Related papers: AI Alignment Breaks at the Edge

Incident monitoring can drive safety improvements in high-reliability industries and population-scale technologies, but remains underdeveloped in AI governance. Public databases catalog thousands of AI incidents, but simple incident counts…

Recent published evidence from frontier laboratories shows that contemporary AI models can recognise evaluation contexts, latently represent them, and behave differently under those contexts than under deployment-continuous conditions.…

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…

As AI systems advance, AI evaluations are becoming an important pillar of regulations for ensuring safety. We argue that such regulation should require developers to explicitly identify and justify key underlying assumptions about…

AI is undergoing a paradigm shift with the rise of models (e.g., BERT, DALL-E, GPT-3) that are trained on broad data at scale and are adaptable to a wide range of downstream tasks. We call these models foundation models to underscore their…

Evaluating agentic AI on open-ended professional tasks faces a fundamental dilemma between rigor and flexibility. Static rubrics provide rigorous, reproducible assessment but fail to accommodate diverse valid response strategies, while…

As the development of Large Models (LMs) progresses rapidly, their safety is also a priority. In current Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) safety workflow, evaluation, diagnosis, and alignment are…

Can competition among misaligned AI providers yield aligned outcomes for a diverse population of users, and what role does model personalization play? We study a setting where multiple competing AI providers interact with multiple users who…

Agentic AI systems plan, use tools, maintain state, and act across multi-step workflows with external effects, meaning trustworthy deployment can no longer be judged by task completion alone. The current literature remains fragmented across…

Human-in-the-loop validation is essential in safety-critical clinical AI, yet the transition between initial model inference and expert correction is rarely analyzed as a structured signal. We introduce a diagnostic alignment framework in…

Recent Artificial Intelligence (AI) models have matched or exceeded human experts in several benchmarks of biomedical task performance, but surgical benchmarks in particular are often missing from prominent medical benchmark suites. Since…

With the availability of large databases and recent improvements in deep learning methodology, the performance of AI systems is reaching or even exceeding the human level on an increasing number of complex tasks. Impressive examples of this…

Edge-AI, the convergence of edge computing and artificial intelligence (AI), has become a promising paradigm that enables the deployment of advanced AI models at the network edge, close to users. In Edge-AI, federated continual learning…

Federated learning (FL) has emerged as a transformative paradigm for edge intelligence, enabling collaborative model training while preserving data privacy across distributed personal devices. However, the inherent volatility of edge…

Despite advances in multimodal AI, current vision-based assistants often remain inefficient in collaborative tasks. We identify two key gulfs: a communication gulf, where users must translate rich parallel intentions into verbal commands…

Recent research suggests that systematic generalization in natural language understanding remains a challenge for state-of-the-art neural models such as Transformers and Graph Neural Networks. To tackle this challenge, we propose Edge…

Many researchers have reached the conclusion that AI models should be trained to be aware of the possibility of variation and disagreement in human judgments, and evaluated as per their ability to recognize such variation. The LEWIDI series…

Artificially intelligent agents are increasingly being integrated into human decision-making: from large language model (LLM) assistants to autonomous vehicles. These systems often optimize their individual objective, leading to conflicts,…

Feedback alignment algorithms are an alternative to backpropagation to train neural networks, whereby some of the partial derivatives that are required to compute the gradient are replaced by random terms. This essentially transforms the…

The integration of Large Language Models into Intelligent Tutoring Systems pre-sents significant challenges in aligning with diverse and often conflicting values from students, parents, teachers, and institutions. Existing architectures…