mi
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
MIST: Mutual Information Estimation Via Supervised Training
arXiv:2511.18945v4 Announce Type: replace Abstract: We propose a fully data-driven approach to designing mutual information (MI) estimators. Since any MI estimator is a function of the observed sample from two random variables, we parameterize this function with a neural network (MIST) and train it end-to-end to predict MI values. Training is performed on a large meta-dataset of 625,000 synthetic joint distributions with known ground-truth MI.
Random Erasing vs. Model Inversion: A Promising Defense or a False Hope?
arXiv:2409.01062v4 Announce Type: replace Abstract: Model Inversion (MI) attacks pose a significant privacy threat by reconstructing private training data from machine learning models. While existing defenses primarily concentrate on model-centric approaches, the impact of data on MI robustness remains largely unexplored. In this work, we explore Random Erasing (RE), a technique traditionally used for improving model generalization under occlusion, and uncover its surprising effectiveness as...
How a decade-long bet on photonics handed this Chinese venture capital firm an AI windfall
ExclusiveHow a decade-long bet on photonics handed this Chinese venture capital firm an AI windfall For Mi Lei, founder of venture capital firm CAS Star, the sudden fascination with photonics is less a surprise than a delayed validation As artificial intelligence strains the physical limits of existing data centres, scientists and investors are turning to the ultimate speed limit of the universe for the next computing frontier: light. For Mi Lei, founder of CAS Star, a venture capital firm...
Personalized 3D Myocardial Infarct Geometry Reconstruction from Cine MRI for Cardiac Digital Twins
arXiv:2606.01808v1 Announce Type: new Abstract: Accurate 3D geometric characterization of myocardial infarction (MI) is essential for building cardiac digital twins (CDTs) to precisely simulate infarct-related electrophysiology. Late gadolinium enhancement magnetic resonance imaging (LGE MRI) is the clinical reference for locating MI, yet its reliance on contrast agents restricts use in renally impaired patients and limits longitudinal follow-ups. As an alternative, contrast-free cine MRI...
Analysis of Information Theory for Explainable AI
Announce Type: replace Abstract: With the intervention of machine vision in our crucial day to day necessities including healthcare and automated power plants, attention has been drawn to the internal mechanisms of convolutional neural networks, and the reason why the network provides specific inferences. This paper proposes a novel post-hoc visual explanation method called MI CAM based on activation mapping. Differing from previous class activation mapping based approaches, MI CAM produces...
Primary cilia promote cardiac fibrosis and limit heart function after myocardial infarction
Cardiomyocytes die and do not regenerate after an injury such as a myocardial infarction (MI), a leading cause of mortality worldwide. Following MI, cardiac fibroblasts (CFs) proliferate and differentiate into myofibroblasts, which then produce increased collagen and extracellular matrix (ECM) leading to fibrosis. Fibrosis can weaken cardiac output via excessive stiffening and interference with electric signal transmission, but can also prevent wall rupture under load.
SUSD: Structured Unsupervised Skill Discovery through State Factorization
Announce Type: replace Abstract: Unsupervised Skill Discovery (USD) aims to autonomously learn a diverse set of skills without relying on extrinsic rewards. One of the most common USD approaches is to maximize the Mutual Information (MI) between skill latent variables and states. However, MI-based methods tend to favor simple, static skills due to their invariance properties, limiting the discovery of dynamic, task-relevant behaviors.
Translation Heads: Disentangling meaning from language in LLM-based machine translation
Announce Type: replace Abstract: Mechanistic Interpretability (MI) seeks to explain how neural networks implement their capabilities, but the scale of Large Language Models (LLMs) has limited prior MI work in Machine Translation (MT) to word-level analyses. We study sentence-level MT from a mechanistic perspective by analyzing attention heads to understand how LLMs internally encode and distribute translation functions. We decompose MT into two subtasks: producing text in the target language...