Mathematics - Microsoft Research

Publication

Enabling ab initio geometry optimization of strongly correlated systems with transferable deep quantum Monte Carlo

P. Szab'o, Zeno Schatzle, Frank Noé

March 2026

arXiv | March 2026

Publication

Phased outcome-complete simulation

Vadym Kliuchnikov, A. Paetznick, M. Silva

March 2026

arXiv | March 2026

Publication

Clifford synthesis via generalized S and CZ gates

Vadym Kliuchnikov, M. Silva

March 2026

arXiv | March 2026

Publication

Modeling Adversarial Wildfires for Power Grid Disruption

M. Brun, Xin Sun, Jean-Paul Watson

March 2026

arXiv | March 2026

Publication

MM-SCALE: Grounded Multimodal Moral Reasoning via Scalar Judgment and Listwise Alignment

Eunkyu Park, Wesley Deng, Cheyon Jin, Matheus Kunzler Maldaner, J. Wheeler, Jason I. Hong, Hong Shen, Adam Perer, Kenneth Holstein, Motahhare Eslami, Gunhee Kim

ArXiv | February 2026, Vol abs/2602.03665

Publication

From Abstract to Contextual: What LLMs Still Cannot Do in Mathematics

Bowen Cao, Dongdong Zhang, Yixia Li, Junpeng Liu, Shijue Huang, Chufan Shi, Hongyuan Lu, Yaokang Wu, Guanhua Chen, Wai Lam, Furu Wei

ICLR 2026 | January 2026

Video

Microsoft Research India 2025 Highlights

January 19, 2026

Here are some highlights of the research and impact at Microsoft Research India in 2025, along with some glimpses of the lab milieu.

Microsoft Research India 2025 Key Highlights

05:52

Microsoft Research Blog

OptiMind: A small language model with optimization expertise

January 15, 2026 | Xinzhi Zhang, Zeyi Chen, Humishka Hope, Hugo Barbalho, Konstantina Mellou, Marco Molinaro, Janardhan (Jana) Kulkarni, Ishai Menache, Sirui Li

OptiMind is a small language model that converts business operation challenges, described naturally, into mathematical formulations that optimization software can solve. It reduces formulation time & errors & enables fast, privacy-preserving local use.

A flowchart with three horizontal sections on a blue-to-green gradient background. The first section, labeled “Classification,” shows icons of a computer, an arrow pointing to a robot face, and another arrow pointing to a box labeled “TSP.” The second section, labeled “Inference,” displays a robot icon connected by arrows to two document icons, one of which includes a magnifying glass. The third section, labeled “Test-time scaling,” shows a document with a checkmark connected by an arrow to a circular refresh icon. Arrows indicate the flow between sections, starting from Classification to Inference and then to Test-time scaling.

Tool

OptiMind

OptiMind-SFT is a specialized 20B parameter model designed to bridge the gap between natural language and executable optimization solvers. It automates the translation of complex decision-making problems—such as supply chain planning, scheduling, and resource allocation—into…

Access Publication

Publication

Vibe Reasoning: Eliciting Frontier AI Mathematical Capabilities — A Case Study on IMO 2025 Problem 6

Jiaao Wu, Xian Zhang, Fan Yang, Yinpeng Dong

December 2025

arXiv | December 2025