Jessica Landon

Co-constructing Knowledge to Benefit an Innovative Social Work Practicum: A Participatory Action Research (PAR) and Integrated Knowledge Translation (iKT) Approach

Jane E. Sanders, Ariel Seale, Esther Bernal, Jessica Landon et autres

This participatory action research (PAR) study is of an innovative virtual pilot practicum program developed through a university – school board partnership to provide relevant experiential learning for social work students pursuing their bachelor’s and master’s degrees while delivering social work services …

Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Gemini Robotics Team, Petko Georgiev, Ving Ian Lei, Ryan Burnell et autres

In this report, we introduce the Gemini 1.5 family of models, representing the next generation of highly compute-efficient multimodal models capable of recalling and reasoning over fine-grained information from millions of tokens of context, including multiple long documents and hours of video …

Gemini: A Family of Highly Capable Multimodal Models

Gemini Robotics Team, Rohan Anil, Sebastian Borgeaud, Jean-Baptiste Alayrac et autres

This report introduces a new family of multimodal models, Gemini, that exhibit remarkable capabilities across image, audio, video, and text understanding. The Gemini family consists of Ultra, Pro, and Nano sizes, suitable for applications ranging from complex reasoning tasks to on-device memory-constrained …

Vision-Language Models as Success Detectors

Yuqing Du, Ksenia Konyushkova, Misha Denil, Jessica Landon et autres

Detecting successful behaviour is crucial for training intelligent agents. As such, generalisable reward models are a prerequisite for agents that can learn to generalise their behaviour. In this work we focus on developing robust success detectors that leverage large, pretrained vision-language models …

Improving Multimodal Interactive Agents with Reinforcement Learning from Human Feedback

Josh Abramson, Arun Kumar Ahuja, Federico Carnevale, Petko Georgiev et autres

An important goal in artificial intelligence is to create agents that can both interact naturally with humans and learn from their feedback. Here we demonstrate how to use reinforcement learning from human feedback (RLHF) to improve upon simulated, embodied agents trained to …

Support and Aid to Families Electronically (SAFE): Addressing Intersecting Academic and Community Needs

Jane E. Sanders, Hazel Antia, Esther Bernal, Jessica Landon et autres

In response to the COVID-19 pandemic, schools from elementary to post-secondary suddenly shifted to remote learning, placing a heavy burden on parents and caregivers. Likewise, social work practicum placements pivoted to remote learning, compounding existing difficulties securing practicum opportunities. This article describes …

ca (code pays fourni par la source)

Evaluating Multimodal Interactive Agents

Josh Abramson, Arun Kumar Ahuja, Federico Carnevale, Petko Georgiev et autres

Creating agents that can interact naturally with humans is a common goal in artificial intelligence (AI) research. However, evaluating these interactions is challenging: collecting online human-agent interactions is slow and expensive, yet faster proxy metrics often do not correlate well with interactive …

Creating Multimodal Interactive Agents with Imitation and Self-Supervised Learning

DeepMind Interactive Agents Team, Josh Abramson, Arun Kumar Ahuja, Arthur Brussee et autres

A common vision from science fiction is that robots will one day inhabit our physical spaces, sense the world as we do, assist our physical labours, and communicate with us through natural language. Here we study how to design artificial agents that …

Creating Multimodal Interactive Agents with Imitation and\n Self-Supervised Learning

DeepMind Interactive Agents Team, Josh Abramson, Arun Ahuja, Arthur Brussee et autres

A common vision from science fiction is that robots will one day inhabit our\nphysical spaces, sense the world as we do, assist our physical labours, and\ncommunicate with us through natural language. Here we study how to design\nartificial agents that can interact naturally …

Imitating Interactive Intelligence

Josh Abramson, Arun Kumar Ahuja, Iain R. Barr, Arthur Brussee et autres

A common vision from science fiction is that robots will one day inhabit our physical spaces, sense the world as we do, assist our physical labours, and communicate with us through natural language. Here we study how to design artificial agents that …

A new display inspired by games to show what you like or don’t like in PDT

V. Anne, Cléo Boninsegna, Céline Frochot, Stéphane Goria et autres

fr (code pays fourni par la source)