Perturbation-based XAI methods for audio classifiers often estimate feature importance by masking spectrogram regions and crediting output changes to the retained signal. Yet they typically assume the fill (the mask replacement) is negligible. We propose logit-space trajectory decomposition to examine this assumption....
Nico Garc\'ia-Peguinho (School of Electronic Engineering and Computer Science, Queen Mary University of London), David Kelly (Department of Informatics et al.· 0 citations
Weighted split conformal prediction reweights calibration scores by the likelihood ratio between the test and training covariate distributions and guarantees marginal coverage under covariate shift. We study its coverage conditional on the calibration data. An elementary argument, based on a single concentration inequa...
Historical manuscript illustrations preserve rich visual evidence of past cultures. They depict people, animals, plants, diagrams, music notations, and decorative forms. Although large digitization projects have made many manuscripts available online, the material itself remains difficult to explore at scale. Extractio...
Yoav Evron, Michal Bar-Asher Siegal, Michael Fire· 0 citations
Recovering probability measures from their moments has numerous applications, esp. in connection with the method of moments in statistics and optimization. In the setting where measure need not be finitely atomic, but its support is known to be compact and semialgebraic with codimension at least one, the problem is sti...
Ruben Karapetyan, Shenyuan Ma, Ales Wodecki et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
This work introduces ANCHOR, a GRPO composition policy trained with multi-objective rewards around a frozen CSP model, and continuous adaptive novelty (CAN), a graded novelty score against known structures and a growing discovery history.
Emma Lei Hovmand, J. Elsborg, Melih Kandemir et al.· 0 citations
It is shown that, whenever the ball radius does not exceed the Polyak radius, the Local LMO step is the Euclidean projection of the current iterate onto the intersection of the feasible set with a half-space that separates the iterate from the solution set; this projection is nonetheless computable by a linear oracle a...
A special semimartingale admits a unique decomposition $X=X_0+M+A$ into a local martingale $M$ and a predictable finite-variation part $A$. We consider the identification of $A$ when $X$ is observed only through repeated cross-sections. The estimand is then the projection of the sampled predictable compensator onto the...
Jakub Mareček, E. Biffis, Abigail Langbridge et al.· 0 citations
Generating differentially private synthetic data with meaningful Wasserstein utility guarantees is challenging in high dimensions. For datasets of size \(n\) on $[0,1]^d$ with $d\ge2$, existing pure \(\varepsilon\)-differentially private mechanisms achieve expected $1$-Wasserstein error of order $(\varepsilon n)^{-1/d}...
Raoof Zare Moayedi, Amir R. Asadi, M. Yassaee et al.· 0 citations
Moving ML-mediated decision making onto privacy-preserving clients decentralises the economic decision along with the inference. Shared budget constraints then depend on information that cannot be globally current, creating an information-structure failure that conventional pacing is not designed to solve. We study thi...
It is found that multiple responses provide a qualitatively stronger benefit in this setting of generative systems, and is shown that a greedy multiplicative-weights learner achieving the upper bounds without any assumption on demonstrator quality is possible.
Accurate modelling of aerodynamic loads is essential for predicting instabilities and ensuring the safety of long-span bridges. A methodology is introduced for modelling aerodynamic self-excited forces in bridge-deck cross-sections using extreme learning machines (ELMs). ELMs, as single-layer feedforward neural network...
G. Tondo, S. Chawdhury, Sergio Andrés Castaño Giraldo et al.· Proceedings of the Instituti...· 0 citations
Finite-sample bounds are derived that separate the effects of critic estimation, neural drift regression, finite-sample SNIS, diffusion discretization, and inherited actor error on expected average policy suboptimality.
Yu-Ling Jiao, Li-Can Kang, Jerry Zhijian Yang et al.· 0 citations
Learn how Google DeepMind and GovTech Singapore uses lightweight on-device Gemma models to intercept conversational scams in private chats with zero cloud data egress.
MIT News · Artificial Intelligence· news.mit.eduOct 13, 2026
Machine-learning networks can learn without detailed instructions from a designer. Those that do may offer insight into how the brain reorganizes itself during learning.
Microsoft Research Blog· microsoft.comOct 12, 2026
StudentSim is a research system for evaluating and improving AI tutoring tools before they are tested with learners. It models how individuals may engage with tutors, giving feedback to improve tutor performance across subjects like chess, writing, and mathematics. The post Simulating student learning for better AI tutoring appeared first on Microsoft Research.
Exploring how generative AI could make machine vision more accessible to businesses. The post GenEye in a Box: Making Machine Vision Something You Can Just Ask For appeared first on GPT-Lab.
MIT News · Artificial Intelligence· news.mit.eduOct 7, 2026
Students in MIT’s Concourse program delve deeply into the human condition, debate challenging questions, and learn to develop judgment about issues that can’t be quantified.
Training AI agents with reinforcement learning can be challenging because their tools, context, and decision-making are managed by complex frameworks. Agent Lightning connects existing agents to RL training, making it easier to improve them without rebuilding them. The post Agent Lightning v1.0: A 3,500-Line Lightweight Agentic RL Framework for Training Agents with Real Harnesses appeared first on Microsoft Research.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
