Abstract
Information retrieval systems have progressed notably from lexical techniques such as BM25 and TF-IDF to modern semantic retrievers. This survey provides a brief overview of the BM25 baseline, then discusses the architecture of modern state-of-the-art semantic retrievers. Advancing from BERT, we introduce dense bi-encoders (DPR), late-interaction models (ColBERT), and neural sparse retrieval (SPLADE). Finally, we examine MonoT5, a cross-encoder model. We conclude with common evaluation tactics, pressing challenges, and propositions for future directions.

Abstract
Vector embeddings have been tasked with an ever-increasing set of retrieval tasks over the years, with a nascent rise in using them for reasoning, instruction-following, coding, and more. These new benchmarks push embeddings to work for any query and any notion of relevance that could be given. While prior works have pointed out theoretical limitations of vector embeddings, there is a common assumption that these difficulties are exclusively due to unrealistic queries, and those that are not can be overcome with better training data and larger models. In this work, we demonstrate that we may encounter these theoretical limitations in realistic settings with extremely simple queries. We connect known results in learning theory, showing that the number of top-k subsets of documents capable of being returned as the result of some query is limited by the dimension of the embedding. We empirically show that this holds true even if we restrict to k=2, and directly optimize on the test set with free parameterized embeddings. We then create a realistic dataset called LIMIT that stress tests models based on these theoretical results, and observe that even state-of-the-art models fail on this dataset despite the simple nature of the task. Our work shows the limits of embedding models under the existing single vector paradigm and calls for future research to develop methods that can resolve this fundamental limitation.

Abstract
Deep learning has transformed computer vision (CV), achieving outstanding performance in classification, segmentation, and related tasks. Such AI-based CV systems are becoming prevalent, with applications spanning from medical imaging to surveillance. State of the art models such as convolutional neural networks (CNNs) and vision transformers (ViTs) are often regarded as ``black boxes,'' offering limited transparency into their decision-making processes. Despite a recent advancement in explainable AI (XAI), explainability remains underutilized in practical CV deployments. A primary obstacle is the absence of integrated software solutions that connect XAI techniques with robust knowledge management and monitoring frameworks. To close this gap, we have developed Obz AI, a comprehensive software ecosystem designed to facilitate state-of-the-art explainability and observability for vision AI systems. Obz AI provides a seamless integration pipeline, from a Python client library to a full-stack analytics dashboard. With Obz AI, a machine learning engineer can easily incorporate advanced XAI methodologies, extract and analyze features for outlier detection, and continuously monitor AI models in real time. By making the decision-making mechanisms of deep models interpretable, Obz AI promotes observability and responsible deployment of computer vision systems.

Abstract
I consider motivation and value-alignment in AI systems from the perspective of (constrained) entropy maximization. Though the structures encoding knowledge in any physical system can be understood as energetic constraints, only living agents harness entropy in the endogenous generation of actions. I argue that this exploitation of "mortal" or thermodynamic computation, in which cognitive and physical dynamics are inseparable, is of the essence of desire, motivation, and value, while the lack of true endogenous motivation in simulated "agents" predicts pathologies like reward hacking.

Abstract
With the advancement of large language models (LLMs), significant progress has been achieved in various Natural Language Processing (NLP) tasks. However, existing LLMs still face two major challenges that hinder their broader adoption: (1) their responses tend to be generic and lack personalization tailored to individual users, and (2) they rely heavily on cloud infrastructure due to intensive computational requirements, leading to stable network dependency and response delay. Recent research has predominantly focused on either developing cloud-based personalized LLMs or exploring the on-device deployment of general-purpose LLMs. However, few studies have addressed both limitations simultaneously by investigating personalized on-device language models. To bridge this gap, we propose CDCDA-PLM, a framework for deploying personalized on-device language models on user devices with support from a powerful cloud-based LLM. Specifically, CDCDA-PLM leverages the server-side LLM's strong generalization capabilities to augment users' limited personal data, mitigating the issue of data scarcity. Using both real and synthetic data, A personalized on-device language models (LMs) is fine-tuned via parameter-efficient fine-tuning (PEFT) modules and deployed on users' local devices, enabling them to process queries without depending on cloud-based LLMs. This approach eliminates reliance on network stability and ensures high response speeds. Experimental results across six tasks in a widely used personalization benchmark demonstrate the effectiveness of CDCDA-PLM.

Abstract
Affective Recommender Systems are an emerging class of intelligent systems that aim to enhance personalization by aligning recommendations with users' affective states. Reflecting a growing interest, a number of surveys have been published in this area, however they lack an organizing taxonomy grounded in psychology and they often study only specific types of affective states or application domains. This survey addresses these limitations by providing a comprehensive, systematic review of affective recommender systems across diverse domains. Drawing from Scherer's typology of affective states, we introduce a classification scheme that organizes systems into four main categories: attitude aware, emotion aware, mood aware, and hybrid. We further document affective signal extraction techniques, system architectures, and application areas, highlighting key trends, limitations, and open challenges. As future research directions, we emphasize hybrid models that leverage multiple types of affective states across different modalities, the development of large-scale affect-aware datasets, and the need to replace the folk vocabulary of affective states with a more precise terminology grounded in cognitive and social psychology. Through its systematic review of existing research and challenges, this survey aims to serve as a comprehensive reference and a useful guide for advancing academic research and industry applications in affect-driven personalization.

Abstract
Large language models (LLMs) rely heavily on web-scale datasets like Common Crawl, which provides over 80\% of training data for some modern models. However, the indiscriminate nature of web crawling raises challenges in data quality, safety, and ethics. Despite the critical importance of training data quality, prior research on harmful content has been limited to small samples due to computational constraints. This project presents a framework for indexing and analyzing LLM training datasets using an ElasticSearch-based pipeline. We apply it to SwissAI's FineWeb-2 corpus (1.5TB, four languages), achieving fast query performance--most searches in milliseconds, all under 2 seconds. Our work demonstrates real-time dataset analysis, offering practical tools for safer, more accountable AI systems.

Abstract
In this article the notion of the nondecreasing (ND) rank of a matrix or tensor is introduced. A tensor has an ND rank of r if it can be represented as a sum of r outer products of vectors, with each vector satisfying a monotonicity constraint. It is shown that for certain poset orderings finding an ND factorization of rank $r$ is equivalent to finding a nonnegative rank-r factorization of a transformed tensor. However, not every tensor that is monotonic has a finite ND rank. Theory is developed describing the properties of the ND rank, including typical, maximum, and border ND ranks. Highlighted also are the special settings where a matrix or tensor has an ND rank of one or two. As a means of finding low ND rank approximations to a data tensor we introduce a variant of the hierarchical alternating least squares algorithm. Low ND rank factorizations are found and interpreted for two datasets concerning the weight of pigs and a mental health survey during the COVID-19 pandemic.

Abstract
Ranking athletes by their performance in competitions and tournaments is common in every popular sport and has significant benefits that contribute to both the organization and strategic aspects of competitions. Although rankings are perhaps the most concise and most straightforward representation of the relative strength among the competitors, beyond this one-dimensional characterization, it is also possible to capture the relationships between athletes in greater detail. Following this approach, our study examines the networks between athletes in individual sports such as tennis and fencing, where the nodes are associated with the contestants and the edges are directed from the winner to the loser. We demonstrate that the connections formed through matches arrange themselves into a time-evolving hierarchy, with the top players positioned at its apex. The structure of the resulting networks exhibits detectable differences depending on whether they are constructed purely from round-robin data or from purely elimination-style tournaments. We find that elimination tournaments lead to networks with a smaller level of hierarchy and thus, importantly, to an increased probability of circular win-loss situations (cycles). The position within the hierarchy, along with other network metrics, can be used to predict match outcomes. In the systems studied, these methods provide predictions with an accuracy comparable to that of forecasts based on official sports ranking points or the Elo rating system. A deeper understanding of the delicate aspects of the networks of pairwise contests enhances our ability to model, predict, and optimize the behaviour of many complex systems, whether in sports tournaments, social interactions, or other competitive environments.