3 papers
cs.AI2025
Antidistillation Sampling
Yash Savani, Asher Trockman, Zhili Feng +5
Frontier models that generate extended reasoning traces inadvertently produce rich token sequences that can facilitate model distillation. Recognizing this vulnerability, model own…
cs.LG2025
Predicting the Performance of Black-box LLMs through Follow-up Queries
Dylan Sam, Marc Finzi, J. Zico Kolter
Reliably predicting the behavior of language models -- such as whether their outputs are correct or have been adversarially manipulated -- is a fundamentally challenging task. This…
cs.CV2024
Diffusing Differentiable Representations
Yash Savani, Marc Finzi, J. Zico Kolter
We introduce a novel, training-free method for sampling differentiable representations (diffreps) using pretrained diffusion models. Rather than merely mode-seeking, our method ach…