Generating realistic and user-preferred advertisements is a key challenge in e-commerce. Existing approaches utilize multiple independent models driven by click-through-rate (CTR) to controllably create attractive image or text advertisements. Howeve... read more
In visual localization, Absolute Pose Regression (APR) enables real-time 6-DoF camera pose inference from single images, yet critically depends on fine-tuning data quality and coverage. While recent methods leverage 3D Gaussian Splatting (3DGS) for n... read more
Large language models (LLMs) are increasingly used to simulate human behavior, but their ability to simulate $individual$ privacy decisions is not well understood. In this paper, we address the problem of evaluating whether a core set of user persona... read more
In language reasoning, longer chains of thought consistently yield better performance, which naturally suggests that visual latent reasoning may likewise benefit from longer latent sequences. However, we discover a counterintuitive phenomenon: the pe... read more
Artificial intelligence systems typically rely on large, centrally collected datasets, a premise that does not hold in many real-world domains such as healthcare and public institutions. In these settings, data sharing is often constrained by storage... read more
Solving optimal transport (OT) on random minibatches is a common surrogate for exact OT in large-scale learning. In flow matching (FM), this surrogate is used to obtain OT-like couplings that can straighten probability paths and reduce numerical inte... read more
Drifting Models have emerged as a new paradigm for one-step generative modeling, achieving strong image quality without iterative inference. The premise is to replace the iterative denoising process in diffusion models with a single evaluation of a g... read more
Emergent misalignment (EM), where fine-tuning on a narrow task (like insecure code) causes broad misalignment across unrelated domains, was first demonstrated by Betley et al. (2025). We conduct the most comprehensive EM study to date, reproducing th... read more
Fine-tuning pre-trained robot policies with reinforcement learning (RL) often inherits the bottlenecks introduced by pre-training with behavioral cloning (BC), which produces narrow action distributions that lack the coverage necessary for downstream... read more
Vision-Language Models (VLMs) increasingly operate on ultra-high-resolution (UHR) Earth observation imagery, yet they remain vulnerable to a severe scale mismatch between large-scale scene context and micro-scale targets. We refer to this empirical g... read more
Join thousands of healthcare professionals staying informed about the latest AI breakthroughs in medicine. Get curated insights delivered to your inbox.