Related papers: Partial Number Theoretic Transform Masking in Post…

Cross-chain bridges constitute the single largest vector of systemic risk in Decentralized Finance (DeFi), accounting for over \$2.8 billion in losses since 2021. The fundamental vulnerability lies in the binary nature of existing bridge…

The deployment of transformer-based models on resource-constrained edge devices represents a critical challenge in enabling real-time artificial intelligence applications. This comprehensive survey examines lightweight transformer…

Triangles are the basic substructure of networks and triangle counting (TC) has been a fundamental graph computing problem in numerous fields such as social network analysis. Nevertheless, like other graph computing problems, due to the…

The entanglement entropy in many gapless quantum systems receives a contribution from corners in the entangling surface in 2+1d. It is characterized by a universal function $a(\theta)$ depending on the opening angle $\theta$, and contains…

Due to the rising privacy concerns on sensitive client data and trained models like Transformers, secure multi-party computation (MPC) techniques are employed to enable secure inference despite attendant overhead. Existing works attempt to…

This paper presents Toeplitz-Hermitian ADMM-Net (THADMM-Net), a deep neural network obtained by deep unfolding the alternating direction method of multipliers (ADMM) algorithm for solving the least absolute shrinkage thresholding operator…

Targeted attacks against network infrastructure are notoriously difficult to guard against. In the case of communication networks, such attacks can leave users vulnerable to censorship and surveillance, even when cryptography is used. Much…

Majorana zero modes, with prospective applications in topological quantum computing, are expected to arise in superconductor/semiconductor interfaces, such as $\beta$-Sn and InSb. However, proximity to the superconductor may also adversely…

We investigate theorerically the non-equilibrium transport through a molecular quantum dot as a function of gate and bias voltage, taking into account the typical situation in molecular electronics. In this respect, our study includes…

Convolutional neural networks (CNNs) are computationally intensive and often accelerated using crossbar-based in-memory computing (IMC) architectures. However, large convolutional layers must be partitioned across multiple crossbars,…

Extensive efforts have been made to boost the performance in the domain of language models by introducing various attention-based transformers. However, the inclusion of linear layers with large dimensions contributes to significant…

Large language models (LLMs) aligned for safety through techniques like reinforcement learning from human feedback (RLHF) often exhibit emergent deceptive behaviors, where outputs appear compliant but subtly mislead or omit critical…

We study an anisotropic holographic bottom-up model displaying a quantum phase transition (QPT) between a topologically trivial insulator and a non-trivial Weyl semimetal phase. We analyze the properties of quantum chaos in the quantum…

Kyber is a lattice-based key encapsulation mechanism selected for standardization by the NIST Post-Quantum Cryptography (PQC) project. A critical component of Kyber's key generation process is the sampling of matrix elements from a uniform…

We study optimization for losses that admit a variance-mean scale-mixture representation. Under this representation, each EM iteration is a weighted least squares update in which latent variables determine observation and parameter weights;…

Large language models demonstrate strong performance on mathematical reasoning benchmarks, yet remain surprisingly fragile to meaning-preserving surface perturbations. We systematically evaluate three open-weight LLMs, Mistral-7B,…

What structural inductive bias helps transformers reason over knowledge graphs? Through controlled ablations of a minimal transformer modification with four independently removable components (sparse adjacency masking, edge-type biases,…

As quantum computers scale, the rise of multi-user and cloud-based quantum platforms can lead to new security challenges. Attacks within shared execution environments become increasingly feasible due to the crosstalk noise that, in…

Depth is one of the key factors behind the success of convolutional neural networks (CNNs). Since ResNet, we are able to train very deep CNNs as the gradient vanishing issue has been largely addressed by the introduction of skip…

We report on aggressive quantization strategies that greatly accelerate inference of Recurrent Neural Network Transducers (RNN-T). We use a 4 bit integer representation for both weights and activations and apply Quantization Aware Training…