3 papers
cs.LG2026
Asking Forever: Universal Activations Behind Turn Amplification in Conversational LLMs
Zachary Coalson, Bo Fang, Sanghyun Hong
Multi-turn interaction length is a dominant factor in the operational costs of conversational LLMs. In this work, we present a new failure mode in conversational LLMs: turn amplifi…
cs.CR2025
Hessian-aware Training for Enhancing DNNs Resilience to Parameter Corruptions
Tahmid Hasan Prato, Seijoon Kim, Lizhong Chen +1
Deep neural networks are not resilient to parameter corruptions: even a single-bitwise error in their parameters in memory can cause an accuracy drop of over 10%, and in the worst…
cs.CL2024
LeaPformer: Enabling Linear Transformers for Autoregressive and Simultaneous Tasks via Learned Proportions
Victor Agostinelli, Sanghyun Hong, Lizhong Chen
A promising approach to preserving model performance in linearized transformers is to employ position-based re-weighting functions. However, state-of-the-art re-weighting functions…