Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2607. 10248v1 Announce Type: cross Abstract: Language builds discourse contexts other than the actual: a painting, a belief, a memory, a hypothetical.
arXiv:2607. 11475v1 Announce Type: new Abstract: Safety alignment in large language models can be fragile under fine-tuning, as even benign task adaptation may increase harmful compliance.
arXiv:2607. 11151v1 Announce Type: cross Abstract: Safety evaluation of large language models (LLMs) relies largely on single-turn attack datasets and single-judge scoring, underestimating risk from adaptive multi-turn adversaries and reporting a single success rate that does not separate partially actionable outputs from those carrying complete operational detail.
arXiv:2604. 06205v2 Announce Type: replace-cross Abstract: The growth of online platforms and user content requires strong content moderation systems that can handle complex inputs from various media types.
arXiv:2607. 10365v1 Announce Type: cross Abstract: Vision Transformers (ViTs) are difficult to interpret because current methods of relevance propagation and attention flow do not fully consider some key architectural features, such as the uneven importance of attention heads and residual connections.
arXiv:2607. 10305v1 Announce Type: cross Abstract: Byzantine-robust aggregation rules such as multi-Krum assume a central coordinator, and decentralising them is obstructed by the rules themselves: they are globally coupled, non-associative, and discontinuous, so an ulpscale perturbation can flip the selected subset, moving the output by a non-vanishing amount.
arXiv:2607. 11063v1 Announce Type: new Abstract: Despite progress in Embodied AI, Vision-and-Language Navigation systems remain vulnerable to adversarial visual disturbances.
arXiv:2607. 10580v1 Announce Type: cross Abstract: AI models are increasingly trained on personal images scraped from social media and public platforms, often without consent, leading to serious privacy violations, such as unauthorized facial recognition and targeted advertising.
arXiv:2501. 13692v2 Announce Type: replace-cross Abstract: Diffusion models have recently unlocked new possibilities in editing images of real-world objects.
arXiv:2607. 09749v1 Announce Type: cross Abstract: Foundation models have recently emerged as a powerful paradigm for learning transferable representations from large scale biomedical data, yet existing approaches for physiological waveforms primarily optimize reconstruction or forecasting objectives that do not explicitly preserve clinically meaningful waveform morphology.
arXiv:2607. 10571v1 Announce Type: cross Abstract: We study stochastic multi-armed bandits on dynamic graphs, where arms correspond to the vertices of a network with time-varying edges.
arXiv:2607. 10871v1 Announce Type: new Abstract: Contemplative traditions have long guided ethical behavior and prosocial interaction, and recent work suggests that contemplative principles (e.
arXiv:2607. 10517v1 Announce Type: cross Abstract: Activation steering offers a lightweight alternative to fine-tuning for controlling large language models at inference time.
arXiv:2604. 07486v3 Announce Type: replace-cross Abstract: Large language models (LLMs) have emerged as a powerful tool for synthetic data generation.
arXiv:2607. 09889v1 Announce Type: cross Abstract: Fixed-state sequence models compress an unbounded past into a bounded state, which caps their associative recall at roughly the state dimension; attention escapes the cap by keeping a key-value entry for every token, at quadratic compute and a cache that grows with the sequence.
arXiv:2607. 10991v1 Announce Type: cross Abstract: As mobile robots become more integrated into everyday human environments, social robot navigation is becoming essential for ensuring human comfort, safety, and trust.
arXiv:2607. 09764v1 Announce Type: cross Abstract: The synthesis of safety-critical scenarios (SCS) and their evaluation through closed-loop simulations are crucial for developing robust autonomous driving systems.
arXiv:2607. 09804v1 Announce Type: cross Abstract: Open-weight medical language models are increasingly used as the base of patient-facing and clinician-support applications.
arXiv:2607. 10113v1 Announce Type: new Abstract: Large language model agents increasingly store reusable procedures outside the model.
arXiv:2607. 10630v1 Announce Type: cross Abstract: Robust motion planning in dense traffic requires autonomous vehicles to interact in rare and safety-critical scenarios that are underrepresented in naturalistic driving data.