Retrieval pipelines, vector search, chunking and reranking: how models are grounded in a corpus instead of their weights.
arXiv:2505.23462v2 Announce Type: replace Abstract: Blind face restoration from low-quality images is a challenging task that requires not only high-fidelity image reconstruction, but also preservati...
arXiv:2608.24053v1 Announce Type: new Abstract: Universal multimodal embeddings are becoming a core component of modern AI systems, enabling heterogeneous content to be represented in a shared space...
Partial manipulation of speech recordings, where only localized segments of an utterance are altered, poses a significant challenge for content integrity verification, as reliable detection and locali...
Partial deepfake speech, where only limited segments of an utterance are synthesized or manipulated, poses a significant challenge to existing deepfake detection systems. As the proportion of spoofed...
We study a tree-structured regularizer over class-prototype layouts in a hierarchical-classification model and ask whether the choice of latent manifold for the prototypes (Euclidean R^d vs. the Poinc...
Knowledge graph (KG) construction pipelines must continuously integrate newly arriving entities into a growing graph. Unlike inserting triples between existing nodes, a newly arriving entity has no gr...
Frozen hematology foundation-model (FM) embeddings reach near-saturated in-domain white-blood-cell (WBC) accuracy, but clinical deployment demands reliability across scanners, sites, stains and prepar...
Fully few-shot class-incremental audio classification (FFCAC) requires recognizing new sound classes from only a handful of labeled examples per session, without forgetting previously learned classes...
Traditional image similarity metrics such as Mean Squared Error (MSE), Peak Signal-to-Noise Ratio (PSNR), and the Structural Similarity Index Measure (SSIM) rely on pixel-level comparisons and often f...
Evaluating Retrieval-Augmented Generation (RAG) systems requires assessing not only end-to-end correctness but also how individual components interact and how errors propagate through the pipeline. We...
Imaging factor disentanglement in text-to-image generation aims to independently control image acquisition properties such as types of camera lenses, sensor types, viewpoints, and domains to enable co...
Although recent Multimodal Large Language Models (MLLMs) have advanced general product understanding, they implicitly encode product information into global embeddings, thereby limiting their ability...
The prediction of student engagement from the online tutoring videos is difficult because engagement is a multidimensional construct comprising distinct behavioral, emotional, and cognitive states. A...
Continual knowledge graph embedding updates entity and relation representations as a graph grows. Existing methods primarily address catastrophic forgetting, but entity admission also changes the cand...
Industrial actor--critic methods usually represent continuous actions as anonymous numerical coordinates. They must therefore learn from limited interactions which process variables each action affect...
The article discusses a case study in enterprise document intelligence where a single document type contains a million files. It outlines a workflow that takes about an hour with two people to extract six to ten structured fields, emphasizing the importance of identifying two key signals that distinguish a valid column from one that could break a filter later. The focus is on converting unstructured documents into a structured SQL table for Retrieval-Augmented Generation (RAG) queries.
Universal multimodal embeddings are becoming a core component of modern AI systems, enabling heterogeneous content to be represented in a shared space for applications such as retrieval, recommendatio...
arXiv:2608.23484v1 Announce Type: new Abstract: We present Team Semiintelligencn's solution for the ACM RecSys 2026 TalkPlayData Challenge, addressing conversational music recommendation through a mu...
The paper introduces Segment Anything Small (SAS), a data‑augmentation method that improves deep‑learning segmentation of small anatomical structures in ultrasound images. SAS uses two transformations: resizing and embedding organ thumbnails into a black background to vary organ scale, and adding noise to regions of interest to mimic tissue texture variability. Experiments on one internal and five external datasets show Dice score gains up to 0.35, with an average improvement of 0.16, and demonstrate that SAS enhances model robustness and generalizability without adding hallucinations or artifacts.