Researchers have unveiled a large-scale dataset designed to accelerate the development of AI algorithms that optimize the complex process of creating masks used in integrated circuit fabrication.
New research demonstrates a novel framework for training language models to be more robust and aligned with human values through adversarial game dynamics.
![Parallel token prediction streamlines sequence generation by enabling a single model call to predict multiple tokens simultaneously, achieved through either integrating sampling directly into the model-using auxiliary variables-or by modeling and predicting the distribution of each token in parallel with those same variables, a departure from traditional autoregressive models that predict tokens one at a time [latex] t_{i} [/latex].](https://arxiv.org/html/2512.21323v1/x2.png)
Researchers have developed a novel framework that dramatically reduces the time it takes for large language models to generate text.
A new approach quantifies uncertainty during the image generation process in diffusion models, leading to higher quality and more reliable results.
Researchers have released a comprehensive dataset of function call graphs, exposing limitations in current malware classification techniques and highlighting the evolving sophistication of Android threats.
Researchers have developed a new method for training deep neural networks that eliminates the need for gradient computation, offering a potentially faster and more efficient alternative to traditional backpropagation.
![A grid-based autoregressive sampling algorithm efficiently generates arbitrary-length, high-quality image sequences by iteratively refining a coarse grid: initial sampling via a Stage 1 diffusion model is followed by iterative refinement using noised control signals to produce spatiotemporally consistent grid elements, then interpolation generates eight new frames between each pair, and finally, a Stage 2 super-resolution step enhances both spatial and temporal fidelity, achieving a sequence length of [latex]L = \frac{12N - 4}{N}[/latex] and surpassing state-of-the-art performance.](https://arxiv.org/html/2512.21276v1/images/snowflake.png)
Researchers have developed a novel diffusion model that efficiently creates extended, high-quality image sequences by separating coarse structure from fine detail.
Researchers have released a large-scale dataset designed to accelerate the development of high-resolution, large-depth-range 3D displays powered by machine learning.
Researchers have developed a novel deep Bayesian reinforcement learning method that streamlines task adaptation and improves performance in complex environments.
A new method combines the power of deep learning with Bayesian principles to tackle complex reinforcement learning tasks with improved efficiency and accuracy.