Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2610.09505v2 Announce Type: replace Abstract: We develop a bias-aware digital-twin calibration and control framework for multiscale bioprocess models within a biological systems-of-systems (Bio...
arXiv:2610.35826v1 Announce Type: new Abstract: Selection bias in large language models (LLMs) can persist despite instructions to ignore presentation order or prompts that elicit reasoning. Recent e...
As large language model agents increasingly compile natural-language requirements into repository-level code, requirement-to-test generation grows in importance to provide validation constraints (or h...
Construction safety management still struggles to produce daily safety bulletins (DSBs), structured daily communications that identify site-specific hazards, convey safety protocols, and set preventiv...
We present Scalable Pixel-anchored End-to-end Diffusion (SpeeDiff), a latent diffusion method that jointly trains the VAE and the diffusion model from scratch. In principle, joint training allows the...
Effective differential diagnosis depends on well structured and unambiguous patient case descriptions, since incomplete or ambiguous clinical information readily leads to diagnostic errors and inconsi...
Large Language Models (LLMs) rely on proprietary system prompts to enforce task directives, safety policies, and access controls. These prompts are vulnerable to query-based leakage attacks, where bla...
The information bottleneck (IB) trades compression of an input $X$ against prediction of a target $Y$ through a multiplier $β=1/λ$, yet each operating point is usually served by training, or fully con...
Large language models (LLMs) show promise in specialty medicine, yet existing evaluations largely focus on isolated clinical encounters rather than tracking how clinical responsibilities evolve across...
Multimodal medical AI requires a common visual interface for encoding heterogeneous imaging evidence for patient condition modeling. However, existing medical visual tokenizers are often tied to a spe...
Human oversight is a pillar of AI safety. It is often exercised by a human in the loop (HITL) who approves critical actions taken by an AI agent. AI agents' increasing ability to bypass guardrails, th...
Existing jailbreak attackers fall into two classes: static planners fix their single- or multi-turn adversarial plans in advance, remaining simple but losing sight of the victim's replies, wasting tur...
Imagery captured by unmanned aerial vehicle (UAV) systems increasingly raises privacy concerns, as UAV aerial surveillance routinely captures sensitive objects such as pedestrians and vehicles alongsi...
Coordinating many miniature robots in a confined arena, with no leader, central planner, or global map, is a core challenge for swarm robotics. As the swarm grows denser, collision avoidance becomes t...
Structure-from-motion (SfM) from the dual-fisheye video of a consumer 360-degree camera recovers geometry only up to a similarity transform; in the pipeline considered here, metric scale is obtained f...
Structured sparse learning is a leading paradigm for high-dimensional data modeling, as it enables rigorous integration of domain-validated structural priors into the learning process. Among these pri...
Import AI episode 478 discusses mathematical techniques for AI alignment, introduces the ProgramBench benchmark, and examines how the Mirendil system interprets RSI. It also poses the question of how a machine perceives the concept of "night."
We develop a derivative-free temporal-difference (TD) framework for calibrating black-box simulators using one-step transitions from a target system and noisy simulator-generated continuation values....
Optical coherence tomography (OCT) is a non-invasive imaging modality used for visualization of retinal tissue. However, OCT volumes are affected by speckle noise, which degrades image contrast and ob...
The number of paper submissions to major AI conferences has increased dramatically in recent years, substantially increasing the peer-review workload of researchers. At the same time, large language m...
