On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

2 results for “reconstruction-free”

Single-Step Reconstruction-Free Anomaly Detection and Segmentation via Diffusion Modelscs.CV

RADAR uses diffusion models to detect anomalies without reconstruction, improving accuracy and efficiency.

problem Challenges in anomaly detection and segmentation, especially in real-time applications.

method RADAR uses attention-based diffusion models to directly produce anomaly maps from the diffusion process, bypassing reconstruction.

result RADAR improves F1 score by 7% on MVTec-AD and 13% on 3D-printed material compared to state-of-the-art methods.

anomaly detection diffusion models attention reconstruction-free real-time

2025-08-06abs ↗pdf ↗

Joint Embedding Variational Bayescs.LG

VJE learns latent representations without contrastive learning, providing probabilistic semantics.

problem Learning latent representations without contrastive signals.

method VJE maximizes a symmetric conditional evidence lower bound (ELBO) on paired encoder embeddings, using a Student-t distribution on a polar representation.

result VJE outperforms standard non-contrastive baselines in ImageNet-1K, CIFAR-10/100, and STL-10.

latent representation self-supervised learning non-contrastive variational inference Student-t distribution

2026-02-05abs ↗pdf ↗