High-fidelity measurements of continuum physical fields are essential for scientific discovery and engineering design but remain challenging under sparse and constrained sensing. Conventional reconstruction methods typically rely on fixed sensor layouts, which cannot adapt to evolving physical states. We propose LASER, a unified, closed-loop framework that formulates active sensing as a Partially Observable Markov Decision Process (POMDP). At its core, LASER employs a continuum field latent world model that captures the underlying physical dynamics and provides intrinsic reward […]

Ver mais

arXiv:2601.20990v1 Announce Type: new Abstract: Positron Emission Tomography (PET) imaging is a vital tool in medical diagnostics, offering detailed insights into molecular processes within the human body. However, PET images often suffer from complicated noise, which can obscure critical diagnostic information. The quality of the PET image is impacted by various factors including scanner hardware, image reconstruction, tracer properties, dose/count level, and acquisition time. In this study, we propose a novel text-guided denoising method capable of enhancing PET […]

Ver mais

Mastering unsupervised learning opens up many avenues for a data scientist. There is so much scope in the vast expanse of unsupervised learning, yet many beginners in machine learning tend to shy away from it. I’m sure most newcomers will stick to basic clustering algorithms like K-Means clustering and hierarchical clustering. Clustering is an essential technique in machine learning and is used widely across domains and industries (think about Uber’s route optimization, Amazon’s recommendation system, Netflix’s customer segmentation, […]

Ver mais

arXiv:2601.03288v1 Announce Type: new Abstract: Jailbreak attacks present a significant challenge to the safety of Large Language Models (LLMs), yet current automated evaluation methods largely rely on coarse classifications that focus mainly on harmfulness, leading to substantial overestimation of attack success. To address this problem, we propose FJAR, a fine-grained jailbreak evaluation framework with anchored references. We first categorized jailbreak responses into five fine-grained categories: Rejective, Irrelevant, Unhelpful, Incorrect, and Successful, based on the degree to which the […]

Ver mais

arXiv:2602.13184v1 Announce Type: cross Abstract: Unbinned likelihood fits aim at maximizing the information one can extract from experimental data, yet their application in realistic statistical analyses is often hindered by the computational cost of profiling systematic uncertainties. Additionally, current machine learning-based inference methods are typically limited to estimating scalar parameters in a multidimensional space rather than full differential distributions. We propose a general framework for Simulation-Based Inference (SBI) that efficiently profiles nuisance parameters while measuring multivariate Distributions of […]

Ver mais

arXiv:2604.13217v1 Announce Type: new Abstract: Reliable evaluation of blastocyst quality is critical for the success of in vitro fertilization (IVF) treatments. Current embryo grading practices primarily rely on visual assessment of morphological features, which introduces subjectivity, inter-embryologist variability, and challenges in standardizing quality assurance. In this study, we propose a multitask embedding-based approach for the automated analysis and prediction of key blastocyst components, including the trophectoderm (TE), inner cell mass (ICM), and blastocyst expansion (EXP). The method leverages […]

Ver mais

The AI race these days isn’t really about who can build the smartest chatbot. It’s about who can build the one people actually want to use every day. Right now, Google is quietly working on a desktop-based AI agent inside Gemini, and it seems different from the chatbots people are used to. Instead of just providing answers, it’s built to handle real tasks like taking instructions, breaking them into steps, and working across Google apps to get things […]

Ver mais

arXiv:2602.11192v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) model architectures can significantly reduce the number of activated parameters per token, enabling computationally efficient training and inference. However, their large overall parameter counts and model sizes have precluded their widespread usage in resource-constrained settings as all of the parameters must still be loaded into GPU memory. Prior works aim to address this memory bottleneck by offloading certain experts into CPU memory and porting them to GPU memory only when they […]

Ver mais