Stories tagged science & research.
arXiv
arXiv:2609.25405v1 Announce Type: new Abstract: Modern information retrieval increasingly employs both embedding and generative models to handle complex queries. However, current serving systems suffer from low throughput and poor GPU utilization because they execute these models in isolation…
arXiv
arXiv:2609.25467v1 Announce Type: new Abstract: We often teach a colleague by showing the work and explaining the decisions as we go. How can we check what an agent understood from the same lesson? We introduce ShowTellArena, a benchmark protocol and public dataset for comprehension after narrated…
arXiv
arXiv:2609.25508v1 Announce Type: new Abstract: Structure-mapping forms analogies by aligning systems of relationally connected elements based on shared structure instead of surface features. We introduce a new structure-mapping algorithm: Structure-Mapping with Tight Bounds (SMTB) that is 5--15x…
arXiv
arXiv:2609.25620v1 Announce Type: new Abstract: Scientific investigations into microbial natural products (NPs) present significant challenges for novices, largely due to the complexity of microbial systems, biochemical diversity, technical skill requirements, and the demands of bioinformatics and…
arXiv
arXiv:2609.25686v1 Announce Type: new Abstract: Long-horizon assigned work requires an LLM agent to track the state of a task: which steps are done, blocked, cancelled, or open to repetition. Agent systems either keep this state as text in the prompt and rely on the model to read that text, or move…
arXiv
arXiv:2609.25766v1 Announce Type: new Abstract: AI planning studies how an agent can reach a goal by executing a sequence of actions. To plan correctly, the agent needs an action model describing when each action can be executed and how it changes the world. Constructing such models by hand…
arXiv
arXiv:2609.25021v1 Announce Type: cross Abstract: Large Language Models (LLMs) tend to add disclaimers like "I'm just an AI" when asked about something related to themselves. The self-reports from such responses are used in debates about AI safety or self-knowledge of the models, yet what drives…
arXiv
arXiv:2609.25051v1 Announce Type: cross Abstract: Dual-source encrypted points of interest (DSEP), POIs from two encrypted coordinate systems, suffer from intertwined location and attribute uncertainties, including nonlinear systematic misalignment and naming inconsistency, hindering…
arXiv
arXiv:2609.25471v1 Announce Type: cross Abstract: Semi-supervised federated learning (SSFL) trains models on clients' unlabeled data using a teacher to generate pseudo-labels, with a small labeled seed dataset on the server. Automatic Speech Recognition (ASR) is particularly fragile here…
arXiv
arXiv:2609.25512v1 Announce Type: cross Abstract: We introduce a stretched-grid artificial intelligence (AI) weather forecasting model with 2-km resolution over the western United States and part of the Northeast Pacific and approximately 31-km resolution elsewhere globally. Forecasting over the…
arXiv
arXiv:2609.25562v1 Announce Type: cross Abstract: Open robot policies increasingly follow two paradigms: vision-language-action models (VLAs) directly map observations and instructions to actions, whereas world-action models (WAMs) incorporate learned video or world dynamics into policy learning or…
arXiv
arXiv:2609.25821v1 Announce Type: cross Abstract: Persuasive video generation (PVG) is a valuable yet under-explored research topic. Despite the significant advances in multimodal content generation, AI-empowered automated creation of human-made-like videos with substantial persuasiveness remains a…
arXiv
arXiv:2609.25921v1 Announce Type: cross Abstract: Cybersecurity literature has extensively documented the operational benefits of artificial intelligence (AI) for threat detection, incident response, and prevention, while raising qualitative concerns about over-automation, algorithmic bias, and…
arXiv
arXiv:2609.26016v1 Announce Type: cross Abstract: We call the object this paper derives and certifies a minimal sufficient governance context: given a finite reachable-state model, a deterministic declared verdict, and candidate observable attributes, we compute sufficient observation sets…
arXiv
arXiv:2609.26547v1 Announce Type: cross Abstract: Accurate generation of crystal structures is the foundation to the discovery of high-performance materials for extreme-environment applications, such as aerospace, additive manufacturing, and fusion energy systems. Although generative modeling has…
arXiv
arXiv:2609.26761v1 Announce Type: cross Abstract: Agents using the Model Context Protocol (MCP) rely on semantic matching to select tools from third-party servers, exposing a semantic supply-chain risk through attacker-controlled metadata and outputs. We introduce A2M (Attraction-to-Manipulation)…
arXiv
arXiv:2609.26037v1 Announce Type: cross Abstract: Explanations are central to causal reasoning, and cognitive science has long established that the human drive to explain is itself a mechanism for learning about causality. Despite this, learning from those abductive signals is largely ignored in…
arXiv
arXiv:2609.25541v1 Announce Type: cross Abstract: Tabular foundation models learn to predict cell values in context, whereas world-model self-supervision asks for prediction in representation space (LeCun, 2022; Assran et al., 2023). On a tabular foundation-model prior, the latent term of a…
arXiv
arXiv:2609.26000v1 Announce Type: cross Abstract: Speech enhancement (SE) models typically rely on supervised learning with paired data examples where clean speech is synthetically degraded. This paradigm limits performance in real-world scenarios where the target environment's specific acoustic…
arXiv
arXiv:2609.25889v1 Announce Type: cross Abstract: AI-based autonomous agents, typically hosted at data centers, must acquire state information from robots or edge devices in order to issue informed control decisions. Managing uncertainty about the state is particularly consequential in…
arXiv
arXiv:2609.25634v1 Announce Type: cross Abstract: We trained 64 independently seeded networks in four configurations, continuing each to sustained convergence or a 40,000-epoch ceiling. We then asked whether an RSB-inspired distribution of pairwise weight overlaps changes across the grokking…
arXiv
arXiv:2606.14157v2 Announce Type: replace-cross Abstract: Cities deliver basic services through mixed public-private facility networks, including schools, clinics, transit providers, and subsidized service points. In these systems, planners often observe where households go, but not the latent cost…
arXiv
arXiv:2609.25809v1 Announce Type: cross Abstract: Fine-grained mixture-of-experts (MoE) architectures have become a mainstream design for open-weight LLMs, with hundreds of experts and increasingly many selected per token. This shift makes dynamic expert pruning an attractive route to cheaper…
arXiv
arXiv:2609.25510v1 Announce Type: cross Abstract: Large language models (LLMs) can improve solutions to verifiable scientific and algorithmic problems by spending additional computation at test time. Recent systems achieve strong results with increasingly elaborate evolutionary search harnesses or…
arXiv
arXiv:2609.26125v1 Announce Type: new Abstract: Passive Acoustic Monitoring produces large archives whose recordings are clustered by deployment, season, station identifier, and acquisition configuration. We analyze 908,072 AIS-labeled 679-second recordings from 38 deployments, 20 Atlantic Canadian…
arXiv
arXiv:2609.25460v1 Announce Type: cross Abstract: Autonomous spacecraft guidance and control requires a fast solution to non-convex trajectory optimization, which can be accelerated by providing a near-optimal initial guess to an optimization protocol, i.e., warm-starting. A robust warm starting…
arXiv
arXiv:2609.25397v1 Announce Type: cross Abstract: The one-dimensional bin packing problem (1D-BPP) is a classical NP-hard combinatorial optimization problem with applications ranging from logistics and manufacturing to cloud resource management. Although deep reinforcement learning (DRL) has become…
arXiv
arXiv:2609.26565v1 Announce Type: new Abstract: Massive connectivity in next-generation networks demands energy- and spectrum-efficient solutions for large-scale Internet of Things (IoT) deployments. Symbiotic radio (SR) enables passive IoT devices to communicate by backscattering existing cellular…
arXiv
arXiv:2609.25769v1 Announce Type: new Abstract: Graphical User Interface (GUI) Agents autonomously interact with software to fulfill user requests, where GUI navigation stands out as the most critical and challenging capability. Mastering this capability demands a complex synergy of step-wise…
arXiv
arXiv:2609.25244v2 Announce Type: cross Abstract: Children increasingly interact with AI chatbots, making trust calibration essential to AI literacy. Prior research has examined children's trust in AI mainly as users evaluating systems built by others, rather than as designers of their own…