Elvis Nunez — accepted AI-conference papers

2026

Gated KalmaNet: A Fading Memory Layer through Test-time Ridge Regression

Liangzu Peng, Aditya Chattopadhyay, Luca Zancato, Elvis Nunez, Wei Xia, Stefano Soatto

CVPR 2026

As efficient alternatives to softmax Attention, linear state space models (SSMs) achieve constant memory and linear compute, but maintain only a lossy, fading summary of the past, often leading to inferior performance in recall oriented settings. We propose Gated KalmaNet (GKA), a layer that reduces

Cited by 0 Source ↗code ↗Scholar ↗

2026

Learning When to Attend: Conditional Memory Access for Long-Context LLMs

Sakshi Choudhary, Aditya Chattopadhyay, Luca Zancato, Elvis Nunez, Matthew Trager, Wei Xia +1

ICML 2026poster

Language models struggle to generalize beyond the context lengths seen during pretraining, limiting performance on long-horizon reasoning and retrieval. Continued pretraining on long-context data can mitigate this limitation, but it is prohibitively expensive due to the quadratic scaling of Attentio…

Cited by 0 Source ↗Scholar ↗