Related papers: SpectralGuard: Detecting Memory Collapse Attacks i…

Recursive learning -- where models are trained on data generated by previous versions of themselves -- is increasingly common in large language models, autonomous agents, and self-supervised systems. However, standard performance metrics…

State space models (SSMs) like Mamba have gained significant traction as efficient alternatives to Transformers, achieving linear complexity while maintaining competitive performance. However, Hidden State Poisoning Attacks (HiSPAs), a…

Deep selective State-Space Models (SSMs), whose state-space parameters are modulated online by a selection signal, offer significant expressive power but pose challenges for stability analysis, especially under discontinuous gating. We…

Vision State Space Models (VSSMs), a novel architecture that combines the strengths of recurrent neural networks and latent variable models, have demonstrated remarkable performance in visual perception tasks by efficiently capturing…

Place recognition is the foundation for enabling autonomous systems to achieve independent decision-making and safe operations. It is also crucial in tasks such as loop closure detection and global localization within SLAM. Previous methods…

In recent years, there has been a growing interest in integrating linear state-space models (SSM) in deep neural network architectures of foundation models. This is exemplified by the recent success of Mamba, showing better performance than…

Radar-based Human Activity Recognition (HAR) is an attractive alternative to wearables and cameras because it preserves privacy, and is contactless and robust to occlusions. However, dominant Convolutional Neural Network (CNN)- and…

Balancing fine-grained local modeling with long-range dependency capture under computational constraints remains a central challenge in sequence modeling. While Transformers provide strong token mixing, they suffer from quadratic…

Selective State Space Models (SSMs), notably Mamba, employ diagonal state transitions that limit both memory retention and bilinear computational capacity. We propose a factorized bilinear input modulation that augments the SSM with a…

Attention-based methods have demonstrated exceptional performance in modelling long-range dependencies on spherical cortical surfaces, surpassing traditional Geometric Deep Learning (GDL) models. However, their extensive inference time and…

Predicting user preferences and sequential dependencies based on historical behavior is the core goal of sequential recommendation. Although attention-based models have shown effectiveness in this field, they often struggle with inference…

Modern adversarial campaigns unfold as sequences of behavioural phases - Reconnaissance, Lateral Movement, Intrusion, and Exfiltration - each often indistinguishable from legitimate traffic when viewed in isolation. Existing intrusion…

Long-term memory has emerged as a foundational component of autonomous Large Language Model (LLM) agents, enabling continuous adaptation, lifelong multimodal learning, and sophisticated reasoning. However, as memory systems transition from…

This paper provides the first systematic analysis of a synergistic threat model encompassing memory corruption vulnerabilities and microarchitectural side-channel vulnerabilities. We study speculative shield bypass attacks that leverage…

Memory spatial errors, i.e., buffer overflow vulnerabilities, have been a well-known issue in computer security for a long time and remain one of the root causes of exploitable vulnerabilities. Most of the existing mitigation tools adopt a…

Mamba's recurrent state h_t is, by construction, a compressed summary of every token seen so far. This raises a tempting hypothesis: if we extract token-level outputs y_t at fixed patch boundaries, we obtain semantic sentence summaries for…

Probabilistic State Space Models (SSMs) are essential for Reinforcement Learning (RL) from high-dimensional, partial information as they provide concise representations for control. Yet, they lack the computational efficiency of their…

State space models (SSMs) have emerged as an efficient alternative to transformer-based models, offering linear complexity that scales better than transformers. One of the latest advances in SSMs, Mamba, introduces a selective scan…

State-space models (SSMs) have recently attention as an efficient alternative to computationally expensive attention-based models for sequence modeling. They rely on linear recurrences to integrate information over time, enabling fast…

Attention layers are the core component of transformers, the current state-of-the-art neural network architecture. Alternatives to softmax-based attention are being explored due to its tendency to hinder effective information flow. Even at…