Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2607. 18429v1 Announce Type: cross Abstract: Phishing emails remain one of the most persistent cybersecurity threats, and machine-learning classifiers are widely used to detect them.
arXiv:2607. 19190v1 Announce Type: cross Abstract: Real-to-sim conversion for robotic interaction with objects remains labor-intensive because it requires more than visual reconstruction: a streamlined real2sim process must recover scene geometries and object states, infer physical parameters, and assemble actors, objects, cameras, poses, and trajectories into a runnable physical simulation.
arXiv:2607. 18759v1 Announce Type: new Abstract: Transformers with relative positional encodings often extrapolate to sequences longer than those seen during training, whereas transformers with learned absolute encodings typically do not.
arXiv:2607. 18271v1 Announce Type: new Abstract: Time series forecasts are widely used in decision-critical domains, where they are rarely consumed without accompanying explanations.
arXiv:2607. 18239v1 Announce Type: new Abstract: Power-seeking defined as behaviors where AI systems acquire resources, evade oversight, or resist termination beyond task requirements is identified as a key driver of Loss of Control (LoC) risk.
arXiv:2607. 19332v1 Announce Type: new Abstract: Generative models have undergone many generations of evolution, from VAEs/GANs to diffusion/flow matching.
arXiv:2607. 18305v1 Announce Type: cross Abstract: Some limits on what language models know are not gaps in data coverage but structural properties of learning from text.
arXiv:2607. 18304v1 Announce Type: new Abstract: The sycophancy of large language models can increase the safety risk in intervention dialogue for autistic children.
arXiv:2607. 18678v1 Announce Type: cross Abstract: Breast MRI is highly sensitive for detecting breast tumors, but exams contain many slices and require substantial reading time.
arXiv:2607. 18639v1 Announce Type: new Abstract: Safety interventions on dual-use knowledge typically choose between destroying hazardous content (e.
arXiv:2607. 18267v1 Announce Type: cross Abstract: The transition to sixth-generation (6G) networks transforms wireless infrastructure into a cognitive substrate supporting Vehicle-to-Everything (V2X), Industrial IoT (IIoT), and Integrated Sensing and Communication (ISAC).
arXiv:2607. 18470v1 Announce Type: cross Abstract: Group Relative Policy Optimization (GRPO) has shown strong effectiveness in reinforcement learning from verifiable feedback, where sampled rollouts can be compared within a group using task-provided correctness signals.
arXiv:2607. 18366v1 Announce Type: new Abstract: Large language models (LLMs) serving as planners in tool-using autonomous agents introduce dynamic reliability risks in multi-turn execution.
arXiv:2607. 18268v1 Announce Type: new Abstract: Real-world applications that use closed-source large language models (LLMs) need advanced safety measures that go beyond the basic content filters.
arXiv:2606. 12442v2 Announce Type: replace-cross Abstract: At present, loss of control risks have gained much prominence in public discussion, particularly in relation to AI, with extensive discourse present among academics, frontier labs, and even governments.
Robots deployed in delivery, campus, and emergency-response settings often need to navigate from buildings to streets within a single continuous episode. Existing benchmarks usually evaluate indoor and outdoor navigation separately, and many abstract away robot execution, leaving exit finding, boundary traversal, adaptation, and kinodynamic failures underexplored.
Generative models have undergone many generations of evolution, from VAEs/GANs to diffusion/flow matching. Along the way, the underlying techniques have become more complicated and various beliefs about what drives strong empirical performance have taken hold.
Test-time scaling offers a promising method to improve the inference performance of Vision-Language Models (VLMs) without additional training. Existing approaches to vision-language navigation (VLN) for Unmanned Aerial Vehicle (UAV) typically relies on a single inference pass, which can falter in complex environments by producing suboptimal or unsafe trajectories.
Practitioners make three prompt-design decisions with almost no controlled evidence behind them: how to format instructions and context (markdown, plain text, prose, or tabular), how many simultaneous instructions a system prompt can carry before compliance degrades, and how much context a model can hold before recall and honesty degrade. We report two controlled experiments crossing all three factors on one held, contamination-free synthetic corpus (the "Book of Veyra," 8,780 uniquely-named entities, deterministically regenerable from a fixed seed), evaluated across five models.
Enterprise Document Intelligence [Vol. 1 #9bis] - Your RAG isn’t hallucinating, it’s answering the wrong context faithfully.