Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2607. 26947v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) rely on a projector to align visual representations with the language embedding space, making it central to cross-modal understanding.
arXiv:2601. 11178v3 Announce Type: replace Abstract: Social media platforms are increasingly dominated by long-form multimodal content, where harmful narratives are constructed through a complex interplay of audio, visual, and textual cues.
arXiv:2607. 27066v1 Announce Type: cross Abstract: Scientific figure assessment in peer review differs fundamentally from general image quality evaluation: a figure must be visually legible, faithfully support the manuscript's claims, and communicate evidence with a clear visual hierarchy.
arXiv:2512. 00807v2 Announce Type: replace Abstract: Vision-Language Models (VLMs) inherit significant social biases from their training data, notably in gender representation.
arXiv:2607. 26120v1 Announce Type: new Abstract: Large Language Models (LLMs)-powered multi-agent systems are increasingly deployed in mixed-motive environments, where agents operate under asymmetric information and strategic deception due to conflicting or hidden objectives.
arXiv:2602. 23971v4 Announce Type: replace-cross Abstract: Sycophancy, the tendency of large language models to favour user-affirming responses over critical engagement, has been identified as an alignment failure, particularly in high-stakes advisory and social contexts.
arXiv:2607. 26946v1 Announce Type: new Abstract: Recent advancements in Computer Go, driven by AlphaZero and MuZero, rely heavily on Monte Carlo Tree Search (MCTS) to correct the errors of the neural network policy.
arXiv:2607. 26641v1 Announce Type: cross Abstract: Identity document (ID) authentication relies on the structural integrity of complex, high-frequency security patterns.
arXiv:2601. 10600v2 Announce Type: replace-cross Abstract: In the context of multi-agent multi-armed bandits (MA-MAB), fairness is often reduced to outcomes: maximizing welfare, reducing inequality, or balancing utilities.
arXiv:2607. 26735v1 Announce Type: cross Abstract: Prompt inversion, as a typical reverse engineering technique, enables text-to-image (T2I) diffusion models to generate the desired target images without extensive prompt engineering.
arXiv:2506. 23033v5 Announce Type: replace Abstract: Fairness audits are a key component of responsible machine-learning deployment.
arXiv:2607. 27568v1 Announce Type: new Abstract: Recognition accuracy obtained during a recording session does not persist when a user puts on the electrodes again after the electrodes had previously been removed.
arXiv:2607. 28415v1 Announce Type: new Abstract: Latent world models enable efficient planning by predicting future states in a compact representation space, but their performance depends critically on the quality of the learned latent distribution.
arXiv:2607. 26071v1 Announce Type: cross Abstract: In this work, we propose GuidedRAG, a novel extension to traditional Retrieval-Augmented Generation (RAG) that introduces a dedicated selection stage and semantic steering during retrieval.
arXiv:2605. 25567v3 Announce Type: replace-cross Abstract: We study denoising score matching (DSM) when data are drawn from an embedded manifold $M \subset \mathbb{R}^D$.
arXiv:2607. 18785v2 Announce Type: replace Abstract: As large language model agents gain access to increasingly large skill libraries, retrieving the right skill becomes critical to reliable capability selection and execution.
arXiv:2607. 26381v1 Announce Type: cross Abstract: Wi-Fi-based human activity recognition has advanced substantially, but most existing methods assume a closed set of activities and require labeled Wi-Fi samples for every target class, limiting their ability to recognize unseen activities.
arXiv:2512. 03661v2 Announce Type: replace Abstract: Activation steering has emerged as a powerful method for guiding the behavior of generative models towards desired outcomes such as toxicity mitigation.
arXiv:2607. 28408v1 Announce Type: new Abstract: This thesis studies policy learning in interactive systems where an agent observes a context, selects an action from a very large set, and receives partial feedback.
arXiv:2607. 27968v1 Announce Type: new Abstract: Machine unlearning seeks to selectively remove specific knowledge from trained language models without full retraining, a growing necessity under privacy regulations such as GDPR and the EU AI Act.