Tootfinder

Data-Balanced Curriculum Learning for Audio Question Answering
Gijs Wijngaard, Elia Formisano, Michele Esposito, Michel Dumontier
https://arxiv.org/abs/2507.06815

Data-Balanced Curriculum Learning for Audio Question Answering
Audio question answering (AQA) requires models to understand acoustic content and perform complex reasoning. Current models struggle with dataset imbalances and unstable training dynamics. This work combines curriculum learning with statistical data balancing to address these challenges. The method labels question difficulty using language models, then trains progressively from easy to hard examples. Statistical filtering removes overrepresented audio categories, and guided decoding constrains …

Happy Pride! Everyone deserves dignity and respect at every stage of their life - including end of life. Help your loved ones and community celebrate you properly and appropriately by doing all your advance planning now -just think of how hard you'll party when it's done 🎉🌈
Got questions? I'm here to help and I am an ally and safe space for everyone in the LGBTIQA community and the kink community.

How Robust is Model Editing after Fine-Tuning? An Empirical Study on Text-to-Image Diffusion Models
Feng He, Zhenyang Liu, Marco Valentino, Zhixue Zhao
https://arxiv.org/abs/2506.18428

How Robust is Model Editing after Fine-Tuning? An Empirical Study on Text-to-Image Diffusion Models
Model editing offers a low-cost technique to inject or correct a particular behavior in a pre-trained model without extensive retraining, supporting applications such as factual correction and bias mitigation. Despite this common practice, it remains unknown whether edits persist after fine-tuning or whether they are inadvertently reversed. This question has fundamental practical implications. For example, if fine-tuning removes prior edits, it could serve as a defence mechanism against hidden …