Current neural re-rankers often struggle with complex information needs and long, content-rich documents. The fundamental issue is not computational--it is intelligent content selection: identifying what matters in lengthy, multi-faceted texts. While humans naturally anchor their understanding around key entities and concepts, neural models process text within rigid token windows, treating all interactions as equally important and missing critical semantic signals. We introduce REGENT, a neural re-ranking model that mimics human-like understanding by using entities as a "semantic skeleton" to guide attention. REGENT integrates relevance guidance directly into the attention mechanism, combining fine-grained lexical matching with high-level semantic reasoning. This relevance-guided attention enables the model to focus on conceptually important content while maintaining sensitivity to precise term matches. REGENT achieves new state-of-the-art performance in three challenging datasets, providing up to 108% improvement over BM25 and consistently outperforming strong baselines including ColBERT and RankVicuna. To our knowledge, this is the first work to successfully integrate entity semantics directly into neural attention, establishing a new paradigm for entity-aware information retrieval.

Building generalist agents that can rapidly adapt to new environments is a key challenge for deploying AI in the digital and real worlds. Is scaling current agent architectures the most effective way to build generalist agents? We propose a novel approach to pre-train relatively small policies on relatively small datasets and adapt them to unseen environments via in-context learning, without any finetuning. Our key idea is that retrieval offers a powerful bias for fast adaptation. Indeed, we demonstrate that even a simple retrieval-based 1-nearest neighbor agent offers a surprisingly strong baseline for today's state-of-the-art generalist agents. From this starting point, we construct a semi-parametric agent, REGENT, that trains a transformer-based policy on sequences of queries and retrieved neighbors. REGENT can generalize to unseen robotics and game-playing environments via retrieval augmentation and in-context learning, achieving this with up to 3x fewer parameters and up to an order-of-magnitude fewer pre-training datapoints, significantly outperforming today's state-of-the-art generalist agents. AI agents, both in the digital [38, 19, 37, 28, 53] and real world [5, 7, 63, 33, 48, 24], constantly face changing environments that require rapid or even instantaneous adaptation. True generalist agents must not only be capable of performing well on large numbers of training environments, but arguably more importantly, they must be capable of adapting rapidly to new environments. While this goal has been of considerable interest to the reinforcement learning research community, it has proven elusive. The most promising results so far have all been attributed to large policies [38, 19, 37, 28, 5], pre-trained on large datasets across many environments, and even these models still struggle to generalize to unseen environments without many new environment-specific demonstrations. In this work, we take a different approach to the problem of constructing such generalist agents. We start by asking: Is scaling current agent architectures the most effective way to build generalist agents? Observing that retrieval offers a powerful bias for fast adaptation, we first evaluate a simple 1-nearest neighbor method: "Retrieve and Play (R&P)". To determine the action at the current state, R&P simply retrieves the closest state from a few demonstrations in the target environment and plays its corresponding action. Tested on a wide range of environments, both robotics and game-playing, R&P performs on-par or better than the state-of-the-art generalist agents.

Machine learning based autonomous driving systems often face challenges with safety-critical scenarios that are rare in real-world data, hindering their large-scale deployment. While increasing real-world training data coverage could address this issue, it is costly and dangerous. This work explores generating safety-critical driving scenarios by modifying complex real-world regular scenarios through trajectory optimization. We propose ReGentS, which stabilizes generated trajectories and introduces heuristics to avoid obvious collisions and optimization problems. Our approach addresses unrealistic diverging trajectories and unavoidable collision scenarios that are not useful for training robust planner. We also extend the scenario generation framework to handle real-world data with up to 32 agents.

A pair of artificial intelligence degrees are coming to Dakota State University. In March, the Board of Regents approved a bachelor of science degree in AI, which will be offered by the Beacom College of Computer and Cyber Sciences. Now another program, geared more toward the workplace, has the green light. The Board of Regents has given Dakota State University the okay to offer a bachelor of science in Artificial Intelligence in Organizations. Instead of focusing on the computer science side of AI, this degree will be offered through the College and Business and Information Systems.

A new artificial intelligence graduate degree program at Iowa State University will be the first of its kind in the state. The Iowa Board of Regents approved the two-year master's of science degree program Thursday through consent agenda after being presented with the program Wednesday in committee. The graduate program is expected to begin this fall. Hridesh Rajan, a professor and chairperson of ISU's Department of Computer Science, said the new program seeks to produce graduates that can work on building and enhancing components of artificial intelligence -- not only to be able to understand and make practical use of machine learning and big data, but also be able to communicate the capabilities and limitations of AI. Artificial intelligence, or AI, is the study of techniques that help incorporate intelligence into software, Rajan said.

DBSCAN may not be sufficient when the input data type is heterogeneous in terms of textual description. When we aim to discover clusters of geo-tagged records relevant to a particular point-of-interest (POI) on social media, examining only one type of input data (e.g., the tweets relevant to a POI) may draw an incomplete picture of clusters due to noisy regions. To overcome this problem, we introduce DBSTexC, a newly defined density-based clustering algorithm using spatio--textual information. We first characterize POI-relevant and POI-irrelevant tweets as the texts that include and do not include a POI name or its semantically coherent variations, respectively. By leveraging the proportion of POI-relevant and POI-irrelevant tweets, the proposed algorithm demonstrates much higher clustering performance than the DBSCAN case in terms of $\mathcal{F}_1$ score and its variants. While DBSTexC performs exactly as DBSCAN with the textually homogeneous inputs, it far outperforms DBSCAN with the textually heterogeneous inputs. Furthermore, to further improve the clustering quality by fully capturing the geographic distribution of tweets, we present fuzzy DBSTexC (F-DBSTexC), an extension of DBSTexC, which incorporates the notion of fuzzy clustering into the DBSTexC. We then demonstrate the robustness of F-DBSTexC via intensive experiments. The computational complexity of our algorithms is also analytically and numerically shown.

Most English dictionaries list words alphabetically, but how do we store them in our head? Finding out could have an unexpected pay-off: being able to tell what someone is thinking from their brain activity. Although neuroscientists can already do this to a limited extent, the brain's internal filing system for words and concepts – an important step towards accurately reading a person's thoughts – remains murky. Now Jack Gallant at the University of California, Berkeley, and his team have charted the "semantic system" of the human brain. The resulting map reveals that we organise words according to their deeper meaning, in subcategories based around numbers, places, and other common themes. Previous "mind-reading" studies have shown that certain parts of the brain respond to particular words.