activity
20232025
most citedHarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

23 citations · 32 across the 14 of their papers we have counts for

collaborators

14 papers

cs.RO2025

MobileH2R: Learning Generalizable Human to Mobile Robot Handover Exclusively from Scalable and Diverse Synthetic Data

Zifan Wang, Ziqing Chen, Junyu Chen +6

This paper introduces MobileH2R, a framework for learning generalizable vision-based human-to-mobile-robot (H2MR) handover skills. Unlike traditional fixed-base handovers, this tas…

cond-mat.mtrl-sci2024

Downscaling of non van der Waals Semimetallic W5N6 with Resistivity Preservation

Hongze Gao, Da Zhou, Lu Ping +10

The bulk phase of transition metal nitrides (TMNs) has long been a subject of extensive investigation due to their utility as coating materials, electrocatalysts, and diffusion bar…

cs.CL20241 cited

Generative Language Models with Retrieval Augmented Generation for Automated Short Answer Scoring

Zifan Wang, Christopher Ormerod

Automated Short Answer Scoring (ASAS) is a critical component in educational assessment. While traditional ASAS systems relied on rule-based algorithms or complex deep learning met…

cond-mat.mtrl-sci2024

Thermal conversion of ultrathin nickel hydroxide for wide bandgap 2D nickel oxides

Lu Ping, Nicholas Russo, Zifan Wang +3

Wide bandgap (WBG) semiconductors (Eg >2.0 eV) are integral to the advancement of next generation electronics, optoelectronics, and power industries, owing to their capability for…

cs.LG202423 cited

HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

Mantas Mazeika, Long Phan, Xuwang Yin +9

Automated red teaming holds substantial promise for uncovering and mitigating the risks associated with the malicious use of large language models (LLMs), yet the field lacks a sta…

cs.CV2024

CrossVideo: Self-supervised Cross-modal Contrastive Learning for Point Cloud Video Understanding

Yunze Liu, Changxi Chen, Zifan Wang +1

This paper introduces a novel approach named CrossVideo, which aims to enhance self-supervised cross-modal contrastive learning in the field of point cloud video understanding. Tra…