Long-range distillation is introduced, whereby a long-timestep probabilistic ``student''model is trained to forecast directly at long-range using a huge synthetic dataset generated by an autoregressive ``teacher''model, representing the first demonstration that real-world skill can be improved by training on AI-generat...
Scott A. Martin, Noah D. Brenowitz, Dale R. Durran et al.· arXiv.org· 5 citations
This work developed an algorithmic framework for variational quantum kernels utilizing resource- efficient quantum kernels utilizing resource- efficient ansatze for complex classification tasks and introduced a parameter scaling technique to accelerate convergence.
In-context reinforcement learning (ICRL) has emerged as an effective paradigm for test time adaptation to unseen tasks without parameter updates. However, existing ICRL methods can exhibit brittle and unstable adaptions, and the mechanisms underlying such adaptions remain poorly understood. We provide a policy-gradient...
Wenhao Zhang, Shao Zhang, Xihuai Wang et al.· 0 citations
Sig-DEG (Signature-based Differential Equation Generator), a generator for distilling pre-trained diffusion models, combines partial signatures that summarize Brownian motion over subintervals with a recurrent structure to approximate stochastic differential equation solutions to achieve universality.
Wen-Hang Ge, Lei Jiang, Ling-Yi Yang et al.· arXiv.org· 4 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Recent advances highlight Reinforcement Learning with Verifiable Rewards (RLVR) as a promising approach to enhancing LLM capabilities. However, it remains unclear whether the current practice of RLVR truly expands models' reasoning boundary or mainly amplifies high-reward outputs that base models already know. We intro...
Fang Wu, Weihao Xuan, Danny Xing et al.· 0 citations
Scheduling echocardiographic examinations in a hospital setting presents significant challenges due to non-deterministic factors such as patient no-shows, variable arrival times, and heterogeneous exam durations, as well as asymmetric resource constraints between fetal and non-fetal patient streams. Fetal cases involve...
Bozhi Sun, Seda Tierney, Jeffrey A. Feinstein et al.· 0 citations
It is taken that current research practices of improving one or two aspects in isolation are insufficient and research on Trustworthy AI must account for interactions between aspects and adopt a holistic view across all relevant axes at once.
A model of time series dependencies, that flexibly adapt to different time series regularity, while enabling us to learn these dependencies from observations is proposed.
I. Lerner, A. Burgun, F. Bach· arXiv.org· 1 citation
It is suggested that simple in-training interpolation deserves consideration before introducing more elaborate forgetting-mitigation mechanisms, and Sequential Fine-tuning with Averaging with Averaging with SFA is introduced and evaluated.
Anat Kleiman, G. Dziugaite, Jonathan Frankle et al.· 16 citations· ⚡2
Standard deep learning architectures used for classification generate label predictions with a projection head and softmax activation function. Although successful, these methods fail to leverage the relational information between samples for generating label predictions. In recent works, graph-based learning technique...
Jason Brown, Bohan Chen, Harris Hardiman-Mostow et al.· 0 citations
We introduce Bellman Conformal Inference (BCI), a framework that wraps around any time series forecasting models and provides calibrated prediction intervals. Unlike the existing methods, BCI is able to leverage multi-step ahead forecasts and explicitly optimize the average interval lengths by solving a one-dimensional...
Zitong Yang, Yu Ming Huang, Emmanuel Cand\`es et al.· 0 citations
The generation of discontinuous distributions is a difficult task for most known frameworks such as generative autoencoders and generative adversarial networks. Generative non-invertible models are unable to accurately generate such distributions, require long training and often are subject to mode collapse. Variationa...
Mariia Drozdova, Vitaliy Kinakh, Guillaume Qu\'etant et al.· 0 citations
A machine-learning approach called CheMeleon provides a practical way to develop new drugs or other molecules with much less detailed, expensive experimentation.
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.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
