Want to understand why a computed tomography classifier made a prediction? The code just went online for generating counterfactual explanations for 2D/3D CT classifiers! Here is an explanation for Plural Effusion: #radiology #radiologyai @StanfordAIMI https://t.co/1Kh3tCQyMP

We're looking for 2 interns for Summer 2026 at the MIT-IBM Watson AI Lab Foundation Models Team. Work on RL environments, enterprise benchmarks, model architecture, efficient training and finetuning, and more! Apply here:

VizWiz is back at #CVPR2025! Come join us for fun challenges and an exciting speaker line up! Details can be found at: https://t.co/yLi699kKPV @CVPR

"Any measurement that you make without the knowledge of its uncertainty is completely meaningless" -Walter Lewin Please consider this when you put a table full of numbers in your paper!

Poster #280!

Attending #CVPR2024? Check out our method for identifying spurious correlations in neural networks using counterfactuals at the #XAI4CV workshop on Tuesday! https://t.co/tYH9TtxQY9 https://t.co/vMI97LCVlv @CVPR @CVPRConf @XAI_Research

This is pretty cool! https://t.co/oHevS9hX0S Just in the onboarding it is finding interesting papers I wasn't aware of!

Proof that consciousness doesn't exist: - An atom isn't conscious. - Adding an atom to something that's not conscious doesn't make it conscious. - Therefore nothing is conscious.

Grok-1, 3 days, 300GB, 5638 downloads, 1.6PB downloaded, 8.12MB/s average download speed. Here is a map of the 2000 hosting locations! #academictorrents https://t.co/XkcK5WRyn9

The XAI4CV workshop will be back at #CVPR2024 led by the amazing @indu_panigrahi! https://t.co/6QE84yj0l5 This year the organizing team spans 8 institutions @sukrutrao @KolekDe @LenkaTetkova @_Kate_Morrison_ @deeptigp + Jawad, Pushkar, Vikram ❤️ @CVPR @CVPRConf @XAI_Research

MLHC 2024 Call for Papers is now open! https://t.co/uS30VHqfEf

Registration is open for MLHC 2024 in Toronto! Register today to reserve your space! https://t.co/vJ3I7R12aC

Vision-language conversational models for healthcare may fit a use case with physicians better than task-specific tools. How to validate them remains a challenge but the conversational interface may be the key to get adoption by physicians.

⭐️ Excited to share our latest work about AI in healthcare. We present CheXagent, a foundation model for Chest X-ray interpretation. 📄 Paper: https://t.co/GIxXNwK7N9 🌐 Website: https://t.co/rrbR2zHNNy 🧵 1/N

CheXagent: Towards a Foundation Model for Chest X-Ray Interpretation paper page: https://t.co/VZ7p78eyaz Chest X-rays (CXRs) are the most frequently performed imaging test in clinical practice. Recent advances in the development of vision-language foundation models (FMs) give

This work also discusses how to fix biased classifiers. This colab notebook will get you started with Latent Shift Counterfactuals

Counterfactuals are needed for this as overlapping heatmaps don't distinguish features well. Shown here with pointy and big noses that have overlapping heatmaps but distinct counterfactuals.

This process can be used to compute aggregate statistics over a dataset of the biases between the features used. This can identify trends to explore and you can then drill down and study specific predictions.

Counterfactual Alignment uses the alignment between classifiers when presented with counterfactual inputs (generated using the Latent Shift method) to identify features that are shared between the classifiers.

Curious why your neural network is making a prediction? Maybe it is using spurious correlations! Counterfactuals are a solution but how to use them at scale? We explore this challenge in our latest work on Counterfactual Alignment! https://t.co/tYH9Ttxj8B https://t.co/vMI97LCnvX