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 Osbert Bastani
Computer Science > Machine Learning
Auto-formalization is critical for scalable formal verification, but existing progress largely focuses on isolated statements, while theory-scale auto-formalization, which coherently translates hundreds of interdependent definitions, lemmas, and theorems, remains open due to challenges in consistency, faithfulness, scalability, and correctness. In this paper, we introduce LCS-Bench, a stand-alone, theory-scale benchmark based on Logics for Computer Science.
Improving access to essential medicines via decision-aware machine learning
Abstract A critical challenge in healthcare systems in low- and middle-income countries is the efficient and equitable allocation of scarce resources, particularly essential medicines1. This problem is complicated by limited high-quality data, which restricts the applicability of traditional data-driven techniques2,3,4,5.
RAPID: An Efficient Reinforcement Learning Algorithm for Small Language Models
arXiv:2510.03515 (cs) View PDF HTML (experimental) Subjects: Machine Learning (cs.LG) Cite as: arXiv:2510.03515 [cs.LG] (or arXiv:2510.03515v1 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2510.03515 Submission history From: Sagnik Anupam [ view email] [v1] Fri, 3 Oct 2025 20:58:49 UTC (92 KB) Bibliographic Tools Bibliographic Explorer Toggle Bibliographic Explorer () Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?)...
Generative AI without guardrails can harm learning: Evidence from high school mathematics
Generative AI without guardrails can harm learning: Evidence from high school mathematics Edited by Emma Brunskill, Stanford University, Stanford, CA; received November 3, 2024; accepted May 5, 2025 by Editorial Board Member Mark Granovetter Significance While generative AI has been shown to enhance productivity, its influence on learning new skills remains unclear. Our research examines the impact of generative AI, specifically GPT-4, on student learning in math education.
[2505.19387] Alignment of large language models with constrained learning
Work on one of the world's most important websites and make an impact on open science.
[2408.06186] Improving Structural Diversity of Blackbox LLMs via Chain-of-Specification Prompting
Want to support truly open science and create access to research, regardless of disability? Sign up for the arXiv Accessibility Forum in September and Learn more.
Improved modeling of RNA-binding protein motifs in an interpretable neural model of RNA splicing - Genome Biology
We structure our LSSI models as simple feedforward neural networks that first map their input to 100 hidden neurons, then have 5 hidden 100-wide layers with ReLU activations, and then finally mapping to a prediction output. These models are trained on the same training dataset as our other models, using 10 epochs, a batch size of 150, and a learning rate of 10-3.
[2108.08454] Improving Human Sequential Decision-Making with Reinforcement Learning
[Submitted on 19 Aug 2021 ( v1 ), last revised 19 Mar 2024 (this version, v5)] Title:Improving Human Sequential Decision-Making with Reinforcement Learning Download a PDF of the paper titled Improving Human Sequential Decision-Making with Reinforcement Learning, by Hamsa Bastani and 2 other authors Download PDF HTML (experimental) Abstract:Workers spend a significant amount of time learning how to make good decisions.
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 Osbert
Contact Osbert, search articles and posts on X, monitor coverage, and track replies from one place.
Learn more about Muck Rack