arXiv Machine Learning
Adaptive Computation with Conformal Certification
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
Jun 30
CADS: Conformal Adaptive Decision System for Cost-Efficient Image Classification
arXiv:2605. 16401v2 Announce Type: replace-cross Abstract: While high-capacity AI models have advanced state-of-the-art performance, their practical deployment is often hindered by high inference costs, environmental impact, and a "one-size-fits-all" approach that ignores varying sample complexity.
arXiv Machine Learning
Jul 10
ConRad: Efficient Conformal Prediction for Radiomics
arXiv:2607. 08084v1 Announce Type: cross Abstract: Radiomic features derived from medical images and segmentation masks are used to support decision making in clinical imaging pipelines.
arXiv Computer Vision
Sep 14
Uni-Light: An Ultra-Lightweight Framework via Uncertainty-Aware Knowledge Distillation for Brain Tumour Segmentation
arXiv:2609.06729v2 Announce Type: replace Abstract: Accurate 3D brain tumour segmentation from multi-modal Magnetic Resonance Imaging (MRI) is essential for clinical diagnosis and treatment planning....
arXiv Computer Vision
Sep 21
Uncertainty-driven training for three-dimensional calibrated lung nodule classification
The paper introduces an uncertainty‑driven training framework for 3D CT lung nodule classification that uses validation‑based uncertainty estimates to reweight the loss, aiming to improve predictive performance and probability calibration. Two uncertainty quantification methods—Monte Carlo Dropout and Evidential Deep Learning—are evaluated across multiple backbone architectures (ResNet, DenseNet, EfficientNet, ViT, Swin) on the LIDC‑IDRI and NoduleMNIST3D datasets. The approach yields comparable classification accuracy to conventional training while substantially reducing expected calibration error, especially on convolutional backbones, and shows that simple temperature scaling can also achieve strong calibration.
arXiv Computer Vision
Oct 22
SpineContextResUNet: A Computationally Efficient Residual UNet for Spine CT Segmentation
SpineContextResUNet is a lightweight 3D Residual U‑Net that uses a Context Block with parallel multi‑dilated convolutions to efficiently capture long‑range anatomical dependencies for spine CT segmentation. It achieves Dice scores of 88.17% on VerSe2020 and 88.13% on CTSpine1K while maintaining a small ~1.7 M parameter footprint. Compared to resource‑heavy Transformers and baselines that fail on commodity hardware, SpineContextResUNet delivers robust inference on edge devices such as the Nvidia Jetson Orin Nano.
arXiv AI
Aug 10
Fast LapSum: Exact Differentiable Top-k at Million Scale
arXiv:2608. 06912v1 Announce Type: new Abstract: The top-$k$ operation is a fundamental building block of modern sparse computation, enabling token routing, expert activation, memory selection, and attention pruning.