Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2610.07083v1 Announce Type: cross Abstract: Driver fatigue poses a significant challenge to railway safety, with traditional systems like the dead-man switch offering limited and basic alertnes...
arXiv:2610.07925v1 Announce Type: new Abstract: Partially Relevant Video Retrieval (PRVR) aims to retrieve untrimmed videos containing moments relevant to a given text query. Despite recent progress,...
arXiv:2610.08621v1 Announce Type: new Abstract: Recent game design agents have made substantial progress in generating playable games. However, program correctness does not ensure an enjoyable experi...
The paper introduces DEFER1, a deterministic-first enforcement system for large‑language‑model based multi‑agent systems that uses 28 checks to block most attacks and refers only a small fraction to human judges. In tests across four domains, DEFER1 reduces attack success from about 30% to roughly 3%, with 78% of attacks blocked deterministically and only a quarter reaching the judges. The study highlights that rules effectively handle clear policy violations while judges address ambiguous intent, but also reveals weaknesses such as a risk‑score gate that misclassifies many proposals.
arXiv:2610.08533v1 Announce Type: cross Abstract: Geometric alignment scores based on Gram determinants provide a compact way to model higher-order consistency among modalities, yet how such scores r...
Scribble-based interaction provides a lightweight and intuitive way for users to specify image editing intents in interactive editing tools. However, current image editing models based on VLMs or LLMs...
Facial movements convey subtle and important information that is critical for human social communication. Optical methods for face capture are difficult or impossible to use when the face is occluded...
Large language models are informing decisions with ever-higher stakes. As the consequences of their errors grow, a central question becomes harder to ignore: how much can we trust an individual answer...
Continuous cardiac monitoring outside clinical settings requires signals that are both informative and practical to collect during daily life. Electrocardiography (ECG) provides rich information about...
Multi-agent path planning (MAPP) in continuous environments often relies on roadmaps to balance safety and search efficiency. However, traditional roadmap generation methods, such as lattice grids or...
Scanner variation changes how pathology foundation models represent the same tissue. We introduce SlideRuler, which uses regions within a slide as internal controls to estimate and correct acquisition...
Enterprise generative AI applications require robust safety mechanisms that can accommodate diverse risk postures, evolving policies, and varying latency constraints. Current guardrail solutions often...
A common approach to measuring bias in Large Language Models is to compare the log-likelihoods of two contrastive stereotype sentences. We argue that such single-pair comparisons are often unreliable:...
We study path-flow alignment as a unified training objective for flow matching. Instead of fixing the interpolation path and learning only the velocity field, we jointly train an endpoint-preserving p...
The following motif is common in spatiotemporal settings: we have a sequence of covariate and label pairs observed for a relatively short, recent time period. We have access to unlabeled covariates ov...
Proactive power management systems reduce processor dynamic power through runtime power prediction and power-aware scheduling. Accurate, stable and low-overhead digital on-chip power meters (OPMs) are...
Slice-to-volume registration between ultrasound (US) and preoperative computed tomography (CT) imaging would enhance many minimally invasive interventions, for example by locating soft tissue structur...
Many social applications of machine learning exhibit performative effects: population behavior changes in response to deployed models. Performative prediction studies this interaction through a distri...
Multimodal vision-language systems typically fuse image and text embeddings through classical operators such as concatenation, attention, bilinear pooling, or tensor interactions. We propose Quantum E...
COMET reports translation quality as a single number, and that number is routinely compared across target languages written in different scripts. Such a comparison assumes Script Invariance: the score...