Variational autoencoders (VAEs) are widely used deep generative models capable of learning unsupervised latent representations of data. Such representations are often difficult to interpret or control. We consider the problem of unsupervised learning of features correlated to specific labels in a dataset. We propose a VAE-based generative model which we show is capable of extracting features correlated to binary labels in the data and structuring it in a latent subspace which is easy to interpret. Our model, the Conditional Subspace VAE (CSVAE), uses mutual information minimization to learn a low-dimensional latent subspace associated with each label that can easily be inspected and independently manipulated. We demonstrate the utility of the learned representations for attribute manipulation tasks on both the Toronto Face and CelebA datasets.

As Iranian-designed Shahed drones spread from Ukraine to the Gulf, U.S. and allied forces are using multimillion-dollar air defenses to counter low-cost attacks, raising sustainability concerns.

Our study of 22 mitigation techniques and five baselines reveals up to 12.6% fairness variance across identical training runs with identical seeds.

Iranian forces deploy explosive drone boats disguised as fishing vessels in Strait of Hormuz, defense expert Cameron Chell warns, marking new phase of hybrid warfare.

Israel's elite drone Squadron 200 reportedly destroys over half of Iran's ballistic missile launchers in ongoing Middle East conflict operations.

Neural Information Processing Systems http://nips.cc/

Neural Information Processing Systems http://nips.cc/

Iranian sleeper cells prompt President Donald Trump warning as Canadian opposition lawmakers accuse government of allowing Tehran operatives to remain despite visa cancellations.

The speed at which artificial intelligence is gaining in mathematical ability has taken many by surprise. Are the days of handwritten mathematics coming to an end? In March 2025, mathematician Daniel Litt made a bet. Despite the march of progress of artificial intelligence in many fields, he believed his subject was safe, wagering with a colleague that there was only a 25 per cent chance an AI could write a mathematical paper at the level of the best human mathematicians by 2030. Only a year later, he thinks he was wrong.