Retrieval pipelines, vector search, chunking and reranking: how models are grounded in a corpus instead of their weights.
arXiv:2504.01627v2 Announce Type: replace-cross Abstract: Introduction: Horizon scanning in healthcare assesses early signals of innovation, crucial for timely adoption. Current horizon scanning face...
arXiv:2610.14863v1 Announce Type: new Abstract: Data-driven weather forecasting models are commonly trained on ERA5, yet operational deployment must use timely initial states from physics-based numer...
arXiv:2610.15642v1 Announce Type: new Abstract: Under a limited context budget, a long-term agent must recall not merely memories that are individually relevant, but evidence that is collectively suf...
arXiv:2610.15463v1 Announce Type: new Abstract: With the rapid proliferation of social media, harmful memes have become a growing threat to online ecosystems. Their harmfulness is often implicitly co...
arXiv:2610.17164v1 Announce Type: new Abstract: The relationship between odor chemistry and perception remains incompletely understood. Many existing studies focus on the perception of single molecul...
arXiv:2610.17399v1 Announce Type: cross Abstract: Continuous monitoring of generative AI systems requires detecting distribution shifts in the unstructured data they ingest and generate. Existing mon...
We identify a theoretical incompatibility between 3D point cloud masked autoencoding and SE(3)-equivariant networks. We prove that standard masking triggers a topological collapse, effectively forcing...
Geo-foundation models (GFMs) are typically evaluated by downstream task predictive performance, revealing little about which physical features they are sensitive to or use in prediction. This limits d...
Unified multimodal generation covers discrete, continuous, and hybrid paradigms. Discrete approaches with single-codebook visual tokenizers align naturally with text modeling but have limited represen...
The article explores how word embeddings encode relationships between words within a learned vector space. It explains the mechanisms by which words become related through their positions and distances in that space. The post provides insights into the underlying processes that allow embeddings to capture semantic connections.
Language models often produce semantically similar answers to open-ended questions, even when many plausible alternatives exist. Generating useful alternatives requires identifying both what the query...
Self-supervised joint embedding learning aligns representations of augmented views while regularizing their distribution to prevent collapse. Regularization aims to shape the overall representation di...
Retrieving external knowledge can improve large language model (LLM) translation by providing supplementary information such as idiom interpretations and terminology. However, existing retrieval-augme...
Recent advancements in topic modeling have split into two main paths: efficient embedding-based methods that offer scalability but are often outperformed on standard clustering metrics, and Large Lang...
Generative approaches to automatic International Classification of Diseases (ICD) coding use large language models (LLMs) to predict ICD codes from clinical documents. However, original ICD code strin...
Generative retrieval (GR) has emerged as a strong candidate generator for sequential recommendation as language models and semantic-item identifiers have improved. However, GR is not a uniformly stron...
Agentic robotics places a large language model (LLM) agent in the robot control loop, where it composes perception, motion, and vision-language-action (VLA) tools under the guidance of a memory and th...
Large language models (LLMs) generally rely on sampling temperature to regulate the amount of randomness in their outputs. Mainstream methods for selecting temperature typically involve fixed, heurist...
The paper investigates configuration problems in Retrieval-Augmented Generation (RAG) systems, which combine large language models with components like vector or graph databases. An empirical study of 654 real-world issues from 10 RAG systems categorizes symptoms, root causes, stages, and fix patterns, revealing that symptoms often appear early or late in the pipeline while root causes may lie elsewhere. The authors also offer nine actionable insights for practitioners to test, localize, and resolve configuration issues in RAG systems.
FALLNEST is a data‑centric framework that condenses large, imbalanced inertial measurement unit (IMU) datasets into tiny, class‑balanced synthetic training sets for wearable fall detection. It combines dual‑domain time‑series condensation, normalized‑gradient matching, MMD‑based embedding alignment, and multi‑view Fourier augmentation to generate 32–146 synthetic windows that enable a 102K‑parameter TinyCNN to achieve 93.5–95.8% mean accuracy and 0.89–0.98 PR‑AUC on SisFall, KFall, and MobiFall benchmarks.