AI Networking Cookbook: Practical recipes for AI-assisted network automation and development
Category
2,652 papers
It is argued that accelerated samplers such as flow maps are essential infrastructure for efficient post-training, and that the dominant KL-regularized formulation is only one of many choices worth revisiting.
The Gravitational Reference Advanced Technology Test In Space (GRATTIS) mission will demonstrate the functionality and sensitivity performance of the Simplified Gravitational Reference Sensor (S-GRS), an ultra-precise inertial sensor for future Earth geodesy missions. These sensors are used to measure or compensate for...
Purpose: The current state of wearable biosensors for remote monitoring and early cardiovascular disease (CVD) detection is examined in this systematic literature review, which also highlights the technological advancements, clinical applicability, and implementation difficulties of these devices.Methodology: A thoroug...
This work proposes count-FM, a flow-matching framework for count data based on a continuous-time birth-death process with local unit jumps, which achieves better sample quality than representative baselines while using substantially fewer parameters in simulation.
Reach audiences
Advertise in front of researchers, engineers, and readers.
Beyond conditional average treatment effects, treatments may impact the entire outcome distribution in covariate-dependent ways, for example, by altering the variance or tail risks for specific subpopulations. We propose a novel estimand to capture such conditional distributional treatment effects, and develop a doubly...
Deep learning problems rarely involve objectives that are equal in importance. A primary objective defines the goal, whilst secondary objectives, such as sparsity, compression, or robustness constrain the solution. While existing multi-objective methods have proven effective in practice, they have a clear symmetry prob...
This work revisits the analysis of best-policy identification for finite-horizon risk-sensitive reinforcement learning under the entropic risk measure through a forward-model based algorithm building on KL-based exploration bonuses that adapt to the entropic criterion.
Generative models for time-series imputation achieve strong reconstruction accuracy, yet provide no finite-sample reliability guarantees, a critical limitation in power systems where imputed values inform dispatch and planning. We introduce SPLICE (Self-supervised Predictive Latent Inpainting with Conformal Envelopes),...
PRISM-FCP is a communication-efficient Byzantine-robust federated conformal prediction framework that uses partial model sharing to mitigate stochastic model-poisoning attacks during training and histogram-based filtering to mitigate adversarial calibration submissions.
We study decentralized partially observable team decision problems with low-rank latent dynamics and unknown system models. The proposed framework combines team-theoretic equivalence with low-rank model representations to address cooperative decision-making in partially observable Markov decision processes without prio...
Clustering is an unsupervised learning technique that partitions unlabeled data into groups. Most existing methods require user-specified parameters, such as the number of clusters or neighborhood size. Conversely, we propose automatic depth-based local center clustering (A-DLCC), a fully data-driven method that elimin...
It is shown how a limited budget for ground-truth data-annotation can be used via doubly-robust OPE with missing rewards, and the optimal annotation probabilities for sequential forward-monotone annotation protocols are characterized, and a feasible batch-adaptive implementation is provided.
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.
