7 papers
Evaluating the Applicability of LLM Inference Optimizations on Apple Silicon
Kyrylo Yemets, Andrii Yaroshevych, Victor Muryn +5
Apple Silicon is among the most widely used platforms for local LLM inference, yet nearly all inference optimizations are designed and validated on server-class NVIDIA GPUs under b…
MacArena: Benchmarking Computer Use Agents on an Online macOS Environment
Victor Muryn, Maksym Shamrai, Sofiia Mazepa +1
Computer-use agents (CUAs) operate graphical user interfaces (GUIs) through vision and control primitives, and their capabilities have advanced rapidly, driven in part by standardi…
Concatenated Matrix SVD: Compression Bounds, Incremental Approximation, and Error-Constrained Clustering
Maksym Shamrai
Large collections of matrices arise throughout modern machine learning, signal processing, and scientific computing, where they are commonly compressed by concatenation followed by…
GUIrilla: A Scalable Framework for Automated Desktop UI Exploration
Sofiya Garkot, Maksym Shamrai, Ivan Synytsia +1
The performance and generalization of foundation models for interactive systems critically depend on the availability of large-scale, realistic training data. While recent advances…
Deep Language Geometry: Constructing a Metric Space from LLM Weights
Maksym Shamrai, Vladyslav Hamolia
We introduce a novel framework that utilizes the internal weight activations of modern Large Language Models (LLMs) to construct a metric space of languages. Unlike traditional app…
Closed-Form Robustness Bounds for Second-Order Pruning of Neural Controller Policies
Maksym Shamrai
Deep neural policies have unlocked agile flight for quadcopters, adaptive grasping for manipulators, and reliable navigation for ground robots, yet their millions of weights confli…
Perturbation Analysis of Singular Values in Concatenated Matrices
Maksym Shamrai
Concatenating matrices is a common technique for uncovering shared structures in data through singular value decomposition (SVD) and low-rank approximations. The fundamental questi…