Tootfinder

OpenAI details why "emergent misalignment", where training on wrong answers in one area can lead to misalignment in others, happens and how it can be mitigated (Maxwell Zeff/TechCrunch)
https://techcrunch.com/2025/06/18/open

OpenAI found features in AI models that correspond to different 'personas' | TechCrunch
OpenAI researchers say they've discovered hidden features inside AI models that correspond to misaligned "personas," according to new research published

Dolphins WR Tyreek Hill, Olympic gold medalist Noah Lyles cancel race due to personal reasons https://www.nfl.com/news/dolphins-wr-tyreek-hill-olympic-gold-medalist-noah-lyles-cancel-race-due-to-personal-reasons

NetRoller: Interfacing General and Specialized Models for End-to-End Autonomous Driving
Ren Xin, Hongji Liu, Xiaodong Mei, Wenru Liu, Maosheng Ye, Zhili Chen, Jun Ma
https://arxiv.org/abs/2506.14589

NetRoller: Interfacing General and Specialized Models for End-to-End Autonomous Driving
Integrating General Models (GMs) such as Large Language Models (LLMs), with Specialized Models (SMs) in autonomous driving tasks presents a promising approach to mitigating challenges in data diversity and model capacity of existing specialized driving models. However, this integration leads to problems of asynchronous systems, which arise from the distinct characteristics inherent in GMs and SMs. To tackle this challenge, we propose NetRoller, an adapter that incorporates a set of novel mechan…

Querying Large Automotive Software Models: Agentic vs. Direct LLM Approaches
Lukasz Mazur, Nenad Petrovic, James Pontes Miranda, Ansgar Radermacher, Robert Rasche, Alois Knoll
https://arxiv.org/abs/2506.13171

Querying Large Automotive Software Models: Agentic vs. Direct LLM Approaches
Large language models (LLMs) offer new opportunities for interacting with complex software artifacts, such as software models, through natural language. They present especially promising benefits for large software models that are difficult to grasp in their entirety, making traditional interaction and analysis approaches challenging. This paper investigates two approaches for leveraging LLMs to answer questions over software models: direct prompting, where the whole software model is provided …

Zero-Shot Scene Understanding with Multimodal Large Language Models for Automated Vehicles
Mohammed Elhenawy, Shadi Jaradat, Taqwa I. Alhadidi, Huthaifa I. Ashqar, Ahmed Jaber, Andry Rakotonirainy, Mohammad Abu Tami
https://arxiv.org/abs/2506.12232

Zero-Shot Scene Understanding with Multimodal Large Language Models for Automated Vehicles
Scene understanding is critical for various downstream tasks in autonomous driving, including facilitating driver-agent communication and enhancing human-centered explainability of autonomous vehicle (AV) decisions. This paper evaluates the capability of four multimodal large language models (MLLMs), including relatively small models, to understand scenes in a zero-shot, in-context learning setting. Additionally, we explore whether combining these models using an ensemble approach with majority…

From Black Boxes to Transparent Minds: Evaluating and Enhancing the Theory of Mind in Multimodal Large Language Models
Xinyang Li, Siqi Liu, Bochao Zou, Jiansheng Chen, Huimin Ma
https://arxiv.org/abs/2506.14224

From Black Boxes to Transparent Minds: Evaluating and Enhancing the Theory of Mind in Multimodal Large Language Models
As large language models evolve, there is growing anticipation that they will emulate human-like Theory of Mind (ToM) to assist with routine tasks. However, existing methods for evaluating machine ToM focus primarily on unimodal models and largely treat these models as black boxes, lacking an interpretative exploration of their internal mechanisms. In response, this study adopts an approach based on internal mechanisms to provide an interpretability-driven assessment of ToM in multimodal large …

A Variational Framework for Improving Naturalness in Generative Spoken Language Models
Li-Wei Chen, Takuya Higuchi, Zakaria Aldeneh, Ahmed Hussen Abdelaziz, Alexander Rudnicky
https://arxiv.org/abs/2506.14767

A Variational Framework for Improving Naturalness in Generative Spoken Language Models
The success of large language models in text processing has inspired their adaptation to speech modeling. However, since speech is continuous and complex, it is often discretized for autoregressive modeling. Speech tokens derived from self-supervised models (known as semantic tokens) typically focus on the linguistic aspects of speech but neglect prosodic information. As a result, models trained on these tokens can generate speech with reduced naturalness. Existing approaches try to fix this by…

Olympic gold medalist Noah Lyles calls off 100-meter race against Dolphins' Tyreek Hill for 'personal reasons'

https://www.cbsspor…

Exploring Cultural Variations in Moral Judgments with Large Language Models
Hadi Mohammadi, Efthymia Papadopoulou, Yasmeen F. S. S. Meijer, Ayoub Bagheri
https://arxiv.org/abs/2506.12433

Exploring Cultural Variations in Moral Judgments with Large Language Models
Large Language Models (LLMs) have shown strong performance across many tasks, but their ability to capture culturally diverse moral values remains unclear. In this paper, we examine whether LLMs can mirror variations in moral attitudes reported by two major cross-cultural surveys: the World Values Survey and the PEW Research Center's Global Attitudes Survey. We compare smaller, monolingual, and multilingual models (GPT-2, OPT, BLOOMZ, and Qwen) with more recent instruction-tuned models (GPT-4o,…

Branch, or Layer? Zeroth-Order Optimization for Continual Learning of Vision-Language Models
Ziwei Liu, Borui Kang, Wei Li, Hangjie Yuan, Yanbing Yang, Wenbin Li, Jun Luo, Yifan Zhu, Tao Feng
https://arxiv.org/abs/2506.12409

Branch, or Layer? Zeroth-Order Optimization for Continual Learning of Vision-Language Models
Continual learning in vision-language models (VLMs) faces critical challenges in balancing parameter efficiency, memory consumption, and optimization stability. While First-Order (FO) optimization (e.g., SGD) dominate current approaches, their deterministic gradients often trap models in suboptimal local minima and incur substantial memory overhead. This paper pioneers a systematic exploration of Zeroth-Order (ZO) optimization for vision-language continual learning (VLCL). We first identify the…