Sophisticated instrumentation for AI systems might have indicators that signal misalignment from human values, not unlike a "check engine" light in cars. One such indicator of misalignment is deceptiveness in generated responses. Future AI instrumentation may have the ability to detect when an LLM generates deceptive responses while reasoning about seemingly plausible but incorrect answers to factual questions. In this work, we demonstrate that linear probes on LLMs internal activations can detect deception in their responses with extremely high accuracy. Our probes reach a maximum of greater than 90% accuracy in distinguishing between deceptive and non-deceptive arguments generated by llama and qwen models ranging from 1.5B to 14B parameters, including their DeepSeek-r1 finetuned variants. We observe that probes on smaller models (1.5B) achieve chance accuracy at detecting deception, while larger models (greater than 7B) reach 70-80%, with their reasoning counterparts exceeding 90%. The layer-wise probe accuracy follows a three-stage pattern across layers: near-random (50%) in early layers, peaking in middle layers, and slightly declining in later layers. Furthermore, using an iterative null space projection approach, we find multitudes of linear directions that encode deception, ranging from 20 in Qwen 3B to nearly 100 in DeepSeek 7B and Qwen 14B models.

The integration of multi-omics data presents a major challenge in precision medicine, requiring advanced computational methods for accurate disease classification and biological interpretation. This study introduces the Multi-Omics Graph Kolmogorov-Arnold Network (MOGKAN), a deep learning model that integrates messenger RNA, micro RNA sequences, and DNA methylation data with Protein-Protein Interaction (PPI) networks for accurate and interpretable cancer classification across 31 cancer types. MOGKAN employs a hybrid approach combining differential expression with DESeq2, Linear Models for Microarray (LIMMA), and Least Absolute Shrinkage and Selection Operator (LASSO) regression to reduce multi-omics data dimensionality while preserving relevant biological features. The model architecture is based on the Kolmogorov-Arnold theorem principle, using trainable univariate functions to enhance interpretability and feature analysis. MOGKAN achieves classification accuracy of 96.28 percent and demonstrates low experimental variability with a standard deviation that is reduced by 1.58 to 7.30 percents compared to Convolutional Neural Networks (CNNs) and Graph Neural Networks (GNNs). The biomarkers identified by MOGKAN have been validated as cancer-related markers through Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analysis. The proposed model presents an ability to uncover molecular oncogenesis mechanisms by detecting phosphoinositide-binding substances and regulating sphingolipid cellular processes. By integrating multi-omics data with graph-based deep learning, our proposed approach demonstrates superior predictive performance and interpretability that has the potential to enhance the translation of complex multi-omics data into clinically actionable cancer diagnostics.

Radio remains a pervasive medium for mass information dissemination, with AM/FM stations reaching more Americans than either smartphone-based social networking or live television. Increasingly, radio broadcasts are also streamed online and accessed over the Internet. We present WavePulse, a framework that records, documents, and analyzes radio content in real-time. While our framework is generally applicable, we showcase the efficacy of WavePulse in a collaborative project with a team of political scientists focusing on the 2024 Presidential Elections. We use WavePulse to monitor livestreams of 396 news radio stations over a period of three months, processing close to 500,000 hours of audio streams. These streams were converted into time-stamped, diarized transcripts and analyzed to track answer key political science questions at both the national and state levels. Our analysis revealed how local issues interacted with national trends, providing insights into information flow. Our results demonstrate WavePulse's efficacy in capturing and analyzing content from radio livestreams sourced from the Web. Code and dataset can be accessed at \url{https://wave-pulse.io}.

Autonomous surgical robots have demonstrated significant potential to standardize surgical outcomes, driving innovations that enhance safety and consistency regardless of individual surgeon experience. Deep anterior lamellar keratoplasty (DALK), a partial thickness corneal transplant surgery aimed at replacing the anterior part of cornea above Descemet membrane (DM), would greatly benefit from an autonomous surgical approach as it highly relies on surgeon skill with high perforation rates. In this study, we proposed a novel autonomous surgical robotic system (AUTO-DALK) based on a customized neural network capable of precise needle control and consistent big bubble demarcation on cadaver and live rabbit models. We demonstrate the feasibility of an AI-based image-guided vertical drilling approach for big bubble generation, in contrast to the conventional horizontal needle approach. Our system integrates an optical coherence tomography (OCT) fiber optic distal sensor into the eye-mountable micro robotic system, which automatically segments OCT M-mode depth signals to identify corneal layers using a custom deep learning algorithm. It enables the robot to autonomously guide the needle to targeted tissue layers via a depth-controlled feedback loop. We compared autonomous needle insertion performance and resulting pneumo-dissection using AUTO-DALK against 1) freehand insertion, 2) OCT sensor guided manual insertion, and 3) teleoperated robotic insertion, reporting significant improvements in insertion depth, pneumo-dissection depth, task completion time, and big bubble formation. Ex vivo and in vivo results indicate that the AI-driven, AUTO-DALK system, is a promising solution to standardize pneumo-dissection outcomes for partial thickness keratoplasty.

AI assistants are becoming an integral part of society, used for asking advice or help in personal and confidential issues. In this paper, we unveil a novel side-channel that can be used to read encrypted responses from AI Assistants over the web: the token-length side-channel. We found that many vendors, including OpenAI and Microsoft, have this side-channel. However, inferring the content of a response from a token-length sequence alone proves challenging. This is because tokens are akin to words, and responses can be several sentences long leading to millions of grammatically correct sentences. In this paper, we show how this can be overcome by (1) utilizing the power of a large language model (LLM) to translate these sequences, (2) providing the LLM with inter-sentence context to narrow the search space and (3) performing a known-plaintext attack by fine-tuning the model on the target model's writing style. Using these methods, we were able to accurately reconstruct 29\% of an AI assistant's responses and successfully infer the topic from 55\% of them. To demonstrate the threat, we performed the attack on OpenAI's ChatGPT-4 and Microsoft's Copilot on both browser and API traffic.

We study the classical problem of deriving minimax rates for density estimation over convex density classes. Building on the pioneering work of Le Cam (1973), Birge (1983, 1986), Wong and Shen (1995), Yang and Barron (1999), we determine the exact (up to constants) minimax rate over any convex density class. This work thus extends these known results by demonstrating that the local metric entropy of the density class always captures the minimax optimal rates under such settings. Our bounds provide a unifying perspective across both parametric and nonparametric convex density classes, under weaker assumptions on the richness of the density class than previously considered. Our proposed `multistage sieve' MLE applies to any such convex density class. We further demonstrate that this estimator is also adaptive to the true underlying density of interest. We apply our risk bounds to rederive known minimax rates including bounded total variation, and Holder density classes. We further illustrate the utility of the result by deriving upper bounds for less studied classes, e.g., convex mixture of densities.

The delivery drivers of the future may not leave a package at your door. Instead, they'll be sitting several miles or even time zones away in a control room overseeing a fleet of delivery robots or drones. A look at how innovation and technology are transforming the way we live, work and play. Companies are plowing billions of dollars into autonomous technologies they hope will improve efficiency and solve worker shortages. But executives in these industries say true autonomy is many years away–and may never come.

BENTONVILLE, Ark. and SAN DIEGO, Ca.--Sam's Club has completed a roll out of inventory scanning towers that have been added to its existing fleet of floor scrubbing robots. The club store had started adding the inventory towers to its robots in January, and now all locations have the technology added. "Our initial goal at Sam's Club was to convert time historically spent on scrubbers to more member-focused activities. Our autonomous scrubbers have exceeded this goal. In addition to increasing the consistency and frequency of floor cleaning, intelligent scrubbers have empowered associates with critical insights," said Todd Garner, vice president, in-club product management.

One characteristic that makes humans superior to modern artificially intelligent models is the ability to interpret images beyond what is visually apparent. Consider the following two natural language search queries - (i) "a queue of customers patiently waiting to buy ice cream" and (ii) "a queue of tourists going to see a famous Mughal architecture in India." Interpreting these queries requires one to reason with (i) Commonsense such as interpreting people as customers or tourists, actions as waiting to buy or going to see; and (ii) Fact or world knowledge associated with named visual entities, for example, whether the store in the image sells ice cream or whether the landmark in the image is a Mughal architecture located in India. Such reasoning goes beyond just visual recognition. To enable both commonsense and factual reasoning in the image search, we present a unified framework, namely Knowledge Retrieval-Augmented Multimodal Transformer (KRAMT), that treats the named visual entities in an image as a gateway to encyclopedic knowledge and leverages them along with natural language query to ground relevant knowledge. Further, KRAMT seamlessly integrates visual content and grounded knowledge to learn alignment between images and search queries. This unified framework is then used to perform image search requiring commonsense and factual reasoning. The retrieval performance of KRAMT is evaluated and compared with related approaches on a new dataset we introduce - namely COFAR. We make our code and dataset available at https://vl2g.github.io/projects/cofar

Insite AI, a platform for consumer packaged goods companies that uses AI to provide recommendations on how to price, distribute and promote their products in physical stores, today launched out of stealth with $19 million in Series A capital from NewRoad Capital and M12, Microsoft's corporate venture arm. Co-founder Shaveer Mirpuri says that the funding will be put toward customer onboarding, building a team of industry experts to help shape product initiatives and an expanded feature set. Mirpuri and Jonathan Reid co-launched Insite with the belief there was a large addressable market for brick-and-mortar sales revenue growth management software. It's true retailers -- and by extension, brands -- face considerable challenges in this area, particularly as the economy takes a precipitous turn. According to NPD, more than 80% of U.S. consumers said in May that they'd rein in product spending within the next three to six months.