Category
2,619 papers
A faster implementation of mixtures of Manly transformations is proposed, which uses Newton's method for optimization in an EM gradient algorithm instead of Nelder-Mead in a traditional EM.
Recursive models show promise on reasoning and language tasks, yet their test-time scaling lacks a principled criterion for selecting trajectories or determining recurrent depth. We introduce \textbf{Energy-guided Recursive Model (ERM)}, which uses Hopfield-type memories of valid local and global structures to assign i...
The lift is proposed, which replaces the free latent weight by a learnable slack plus an unconstrained network---the body---that takes a permutation-invariant summary of the training batch as input and couples to the gradient formed on it.
Protein language models are trained primarily with masked language modeling (MLM), which predicts masked amino-acid identities, but joint-embedding predictive architectures (JEPA) instead predict latent representations, but have not been applied to proteins.
Reach audiences
Advertise in front of researchers, engineers, and readers.
Neural networks, particularly message-passing neural networks (MPNNs), are increasingly used as heuristics for hard combinatorial optimization problems. Yet many learning-based methods rely on supervision, reinforcement learning, or gradient estimators, causing high computational cost, unstable training, or limited gua...
We introduce a new multivariate statistical problem that we refer to as the Ensemble-conditioned Inverse Problem (EIP). The aim of EIP is to invert for an ensemble that is distributed according to the pushforward of a prior under a forward process. In high energy physics (HEP), this is related to a widely known problem...
Diffusion models are state-of-the-art tools for various generative tasks. Yet training these models involves estimating high-dimensional score functions, a task that in principle suffers from the curse of dimensionality. It is therefore important to understand how low-dimensional structure in the target distribution ca...
This work introduces a class of random polytopes which simultaneously generalizes several known constructions and indicates how these properties can be exploited for classification and clustering tasks in data analysis.
This work establishes and discusses local geometric mixing bounds through Dobrushin contraction, and applies this approach to Diffusion Path Monte Carlo, a recently proposed Markov chain Monte Carlo method aimed at leveraging advances in score-based modeling.
LLM leaderboard gains can reflect selection among privately evaluated model variants, yet neither the number of variants nor their dependence is public. We ask how many hidden variants a published margin can support while retaining statistical evidence of a provider's advantage over a fixed comparator. For a fixed cand...
Neural Processes (NPs) are model-based meta-learners that implicitly learn a stochastic process and adapt to a new task from a small context set. Most extensions of NPs focus on improving the neural network architecture. We instead develop an extension motivated by the shared hierarchical interpretation of meta-learnin...
Data assimilation estimates a dynamical state from partial and noisy observations. Classical ensemble filters are efficient but restrict analysis updates through finite sample covariance and affine Gaussian distribution. We introduce the Flow Ensemble Filter (FlowEF), which uses conditional flow matching to transport t...
MIT Statistics and Data Science Center Director Alexander (Sasha) Rakhlin shares important considerations for departments and institutions.
By rethinking how large cloud computing systems operate, Associate Professor Christina Delimitrou seeks to make data centers more energy efficient.
As director, Bourg has focused on digital access, open and equitable scholarly publishing, and expanded support for data-intensive research.
Jennifer Neville did not want to go into computer science—but that’s exactly where she landed. Neville discusses the starts and stops that led to her professional sweet spot and her work identifying “surprising failures” making it hard for AI to handle complexity. The post What AI gets wrong and what failure teaches us appeared first on Microsoft Research.
Mobile Systems
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
