Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.
Claim your profile
Articles by N. Benjamin
Quantitative Biology > Quantitative Methods
Generative models are increasingly used to propose molecules for drug discovery. They can produce far more candidates than can be experimentally tested, making computational selection essential. Most selection methods rely on predicted molecular properties, such as potency and toxicity, but overlook how these properties translate into drug exposure at a given dose. As a result, molecules that appear promising on paper may require impractical doses or raise safety concerns.
Computer Science > Machine Learning
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Statistics > Machine Learning
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Computer Science > Machine Learning
Computationally expensive simulations and real-world observations often provide data at a lower temporal resolution than downstream tasks require. Averaging observations at fixed grid points can introduce errors, and motion estimates alone do not determine how the physical field values change. In this work, we study whether learning to correct a simple numerical interpolation improves the reconstruction of intermediate scientific fields.
Computer Science > Artificial Intelligence
Multi-turn jailbreaks use feedback from a victim large language model to adapt their queries over several turns. However, once an effective trajectory has been found, it is unclear how much of the earlier query history is still needed.
Computer Science > Machine Learning
[Submitted on 8 Oct 2026] Title:Zatom-2: Multitask Pretraining on Atomistic Data for Generative Modeling across Domains Authors:Miruna Cretu , Alex Abrudan , Antonia Panescu , Tynan Perez , Rishabh Anand , N. Benjamin Erichson , Michael W.
Statistics > Machine Learning
We introduce AREX, a training-free sampler for pretrained flow matching models that uses the target mean and covariance to capture an analytically tractable part of the sampling dynamics. We show that the velocity field of the moment-matched Gaussian target is the $L^2$-optimal affine approximation to the marginal velocity field.
Computer Science > Machine Learning
[Submitted on 1 Oct 2026] Title:Variational Streaming Flow: Probabilistic Forecasting in Physical Time View a PDF of the paper titled Variational Streaming Flow: Probabilistic Forecasting in Physical Time, by Hans Hao-Hsun Hsu and 4 other authors View PDF HTML (experimental) Abstract:Probabilistic forecasting is important for predicting complex dynamical systems because intrinsic randomness and incomplete observations can cause the same observed state to evolve into multiple plausible futures.
Zatom-1: A Multimodal Flow Foundation Model for 3D Molecules and Materials
[Submitted on 24 Feb 2026] Title:Zatom-1: A Multimodal Flow Foundation Model for 3D Molecules and Materials Authors:Alex Morehead , Miruna Cretu , Antonia Panescu , Rishabh Anand , Maurice Weiler , Tynan Perez , Samuel Blau , Steven Farrell , Wahid Bhimji , Anubhav Jain , Hrushikesh Sahasrabuddhe , Pietro Lio , Tommi Jaakkola , Rafael Gomez-Bombarelli , Rex Ying , N. Benjamin Erichson , Michael W.
Statistics > Machine Learning
[Submitted on 9 Feb 2026 ( v1 ), last revised 14 Oct 2026 (this version, v3)] Title:Is Flow Matching Just Trajectory Replay for Sequential Data? View a PDF of the paper titled Is Flow Matching Just Trajectory Replay for Sequential Data?, by Soon Hoe Lim and 3 other authors View PDF HTML (experimental) Abstract:Flow matching (FM) is increasingly used in scientific domains for time series generation and forecasting, where data often arise from underlying dynamical systems.
[2602.08874] Is Reasoning Capability Enough for Safety in Long-Context Language Models?
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
HydroDiffusion: Diffusion-Based Probabilistic Streamflow Forecasting with a State Space Backbone
[Submitted on 13 Dec 2025] Title:HydroDiffusion: Diffusion-Based Probabilistic Streamflow Forecasting with a State Space Backbone View a PDF of the paper titled HydroDiffusion: Diffusion-Based Probabilistic Streamflow Forecasting with a State Space Backbone, by Yihan Wang and 4 other authors View PDF HTML (experimental) Abstract:Recent advances have introduced diffusion models for probabilistic streamflow forecasting, demonstrating strong early flood-warning skill.
[2505.09022] Block-Biased Mamba for Long-Range Sequence Processing
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
[2501.14980] A Deep State Space Model for Rainfall-Runoff Simulations
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
[2412.03447] Spectral theory of effective transport for discrete uniaxial polycrystalline materials
[Submitted on 4 Dec 2024] Title:Spectral theory of effective transport for discrete uniaxial polycrystalline materials View a PDF of the paper titled Spectral theory of effective transport for discrete uniaxial polycrystalline materials, by N.
[2412.01105] Spectral theory of effective transport for continuous uniaxial polycrystalline materials
[Submitted on 2 Dec 2024] Title:Spectral theory of effective transport for continuous uniaxial polycrystalline materials View a PDF of the paper titled Spectral theory of effective transport for continuous uniaxial polycrystalline materials, by N.
[2410.02035] Tuning Frequency Bias of State Space Models
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
WaveCastNet: An AI-enabled Wavefield Forecasting Framework for Earthquake Early Warning
[Submitted on 30 May 2024] Title:WaveCastNet: An AI-enabled Wavefield Forecasting Framework for Earthquake Early Warning View a PDF of the paper titled WaveCastNet: An AI-enabled Wavefield Forecasting Framework for Earthquake Early Warning, by Dongwei Lyu and 5 other authors View PDF HTML (experimental) Abstract:Large earthquakes can be destructive and quickly wreak havoc on a landscape.
[2310.01698] Robustifying State-space Models for Long Sequences via Approximate Diagonalization
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
SuperBench: A Super-Resolution Benchmark Dataset for Scientific Machine Learning
arXiv:2306.14070 (cs) Download a PDF of the paper titled SuperBench: A Super-Resolution Benchmark Dataset for Scientific Machine Learning, by Pu Ren and 4 other authors Download PDF Submission history From: N.
Show More
loading
Actions
Is this you?
As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.Get in touch with N.
Contact N., search articles and posts on X, monitor coverage, and track replies from one place.
Learn more about Muck Rack