Goto

Collaborating Authors

 Industry


Bill Gates a no-show at India AI summit, event marred by organizational chaos

The Japan Times

U.S. philanthropist and Microsoft co-founder Bill Gates attends an event in New Delhi on March 19, 2025. NEW DELHI - Bill Gates pulled out of India's AI Impact Summit hours before his scheduled keynote address on Thursday, dealing another blow to a flagship event already marred by organizational lapses, a robot bungle and delegate complaints over traffic disruptions. The Gates Foundation said the billionaire would not deliver his address to ensure the focus remains on the AI Summit's key priorities. Only days ago, the foundation had dismissed rumors of his absence and insisted he was on track to attend. In a time of both misinformation and too much information, quality journalism is more crucial than ever.



RGMDT: Return-Gap-MinimizingDecisionTree ExtractioninNon-EuclideanMetricSpace

Neural Information Processing Systems

In this paper, we establish an upper bound on the return gap between the oracle expert policy and an optimal decision tree policy. This enables us to recast the DT extraction problem into a novel non-euclidean clustering problem over the local observation and action values space of each agent, with action values as cluster labels and the upper bound on the return gap as clustering loss.




Face Reconstruction from Facial Templates by Learning Latent Space of a Generator Network

Neural Information Processing Systems

Among potential attacks against FR systems [Galbally et al., 2014, Biggio et al., 2015, Hadid et al., 2015, Mai et al., 2018, Marcel et al., 2023], the template inversion (TI) attack significantly jeopardizes the users' privacy. In a TI attack, the adversary gains access to templates stored in the FR system's database and aims





6f5216f8d89b086c18298e043bfe48ed-Paper.pdf

Neural Information Processing Systems

Withoutrequiring repeatable trials, itcanflexibly capture covariate-dependent jointSCDs, andprovide interpretable latent causes underlying the statistical dependencies between neurons.