Tootfinder

Ask yourself: How many water bottles thrown at cops are worth keeping one innocent American* teen out of inhumane #ICE detention?
For anyone criticizing the #LA protests or suggesting they should stop for any reason, let's be clear about the stakes. Read this article (or my summary):
https://abcnews.go.com/US/massachusetts-teen-detained-ice-family-video-ice/story?id=122511685
This 18-year-old was snatched without a warrant, because he was in his dad's car and allegedly (possibly a lie or mistake) his dad drove recklessly. He's been in the US since he was 5, originally on a student visa that's since expired. He is an innocent American, by any reasonable definition of those two words*. Thankfully, he's since been released on bail, but he may yet be held indefinitely in ICE detention (in inhumane conditions that have been repeatedly documented) and/or separated from his family & friends and shipped off to Brazil where he last lived when he was 5 (ICE does not care whether he speaks Portuguese, has any family there, etc), all potentially without due process (though he seems to be getting that in this case). Even if this doesn't happen to Marcelo due to the media attention & protests, it is certainly happening to other innocent Americans throughout the country who aren't as lucky to have people standing up for them.
Here's Marcelo speaking about detention conditions and those he was detained with:
https://youtube.com/shorts/ZpZMUb9aEys?si=bpK-022CU7Acb5RY
Do you know how many kids like Marcelo were detained in LA yesterday? Probably zero, because of the protests, including their confrontational tactics. The most "violence" I've seen (from the protestors) is throwing a water bottle at a line of heavily-armored riot police. So the protests are working to protect the community. If you're suggesting a change in tactics, consider whether your suggested tactics (like pre-scheduled non-confrontational protests that have been happening for weeks) will protect the Marcelos of LA.
*Whether he's innocent or American should not in fact matter, but sadly it might to some reading this. If that's you, you've still got some growing up to do.

Membership Inference Attacks on Sequence Models
Lorenzo Rossi, Michael Aerni, Jie Zhang, Florian Tram\`er
https://arxiv.org/abs/2506.05126 https://

Membership Inference Attacks on Sequence Models
Sequence models, such as Large Language Models (LLMs) and autoregressive image generators, have a tendency to memorize and inadvertently leak sensitive information. While this tendency has critical legal implications, existing tools are insufficient to audit the resulting risks. We hypothesize that those tools' shortcomings are due to mismatched assumptions. Thus, we argue that effectively measuring privacy leakage in sequence models requires leveraging the correlations inherent in sequential g…

Datasheets Aren't Enough: DataRubrics for Automated Quality Metrics and Accountability
Genta Indra Winata, David Anugraha, Emmy Liu, Alham Fikri Aji, Shou-Yi Hung, Aditya Parashar, Patrick Amadeus Irawan, Ruochen Zhang, Zheng-Xin Yong, Jan Christian Blaise Cruz, Niklas Muennighoff, Seungone Kim, Hanyang Zhao, Sudipta Kar, Kezia Erina Suryoraharjo, M. Farid Adilazuarda, En-Shiun Annie Lee, Ayu Purwarianti, Derry Tanti Wijaya, Monojit Choudhury

Datasheets Aren't Enough: DataRubrics for Automated Quality Metrics and Accountability
High-quality datasets are fundamental to training and evaluating machine learning models, yet their creation-especially with accurate human annotations-remains a significant challenge. Many dataset paper submissions lack originality, diversity, or rigorous quality control, and these shortcomings are often overlooked during peer review. Submissions also frequently omit essential details about dataset construction and properties. While existing tools such as datasheets aim to promote transparency…

Evaluating Gemini in an arena for learning
LearnLM Team, Abhinit Modi, Aditya Srikanth Veerubhotla, Aliya Rysbek, Andrea Huber, Ankit Anand, Avishkar Bhoopchand, Brett Wiltshire, Daniel Gillick, Daniel Kasenberg, Eleni Sgouritsa, Gal Elidan, Hengrui Liu, Holger Winnemoeller, Irina Jurenka, James Cohan, Jennifer She, Julia Wilkowski, Kaiz Alarakyia, Kevin R. McKee, Komal Singh, Lisa Wang, Markus Kunesch, Miruna P\^islar, Niv Efron, Parsa Mahmoudieh, Pierre-Alexandre Kamienny, Sara Wiltb…

Evaluating Gemini in an arena for learning
Artificial intelligence (AI) is poised to transform education, but the research community lacks a robust, general benchmark to evaluate AI models for learning. To assess state-of-the-art support for educational use cases, we ran an "arena for learning" where educators and pedagogy experts conduct blind, head-to-head, multi-turn comparisons of leading AI models. In particular, $N = 189$ educators drew from their experience to role-play realistic learning use cases, interacting with two models se…

Towards Machine Unlearning for Paralinguistic Speech Processing
Orchid Chetia Phukan, Girish, Mohd Mujtaba Akhtar, Shubham Singh, Swarup Ranjan Behera, Vandana Rajan, Muskaan Singh, Arun Balaji Buduru, Rajesh Sharma
https://arxiv.org/abs/2506.02230

Towards Machine Unlearning for Paralinguistic Speech Processing
In this work, we pioneer the study of Machine Unlearning (MU) for Paralinguistic Speech Processing (PSP). We focus on two key PSP tasks: Speech Emotion Recognition (SER) and Depression Detection (DD). To this end, we propose, SISA++, a novel extension to previous state-of-the-art (SOTA) MU method, SISA by merging models trained on different shards with weight-averaging. With such modifications, we show that SISA++ preserves performance more in comparison to SISA after unlearning in benchmark SE…

SNIFR : Boosting Fine-Grained Child Harmful Content Detection Through Audio-Visual Alignment with Cascaded Cross-Transformer
Orchid Chetia Phukan, Mohd Mujtaba Akhtar, Girish, Swarup Ranjan Behera, Abu Osama Siddiqui, Sarthak Jain, Priyabrata Mallick, Jaya Sai Kiran Patibandla, Pailla Balakrishna Reddy, Arun Balaji Buduru, Rajesh Sharma
https://

SNIFR : Boosting Fine-Grained Child Harmful Content Detection Through Audio-Visual Alignment with Cascaded Cross-Transformer
As video-sharing platforms have grown over the past decade, child viewership has surged, increasing the need for precise detection of harmful content like violence or explicit scenes. Malicious users exploit moderation systems by embedding unsafe content in minimal frames to evade detection. While prior research has focused on visual cues and advanced such fine-grained detection, audio features remain underexplored. In this study, we embed audio cues with visual for fine-grained child harmful c…