A two-stage fine-tuning pipeline is proposed that distills a fitted black-box estimator and its post hoc interpretation into a small, open-weight large language model (LLM) that returns an individual-level estimate and explains in natural language that predicts and explains offline on a commodity laptop, so student rec...
COEC (Calibrated Orthogonal-Equivalence Compensation), a training-free compensation framework that applies alternating left and right orthogonal rotations to the retained weight, improves perplexity on every model and zero-shot accuracy in most settings over existing compensation methods.
Peiqi Yu, Nam Ling, Wei Wang et al.· 1 citation· ⚡1
The results establish BF1 as a reproducible sparse operator and selective retrofit primitive with real long-context systems value, and evaluates numerical correctness, selected-interaction scaling, kernel performance, partial-model inference, and matched next-token language modeling.
Large language models have significantly enriched the toolkit for computational humor research, particularly in the automated generation of jokes and puns. A key innovation, contextual embedding vectors, offers new opportunities to revisit and refine earlier hypotheses. Notably, Petrovic and Matthews (2013) proposed a...
Fabio De Ponte· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
This work studies six functionally distinct web applications, each generated in two prompt variants that are identical except for an appended security-requirements section: a baseline (A) and a security-aware (B) variant.
The results suggest that dialogue format should be selected according to learner characteristics in TTS dialogue-based lessons, with a significant interaction between learner characteristics and dialogue format for ARCS-based motivation.
Fumie Watanabe, Tota Suko, Takashi Ishida et al.· 0 citations
The findings show that LLMs can approximate structured cybersecurity reasoning under controlled representations, but do not apply it robustly, which has important implications for the design and evaluation of AI-assisted security decision-support systems.
This work establishes a minimax lower bound under the score-entropy loss, and proposes an MLE-based thresholding estimator that matches this lower bound up to constant and polylogarithmic factors that depend on neighboring density ratios.
SmolDocling, a compact 256M-parameter vision-language model (VLM), is fine-tune to perform end-to-end key-value extraction directly from document images, jointly solving identification, localization, and association in a single pass without OCR preprocessing.
A. Gurbuz, Ahmed S. Nassar, Christoph Auer et al.· IEEE International Conferenc...· 0 citations
GRASSP provides a competitive framework for integrating pretrained RNA representations with spatial structural context while reducing reliance on additional handcrafted structural annotations, and is demonstrated to outperform state-of-the-art baselines.
Thi Lan Nguyen, N. Le· Bioinformatics· 0 citations
The feasibility of yoga nidra as a complementary intervention for autistic children is supported and directions for future research are suggested, including larger trials and further co-design with the autistic community.
T. Loftus, Shu H. Yau, Sophia Soares et al.· Research in Developmental Di...· 1 citation
Contemporary language models are dominated by the transformer architecture, which leverages self-attention mechanisms to enable more efficient, parallelized training across a wide set of documents and corpora. This has allowed transformers to effectively model data across a wide range of modalities and contexts. Howeve...
Archie Chaudhury· Lecture notes in computer sc...· 0 citations
