This paper proposes using transformer-based models on program slices to accurately detect C/C++ software vulnerabilities by capturing both local and global contextual information.

The paper analyzes the expressivity of padded transformers, proving that their computational power is primarily determined by model depth and numeric precision, rather than attention type or width.

The paper introduces Morlet Positional Encoding (MoPE), a novel wavelet-based positional encoding that models position and locality simultaneously, outperforming standard sinusoidal and RoPE methods.

The paper proposes an uncertainty-aware transfer learning framework using the Temporal Fusion Transformer (TFT) to achieve robust and scalable energy forecasting across different buildings, demonstrat…

This paper proposes an explainability-guided adversarial attack that successfully evades transformer-based malware detectors by perturbing the most influential components of the control flow graph rep…

The paper introduces CritBench, a novel framework to evaluate LLM cybersecurity capabilities specifically within IEC 61850 Digital Substation Operational Technology (OT) environments, finding that whi…

This paper investigates the application of Parameter-Efficient Fine-Tuning (PEFT) methods, specifically adapters and LoRA, to large pretrained models for instance segmentation, demonstrating that thes…

This paper systematically studies the robustness of vision foundation models to common image perturbations, finding that most models are generally non-robust and proposing a fine-tuning method to impr…

EncFormer is a novel two-party framework that significantly improves the efficiency and scalability of private Transformer inference by optimizing the combination of Fully Homomorphic Encryption (FHE)…

The paper demonstrates that positional encodings are not necessary for transformers to achieve universal computation, showing that the inherent mechanism of sliding context windows already provides su…

The paper proposes a Transformer-based end-to-end architecture to reconstruct 3D house roof wireframes from sparse point clouds and semantic data, achieving state-of-the-art results on the S23DR Chall…

The paper demonstrates that using the transformer-based foundation model TabPFNv2.5 can significantly speed up IoT intrusion detection compared to traditional ensemble methods while maintaining high a…

The paper addresses the reliability of open-weight LLMs for power system code generation by identifying structured API-knowledge boundary errors and proposing a boundary-aware intervention that signif…

CART introduces a parameter-efficient recurrent transformer architecture that reuses a core block multiple times, but its performance does not surpass a dense baseline, suggesting that weight sharing…

The paper demonstrates that Low-Rank Adaptation (LoRA) is an effective and superior method for adapting large, pretrained Transformer surrogates for automotive aerodynamics to new vehicle families usi…

The paper proposes EEG-FuseFormer, a transformer-based framework that fuses features from CNN-LSTM and ResNet-18 to achieve high accuracy in predicting seizure onset from EEG signals.

The paper introduces Chimera, a highly efficient and scalable MCU designed for ultra-low-power edge AI inference, achieving 3.1 TOPS/W by integrating a dedicated transformer accelerator and a QoS-guar…

This study evaluates various data preprocessing pipelines to improve the transferability and generalization of Machine Learning models for detecting malware in Portable Executable (PE) files across di…

This paper demonstrates that transformer-based policies can provably learn complex tree search mechanisms, such as depth-first search, purely through reinforcement learning in a stochastic environment…