An earlier conditional variational autoencoder framework is extended with a recurrent decoder that predicts multiscale wavelet coefficients and reconstructs waveforms through an inverse discrete wavelet transform and demonstrates superior performance across four holdout benchmark datasets and competitive performance on...
Adam Watts, Charles Young, Ryan Bowering et al.· 0 citations
RDMA can reduce communication overhead in distributed machine learning systems, but realizing these benefits in production requires more than replacing TCP. Variable-size messages, concurrent connections, bursty incasts, and service failures introduce challenges that hardware offload alone cannot address. This paper re...
Yibo Huang, Yi Cui, Yukai Huang et al.· 0 citations
Continuous random node features increase the expressivity of message-passing neural networks (MPNNs), but existing theoretical analyses are not fine-grained enough to capture their limitations, particularly in approximating functions across graph sizes or under a fixed number of random bits. We develop a population-lev...
Robert R. Nerem, Mitchell Black, Antonis Vasileiou et al.· 0 citations
Automatic differentiation (AD) is a cornerstone of modern machine learning. Since all AD frameworks implicitly fix a basis of Euclidean space to define gradients and Jacobians, they natively process mathematical objects that are arrays of a fixed set of coordinates. This makes it awkward to express objects such as rota...
Alex Guerra, Joshua Aduol, Yaqian Tang et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
This work mapped the institutional provenance of the Perovskite Database and established a rigorous hierarchy of grouped splits that progressively isolate duplicate devices, publications, and institutions, which empowers the community to separate memorisation from true physical discovery.
We propose NV-Tesseract-AD, a curriculum learning-enhanced conditional diffusion framework for multivariate time-series anomaly detection. Our central hypothesis is that reconstruction difficulty can be explicitly structured along two complementary axes, masking severity and diffusion noise level, and that training fro...
Aditi Gautam, Manikandan Ravikiran, Saira Qureshi et al.· 0 citations
Parameter-efficient continual learning updates a restricted subset of adapter parameters to incorporate sequential tasks while limiting catastrophic forgetting. Gradient attribution is a common rule for selecting that subset, but it requires an additional backward pass over calibration data. We identify a parameter-poo...
Yu Sun, Junwei Zhou, Zuodong Xiang et al.· 0 citations
We interpret Transformer networks as learned approximations to a hybrid probabilistic-inference procedure that combines max-product Loopy Belief Propagation (LBP) with Expectation--Maximization (EM). In this view, a Transformer performs inference in partially observed Markov Random Fields (MRFs) whose structure and par...
Gradient-based attribution provides input-specific information about model parameters, but computing it via backpropagation for many samples is expensive, while static importance scores discard input dependence. We derive KPSA (Kernelized Parameter Sensitivity Atlas) from a block decomposition of the empirical neural t...
Davide Wiest, Ahanaf Hasan Ariq, Abdul Monaf Chowdhury· 0 citations
Parameter-efficient fine-tuning has hundreds of methods, usually compared by parameter count and benchmark score. We compare them as maps. A pretrained checkpoint is a base point in weight space, and a weight-space method is a smooth map from a small parameter space that starts at that point. These maps form a slice ca...
Xiaoyu Li, Zhizhou Sha, Chi-Wun Yang et al.· 0 citations
Neural surrogates that forecast a physical field from sparse, noisy sensors read a window of nearby sensors and a history of past snapshots. Practitioners choose both by comparing fitted models with each other. Such comparisons cannot tell a model's shortfall from missing information. We measure the trade-off between w...
Federated Large Language Models (FedLLMs) are promising to deliver privacy-preserving, collaborative intelligence. The decentralized training process is vulnerable to Byzantine attacks that corrupt semantic consistency and factual resilience through malicious model updates. This paper presents a new resilience strategy...
Professor Paris Smaragdis develops computers with superhuman hearing for applications like speech recognition, music understanding, and environmental monitoring.
MIT News · Artificial Intelligence· news.mit.eduOct 27, 2026
Prabha Jha used her experience with MIT Open Learning’s program for senior executives to develop AI solutions for her employer, Verizon, and to write a book.
Assistant Professor Benjamin Lindquist studies how engineers deliberately injected randomness into early AI, giving rise to deep-learning models that sometimes hallucinate.
