As AI systems become more capable, deceptive behaviors can undermine evaluation and mislead users at deployment. Recent work has shown that lie detectors can accurately classify deceptive behavior, but they are not typically used in the training pipeline due to concerns around contamination and objective hacking. We examine these concerns by incorporating a lie detector into the labelling step of LLM post-training and evaluating whether the learned policy is genuinely more honest, or instead learns to fool the lie detector while remaining deceptive. Using DolusChat, a novel 65k-example dataset with paired truthful/deceptive responses, we identify three key factors that determine the honesty of learned policies: amount of exploration during preference learning, lie detector accuracy, and KL regularization strength. We find that preference learning with lie detectors and GRPO can lead to policies which evade lie detectors, with deception rates of over 85%. However, if the lie detector true positive rate (TPR) or KL regularization is sufficiently high, GRPO learns honest policies. In contrast, off-policy algorithms (DPO) consistently lead to deception rates under 25% for realistic TPRs. Our results illustrate a more complex picture than previously assumed: depending on the context, lie-detector-enhanced training can be a powerful tool for scalable oversight, or a counterproductive method encouraging undetectable misalignment.

Artificial intelligence (AI) has played a transformative role in chemical research, greatly facilitating the prediction of small molecule properties, simulation of catalytic processes, and material design. These advances are driven by increases in computing power, open source machine learning frameworks, and extensive chemical datasets. However, a persistent challenge is the limited amount of high-quality real-world data, while models calculated based on large amounts of theoretical data are often costly and difficult to deploy, which hinders the applicability of AI models in practical scenarios. In this study, we enhance the prediction of solutesolvent properties by proposing a novel sample selection method: Core Subset Iterative Extraction (CSIE). CSIE iteratively updates the core sample subset based on information gain to remove redundant samples in theoretical data and optimize the performance of the model on real chemical datasets. Furthermore, we introduce an asymmetric molecular interaction graph neural network (AMGNN) that combines positional information and bidirectional edge connections to simulate real-world chemical reaction scenarios to better capture solute-solvent interactions. Experimental results show that our method can accurately extract the core subset and improve the prediction accuracy. Code is available at: https://CISE-AMGNN.

The ability to quickly and accurately compute properties from atomic simulations is critical for advancing a large number of applications in chemistry and materials science including drug discovery, energy storage, and semiconductor manufacturing. To address this need, we present a family of Universal Models for Atoms (UMA), designed to push the frontier of speed, accuracy, and generalization. UMA models are trained on half a billion unique 3D atomic structures (the largest training runs to date) by compiling data across multiple chemical domains, e.g.

Palpation, the use of touch in medical examination, is almost exclusively performed by humans. We investigate a proof of concept for an artificial palpation method based on self-supervised learning. Our key idea is that an encoder-decoder framework can learn a representation from a sequence of tactile measurements that contains all the relevant information about the palpated object. We conjecture that such a representation can be used for downstream tasks such as tactile imaging and change detection. With enough training data, it should capture intricate patterns in the tactile measurements that go beyond a simple map of forces - the current state of the art. To validate our approach, we both develop a simulation environment and collect a real-world dataset of soft objects and corresponding ground truth images obtained by magnetic resonance imaging (MRI). We collect palpation sequences using a robot equipped with a tactile sensor, and train a model that predicts sensory readings at different positions on the object. We investigate the representation learned in this process, and demonstrate its use in imaging and change detection.

Follow this section to personalize your feed and get instant alerts. Follow Go to your personalized feed WHY FOLLOW? Smart Alerts: Get notified about major news as it happens. Follow this tag to personalize your feed and get instant alerts. Follow Go to your personalized feed WHY FOLLOW?

When you purchase through links in our articles, we may earn a small commission. Fan Control is an excellent free utility that lets you create custom fan curves, monitor temps, and quiet your system. If you've ever tried to tweak your PC's fan speeds, you already know that it isn't the easiest experience. You have to navigate through archaic menus, confusing sliders, and software that feels like it's pre-Y2K. Thankfully, there's the Fan Control app, which feels like a revelation compared to other controllers.

Where does'A man is walking in a Locate the moment where "A man For the query'A man recommends narrow alley, with street noise and Determine the precise timestamp in wearing a white mask is speaking visiting local areas in Tokyo, filming the conversations in the background.

Visual generative and understanding models typically rely on distinct tokenizers to w process ork.

Video Question Answering (VideoQA) task serves as a critical playground for evaluating whether foundation models can effectively perceive, understand, and reason about dynamic real-world scenarios.

A.1 Compilation and Standardization of Datasets We compile ESCAPE from 27 peptide databases by systematically extracting experimentally validated antimicrobial peptides annotated for antibacterial, antifungal, antiparasitic, or antiviral activity. Databases exclusively focusing on a single category, such as AVPdb [1] (antiviral), are directly mapped to one of the four target classes. Additionally, we follow the methodology outlined in TransImbAMP[6], selecting non-antimicrobial peptides from UniProt [7] by applying strict exclusion criteria. Specifically, we discard sequences containing keywords such as "membrane," "toxic," "secretory," "defensive," "antibiotic," "anticancer," "antiviral," or "antifungal" to enhance the quality of the negative class. For large and hierarchically structured databases such as DBAASP[8], DRAMP[9], dbAMP (with species-level annotations)[10], and SATPdb (which lists 38 functional categories)[11], we retain all peptides with annotations that map either directly or through hierarchical or taxonomic relationships to one of our four defined antimicrobial classes (antibacterial, antifungal, antiparasitic, antiviral).