649 citations · 689 across the 9 of their papers we have counts for
4 papers · 1 filter
Output Dilution: Redundant but Fragile Representations in MoE Models
Orion Reblitz-Richardson
Mixture-of-Experts (MoE) models appear to encode moral content as robustly as dense models, yet prove far more fragile in their encoding. In OLMoE-1B-7B, linear probes recover mora…
ExecuTorch -- A Unified PyTorch Solution to Run AI Models On-Device
Mergen Nachin, Digant Desai, Sicheng Stephen Jia +36
Local execution of AI on edge devices is important for low latency and offline operation. However, deploying models on diverse hardware remains fragmented, often requiring model co…
Investigating sanity checks for saliency maps with image and text classification
Narine Kokhlikyan, Vivek Miglani, Bilal Alsallakh +2
Saliency maps have shown to be both useful and misleading for explaining model predictions especially in the context of images. In this paper, we perform sanity checks for text mod…
Captum: A unified and generic model interpretability library for PyTorch
Narine Kokhlikyan, Vivek Miglani, Miguel Martin +8
In this paper we introduce a novel, unified, open-source model interpretability library for PyTorch [12]. The library contains generic implementations of a number of gradient and p…