decay-based persistence to identify high-risk channels during offline calibration and stores these channels at higher precision and the remainder in INT8, the first to study post-training quantization of recurrent states in GDN and KDA based language models.
Tao Zhang, Jian-Chao Tan, Ping-Wei Sun et al.· 6 citations· ⚡3
It is found that cue-based prompting can influence multilingual sentence-level Easy-to-Read simplification, but its benefits are modest, metric-dependent, and language-dependent.
Mehrzad Tareh, Horacio Saggion, Stefan Bott· 0 citations
