#zero-shot learning

try —

18 papers match

cs.CV2026

Benchmarking Foundation and Large Language Models for Few-Shot Medical Image Segmentation

Jinghong Liu, Yuchuan Deng, Fanping Liu +2

The paper presents FAME, a unified benchmark for evaluating few-shot medical image segmentation methods across multiple anatomical sites, imaging modalities, and settings, and anal…

#few-shot segmentation#medical imaging#benchmarking#zero-shot learning
cs.RO2026

SemAnCorr: Semantic Anchored Correspondence for Zero-Shot Manipulation Skill Transfer

Xiaoxiang Dong, William Baron, Hongyi Chen +3

The paper presents SemAnCorr, a training‑free method that uses semantically consistent anchor regions and functional maps to create dense, geometrically coherent correspondences be…

#manipulation skill transfer#zero-shot learning#dense correspondence#semantic anchors
cs.CV2026

Zero-Fi: Zero-Shot Wi-Fi-Based Human Activity Recognition via Contrastive Signal-Language Alignment

Yitong Shen, Cheng Guo, Peiliang Wang +5

Zero-Fi introduces a contrastive learning framework that aligns Wi‑Fi signal features with natural‑language descriptions of activities, enabling recognition of unseen human activit…

#zero-shot learning#human activity recognition#wifi sensing#contrastive learning
eess.AS2026

Zero-Shot Face-to-Speech Synthesis via Latent Space Adaptation of a Style-Diffusion TTS Model

Carlos Muñoz-Romero, Jose A. Gonzalez-Lopez

The paper presents a zero-shot Face-to-Speech system that generates a plausible voice from a single facial image by adapting a frozen StyleTTS 2 model with a lightweight face adapt…

#face-to-speech#zero-shot learning#style diffusion#cross-lingual synthesis
cs.CL2026

Selecting Open-Weight Language Models for Zero-Shot Intent Classification: A Systematic Evaluation of 41 Models

Parishruthi Ganesh, Gerry Dozier, Cheryl Seals

The paper systematically evaluates 41 open-weight language models for zero‑shot intent classification across multiple datasets, analyzing accuracy, calibration, robustness, and dep…

#intent classification#zero-shot learning#language model evaluation#instruction tuning
cs.CV2026

SUFLECA: Scaling Up Feature Learning for CAD-to-image Alignment

Saad Ejaz, Miguel Fernandez-Cortizas, Javier Civera +2

The paper introduces SUFLECA, a weakly‑supervised framework that learns geometry‑aware features from large image collections to align CAD models to single RGB images, enabling zero…

#cad-to-image alignment#zero-shot learning#feature learning#geometry-aware representations