While Physics-Informed Neural Networks offer a promising framework for solving partial differential equations, the standard $L^2$ loss formulation is fundamentally insufficient when applied to the Bhatnagar-Gross-Krook (BGK) model. Specifically, simply minimizing the standard loss does not guarantee accurate prediction...
Gyounghun Ko, Sung-Jun Son, Seung Yeon Cho et al.· 0 citations
This work proposes AIMER (AIMER), a simple calibration-free criterion that identifies more distinct experts by capturing the concentration pattern of expert weights, making it well suited for task-agnostic expert pruning.
Zong-Fang Liu, Guang-Yi Chen, Yi-Fan Shen et al.· Conference on Empirical Meth...· 7 citations
Generative foundation models are increasingly scaled in both width and depth, posing significant challenges for stable feature learning and reliable hyperparameter (HP) transfer across model sizes. While maximal update parameterization~($\mu$P) has provided a principled solution to both problems for width scaling, exis...
Chenyu Zheng, Rongzhen Wang, Xinyu Zhang et al.· 0 citations
Discrete diffusion models are often said to outperform autoregressive models on planning tasks, but the specific mechanisms enabling this are not yet well understood. To explain why, we abstract the complexity of studying "planning" into graph traversal problems, which offer a minimal setup for evaluating language mode...
Itamar Trainin, Shauli Ravfogel, Omri Abend et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Scaling up model parameters has long been a prevalent training paradigm driven by the assumption that larger models yield superior generation capabilities. However, under lossy context compression in a compressor--decoder setup, we find a \textbf{\textit{Size-Fidelity Paradox}}: increasing compressor size can lessen th...
Ruishan Guo, Yibing Liu, Guoxin Ma et al.· 0 citations
A contractive propagation condition and a stability certificate obtained by unrolling the resulting recursion are proposed and it is proved that there exist interpolating regimes with small risk where such contractive sensitivity cannot hold, showing that stability is not a universal explanation.
We develop a unified matrix-spectral framework for analyzing stability and interpretability in deep neural networks. Representing networks as data-dependent products of linear operators reveals spectral quantities governing sensitivity to input perturbations, label noise, and training dynamics.
We introduce a Global...
A causal model is formally defined that explicitly captures both types of anomalies by treating outliers as latent interventions on latent ("true") and observed ("measured") variables and show under which conditions the distinction is possible.
Distribution system operators need realistic load and generation profiles when measurements are unavailable, incomplete, or too coarse for the intended analysis. Training separate models for synthetic data generation, imputation, and super-resolution can duplicate modeling effort as observation requirements change. Thi...
Nan Lin, Yanbo Wang, Jacco Heres et al.· 0 citations
Training of multimodal foundation models is currently restricted to centralized data centers containing massive, aligned datasets (e.g., image-text pairs). However, in realistic federated environments, data is often unpaired and fragmented across disjoint nodes; one node may hold sensor data, while another holds textua...
In many learning tasks, certain requirements on the processing of individual data samples can arguably be formalized, in an intelligible way, as strict constraints of the underlying optimization problem, rather than by means of arbitrary penalties that often require heavy trial-and-error tuning. In this paper we show t...
Francesca Lanzillotta, Chiara Albisani, Davide Pucci et al.· 0 citations
Reinforcement Learning from Verifier Rewards (RLVR) has emerged as a widely used approach for post-training large language models on reasoning tasks, with group-based methods such as GRPO and its variants gaining broad adoption. These methods rely on group-relative advantage estimation to avoid learned critics, yet its...
Fengkai Yang, Zherui Chen, Xiaohan Wang et al.· 0 citations
Research Manager Mike Walker reflects on a career spanning hacker culture, cybersecurity, and AI, sharing lessons about trust, teamwork, leadership, and why solving difficult problems requires curiosity, judgment, agility—and an understanding of the rules. The post Learn the rules: The hacker mindset appeared first on Microsoft Research.
Learn how Google Antigravity and our Cheminformatics Skills accelerate drug discovery workflows, search compounds, and propose novel rigidified macrocycles.
MIT News · Artificial Intelligence· news.mit.eduOct 28, 2026
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.
