#domain adaptation
27 papers · 1 filter
Improving Mental Health Screening and Early Risk Detection in Spanish
Andreu Casamayor-Segarra, Vicent Ahuir, Antonio Molina-Marco +1
The paper presents Spanish language models adapted for mental‑health analysis, introduces an Incremental Context Expansion method to automatically relabel social‑media histories fo…
RoboBRIDGE: A Modular Framework for Bridging Policies to Robust Real-World Robotic Agents
Sihyung Yoon, Minjong Yoo, Sanghyun Ahn +2
RoboBRIDGE is a modular orchestration framework that equips pretrained vision‑language‑action models with monitoring, perception, planning, control, and robot interface modules to…
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…
ZMIS-SAM: Segment Anything Model Enhanced with Wavelet Transform for Zooplankton Microscopy Image Instance Segmentation
Dekun Yuan, Zhongwei Li, Zheng Qiao +1
The paper introduces ZMIS-SAM, a model that combines the Segment Anything Model with wavelet transforms and specialized adapters to improve instance segmentation of zooplankton mic…
Recognition and Label-Free Adaptation Across Recording Sessions in Surface-EMG Gesture Decoding
Jethro Odeyemi, W. J. Zhang
The paper proposes a montage‑agnostic encoder for surface EMG gesture decoding that can be applied across different recording sessions without recalibration, and evaluates label‑fr…
A Lightweight Foundation Model for Collider Physics with Multi-Domain Adaptation
Liangyu Wu, Qibin Liu, Alexander Yue +1
The paper introduces NEXUS, a lightweight autoencoder foundation model with ~3 M parameters that is pretrained on Large Hadron Collider track data and fine‑tuned for collider tasks…