MAX HARTMAN

Research

Publications

reverse chronological · google scholar

2026

In-Review

Hiding in Plain Sight: Detectability-Aware Antidistillation of Reasoning Models

Max Hartman, Vidhata Jayaraman, Moulik Choraria, Yash Savani, Lav R. Varshney

Manuscript
ICML WS

Protecting the Trace: A Principled Black-Box Approach Against Distillation Attacks

Max Hartman, Vidhata Jayaraman, Moulik Choraria, Lav R. Varshney — ICML (Second) Workshop on Technical AI Governance Research

openreview
ICML

Skip-It? Theoretical Conditions for Layer Skipping in Vision–Language Models

Max Hartman, Vidhata Jayaraman, Moulik Choraria, Akhil Bhimaraju, Lav R. Varshney — Forty-Third International Conference on Machine Learning

openreview
ACC

Federated Nonlinear System Identification

Omkar Tupe, Max Hartman, Lav R. Varshney, Saurav Prakash — The 2026 American Control Conference

Manuscript
JSTSP

Continual Instruction Tuning via Increasing Experts

Xinbo Wu, Max Hartman, Vidhata Arjun Jayaraman, Lav R. Varshney — IEEE Journal of Selected Topics in Signal Processing

IEEE Explore

2025

ICCV WS

Unmasking the Functionality of Early Layers in VLMs

Max Hartman, Vidhata Jayaraman, Moulik Choraria, Akhil Bhimaraju, Lav R. Varshney — ICCV 2025 Workshop on Explainable Computer Vision: Quo Vadis?

openreview
JSAIT

Energy-Aware Routing to Large Reasoning Models

Austin R. Ellis-Mohr, Max Hartman, Lav R. Varshney — IEEE Journal of Selected Areas in Information Theory

IEEE Explore
arXiv

SparseJEPA: Sparse Representation Learning of Joint Embedding Predictive Architectures - Undergraduate Thesis

Max Hartman, Lav Varshney

Manuscript