We consider the problem of restoring linear conservation laws in data-driven linear dynamical models. Given a learned operator widehat{A} and a full-rank constr...
Projected Gradient Descent (PGD) is a strong and widely used first-order adversarial attack, yet its computational cost scales poorly, as all training samples u...
Energy consumption dictates the cost and environmental impact of deploying Large Language Models. This paper investigates the impact of on-chip SRAM size and op...
Real-time, streaming interactive avatars represent a critical yet challenging goal in digital human research. Although diffusion-based human avatar generation m...
Natural Language Processing (NLP) systems are increasingly used in sensitive domains such as healthcare, finance, and government, where they handle large volume...
Stability analyses of modern learning systems are frequently derived under smoothness assumptions that are violated by ReLU-type nonlinearities. In this note, w...
This volume contains the post-proceedings of the Workshop on Adaptable Cloud Architectures (WACA 2025), held on June 20, 2025, in Lille, France, co-located with...
The development of GUI agents could revolutionize the next generation of human-computer interaction. Motivated by this vision, we present MAI-UI, a family of fo...
Prompt-driven Video Segmentation Foundation Models (VSFMs) such as SAM2 are increasingly deployed in applications like autonomous driving and digital pathology,...
Binary program analysis is still very important in system security. There are many practical achievements in binary code analysis, but fine-grained analysis suc...
Large-scale Mixture-of-Experts (MoE) models rely on expert parallelism for efficient training and inference, which splits experts across devices and necessitate...
Federated Fine-Tuning (FFT) has attracted growing interest as it leverages both server- and client-side data to enhance global model generalization while preser...
