About Me š
I am a PhD student at Harvard under the mentorship of Dr. Flavio du Pin Calmon and Dr. Hima Lakkaraju and am supported by the NSF Graduate Student Research Fellowship.
I am broadly interested in fair, interpretable, and trustworthy machine learning, and my current projects apply information theoretic tools to problems in fairness and representation learning. Although I love digging into theory, I am an engineer by training and hope to use my research to design actionable solutions for society.
Outside of the lab, you can find me playing jazz guitar šø, volleyball š (Iām a middle blocker!), or playing board games with my friends.
Publications āļø
Leveraging the Sequential Nature of Language for Interpretability 
                    
                    Oral, ICML 2025 Workshop on Assessing World Models
Soft Best-of-n Sampling for Model Alignment 
                    
                    ISIT 2025
Inference-Time Reward Hacking in Large Language Models 
                    Hadi Khalaf, Claudio Mayrink Verdun, 
                    ICML 2025 Workshop on Models of Human Feedback for AI Alignment
Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE šŖ¢) 
                    
                    NeurIPS 2024
Multi-Group Proportional Representation in Retrieval 
                    
                    NeurIPS 2024
Measuring Representational Harms in Image Generation with a Multi-Group Proportional Metric. 
                    Sangwon Jung, 
                    CVPR 2025, Prev. AFME Workshop, NeurIPS 2024
Operationalizing the Blueprint for an AI Bill of Rights: Recommendations for Practitioners, Researchers, and Policy Makers 
                    
                    Under Review.
Fair Machine Unlearning: Mitigating Disparities during Data Deletion 
                    
                    AISTATS 2024
                    Prev. at Data Centric Machine Learning Workshop, ICML 2023
Multitask Learning for Citation Purpose Classification 
                    
                    2nd Workshop on Scholarly Document Processing, NAACL 2021
Distributionally Robust Group Backwards Compatibility 
                    Martin Bertran, Natalia Martinez, 
                    DistShift Workshop, NeurIPS 2021
All Roads Lead to Rome? Exploring Representational Similarities Between Latent Spaces of Generative Image Models 
                    Charumathi Badrinath, Usha Bhalla, 
                    HiLD, GRaM, SPIGM Workshops, ICML 2024
Detecting Motion in a Room Using a Dynamic Metasurface Antenna 
                
                IEEE Access, 2020
Integrated single-cell multiomic analysis of HIV latency reversal reveals novel regulators of viral reactivation 
                    Ashokkumar Manickam, Jackson J Peterson, Yuriko Harigaya, David M Murdoch, David M Margolis, 
                Genomics, Proteomics, & Bioinformatics, 2024
Integrated single-cell multiomic profiling of HIV latency reversal 
                    Ashokkumar Manickam, Jackson J Peterson, Wei Mei, David M Murdoch, David M Margolis, 
                Journal of Virus Eradication, 2022
aoesterling [at] g [dot] harvard [dot] edu
google scholar
curriculum vitae