Category
2,518 papers
Closed-form recourse moves a rejected user along the unit gradient $\hat g$ of the classifier score $f$ by the promised distance $d_p=|f(x)|/\|\nabla f(x)\|$, at which the linearized score reaches zero. We ask when this one-shot step succeeds and what additional model queries change. To leading order the step ends on t...
Does representation learning stop when the training loss stops improving? We study this question for matrix Muon, whose polar-normalised updates have a step length set by the gradient's rank rather than its norm. Near the edge of stability, full-batch Muon on teacher-student problems enters approximately period-2 loss...
Pooled statistics of Transformer weights obscure how magnitude is distributed across functional channels, while individual weights are too numerous to compare directly. We study the mesoscopic level between them: row and column scale fields, the median-centred log-RMS profiles of a weight matrix over its channels, whic...
GapFT is introduced, which selects training evidence by the source checkpoint's single-sample outcome and fine-tunes on the Pass@K-Pass@1 gap: problems the policy fails on one sample but solves within K samples, and its analysis relates available gains to transferable failure support.
Reach audiences
Advertise in front of researchers, engineers, and readers.
Ring gossip is a practical serverless alternative when data heterogeneity is moderate, and faster-mixing topologies become important as heterogeneity grows, as well as a centralized reference for a stacked LSTM that detects imminent failure on the NASA C-MAPSS turbofan benchmark.
Analytical methods play a vital role in pharmaceutical development, quality control, stability testing, and regulatory decision-making, as the reliability of drug product identity, strength, purity, safety, and stability depends on the quality of analytical data generated. Conventional analytical method development has...
Background: Childhood overweight and obesity are important public-health concerns, and dietary behaviors such as frequent fast-food consumption may contribute to excess body weight. This study aimed to assess the association between fast-food consumption and overweight/obesity among school-aged children in Mosul. Objec...
Background: Fever is one of the most common reasons for pediatric healthcare visits. Although fever is usually a physiological response to infection, parental misconceptions may lead to inappropriate antipyretic use, unnecessary physical cooling, and inappropriate healthcare-seeking. Assessing parental knowledge and pr...
Analytical methods play a vital role in pharmaceutical development, quality control, stability testing, and regulatory decision-making, as the reliability of drug product identity, strength, purity, safety, and stability depends on the quality of analytical data generated. Conventional analytical method development has...
The rapid digital transformation of the pharmaceutical sector has created a growing demand for professionals who can combine pharmaceutical knowledge with computational and data-analytic skills. Python programming has emerged as a valuable educational and professional tool because of its simple syntax, open-source natu...
Background: Childhood overweight and obesity are important public-health concerns, and dietary behaviors such as frequent fast-food consumption may contribute to excess body weight. This study aimed to assess the association between fast-food consumption and overweight/obesity among school-aged children in Mosul. Objec...
Background: Headache is a common complaint among school-aged children and may interfere with daily activities, academic performance, and quality of life. Its occurrence may be influenced by demographic characteristics, familial susceptibility, and potentially modifiable lifestyle factors. Objectives: To determine the p...
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.
