Research
Research
Research
Research
122+ open-access research outputs.
Training-free token reduction methods for Vision Transformers (ToMe, ToFu, PiToMe, and MCTF) employ different scoring mechanisms, yet they share a closely matched cliff-like collapse at high compressi…
Token compression is crucial for mitigating the quadratic complexity of self-attention mechanisms in Vision Transformers (ViTs), which often involve numerous input tokens. Existing methods, such as To…
Reliable anomaly detection in distributed power plant monitoring systems is essential for ensuring operational continuity and reducing maintenance costs, particularly in regions where telecom operator…
Recent token merging techniques for Vision Transformers (ViTs) provide substantial speedups by reducing the number of tokens processed by self-attention, often without retraining. However, their direc…
Early and accurate detection of Alzheimer's disease (AD) remains a major challenge in medical diagnosis due to its subtle onset and progressive nature. This research introduces an explainable ensemble…
Elastic precision quantization enables multi-bit deployment via a single optimization pass, fitting diverse quantization scenarios.Yet, the high storage and optimization costs associated with the Tran…
Probabilities is the English translation of the book Probabilit\'es Tome 1 and Tome 2. The mathematic content is authored by Prof. Jean-Yves Ouvrard. The English version has been done by his eldest so…
Automatic skin lesion classification from dermoscopy images is important for the early diagnosis of skin diseases such as melanoma. Class imbalance in skin lesion datasets, notably the defects in the …
We compute the delta power operation for morava E-theory of height 2 at the prime 3. The delta power operation was defined using the notion of higher semi additivity by Shachar Carmeli, Tomer M. Schla…
Diabetes is a serious worldwide health issue, and successful intervention depends on early detection. However, overlapping risk factors and data asymmetry make prediction difficult. To use extensive h…
We extend a theorem of Maa, Pearl, and Bartoszynski, which links equality of interpoint distance distributions to equality of underlying multivariate distributions, beyond the restrictive class of hom…
In the neon-lit nights of 2026, Johnson \& Johnson unveiled X. A pill, not larger than a snowflake, that promised a tempest of change. This miraculous drug didn't just allow people to cherry-pick memo…
Recent transformer-based models for 3D Human Mesh Recovery (HMR) have achieved strong performance but often suffer from high computational cost and complexity due to deep transformer architectures and…
One-way puzzles (OWPuzzs) introduced by Khurana and Tomer [STOC 2024] are a natural quantum analogue of one-way functions (OWFs), and one of the most fundamental primitives in ''Microcrypt'' where OWF…
Particle Image Velocimetry (PIV) typically relies on cross-correlation,which makes it difficult to obtain instantaneous velocity fields that are both spatially dense and available in real time at high…
This study examines credit default prediction by comparing three techniques, namely SMOTE, SMOTE-Tomek, and ADASYN, that are commonly used to address the class imbalance problem in credit default situ…
Recent advances in fMRI-based visual decoding have enabled compelling reconstructions of perceived images. However, most approaches rely on subject-specific training, limiting scalability and practica…
Machine learning models hold significant potential for predicting in-hospital mortality, yet data privacy constraints and the statistical heterogeneity of real-world clinical data often hamper their d…
Class imbalance remains a critical challenge in machine learning (ML), particularly in the medical domain, where underrepresented minority classes lead to biased models and reduced predictive performa…
Federated Learning (FL) presents a groundbreaking approach for collaborative health research, allowing model training on decentralized data while safeguarding patient privacy. FL offers formal securit…
Free open-access publishing with Google Scholar indexing.
Submission Guide →