Background: Dementia, characterized by progressive cognitive decline, is a major global health challenge. Alzheimer's disease (AD) is the predominant type, accounting for approximately 70% of dementia cases worldwide. Electroencephalography (EEG)-derived measures have shown potential in identifying AD risk, but obtaining sufficiently large samples for reliable comparisons remains a challenge. Objective: This study implements a comprehensive methodology that integrates signal processing, data harmonization, and statistical techniques to increase sample size and improve the reliability of Alzheimer's disease risk classification models. Methods: We used a multi-step approach combining advanced EEG preprocessing, feature extraction, harmonization techniques, and propensity score matching (PSM) to optimize the balance between healthy non-carriers (HC) and asymptomatic E280A mutation Alzheimer's disease carriers (ACr). Data were harmonized across four databases, adjusting for site effects while preserving important covariate effects such as age and sex. PSM was applied at different ratios (2:1, 5:1, and 10:1) to explore the impact of sample size differences on model performance. The final dataset was subjected to machine learning analysis using decision trees, with cross-validation to ensure robust model performance.

Large language models are revolutionizing every aspect of human life. However, the unprecedented power comes at the cost of significant computing intensity, suggesting long latency and large energy footprint. Key-Value Cache and Semantic Cache have been proposed as a solution to the above problem, but both suffer from limited scalability due to significant memory cost for each token or instruction embeddings. Motivated by the observations that most instructions are short, repetitive and predictable by LLMs, we propose to predict user-instructions by an instruction-aligned LLM and store them in a predictive cache, so-called InstCache. We introduce an instruction pre-population algorithm based on the negative log likelihood of instructions, determining the cache size with regard to the hit rate. The proposed InstCache is efficiently implemented as a hash table with minimal lookup latency for deployment. Experimental results show that InstCache can achieve up to 51.34% hit rate on LMSys dataset, which corresponds to a 2x speedup, at a memory cost of only 4.5GB. Recently Large Language Models (LLMs) as well as their multi-modal equivalents have become the essential driver of a new wave of technology innovation, revolutionizing every aspect of human life.

Large Language Models (LLMs) have quickly become an invaluable assistant for a variety of tasks. However, their effectiveness is constrained by their ability to tailor responses to human preferences and behaviors via personalization. Prior work in LLM personalization has largely focused on style transfer or incorporating small factoids about the user, as knowledge injection remains an open challenge. In this paper, we explore injecting knowledge of prior conversations into LLMs to enable future work on less redundant, personalized conversations. We identify two real-world constraints: (1) conversations are sequential in time and must be treated as such during training, and (2) per-user personalization is only viable in parameter-efficient settings. To this aim, we propose PLUM, a pipeline performing data augmentation for up-sampling conversations as question-answer pairs, that are then used to finetune a low-rank adaptation adapter with a weighted cross entropy loss. Even in this first exploration of the problem, we perform competitively with baselines such as RAG, attaining an accuracy of 81.5% across 100 conversations.

The popularity of large language models (LLMs) continues to increase, and LLM-based assistants have become ubiquitous, assisting people of diverse backgrounds in many aspects of life. Significant resources have been invested in the safety of LLMs and their alignment with social norms. However, research examining their behavior from the information security awareness (ISA) perspective is lacking. Chatbots and LLM-based assistants may put unwitting users in harm's way by facilitating unsafe behavior. We observe that the ISA inherent in some of today's most popular LLMs varies significantly, with most models requiring user prompts with a clear security context to utilize their security knowledge and provide safe responses to users. Based on this observation, we created a comprehensive set of 30 scenarios to assess the ISA of LLMs. These scenarios benchmark the evaluated models with respect to all focus areas defined in a mobile ISA taxonomy. Among our findings is that ISA is mildly affected by changing the model's temperature, whereas adjusting the system prompt can substantially impact it. This underscores the necessity of setting the right system prompt to mitigate ISA weaknesses. Our findings also highlight the importance of ISA assessment for the development of future LLM-based assistants.

Text-to-speech (TTS) models have been widely adopted to enhance automatic speech recognition (ASR) systems using text-only corpora, thereby reducing the cost of labeling real speech data. Existing research primarily utilizes additional text data and predefined speech styles supported by TTS models. In this paper, we propose Hard-Synth, a novel ASR data augmentation method that leverages large language models (LLMs) and advanced zero-shot TTS. Our approach employs LLMs to generate diverse in-domain text through rewriting, without relying on additional text data. Rather than using predefined speech styles, we introduce a hard prompt selection method with zero-shot TTS to clone speech styles that the ASR model finds challenging to recognize. Experiments demonstrate that Hard-Synth significantly enhances the Conformer model, achieving relative word error rate (WER) reductions of 6.5\%/4.4\% on LibriSpeech dev/test-other subsets. Additionally, we show that Hard-Synth is data-efficient and capable of reducing bias in ASR.

Capturing fresh information in near real-time and using it to augment existing large language models (LLMs) is essential to generate up-to-date, grounded, and reliable output. This problem becomes particularly challenging when LLMs are used for informational tasks in rapidly evolving fields, such as Web search related to recent or unfolding events involving entities, where generating temporally relevant responses requires access to up-to-the-hour news sources. However, the information modeled by the parametric memory of LLMs is often outdated, and Web results from prototypical retrieval systems may fail to capture the latest relevant information and struggle to handle conflicting reports in evolving news. To address this challenge, we present the NEON framework, designed to extract emerging entity interactions -- such as events or activities -- as described in news articles. NEON constructs an entity-centric timestamped knowledge graph that captures such interactions, thereby facilitating enhanced QA capabilities related to news events. Our framework innovates by integrating open Information Extraction (openIE) style tuples into LLMs to enable in-context retrieval-augmented generation. This integration demonstrates substantial improvements in QA performance when tackling temporal, entity-centric search queries. Through NEON, LLMs can deliver more accurate, reliable, and up-to-date responses.

Urban air pollution hotspots pose significant health risks, yet their detection and analysis remain limited by the sparsity of public sensor networks. This paper addresses this challenge by combining predictive modeling and mechanistic approaches to comprehensively monitor pollution hotspots. We enhanced New Delhi's existing sensor network with 28 low-cost sensors, collecting PM2.5 data over 30 months from May 1, 2018, to Nov 1, 2020. Applying established definitions of hotspots to this data, we found the existence of additional 189 hidden hotspots apart from confirming 660 hotspots detected by the public network. Using predictive techniques like Space-Time Kriging, we identified hidden hotspots with 95% precision and 88% recall with 50% sensor failure rate, and with 98% precision and 95% recall with 50% missing sensors. The projected results of our predictive models were further compiled into policy recommendations for public authorities. Additionally, we developed a Gaussian Plume Dispersion Model to understand the mechanistic underpinnings of hotspot formation, incorporating an emissions inventory derived from local sources. Our mechanistic model is able to explain 65% of observed transient hotspots. Our findings underscore the importance of integrating data-driven predictive models with physics-based mechanistic models for scalable and robust air pollution management in resource-constrained settings.

President Biden and China's President Xi Jinping met on Saturday, Nov. 16, 2024, at the APEC Summit in Lima, Peru. A federal China commission released its sprawling yearly report to Congress on Tuesday, for the first time recommending lawmakers end China's favored trade status and the provision that allows goods under 800 to enter the U.S. duty-free. The U.S.-China Economic and Security Review Commission, established by Congress as a bipartisan entity to investigate and provide policy recommendations on China, is now directly advocating for Congress to end the Permanent Normal Trade Relations (PNTR) China has enjoyed since 2004. The committee will pitch its 83 policy recommendations to lawmakers on Tuesday, along with a report on China's military capabilities, its threats to U.S. allies in the region and how it is exploiting U.S. policy for its own advancement. "For decades we have engaged in whack-a-mole policy working within international organizations and guidelines to address the increasing and ambitious efforts by China to skirt laws or take advantage of trade loopholes," commission chair Robin Cleveland said. "In our hearing on the threats to American consumers this year we heard from administration and expert witnesses who were starkly clear: U.S. agencies do not know if the majority of packages coming from China include a baby toy painted with a toxic chemical--a counterfeit piece of clothing made with slave labor--or a pin head amount of fentanyl which is enough to kill the average citizen."

TL;DR: Landmines pose a persistent threat and hinder development in over 70 war-affected countries. Humanitarian demining aims to clear contaminated areas, but progress is slow: at the current pace, it will take 1,100 years to fully demine the planet. In close collaboration with the UN and local NGOs, we co-develop an interpretable predictive tool for landmine contamination to identify hazardous clusters under geographic and budget constraints, experimentally reducing false alarms and clearance time by half. The system is being tested in Afghanistan and Colombia, where it has already led to the discovery of new landmines. Anti-personnel landmines are explosive devices hidden in the ground designed to explode by proximity or contact and with the capacity to kill, disable or cause harm to humans (Figure 1). The mere threat of landmine contamination in a territory not only endangers the physical well-being of affected populations but also results in a loss of forest areas, reduction of productive land, exacerbation of social vulnerability, delay of infrastructure development, and damage of natural, physical, and social capital.

It has long been possible to listen to music from within Opera's browser. If you go down its sidebar, you'll see a player icon where you can choose from Apple Music, Spotify and Deezer and then log into any of them with your account details. But now Opera has teamed up with Spotify and has made the music streaming service the default option on the company's flagship browser with generative AI features, Opera One. After logging into your account and activating the player, you'll be able to detach it from the sidebar and move it around the screen to a place that wouldn't interrupt your workflow. The player will float inside the browser and will not disappear if you tab away.