This paper proposes methods to improve the encoding capacity and disentanglement of Variational Autoencoders (VAE) by imposing entropy-based constraints and a weight-filter method.

This paper proposes a Multi-stage Constrained Optimization Framework (MCOF) for Variational Autoencoders (VAEs) to address challenges in sampling, identifying active decision variables, and enforcing…

This paper introduces the Bridge, a lightweight interface that enables distillation between Teachers and Students with different latent resolutions and VAE spaces in Cross-Space Distillation.

This paper proposes Twins, a unified continuous token space for multimodal models using ViT and VAE features, and addresses optimization imbalance with a focal regression objective.

The paper introduces VibeVoice-ASR-BitNet, a compressed real-time speech recognition model optimized for edge CPUs using heterogeneous quantization and custom SIMD kernels.

This paper introduces a formal framework to rigorously verify the security guarantees (confidentiality, integrity, and availability) of AMD SEV confidential virtual machines.

This paper introduces a formal framework to rigorously verify the security guarantees (confidentiality, integrity, and availability) of AMD SEV confidential virtual machines.

PS-UIE proposes a privilege-separated architecture to continuously enforce the integrity of file-backed user-space executable objects within Confidential Virtual Machines (CVMs) like AMD SEV-SNP.

The paper introduces Residualized Sparse Autoencoders (ReSAEs) to improve multi-layer interventions in transformers by training each layer on the residual activation, which better preserves cross-laye…

This paper investigates ways to transform a theory-based methodology for optimizing visual analytics workflows from theory to practice using case studies.

PaCo-VLA introduces a passivity-shielded compliance prior to safely bridge the gap between high-level Vision-Language-Action (VLA) semantic outputs and low-level, force-sensitive robotic control.

The paper presents a highly optimized, low-stack implementation of the HAETAE signature scheme, reducing peak stack usage significantly to enable its use on severely memory-constrained microcontroller…

The paper introduces OS-BLIND, a benchmark demonstrating that current safety evaluations fail to detect critical vulnerabilities in computer-use agents when user instructions are benign, showing high…

The paper introduces V.O.I.C.E, a novel, empirically grounded risk taxonomy that comprehensively models the diverse privacy, security, and governance risks associated with the unconsented synthesis an…

The paper analyzes how agentic AI coding assistants can be compromised via prompt injection attacks embedded in external artifacts, turning them into unauthorized execution shells for attackers.

The paper presents an initial implementation of a quantized, integer-only transformer for jet tagging on the AMD Versal AI Engine using a reusable software framework.

This paper presents a sustainable, low-cost Desktop Virtualization Infrastructure using discarded electronic equipment for digital education.

The paper theoretically analyzes the properties that optimal sparse autoencoder (SAE) dictionaries must satisfy, deriving constraints that explain observed SAE behaviors like hierarchical splitting an…

VFEAgent is a novel multi-agent framework that automates the entire Finite Element Analysis (FEA) workflow, achieving high success rates in generating complete and physically valid simulations directl…

This paper provides a comprehensive formal security analysis of the WPA3 SAE protocol by modeling and analyzing both its high-level communication logic and its low-level state machine implementation.