The linear representation hypothesis states that neural network activations encode high-level concepts as linear mixtures. However, under superposition, this encoding is a projection from a higher-dimensional concept space into a lower-dimensional activation space, and a linear decision boundary in the concept space ne...
Vit\'oria Barin-Pacela, Shruti Joshi, Isabela Camacho et al.· 0 citations
It is shown that diffusion models progressively overfit the denoising training objective, creating a generalization gap between validation and training performance at intermediate noise levels and that predictions made from intermediate trajectory states occupy a distinct feature-space regime from predictions made from...
Predicting transcriptional responses to genetic perturbations is fundamental to functional genomics and therapeutic discovery. Recent deep learning models have shown promise in single-cell perturbation response prediction, but they typically generate each response in isolation, without explicitly leveraging related per...
Andrea Giuseppe Di Francesco, Andrea Rubbi, Rishabh Jain et al.· 0 citations
Sparse plus Low-Rank $(\mathbf{S} + \mathbf{LR})$ decomposition of Large Language Models (LLMs) has emerged as a promising direction in model compression, aiming to decompose pre-trained model weights into a sum of sparse and low-rank matrices $(\mathbf{W} \approx \mathbf{S} + \mathbf{LR})$. Despite recent progress, ex...
Mehdi Makni, Xiang Meng, Rahul Mazumder· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Temporal information in structured electronic health records (EHRs) is often lost in sparse one-hot or count-based representations, while sequence models can be costly and data-hungry. We propose PaReGTA, an LLM-based encoding framework that (i) converts longitudinal EHR events into visit-level templated text with expl...
Kihyuk Yoon, Lingchao Mao, Catherine Chong et al.· 0 citations
Granger causality identifies predictive dependencies in multivariate time series. In distributed settings where parties cannot share data, federated causal learning enables joint analysis. Most federated causal methods assume that clients observe the same features and infer causal relationships as point estimates, with...
Time series data are essential for a wide range of applications, yet access to high-quality datasets is often constrained by privacy concerns, acquisition costs, and labelling challenges. Synthetic time series generation has emerged as a promising approach to address these limitations. In this work, we investigate the...
Jaime Vale, Vanessa Freitas Silva, Maria Eduarda Silva et al.· 0 citations
Prior-Data Fitted Networks (PFNs) perform approximate Bayesian inference in a single forward pass, and tabular foundation models (TFMs) built on them are now widely used. To understand what networks infer internally, recent mechanistic studies of TFMs locate where predictions form, but treat these models as tabular pre...
Kaustubh Sharma, Srijan Tiwari, Ojasva Nema et al.· 0 citations
Local Timescale Gating (LT-Gate) is proposed, a neuron model that combines dual time-constant dynamics with an adaptive gating mechanism that enables individual neurons to preserve slow contextual information while responding to fast signals, addressing the stability-plasticity dilemma.
We develop a source-driven fractional heat-kernel framework for semi-super\-vised graph learning that combines nonlocal propagation with sustained label information. A fixed nonzero label source compatible with the Laplacian null space prevents asymptotic collapse into that space, providing a mechanism for mitigating o...
Farid Bozorgnia, Vyacheslav Kungurtsev, Shirali Kadyrov et al.· 0 citations
We study history-dependent online problems with a possibly inaccurate prediction of the future request sequence. Motivated by several real-world applications, we introduce a \emph{bounded-influence} framework in which past decisions and requests affect the future optimal value by only a bounded amount. Within this fram...
A membership-inference attack gets the output of a learning algorithm, and a target individual, and tries to determine whether this individual is a member of the training data or an independent sample from the same distribution. A successful membership-inference attack typically requires the attacker to have some knowl...
Mahdi Haghifam, Adam Smith, Jonathan Ullman· 0 citations
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.
