Summary of Harmbench: a Standardized Evaluation Framework For Automated Red Teaming and Robust Refusal, by Mantas Mazeika et al.
HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusalby Mantas Mazeika, Long…
HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusalby Mantas Mazeika, Long…
Breaking Data Silos: Cross-Domain Learning for Multi-Agent Perception from Independent Private Sourcesby Jinlong Li, Baolu…
CasCast: Skillful High-resolution Precipitation Nowcasting via Cascaded Modellingby Junchao Gong, Lei Bai, Peng Ye, Wanghan…
A General Theory for Kernel Packets: from state space model to compactly supported basisby Liang…
Exploring the Effects of Population and Employment Characteristics on Truck Flows: An Analysis of NextGen…
Positive concave deep equilibrium modelsby Mateusz Gabor, Tomasz Piotrowski, Renato L. G. CavalcanteFirst submitted to…
Reducing the Cost of Quantum Chemical Data By Backpropagating Through Density Functional Theoryby Alexander Mathiasen,…
Polyp-DDPM: Diffusion-Based Semantic Polyp Synthesis for Enhanced Segmentationby Zolnamar Dorjsembe, Hsing-Kuo Pao, Furen XiaoFirst submitted…
Connecting the Dots: Collaborative Fine-tuning for Black-Box Vision-Language Modelsby Zhengbo Wang, Jian Liang, Ran He,…
PAC-Bayesian Adversarially Robust Generalization Bounds for Graph Neural Networkby Tan Sun, Junhong LinFirst submitted to…