Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2606. 09038v1 Announce Type: new Abstract: Large Language Models (LLMs) have enabled increasingly personalized interactions by adapting to users' preferences, contexts, and long-term histories.
arXiv:2512. 20978v2 Announce Type: replace-cross Abstract: Language Model (LM)-based generative modeling has emerged as a promising direction for TSE, offering potential for improved generalization and high-fidelity speech.
arXiv:2606. 07585v1 Announce Type: cross Abstract: This thesis addresses group emotion recognition (GER) in-the-wild with a focus on privacy preservation.
arXiv:2605. 26078v3 Announce Type: replace Abstract: Wasserstein policy gradient (WPG) is a policy optimization method for reinforcement learning (RL) that exploits the optimal-transport geometry of action distributions.
arXiv:2606. 07620v1 Announce Type: cross Abstract: With the growth of Vision Transformers in safety-critical domains like autonomous systems and medical imaging, ensuring their reliability against soft errors is paramount.
arXiv:2606. 08173v1 Announce Type: cross Abstract: In sixth-generation (6G) networks, billions of cyber-physical systems (CPSs) - autonomous vehicles, smart grids, industrial robots, and remote-surgical equipment - will run over ultra-reliable low-latency slices, collapsing the gap between a remote breach and physical harm to milliseconds, a budget perimeter firewalls and centralised security operations centres cannot meet.
arXiv:2606. 08953v1 Announce Type: new Abstract: Modern generative models often define an entire probability path from a simple prior to the data law, rather than only an endpoint map.
arXiv:2606. 08259v1 Announce Type: new Abstract: This paper investigates the problem of generating synthetic tabular data with differential privacy (DP) guarantees, enabling data sharing in sensitive domains.
arXiv:2605. 29823v2 Announce Type: replace Abstract: Deep networks often exhibit a preference for "simple" solutions, and such a simplicity bias is widely believed to play a key role in generalization.
arXiv:2606. 07770v1 Announce Type: new Abstract: Self-supervised methods that learn representations and predict dynamics fully in the latent space, such as JEPA, have been shown to confuse slowly varying noise with the dynamical signals they aim to capture.
arXiv:2606. 08372v1 Announce Type: cross Abstract: Synthetic data is increasingly promoted as a privacy-preserving substitute for releasing sensitive tabular records, yet its central adversarial threat ("reconstruction", the recovery of an individual's hidden attribute values from a synthetic release and a handful of known quasi-identifiers) has been studied only in scattered, hard-to-compare settings.
arXiv:2601. 11541v2 Announce Type: replace-cross Abstract: To address the scalability of feedback in computer science while mitigating the privacy and cost limitations of commercial Large Language Models (LLMs), this study evaluates a locally hosted Small Language Model (SLM).
arXiv:2606. 08892v1 Announce Type: new Abstract: AI models deployed in critical domains, such as AI safety research, may subtly sabotage our efforts due to misalignment.
arXiv:2606. 09122v1 Announce Type: cross Abstract: Cloud network infrastructure at hyperscale presents unique operational challenges where traditional human-driven incident response cannot keep pace with the volume, velocity, and complexity of failures.
arXiv:2606. 07561v1 Announce Type: new Abstract: Gaussian processes with stationary kernels on bounded domains exhibit inflated posterior variance near the boundary.
arXiv:2605. 09823v3 Announce Type: replace-cross Abstract: Personal AI assistants are beginning to act as delegates with access to calendars, inboxes, and user preferences.
arXiv:2602. 21172v3 Announce Type: replace Abstract: Vision-Language-Action (VLA) models are advancing autonomous driving by replacing modular pipelines with unified end-to-end architectures.
arXiv:2601. 21996v2 Announce Type: replace-cross Abstract: While Mechanistic Interpretability has identified interpretable circuits in LLMs, their causal origins in training data remain elusive.
arXiv:2604. 10842v3 Announce Type: replace-cross Abstract: LLM-powered coding agents increasingly rely on tool-use protocols such as the Model Context Protocol (MCP) to read and write files on a developer's workstation.
arXiv:2507. 19700v2 Announce Type: replace Abstract: We propose a new framework for generating tabular synthetic datasets via disjoint generative models.