α
Research
Alpha Leak
Conferences
Topics
Top Authors
Rankings
Browse All
EN
中
Home
/
Authors
/
Nika Haghtalab
Nika Haghtalab
12
papers
1,755
total citations
papers (12)
Jailbroken: How Does LLM Safety Training Fail?
NEURIPS 2023
arXiv
1,501
citations
Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation
ICML 2024
arXiv
65
citations
Smoothed Analysis of Online and Differentially Private Learning
NEURIPS 2020
arXiv
55
citations
On-Demand Sampling: Learning Optimally from Multiple Distributions
NEURIPS 2022
arXiv
46
citations
Calibrated Stackelberg Games: Learning Optimal Commitments Against Calibrated Agents
NEURIPS 2023
arXiv
31
citations
A Unifying Perspective on Multi-Calibration: Game Dynamics for Multi-Objective Learning
NEURIPS 2023
arXiv
25
citations
Improved Bayes Risk Can Yield Reduced Social Welfare Under Competition
NEURIPS 2023
arXiv
16
citations
Smoothed Analysis of Sequential Probability Assignment
NEURIPS 2023
arXiv
10
citations
From Style to Facts: Mapping the Boundaries of Knowledge Injection with Finetuning
NEURIPS 2025
arXiv
4
citations
Learning With Multi-Group Guarantees For Clusterable Subpopulations
ICML 2025
arXiv
2
citations
Oracle-Efficient Online Learning for Smoothed Adversaries
NEURIPS 2022
0
citations
Sample-Adaptivity Tradeoff in On-Demand Sampling
NEURIPS 2025
arXiv
0
citations
