Zifan Wang

Affiliations

Carnegie Mellon University

papers

1,270

total citations

papers (12)

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

ICML 2024arXiv

802

citations

Mitigating the Human-Robot Domain Discrepancy in Visual Pre-training for Robotic Manipulation

CVPR 2025arXiv

citations

Unlocking Deterministic Robustness Certification on ImageNet

NEURIPS 2023arXiv

citations

Semantic Complete Scene Forecasting from a 4D Dynamic Point Cloud Sequence

AAAI 2024arXiv

citations

Improving Robust Generalization by Direct PAC-Bayesian Bound Minimization

CVPR 2023arXiv

citations

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

CVPR 2025arXiv

citations

Validating Mechanistic Interpretations: An Axiomatic Approach

ICML 2025arXiv

citations

GenH2R: Learning Generalizable Human-to-Robot Handover via Scalable Simulation Demonstration and Imitation

CVPR 2024

citations

Grounding Neural Inference with Satisfiability Modulo Theories

NEURIPS 2023

citations

Zifan Wang

Affiliations

papers (12)

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

The WMDP Benchmark: Measuring and Reducing Malicious Use with Unlearning

Smoothed Geometry for Robust Attribution

Influence Patterns for Explaining Information Flow in BERT

Mitigating the Human-Robot Domain Discrepancy in Visual Pre-training for Robotic Manipulation

Unlocking Deterministic Robustness Certification on ImageNet

Semantic Complete Scene Forecasting from a 4D Dynamic Point Cloud Sequence

Improving Robust Generalization by Direct PAC-Bayesian Bound Minimization

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

Validating Mechanistic Interpretations: An Axiomatic Approach

GenH2R: Learning Generalizable Human-to-Robot Handover via Scalable Simulation Demonstration and Imitation

Grounding Neural Inference with Satisfiability Modulo Theories

papers (12)

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

The WMDP Benchmark: Measuring and Reducing Malicious Use with Unlearning

Smoothed Geometry for Robust Attribution

Influence Patterns for Explaining Information Flow in BERT

Mitigating the Human-Robot Domain Discrepancy in Visual Pre-training for Robotic Manipulation

Unlocking Deterministic Robustness Certification on ImageNet

Semantic Complete Scene Forecasting from a 4D Dynamic Point Cloud Sequence

Improving Robust Generalization by Direct PAC-Bayesian Bound Minimization

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

Validating Mechanistic Interpretations: An Axiomatic Approach

GenH2R: Learning Generalizable Human-to-Robot Handover via Scalable Simulation Demonstration and Imitation

Grounding Neural Inference with Satisfiability Modulo Theories