Skip to content Skip to sidebar Skip to footer

DeepMind’s latest research at ICML 2022

Paving the way for generalised systems with more effective and efficient AI Starting this weekend, the thirty-ninth International Conference on Machine Learning (ICML 2022) is meeting from 17-23 July, 2022 at the Baltimore Convention Center in Maryland, USA, and will be running as a hybrid event. Researchers working across artificial intelligence, data science, machine vision,…

Read More

Google Researchers Unveil DMD: A Groundbreaking Diffusion Model for Enhanced Zero-Shot Metric Depth Estimation

Although it would be helpful for applications like autonomous driving and mobile robotics, monocular estimation of metric depth in general situations has been difficult to achieve. Indoor and outdoor datasets have drastically different RGB and depth distributions, which presents a challenge. Another issue is the inherent scale ambiguity in photos caused by not knowing the…

Read More

Meet HOI-Diff: Text-Driven Synthesis of 3D Human-Object Interactions Using Diffusion Models

In response to the challenging task of generating realistic 3D human-object interactions (HOIs) guided by textual prompts, researchers from Northeastern University, Hangzhou Dianzi University, Stability AI, and Google Research have introduced an innovative solution called HOI-Diff. The intricacies of human-object interactions in computer vision and artificial intelligence have posed a significant hurdle for synthesis tasks.…

Read More

The virtuous cycle of AI research

We recently caught up with Petar Veličković, a research scientist at DeepMind. Along with his co-authors, Petar is presenting his paper The CLRS Algorithmic Reasoning Benchmark at ICML 2022 in Baltimore, Maryland, USA. My journey to DeepMind... Throughout my undergraduate courses at the University of Cambridge, the inability to skilfully play the game of Go…

Read More

Enhanced Large Language Models as Reasoning Engines | by Anthony Alcaraz | Dec, 2023

The recent exponential advances in natural language processing capabilities from large language models (LLMs) have stirred tremendous excitement about their potential to achieve human-level intelligence. Their ability to produce remarkably coherent text and engage in dialogue after exposure to vast datasets seems to point towards flexible, general purpose reasoning skills. However, a growing chorus of…

Read More