3 papers
cs.CL2026
Vision-Language Models Integrate Conflicting Evidence Like Biased Bayesian Observers
Josh Barua, Kyle Mahowald, William Rudman
Vision-language models must reconcile conflicting text and images. Prior work has characterized the resulting behavior in terms of modality biases--e.g., a "blind faith in text"--b…
cs.ET2026
PRIM: Energy- and Endurance-Aware Compiler Optimization for Digital Compute in Non-volatile Memory
Patrick Miller, Ulya R. Karpuzcu
Compute-in-Memory (CiM) is an alternative computing paradigm that circumvents the memory bandwidth bottleneck. Variants utilizing non-volatile memory cells (NVCiM) to perform Boole…
cs.ET2026
Computing In Spintronic Memory: A Thermal Perspective
Patrick Miller, Hüsrev Cilasun, Sachin S. Sapatnekar +1
Computing-in-Memory (CiM) is a promising paradigm to address the memory bottleneck constraining traditional systems. Most power-efficient CiM variants can directly perform Boolean…