7 papers
Neither Adversarial Training Nor Purification: Emergent Adversarial Robustness from Oscillatory Predictive Learning
Mohammed-Yassine Habibi, Klea Ziu, Martin Takáč +1
Adversarial robustness in computer vision is still largely achieved through adversarial training or test-time adversarial purification, both of which introduce significant computat…
SiamJEPA: On the Role of Siamese Student Encoders in JEPA
Makoto Yamada
Recently, Joint Embedding Predictive Architectures (JEPAs) have attracted significant attention in the computer vision and machine learning communities as a promising framework for…
TIPS Over Tricks: Simple Prompts for Effective Zero-shot Anomaly Detection
Alireza Salehi, Ehsan Karami, Sepehr Noey +4
Anomaly detection identifies departures from expected behavior in safety-critical settings. When target-domain normal data are unavailable, zero-shot anomaly detection (ZSAD) lever…
Brain-Inspired Stochastic Joint Embedding Representation Learning
Makoto Yamada, Kian Ming A. Chai, Ayoub Rhim +3
Representation learning is one of the key research topics in machine learning, and the framework of self-supervised learning (SSL) has revolutionized computer vision. However, thes…
Disjoint chorded cycles in a -connected graph
Zai Ping Lu, Shu Dan Xue
A chorded cycle in a graph is a cycle containing an edge of that joins two nonconsecutive vertices of the cycle. In 2010, Gao and Qiao independently proved that a graph of…
Task Vector Bases: A Unified and Scalable Framework for Compressed Task Arithmetic
Siqi Zeng, Yifei He, Meitong Liu +5
Task arithmetic, representing downstream tasks through linear operations on task vectors, has emerged as a simple yet powerful paradigm for transferring knowledge across diverse se…