Medical image classification is frequently complicated by transitional categories whose feature distributions overlap those of adjacent classes, producing ambiguous decision boundaries. Conformal prediction returns uncertainty-aware prediction sets, but these are not directly actionable in clinical screening, where a s...
Saibal Ghosh, Samarup Bhattacharya, Sanjoy Kumar Saha et al.· 0 citations
ReGeoDTA is developed, a representation-preserving framework that maintains affinity-relevant chemical heterogeneity in molecular representations and continuous geometric relationships in protein structures that identifies representation fidelity as an upstream design principle for accurate and generalizable drug--targ...
Yi-Xiao Li, Yi-Ning Qian, Ye-Fan Chen et al.· 0 citations
A CTD approach that decouples convergence and diversity into two stages, aiming to quickly drive the search toward a single point on the Pareto front and focuses on diversity, aiming to spread solutions across the front.
Representation-based Masked Diffusion Model (RMDM) is proposed, a framework that leverages the text representation to explicitly encode global semantics and help to parallel update tokens more precisely, and significantly improves generation quality, particularly in aggressive few-step sampling regimes.
Yang Hu, Ding Huang, Xue-Yu Zhou et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Borders reveal a noise--drift tradeoff: in noise-dominated regimes, first-moment averaging and adaptive preconditioning can yield favorable upper guarantees, whereas in drift-dominated regimes, stale first-moment information and preconditioning can enlarge Adam's tracking guarantee, potentially allowing vanilla SGD to...
Sharan Sahu, Abir Sarkar, Cameron J. Hogan et al.· arXiv.org· 0 citations
Class imbalance complicates probabilistic classification because standard training objectives emphasize majority-class performance. Synthetic oversampling can reduce imbalance, but discrepancies between the synthetic and target minority distributions may bias the fitted classifier, especially because synthetic samples...
Pengfei Lyu, Zhengchi Ma, Linjun Zhang et al.· 0 citations
Mixed-effects models are widely used to model data with complex grouping structures and high-cardinality categorical predictor variables. However, for high-dimensional crossed random effects, current standard computations relying on Cholesky decompositions can become prohibitively slow. In this work, we present Krylov...
This work achieves the first local convergence algorithm for self-selection by providing the first local convergence algorithm for self-selection, thus resolving one of the main open questions of Cherapanamjeri, Daskalakis, Ilyas, and Zampetakis.
Alkis Kalavasis, Anay Mehrotra, F. Zhou· arXiv.org· 1 citation
This article proposes a novel variational framework based on tangent transformation for a broad class of probability models characterized by strongly super-Gaussian likelihoods, thereby inducing conjugacy with Gaussian priors over model parameters in an otherwise intractable setup.
Somjit Roy, Pritam Dey, D. Pati et al.· 0 citations
This work demonstrates how statistical methodology can be used for quantifying uncertainty in metrics that have been aggregated across multiple tasks, and emphasizes bootstrapping, Bayesian hierarchical (i.e., multilevel) modeling, and the visualization of task weightings that consider standard errors.
Motivated by the concept of satisficing in decision-making, we consider the problem of satisficing regret minimization in bandit optimization. In this setting, the learner aims at selecting satisficing arms (arms with mean reward exceeding a certain threshold value) as frequently as possible. The performance is measure...
This paper proposes a general machine learning framework called the localization method, which is fundamentally built on two core concepts: localization kernels and local means -- key components that underpin the self-attention mechanism. To establish a rigorous theoretical foundation, the framework is formally defined...
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 8, 2026
