
Explore STFT phase retrieval, focusing on robustness and generative priors. Learn about stable reconstruction techniques, application of generative models, and reducing required measurements in imaging and acoustics applications.

Explores deep learning in image reconstruction, focusing on model scaling, data requirements, and robustness. Discusses performance under distribution shifts and strategies for improvement.

Explores balancing compressed sensing and deep learning in computational imaging, showcasing Plenoxels for efficient photorealistic view synthesis without neural networks.

Explore the mathematical foundations of AI, its impact on problem-solving in mathematics, and the challenges in developing reliable AI systems. Gain insights into generalization, explainability, and AI applications in inverse problems and PDEs.

Explore forty years of frequent items algorithms, from classic approaches to modern techniques, including turnstile streaming, heavy hitters, and local differential privacy.

Explore deep equilibrium models, their theoretical foundations, and applications in machine learning, including guaranteed convergence and robustness in neural networks.

Explore persistent homology rank functions through PCA, featuring case studies and insights into topological data analysis techniques.

Explore gradient descent on infinitely wide neural networks, examining global convergence and optimization techniques for non-convex problems in machine learning.

Explore quadratic twists of elliptic curves, Selmer groups, and L-values. Delve into the congruent number problem and progress on the BSD conjecture. Gain insights into advanced number theory concepts.

Explore topological simplification of voxelized data, focusing on homological methods to enhance graphical data analysis in scientific fields like medicine and biology.

Explore dimensionality reduction with DIPOLE, a novel approach combining local metric and global topological preservation for improved data visualization and analysis.

Graph representation learning techniques for biomedical applications, focusing on SubGNN for disentangled subgraph embeddings and their use in predicting disease treatments and safe drug combinations.

Explore efficient algorithms for computing Gromov-Hausdorff distances between ultrametric spaces, including complexity analysis and dynamic programming approaches.

Explore ethical considerations and accountability in AI development with Prof. Pascale Fung, addressing crucial questions about responsibility in the field of artificial intelligence.

Explore advanced algorithms and specifications for Versatile Video Coding, the latest video compression standard, presented by experts in the field.

Explore a groundbreaking AI solution for COVID-19 implemented nationwide, presented by Mihaela van der Schaar at the 2020 IEEE International Conference on Multimedia and Expo.

Explore advanced computational imaging techniques with Jong Chul Ye from KAIST, covering innovative approaches in signal processing and image reconstruction.

Explore small intestine motility, including segmentation, peristalsis, and the ileocecal valve. Learn about crucial digestive processes and their impact on nutrient absorption and waste elimination.

Explore efficient and interpretable spatial analysis using multiresolution tensor learning, with applications in geology, sports, and climate science. Discover improved methods for handling complex spatial data.

Explores implicit and explicit regularization in deep neural networks, connecting learning algorithms to H-infinity control and explaining convergence behavior in over-parametrized models, offering insights into generalization abilities.

Explore tensor representations for neural networks, enhancing interpretability, expressive power, generalization, and robustness in deep learning models through spectral methods and innovative architecture design.