Randomized smoothing is a popular certified defense against adversarial attacks.

With the continued advancement of Large Language Models (LLMs) Agents in reasoning, planning, and decision-making, benchmarks have become crucial in evaluating these skills. However, there is a notable gap in benchmarks for real-time strategic decision-making. StarCraft II (SC2), with its complex and dynamic nature, serves as an ideal setting for such evaluations. To this end, we have developed TextStarCraft II, a specialized environment for assessing LLMs in real-time strategic scenarios within SC2. Addressing the limitations of traditional Chain of Thought (CoT) methods, we introduce the Chain of Summarization (CoS) method, enhancing LLMs' capabilities in rapid and effective decision-making. Our key experiments included: 1. LLM Evaluation: Tested 10 LLMs in TextStarCraft II, most of them defeating L V5 build-in AI, showcasing effective strategy skills.

Big Tech Says Generative AI Will Save the Planet. A new report finds that of 154 specific claims about how AI will benefit the climate, just a quarter cited academic research. A third included no evidence at all. A few years ago, Ketan Joshi read a statistic about artificial intelligence and climate change that caught his eye. In late 2023, Google began claiming that AI could help cut global greenhouse gas emissions by between 5 and 10 percent by 2030.

Input reduction reduces the length of the input context before feeding to downstream LLMs.

The CCP method finds the class-wise quantiles of non-conformity scores on calibration data.

Noise in data significantly influences decision-making in the data science process. In fact, it has been shown that noise in data generation processes leads practitioners to find simpler models. However, an open question still remains: what is the degree of model simplification we can expect under different noise levels? In this work, we address this question by investigating the relationship between the amount of noise and model simplicity across various hypothesis spaces, focusing on decision trees and linear models. We formally show that noise acts as an implicit regularizer for several different noise models. Furthermore, we prove that Rashomon sets (sets of near-optimal models) constructed with noisy data tend to contain simpler models than corresponding Rashomon sets with non-noisy data. Additionally, we show that noise expands the set of "good" features and consequently enlarges the set of models that use at least one good feature. Our work offers theoretical guarantees and practical insights for practitioners and policymakers on whether simple-yet-accurate machine learning models are likely to exist, based on knowledge of noise levels in the data generation process.

Cybercriminals buy personal data from brokers to personalize tax scams with fake IRS messages, making fraudulent emails feel legitimate for identity theft.