works on

From the 1 of 11 papers with an AI index.

11 papers

cs.CV2026

OPERA: Offline Policy-guided Expert Routing and Adaptation for Universal Biomedical Image Analysis

Zihan Li, Feiyang Liu, Dandan Shan +2

Biomedical image analysis spans diverse modalities and tasks, yet real-world deployment is hindered by severe distribution shifts across scanners, protocols, and patient population…

astro-ph.GA2026

Megaparsec-Scale Neutral Hydrogen Flows in the Neighborhood of Hickson Compact Group 100

Qingzheng Yu, Taotao Fang, Enrico M. Di Teodoro +2

The evolution of galaxies is strongly influenced by their ability to exchange gas with their surroundings, yet direct observational constraints on these processes remain scarce. Us…

cond-mat.mtrl-sci2026

TXL Fusion: A Hybrid Machine Learning Framework Integrating Chemical Heuristics and Large Language Models for Topological Materials Discovery

Arif Ullah, Rajibul Islam, Yangming Huang +4

The paper presents TXL Fusion, a hybrid machine‑learning system that combines chemical heuristics, physics‑based descriptors, and large language model embeddings to classify and pr…

astro-ph.HE2026

SN 2022erq: A Superluminous Thermonuclear Supernova with Escalating Preexplosion Mass Loss

Qian Zhai, Jujia Zhang, Xiaofeng Wang +51

We present a photometric and spectroscopic study of the superluminous Type Ia supernova SN 2022erq. Its early spectra, dominated by iron-group elements with weak intermediate-mass…

cs.LG2026

Network Dynamics-Based Framework for Understanding Deep Neural Networks

Yuchen Lin, Yong Zhang, Sihan Feng +1

Advancements in artificial intelligence call for a deeper understanding of the fundamental mechanisms underlying deep learning. In this work, we propose a theoretical framework to…

cond-mat.mtrl-sci2026

Quantum-inspired Chemical Rule for Discovering Topological Materials

Xinyu Xu, Rajibul Islam, Ghulam Hussain +5

Topological materials exhibit unique electronic structures that underpin both fundamental quantum phenomena and next-generation technologies, yet their discovery remains constraine…