For every mutation rate p in (0, 1), and for all varepsilon > 0, there is a fitness function f : {0,1}^n to mathbb{R} with a unique maximum for which the opt...
The remarkable performance of modern AI systems has been driven by unprecedented scales of data, computation, and energy -- far exceeding the resources required...
Transformer models contain substantial internal redundancy arising from coordinate-dependent representations and continuous symmetries, in model space and in he...
Clustering is widely used for unsupervised structure discovery, yet it offers limited insight into how reliable each individual assignment is. Diagnostics, such...
Streaming video understanding requires models to robustly encode, store, and retrieve information from a continuous video stream to support accurate video quest...
As embodied agents become central to VR, telepresence, and digital human applications, their motion must go beyond speech-aligned gestures: agents should turn t...
Large Language Models (LLMs) have made significant progress in reasoning tasks across various domains such as mathematics and coding. However, their performance...
Autonomous (noise-agnostic) generative models, such as Equilibrium Matching and blind diffusion, challenge the standard paradigm by learning a single, time-inva...
Integral Field Spectroscopy (IFS) surveys offer a unique new landscape in which to learn in both spatial and spectroscopic dimensions and could help uncover pre...
Comprehensively retrieving diverse documents is crucial to address queries that admit a wide range of valid answers. We introduce retrieve-verify-retrieve (RVR)...
Vision-Language Models (VLMs) have shown remarkable progress in Vision-Language Navigation (VLN), offering new possibilities for navigation decision-making that...
Extended reality (XR) demands generative models that respond to users' tracked real-world motion, yet current video world models accept only coarse control sign...
