ΑΙhub.org
articles
Goal representations for instruction following
BAIR blog
23 Nov 2023
How can we reconcile the ease of specifying tasks through natural language-based approaches with the performance improvements of goal-conditioned learning?
A comprehensive survey on rare event prediction
We review the rare event prediction literature and highlight open research questions and future directions in the field.
Better images of AI can support AI literacy for more people
Better Images Of AI
21 Nov 2023
Marika Jonsson reflects on overcoming the challenge of developing an Easy Read book on AI with so few informative images available.
An approach for automatically determining the possible actions in computer game states
Sasha Volokh
17 Nov 2023
Thoroughly testing video game software by hand is difficult. AI agents that can automatically explore different game functionalities are a promising alternative.
Deep learning model trained to identify least green homes
University of Cambridge
16 Nov 2023
AI model can help policymakers efficiently identify and prioritize houses for retrofitting and other decarbonizing measures.
Pre-trained language models for music captioning and query response
Yinghao Ma
10 Nov 2023
Working towards a system that provides descriptions of the music you are listening to.
Few-shot learning for medical image analysis
Eva Pachetti and Sara Colantonio
08 Nov 2023
Is few-shot learning the gateway to integrating AI into medicine for good? Let's explore the current state of the art.
Utilizing generative adversarial networks for stable structure generation in Angry Birds
Matthew Stephenson and Frederic Abraham
07 Nov 2023
An approach for generating stable structures in the popular physics-based puzzle game.
monthly digest
AIhub monthly digest: October 2023 – probabilistic logic shields, a responsible journalism toolkit, and what the public think about AI
Lucy Smith
31 Oct 2023
Welcome to our monthly digest, where you can catch up with AI research, events and news from the month past.
A deep learning model for identifying disease and risk factor biomarkers
Linköping University
30 Oct 2023
A data-driven deep learning biomarker discovery workflow.
AAAI Fall Symposium: Patrícia Alves-Oliveira on human-robot interaction design
Lucy Smith
27 Oct 2023
We summarise the first keynote from the symposium on artificial intelligence for human-robot interaction.
New technique helps robots pack objects into a tight space
MIT News
25 Oct 2023
Researchers coaxed a family of generative AI models to work together to solve multistep robot manipulation problems.
UK needs AI legislation to create trust so companies can ‘plug AI into British economy’ – report
University of Cambridge
23 Oct 2023
Legislation regulating AI safety and transparency is needed, say researchers, so British industry and education can put resources into AI development with confidence.
World’s biggest bat colony gathers in Zambia every year: we used artificial intelligence to count them
The Conversation
20 Oct 2023
How AI methods are helping shed light on bat numbers.
Enhancing AI robustness for more secure and reliable systems
EPFL
16 Oct 2023
A formulation for strengthening ML systems against adversarial attacks.
Researching more data efficient machine learning models
University of Cambridge
12 Oct 2023
Building reliable machine learning models that can understand complex equations in real-world situations while using less training data than expected
#IJCAI2023 distinguished paper – Safe reinforcement learning via probabilistic logic shields
Wen-Chi Yang
11 Oct 2023
Find out more about shielding, a popular Safe Reinforcement Learning (Safe RL) technique that aims to keep an agent safe whilst finding an optimal policy.
A neural network method for satellite anomaly detection
University of Waterloo
05 Oct 2023
Researchers use AI to detect potential problems with satellites before they happen.
Artificial Intelligence tools shed light on millions of proteins
University of Basel
02 Oct 2023
Researchers have constructed an interactive network of 53 million proteins with AlphaFold structures.
monthly digest
AIhub monthly digest: September 2023 – uncovering concepts in deep-learning models, pollinator policies, and all questions answered
Lucy Smith
28 Sep 2023
Welcome to our monthly digest, where you can catch up with AI research, events and news from the month past.
Which strategies for supporting pollinators?
Martine Barons
26 Sep 2023
How can Bayesian Networks be used to inform pollinator abundance strategies?
Test-time adaptation with slot-centric models
ML@CMU
25 Sep 2023
Improving out-of-distribution scene decomposition accuracy.
Your right to be forgotten in the age of AI
CSIRO
22 Sep 2023
New models, like ChatGPT, are being trained in ways that make it hard to forget users’ data, raising significant concerns for our privacy online.
Machine learning can level the playing field against match fixing – helping regulators spot cheating
The Conversation
21 Sep 2023
A machine learning model for detecting questionable behaviour and unusual outcomes in basketball games.
AI-narrated audiobooks are here – and they raise some serious ethical questions
The Conversation
18 Sep 2023
What does this new technology mean for the industry, and for human actors?
Training diffusion models with reinforcement learning
BAIR blog
15 Sep 2023
We show how diffusion models can be trained on downstream objectives directly using reinforcement learning.
High-tech microscope with ML software for detecting malaria in returning travellers
Frontiers Science News
13 Sep 2023
Method not as accurate as human experts, but shows promise.
Prompt engineering: is being an AI ‘whisperer’ the job of the future or a short-lived fad?
The Conversation
08 Sep 2023
As generative AI settles into the mainstream, growing numbers of courses and certifications are promising entry into the “hot job” of prompt engineering.
AI helps robots manipulate objects with their whole bodies
MIT News
06 Sep 2023
With a new technique, a robot can reason efficiently about moving objects using more than just its fingertips.
How sure is sure? Incorporating human error into machine learning
University of Cambridge
04 Sep 2023
Researchers are developing a way to incorporate uncertainty into machine learning systems.
monthly digest
AIhub monthly digest: August 2023 – ML for biological research, methods in computational creativity, and conferences galore
Lucy Smith
30 Aug 2023
Welcome to our monthly digest, where you can catch up with AI research, events and news from the month past.
#ICML2023 invited talk: Shakir Mohamed on ML with social purpose
Lucy Smith
29 Aug 2023
We summarise the invited talk by Shakir Mohamed at the recent International Conference on Machine Learning.
Three ways AI is transforming music
The Conversation
24 Aug 2023
How will AI systems affect human musicians?
Using quantum computing to protect AI systems from attack
Pursuit, University of Melbourne
22 Aug 2023
AI systems can be fooled into making mistakes, sometimes risking lives, but quantum computing could provide a defence.
Artificial intelligence helps elucidate the precise spatial structure of complex chiral molecules
University of Amsterdam
15 Aug 2023
Combining a genetic algorithm and hierarchical clustering to analyse chiroptical spectra.
A ‘black box’ AI system has been influencing criminal justice decisions for over two decades – it’s time to open it up
The Conversation
11 Aug 2023
Melissa Hamilton and Pamela Ugwudike investigate the use of automated decision-making systems in courts and prisons.
