Sotabase

Career

· Research Scientist, Scale AI2024–

Publications (44)

Universal and Transferable Adversarial Attacks on Aligned Language Models
arXiv.org · 2023
2,427
cited
Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · 2019
1,312
cited
HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
International Conference on Machine Learning · 2024
781
cited
Representation Engineering: A Top-Down Approach to AI Transparency
arXiv.org · 2023
739
cited
The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning
International Conference on Machine Learning · 2024
327
cited
Distributed scheduling problems in intelligent manufacturing systems
2021
148
cited
Smoothed Geometry for Robust Attribution
Neural Information Processing Systems · 2020
62
cited
Consistent Counterfactuals for Deep Models
International Conference on Learning Representations · 2021
56
cited
In situ neutron diffraction investigation of texture-dependent Shape Memory Effect in a near equiatomic NiTi alloy
2021
54
cited
An experimental and numerical analysis of residual stresses in a TIG weldment of a single crystal nickel-base superalloy
Journal of Manufacturing Processes · 2020
51
cited
Synchrotron X-ray quantitative evaluation of transient deformation and damage phenomena in a single nickel-rich cathode particle
Energy & Environmental Science · 2020
47
cited
Can LLMs Follow Simple Rules?
arXiv.org · 2023
44
cited
Grain Structure Engineering of NiTi Shape Memory Alloys by Intensive Plastic Deformation
ACS Applied Materials and Interfaces · 2022
44
cited
Multiscale stress and strain statistics in the deformation of polycrystalline alloys
International journal of plasticity · 2022
38
cited
Evolution of thermal and mechanical properties of Nitinol wire as a function of ageing treatment conditions
Journal of Alloys and Compounds · 2020
36
cited
SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?
arXiv.org · 2025
25
cited
Neutron strain scanning for experimental validation of the artificial intelligence based eigenstrain contour method
Mechanics of materials (Print) · 2020
22
cited
Influence Patterns for Explaining Information Flow in BERT
Neural Information Processing Systems · 2020
19
cited
Interpreting Interpretations: Organizing Attribution Methods by Criteria
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · 2020
19
cited
TOMOGRAPHIC EIGENSTRAIN RECONSTRUCTION FOR FULL-FIELD RESIDUAL STRESS ANALYSIS IN LARGE SCALE ADDITIVE MANUFACTURING PARTS
Additive Manufacturing · 2024
18
cited
Sotabase
Zifan Wang | Researcher Profile | Sotabase | Sotabase