5 papers
KV-Fold: One-Step KV-Cache Recurrence for Long-Context Inference
Alireza Nadali, Patrick Cooper, Ashutosh Trivedi +1
We introduce KV-Fold, a simple, training-free long-context inference protocol that treats the key-value (KV) cache as the accumulator in a left fold over sequence chunks. At each s…
Monotonicity as an Architectural Bias for Robust Language Models
Patrick Cooper, Alireza Nadali, Ashutosh Trivedi +1
Large language models (LLMs) are known to exhibit brittle behavior under adversarial prompts and jailbreak attacks, even after extensive alignment and fine-tuning. This fragility r…
Monotone Neural Barrier Certificates
Saber Jafarpour, Alireza Nadali, Ashutosh Trivedi +1
This report presents a neurosymbolic framework for safety verification and control synthesis in high-dimensional monotone dynamical systems without relying on explicit models or co…
Transfer Learning for Control Systems via Neural Simulation Relations
Alireza Nadali, Bingzhuo Zhong, Ashutosh Trivedi +1
Transfer learning is an umbrella term for machine learning approaches that leverage knowledge gained from solving one problem (the source domain) to improve speed, efficiency, and…
Transfer of Safety Controllers Through Learning Deep Inverse Dynamics Model
Alireza Nadali, Ashutosh Trivedi, Majid Zamani
Control barrier certificates have proven effective in formally guaranteeing the safety of the control systems. However, designing a control barrier certificate is a time-consuming…