MLINFO COLLECTION
画像・動画生成、条件付き生成、編集、3D生成に関係する拡散モデルの論文と実装です。
Masked diffusion models (MDMs) accelerate generation by unmasking multiple tokens in parallel, but sampling these tokens independently ignores their correlations and biases the output. Anari et al.
Computing equilibria in high-dimensional continuous games requires learning and representing rich, multi-modal strategy distributions, something conventional neural policies struggle to achieve.…
We propose a new framework for banner ad auctions, leveraging diffusion models to allow for multiple bidders to co-win a single banner ad opportunity, and in particular influence the ad shown on the…
Generating an image with a diffusion or flow-matching model typically involves integrating a velocity field for hundreds of sequential steps. That computation suits a GPU poorly and an analog…
Regularization-based continual learning protects each parameter in proportion to an estimate of its importance, yet these estimates come from finite samples and heuristics and are used as if they…
Most artificial neural systems are built to map given inputs to outputs. Adaptive agents face a prior problem: they must act without enough evidence, seek encounters with the world, and revise…