Dermatology ddx dataset, Jax implementations of Monte Carlo conformal prediction, plausibility regions and statistical annotation aggregation from our recent work on uncertain ground truth (TMLR'23 and ArXiv pre-print). (⭐ 677)
There are many applications scenarios for which the computational performance and memory footprint of the prediction phase of Deep Neural Networks (DNNs) needs to be optimized. Binary Neural Networks (BDNNs) have been shown to be an effective way of...
AI interactive video generation just crossed a line that changes everything about our digital future. Watch the video tutorial below ? [https://www.youtube.com/watch?v=qNCOcXz63fs&t=2s](https...
This paper presents a software allowing to describe voices using a continuous Voice Femininity Percentage (VFP). This system is intended for transgender speakers during their voice transition and for voice therapists supporting them in this process....
Natural Gradient Boosting for Probabilistic Prediction (⭐ 1838)
Long-range semantic coherence remains a challenge in automatic language generation and understanding. We demonstrate that large language models have insufficiently learned the effect of distant words on next-token prediction. We present coherence boo...
Gradient Boosting (GB) is a popular methodology used to solve prediction problems by minimizing a differentiable loss function, $L$. GB performs very well on tabular machine learning (ML) problems; however, as a pure ML solver it lacks the ability to...
Alzheimer's disease (AD) is a neurodegenerative disorder with no known cure that affects tens of millions of people worldwide. Early detection of AD is critical for timely intervention to halt or slow the progression of the disease. In this study, we...
This paper presents a framework for dynamic object catching using a quadruped robot's front legs while it stands on its rear legs. The system integrates computer vision, trajectory prediction, and leg control to enable the quadruped to visually detec...
Obtaining precise theoretical predictions for both production and decay processes of heavy new particles is of great importance to constrain the allowed parameter spaces of Beyond-the-Standard-Model (BSM) theories, and to properly assess the sensitiv...
High resolution tactile sensing has great potential in autonomous mobile robotics, particularly for legged robots. One particular area where it has significant promise is the traversal of challenging, varied terrain. Depending on whether an environme...
We study certain real Lie-group orbits in the compact duals of Mumford-Tate domains, verifying a prediction made in [Green, Griffiths, Kerr; Mumford-Tate domains: their geometry and arithmetic] and determining which orbits contain a limit point of so...
Weather predictions are often provided as ensembles generated by repeated runs of numerical weather prediction models. These forecasts typically exhibit bias and inaccurate dependence structures due to numerical and dispersion errors, requiring stati...
The versatility of recent machine learning approaches makes them ideal for improvement of next generation video compression solutions. Unfortunately, these approaches typically bring significant increases in computational complexity and are difficult...
Recent data on the $D^*$ masses confirm the QCD prediction based on the \REF{\ICHJL}{Isaac Cohen and Harry J. Lipkin, \plb{84}{323}{1979}} very general assumption $\({\ICHJL}\)$ that the spin-dependence of the quark couplings to photons and gluons...
It is now possible to conduct large scale perturbation screens with complex readout modalities, such as different molecular profiles or high content cell images. While these open the way for systematic dissection of causal cell circuits, integrated s...
Simulate the NCAA tournament based on a kaggle-format bracket (with predictions for every possible matchup) (⭐ 38)
Terahertz communications are envisioned as a key enabler for 6G networks. The abundant spectrum available in such ultra high frequencies has the potential to increase network capacity to huge data rates. However, they are extremely affected by blocka...
Today's Internet traffic is mostly dominated by multimedia content and the prediction is that this trend will intensify in the future. Therefore, main Internet players, such as ISPs, content delivery platforms (e.g. Youtube, Bitorrent, Netflix, etc)...
Work related to the Kaggle Taxi Fare prediction challenge (⭐ 27)