28 citations · 28 across the 6 of their papers we have counts for
6 papers
Wyvern: An Agentic Framework for Generating Grounded Multimodal Reports
Beatrice Alessandra Motetti, Emilien Guandalino, Daniele Jahier Pagliari +4
In the current artificial intelligence-driven innovation era, the pace of knowledge growth is accelerating, and is hard to keep up with. While generative models are increasingly us…
Intent-Driven Storage Systems: From Low-Level Tuning to High-Level Understanding
Shai Bergman, Won Wook Song, Lukas Cavigelli +3
Existing storage systems lack visibility into workload intent, limiting their ability to adapt to the semantics of modern, large-scale data-intensive applications. This disconnect…
Top-Theta Attention: Sparsifying Transformers by Compensated Thresholding
Konstantin Berestizshevsky, Renzo Andri, Lukas Cavigelli
We present Top-Theta (Top-) Attention, a training-free method for sparsifying transformer attention during inference. Our key insight is that static, per-head thresholds can be…
Identifying and Exploiting Sparse Branch Correlations for Optimizing Branch Prediction
Anastasios Zouzias, Kleovoulos Kalaitzidis, Konstantin Berestizshevsky +3
Branch prediction is arguably one of the most important speculative mechanisms within a high-performance processor architecture. A common approach to improve branch prediction accu…
Physics-Informed Deep Neural Network Method for Limited Observability State Estimation
Jonatan Ostrometzky, Konstantin Berestizshevsky, Andrey Bernstein +1
The precise knowledge regarding the state of the power grid is important in order to ensure optimal and reliable grid operation. Specifically, knowing the state of the distribution…
Dynamically Sacrificing Accuracy for Reduced Computation: Cascaded Inference Based on Softmax Confidence
Konstantin Berestizshevsky, Guy Even
We study the tradeoff between computational effort and classification accuracy in a cascade of deep neural networks. During inference, the user sets the acceptable accuracy degrada…