AI’s Memorization Crisis

O n Tuesday, researchers at Stanford and Yale revealed something that AI companies would prefer to keep hidden. Four popular ...
Slator

Italian Benchmark Evaluates Large Language Models, Includes AI Translation

A new community-driven initiative evaluates large language models using Italian-native tasks, with AI translation among the ...
IEEE

Exploring Distortion Prior With Latent Diffusion Models for Remote Sensing Image Compression

Abstract: Learning-based image compression algorithms typically focus on designing encoding and decoding networks and improving the accuracy of entropy model estimation to enhance the rate-distortion ...

New ‘Test-Time Training’ method lets AI keep learning without exploding inference costs

By allowing models to actively update their weights during inference, Test-Time Training (TTT) creates a "compressed memory" ...
GitHub

From Accuracy to Robustness: A Study of Rule- and Model-based Verifiers in Mathematical Reasoning.

This repo contains the resources for the paper "From Accuracy to Robustness: A Study of Rule- and Model-based Verifiers in Mathematical Reasoning." In this work, we take mathematical reasoning as a ...
IEEE

Model Steganography During Model Compression

Abstract: Recently, many compressed neural network models have been implemented on embedded platforms. However, there is still a lack of steganographic methods that utilizes these compressed models ...