Showing cs.LGShow all
2 papers · 1 filter
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,…