Related papers: Embedded Safety-Aligned Intelligence via Different…
We present EASE, a novel method for learning sentence embeddings via contrastive learning between sentences and their related entities. The advantage of using entity supervision is twofold: (1) entities have been shown to be a strong…
Self-supervised learning has revolutionized medical imaging by enabling efficient and generalizable feature extraction from large-scale unlabeled datasets. Recently, self-supervised foundation models have been extended to three-dimensional…
The AI alignment problem, which focusses on ensuring that artificial intelligence (AI), including AGI and ASI, systems act according to human values, presents profound challenges. With the progression from narrow AI to Artificial General…
Social Explainable AI (SAI) is a new direction in artificial intelligence that emphasises decentralisation, transparency, social context, and focus on the human users. SAI research is still at an early stage. Consequently, it concentrates…
As LLM-based systems increasingly operate as agents embedded within human social and technical systems, alignment can no longer be treated as a property of an isolated model, but must be understood in relation to the environments in which…
Mutual Information between agent Actions and environment States (MIAS) quantifies the influence of agent on its environment. Recently, it was found that the maximization of MIAS can be used as an intrinsic motivation for artificial agents.…
In this paper, we argue that the future of Artificial Intelligence research resides in two keywords: integration and embodiment. We support this claim by analyzing the recent advances of the field. Regarding integration, we note that the…
Reinforcement learning (RL) provides a powerful framework for decision-making, but its application in practice often requires a carefully designed reward function. Adversarial Imitation Learning (AIL) sheds light on automatic policy…
We present a hybrid framework for adaptive insider-threat detection that tightly integrates multi-agent simulation (MAS), layered Security Information and Event Management (SIEM) correlation, behavioral and communication forensics,…
The field of embodied AI (EAI) is rapidly advancing. Unlike virtual AI, EAI systems can exist in, learn from, reason about, and act in the physical world. With recent advances in AI models and hardware, EAI systems are becoming increasingly…
The incredible feats of athleticism demonstrated by humans are made possible in part by a vast repertoire of general-purpose motor skills, acquired through years of practice and experience. These skills not only enable humans to perform…
We introduce Advertisement Embedding Attacks (AEA), a new class of LLM security threats that stealthily inject promotional or malicious content into model outputs and AI agents. AEA operate through two low-cost vectors: (1) hijacking…
Latent representations learned by neural networks often exhibit semantic structure, where concept similarity is reflected by geometric proximity in embedding space. However, comparing such spaces across models remains difficult: changes in…
Autonomous AI agents deployed on platforms such as OpenClaw face prompt injection, memory poisoning, supply-chain attacks, and social engineering, yet existing defences address only the platform perimeter, leaving the agent's own threat…
Small language models (SLMs) are increasingly deployed on edge devices, making their safety alignment crucial yet challenging. Current shallow alignment methods that rely on direct refusal of malicious queries fail to provide robust…
We propose Embodied AI as the next fundamental step in the pursuit of Artificial General Intelligence, juxtaposing it against current AI advancements, particularly Large Language Models. We traverse the evolution of the embodiment concept…
Reinforcement learning (RL) agents with pre-specified reward functions cannot provide guaranteed safety across variety of circumstances that an uncertain system might encounter. To guarantee performance while assuring satisfaction of safety…
The vulnerability of deep neural networks to adversarial patches has motivated numerous defense strategies for boosting model robustness. However, the prevailing defenses depend on single observation or pre-established adversary information…
Machine learning has achieved great success in electroencephalogram (EEG) based brain-computer interfaces (BCIs). Most existing BCI studies focused on improving the decoding accuracy, with only a few considering the adversarial security.…
In this paper, we propose AUKAI, an Adaptive Unified Knowledge-Action Intelligence for embodied cognition that seamlessly integrates perception, memory, and decision-making via multi-scale error feedback. Interpreting AUKAI as an embedded…