eLife

Human EEG and artificial neural networks reveal disentangled representations and processing timelines of object real-world size and depth in natural images

Neural and computational evidence reveals that real-world size is a temporally late, semantically grounded, and hierarchically stable dimension of object representation in both human brains and ...
IGN

NVIDIA GeForce RTX 50 Series (Blackwell) - Official Tech Demo | CES 2025

NVIDIA GeForce RTX 50 Series (Blackwell) - Official Tech Demo | CES 2025 Check out how RTX Blackwell uses AI-driven 'neural memory' to enhance everything from graphical fidelity to realistic facial ...
IEEE

Deep Networks as Denoising Algorithms: Sample-Efficient Learning of Diffusion Models in High-Dimensional Graphical Models

Abstract: We investigate the efficiency of deep neural networks for approximating scoring functions in diffusion-based generative modeling. While existing approximation theories leverage the ...
Microsoft

TerpreT: A Probabilistic Programming Language for Program Induction

We study machine learning formulations of inductive program synthesis; given input-output examples, we try to synthesize source code that maps inputs to corresponding outputs. Our aims are to develop ...
IEEE

Segmented Sequence Prediction Using Variable-Order Markov Model Ensemble

Abstract: In recent years, sequence prediction, particularly in natural language processing tasks, has made significant progress due to advanced neural network architectures like Transformer and ...