The app reads your email inbox and your meeting calendar, then gives you a short audio summary. It can help you spend less time scrolling, but of course, there are privacy drawbacks to consider.

The skills needed for wrapping up aren't always what you expect. My house contains a vaguely defined room--a parlor-like space that was created by a renovation decades ago. After my son was born, it served as a playroom, full of baby and toddler toys. Then it became a nook where, late at night, my wife and I could listen to music and read. That equilibrium held until the Legos and board games arrived; their incursion was the beginning of the end.

I Have a Warning for Everyone. Consider this my open admission. When I graduated from UC-Berkeley with my "useless" comparative literature degree, into one of the bleakest job markets in recent American memory, I thought to myself, . That was what brought me to marketing myself as an "academic editor," and an "admissions essay advisor," on various freelancing websites last fall. I figured I had done my fair share of editing for friends throughout the years, and I needed another gig to supplement my inconsistent substitute-teaching paychecks.

Real-world data deviating from the independent and identically distributed (\textit{i.i.d.}) assumption of in-distribution training data poses security threats to deep networks, thus advancing out-of-distribution (OOD) detection algorithms. Detection methods in generative language models (GLMs) mainly focus on uncertainty estimation and embedding distance measurement, with the latter proven to be most effective in traditional linguistic tasks like summarization and translation. However, another complex generative scenario mathematical reasoning poses significant challenges to embedding-based methods due to its high-density feature of output spaces, but this feature causes larger discrepancies in the embedding shift trajectory between different samples in latent spaces. Hence, we propose a trajectory-based method TV score, which uses trajectory volatility for OOD detection in mathematical reasoning. Experiments show that our method outperforms all traditional algorithms on GLMs under mathematical reasoning scenarios and can be extended to more applications with high-density features in output spaces, such as multiple-choice questions.

Placebo and "knowcebo" effects are a problem. But they can also help people feel better. This week I want to look at where we are with psychedelics, the mind-altering substances that have somehow made the leap from counterculture to major focus of clinical research. Compounds like psilocybin--which is found in magic mushrooms--are being explored for all sorts of health applications, including treatments for depression, PTSD, addiction, and even obesity. Over the last decade, we've seen scientific interest in these drugs explode. But most clinical trials of psychedelics have been small and plagued by challenges.

The challenge of discovering new molecules with desired properties is crucial in domains like drug discovery and material design. Recent advances in deep learning-based generative methods have shown promise but face the issue of sample efficiency due to the computational expense of evaluating the reward function. This paper proposes a novel algorithm for sample-efficient molecular optimization by distilling a powerful genetic algorithm into deep generative policy using GFlowNets training, the off-policy method for amortized inference. This approach enables the deep generative policy to learn from domain knowledge, which has been explicitly integrated into the genetic algorithm. Our method achieves state-of-the-art performance in the official molecular optimization benchmark, significantly outperforming previous methods. It also demonstrates effectiveness in designing inhibitors against SARS-CoV-2 with substantially fewer reward calls.

Three people associated with artificial intelligence server maker Super Micro Computer, including its cofounder, have been charged with helping smuggle at least $2.5bn-worth of United States AI technology to China in violation of export laws, according to the US Department of Justice. US prosecutors did not name Super Micro in the complaint, referring only to a "US manufacturer", but San Jose, California-based Super Micro said it was informed by federal prosecutors of the indictment on Thursday. The Justice Department said it had charged Yih-Shyan Liaw, Ruei-Tsang Chang, and Ting-Wei Sun in an indictment unsealed in federal court in Manhattan on Thursday, on allegations of a complex scheme to send US-made servers through Taiwan to other countries in Southeast Asia, where they were swapped into unmarked boxes and sent on to China. The US has had export restrictions on China for advanced AI chips since 2022. In a release, FBI Assistant Director in Charge James Barnacle said the defendants used fabricated documents, staged bogus equipment to pass audit inventories, and used a pass-through company to conceal their misconduct and true clientele list.

The security threat of backdoor attacks is a central concern for deep neural networks (DNNs). Recently, without poisoned data, unlearning models with clean data and then learning a pruning mask have contributed to backdoor defense. Additionally, vanilla fine-tuning with those clean data can help recover the lost clean accuracy. However, the behavior of clean unlearning is still under-explored, and vanilla fine-tuning unintentionally induces back the backdoor effect. In this work, we first investigate model unlearning from the perspective of weight changes and gradient norms, and find two interesting observations in the backdoored model: 1) the weight changes between poison and clean unlearning are positively correlated, making it possible for us to identify the backdoored-related neurons without using poisoned data; 2) the neurons of the backdoored model are more active (, larger gradient norm) than those in the clean model, suggesting the need to suppress the gradient norm during fine-tuning. Then, we propose an effective two-stage defense method. In the first stage, an efficient is proposed based on observation 1). In the second stage, based on observation 2), we design an to replace the vanilla fine-tuning. Extensive experiments, involving eight backdoor attacks on three benchmark datasets, demonstrate the superior performance of our proposed method compared to recent state-of-the-art backdoor defense approaches.

Physical models in the form of partial differential equations serve as important priors for many under-constrained problems. One such application is tumor treatment planning, which relies on accurately estimating the spatial distribution of tumor cells within a patient's anatomy. While medical imaging can detect the bulk of a tumor, it cannot capture the full extent of its spread, as low-concentration tumor cells often remain undetectable, particularly in glioblastoma, the most common primary brain tumor. Machine learning approaches struggle to estimate the complete tumor cell distribution due to a lack of appropriate training data. Consequently, most existing methods rely on physics-based simulations to generate anatomically and physiologically plausible estimations. However, these approaches face challenges with complex and unknown initial conditions and are constrained by overly rigid physical models. In this work, we introduce a novel method that integrates data-driven and physics-based cost functions, akin to Physics-Informed Neural Networks (PINNs).

Privacy is a growing concern in modern deep-learning systems and applications. Differentially private (DP) training prevents the leakage of sensitive information in the collected training data from the trained machine learning models. DP optimizers, including DP stochastic gradient descent (DPSGD) and its variants, privatize the training procedure by gradient clipping and injection. However, in practice, DP models trained using DPSGD and its variants often suffer from significant model performance degradation. Such degradation prevents the application of DP optimization in many key tasks, such as foundation model pretraining.