Rhamba uses region-aware masking strategies and hybrid Attention-Mamba models pretrained on ABIDE fMRI data to achieve top AUROC on schizophrenia and ADHD classification tasks while outperforming prior methods.
behind a mask
6 Pith papers cite this work. Polarity classification is still indexing.
citation-role summary
citation-polarity summary
roles
method 1polarities
use method 1representative citing papers
Introduces a unified framework with full, partial and budgeted anonymization variants plus four heuristics that outperform baselines by retaining more edges and producing more anonymous nodes.
Introduces animal2vec, a self-supervised transformer for sparse bioacoustic audio, and the MeerKAT meerkat vocalization dataset, claiming outperformance over baselines including in few-shot settings.
Empirical before-after analysis of agentic PRs shows instruction files yield no consistent improvement, with 27.7% of projects gaining and 26.35% losing merge rate, and longer structured files linked to gains in some cases.
The paper identifies and analyzes an 'initial era' in scholarly communications where authors used initials instead of full names, examining its causes and implications for research culture.
citing papers explorer
-
Rhamba: Region-Aware Hybrid Attention-Mamba Framework for Self-Supervised Learning in Resting-State fMRI
Rhamba uses region-aware masking strategies and hybrid Attention-Mamba models pretrained on ABIDE fMRI data to achieve top AUROC on schizophrenia and ADHD classification tasks while outperforming prior methods.
-
The anonymization problem in social networks
Introduces a unified framework with full, partial and budgeted anonymization variants plus four heuristics that outperform baselines by retaining more edges and producing more anonymous nodes.
-
animal2vec and MeerKAT: A self-supervised transformer for rare-event raw audio input and a large-scale reference dataset for bioacoustics
Introduces animal2vec, a self-supervised transformer for sparse bioacoustic audio, and the MeerKAT meerkat vocalization dataset, claiming outperformance over baselines including in few-shot settings.
-
Toward Instructions-as-Code: Understanding the Impact of Instruction Files on Agentic Pull Requests
Empirical before-after analysis of agentic PRs shows instruction files yield no consistent improvement, with 27.7% of projects gaining and 26.35% losing merge rate, and longer structured files linked to gains in some cases.
-
The Rise and Fall of the Initial Era
The paper identifies and analyzes an 'initial era' in scholarly communications where authors used initials instead of full names, examining its causes and implications for research culture.
- A Large-Scale Dataset for Molecular Structure-Language Description via a Rule-Regularized Method