#RobustAI

GetNews.me

@getnews-me.bsky.social

5 months ago

Distributionally Robust Causal Abstractions Improve AI Model Reliability

Researchers introduced robust causal abstractions with a Wasserstein ambiguity set in a min‑max formulation, maintaining performance when test environments shift. Read more: getnews.me/distributionally-robust-... #causalabstraction #robustai

Valeriy M., PhD, MBA, CQF

@predict-addict.bsky.social

7 months ago

How deep models can stay stable on "messy" data
#DataCleaning #RobustAI #TimeSeries #forecasting

CoEvolution EU Project

@coevolution-eu.bsky.social

7 months ago

When your LiDAR sees ghosts👻 , who takes the blame?
CoEvolution is shaping AI that not only works well, but fails well.
🤔What’s your strategy for adversarial sensor input in the wild?
#AIsecurity #RobustAI #EdgeComputing #AutonomousSystems #EUFunded

@arxivlens.bsky.social

9 months ago

Beyond Benchmarks: Towards Robust Artificial Intelligence Bone Segmentation in Socio-Technical Systems
Alves, Berge, S. et al.
Paper
Details
#RobustAI #BoneSegmentation #SocioTechnicalSystems

Juan Carlos Niebles

@jcniebles.bsky.social

9 months ago

ViUniT: Visual Unit Tests for More Robust Visual Programming Programming based approaches to reasoning tasks have substantially expanded the types of questions models can answer about visual scenes. Yet on benchmark visual reasoning data, when models answer cor...

Last but not least, presenting "ViUniT: Visual Unit Tests for More Robust Visual Programming" #CVPR2025

🗓️ Sun Jun 15, 10:30AM-12:30PM
📍 ExHall D Poster #346
🔗 Paper: arxiv.org/abs/2412.08859
📝 Blog: www.niebles.net/blog/2025/vi...

#VisualProgramming #RobustAI

AZoAI

@azoai.bsky.social

10 months ago

FairAT Boosts AI Security and Fairness by Targeting Its Weakest Links Researchers at Wuhan University developed Fair Adversarial Training (FairAT), a technique that enhances the fairness and robustness of AI models by focusing on their most vulnerable data points. FairA...

FairAT Boosts AI Security and Fairness by Targeting Its Weakest Links 🔐🤖📊 www.azoai.com/news/2025041... #AI #Cybersecurity #MachineLearning #Fairness #DeepLearning #EthicalAI #AdversarialTraining #TrustworthyAI #DataScience #RobustAI

Brian Anderson

@braindersnn.bsky.social

1 year ago

Join Project Phasor!
Discord: discord.com/invite/jh9VQ...
Homepage: www.project-phasor.org
Invite AMD to join the neuromorphic party: docs.google.com/forms/d/e/1F...

#projectphasor #backprop #robustai #continuallearning #mlir #ml #ai

Ezgi Korkmaz

@ezgikorkmaz.bsky.social

1 year ago

If you are curious about deep reinforcement learning find the compact highlights of my recent papers in this new short piece:

#NeurIPS2024 @neuripsconf.bsky.social #NeurIPS24
#reinforcementlearning #AIsafety #AISecurity #ResponsibleAI #TrustworthyAI #RobustAI #DeepRL

bsky.app/profile/ezgi...

Global Voters

@globalvoters.bsky.social

1 year ago

MIT robotics pioneer Rodney Brooks thinks people are vastly overestimating generative AI He says that the problem is that generative AI is not human or even human-like, and it’s flawed to try and assign human capabilities to it. © 2024 TechCrunch. All rights reserved. For personal use only.

#AI #Robotics #rodneybrooks #RobustAI MIT robotics pioneer Rodney Brooks thinks people are vastly overestimating generative AI: He says that the problem is that generative AI is not human or even human-like, and it’s flawed to try and assign human capabilities to it.


© 2024 TechCrunch. All…