The paper introduces OmniGen, a unified framework for generating aligned multimodal sensor data for autonomous driving using a shared Bird's Eye View (BEV) space. It uses a novel generalizable multimodal reconstruction method (UAE) to jointly decode LiDAR and multi-view camera data through volume rendering. The framework incorporates a Diffusion Transformer (DiT) with a ControlNet branch to enable controllable multimodal sensor generation, demonstrating good performance and multimodal consistency.
The paper introduces the Unscented Autoencoder (UAE), a novel deep generative model based on the Variational Autoencoder (VAE) framework. The UAE uses the Unscented Transform (UT) for a more informative posterior representation compared to the reparameterization trick in VAEs. It replaces Kullback-Leibler (KL) divergence with the Wasserstein distribution metric and demonstrates competitive performance in Fréchet Inception Distance (FID) scores.
MBZUAI master's graduate Rohit Bharadwaj is pursuing a Ph.D. at the University of Edinburgh, following in the footsteps of Geoffrey Hinton. His research focuses on developing generative models, specifically diffusion models, to anonymize datasets while preserving utility, addressing GDPR compliance. He aims to balance privacy protection with the need for useful data in AI systems. Why it matters: This highlights the growing importance of MBZUAI as a feeder institution for top global AI research programs and the increasing focus on privacy-preserving AI technologies.
Patrick van der Smagt, Director of AI Research at Volkswagen Group, discussed the use of generative machine learning models for predicting and controlling complex stochastic systems in robotics. The talk highlighted examples in robotics and beyond and addressed the challenges of achieving quality and trust in AI systems. He also mentioned his involvement in a European industry initiative on trust in AI and his membership in the AI Council of the State of Bavaria. Why it matters: Understanding control in robotics, along with trust in AI, are key issues for further development of autonomous systems, especially in industrial applications within the GCC region.
MBZUAI has been actively involved in developing AI and generative models, contributing to models like Llama 2, Jais, Vicuna, and LaMini. Professor Preslav Nakov notes Llama 2's improvements in size and carbon footprint over Llama 1. MBZUAI aims to tackle challenges like information accuracy, economic costs, and the scarcity of Arabic online content. Why it matters: MBZUAI's work helps address the limitations of current LLMs, particularly for Arabic, and promotes sustainable AI development in the region.
A DeepMind researcher presented work on incorporating symmetries into machine learning models, with applications to lattice-QCD and molecular dynamics. The work includes permutation and translation-invariant normalizing flows for free-energy estimation in molecular dynamics. They also presented U(N) and SU(N) Gauge-equivariant normalizing flows for pure Gauge simulations and its extensions to incorporate fermions in lattice-QCD. Why it matters: Applying symmetry principles to generative models could improve AI's ability to model complex physical systems relevant to materials science and other fields in the region.
This article previews a talk by Gül Varol from Ecole des Ponts ParisTech on bridging natural language and 3D human motions. The talk will cover text-to-motion synthesis using generative models and text-to-motion retrieval models based on the ACTOR, TEMOS, TMR, TEACH, and SINC papers. Varol's research interests include video representation learning, human motion synthesis, and sign languages. Why it matters: Research in this area could enable more intuitive human-computer interaction and new applications in areas like virtual reality and robotics.