3 papers
cs.LG2026
When Interpretability Becomes a Liability: Adversarial Attacks on CBM Concept Layers
Aditya Sridhar
Concept Bottleneck Models (CBMs) have emerged as a cornerstone approach for interpretable machine learning, providing human-understandable intermediate representations through expl…
cs.LG2025
TapOut: A Bandit-Based Approach to Dynamic Speculative Decoding
Aditya Sridhar, Nish Sinnadurai, Sean Lie +1
Speculative decoding accelerates LLMs by using a lightweight draft model to generate tokens autoregressively before verifying them in parallel with a larger target model. However,…
cs.RO2025
Humanoid World Models: Open World Foundation Models for Humanoid Robotics
Muhammad Qasim Ali, Aditya Sridhar, Shahbuland Matiana +2
Humanoid robots, with their human-like form, are uniquely suited for interacting in environments built for people. However, enabling humanoids to reason, plan, and act in complex o…