Microsoft

company

Verified

https://www.microsoft.com/en-us/research/

AI & ML interests

None defined yet.

Recent Activity

Yif29 updated a model about 2 hours ago

microsoft/AesCode-32B

Yif29 updated a model about 2 hours ago

microsoft/AesCode-8B

gaoxin492 submitted a paper about 16 hours ago

AesCode: Aesthetic Code Generation with Decoupled Cross-Modal Rewards

View all activity

Papers

AesCode: Aesthetic Code Generation with Decoupled Cross-Modal Rewards

AutoEnvScaling: Automating the Data Flywheel with Terminal Agents

View all Papers

Articles

The Agent Said It Was Done. The Database Disagreed.

Hugging Face Models on Foundry Managed Compute

Differential Transformer V2

Introducing OptiMind, a research model designed for optimization

View all articles

microsoft 's papers 86

Submitted by

XIN GAO

AesCode: Aesthetic Code Generation with Decoupled Cross-Modal Rewards

microsoft

Submitted by

Simon Yu

AutoEnvScaling: Automating the Data Flywheel with Terminal Agents

microsoft

Submitted by

snowflakewang

From Prompting to Composing: A Spatial Canvas Interface for Poster Generation

microsoft

Submitted by

Yaoqi Chen

Capability-Driven Self-Evolution of Agent Memory

microsoft

3

Submitted by

Dylan

MiniCorp: The Last Mile of the AI Agent Firm

microsoft

Submitted by

Yinheng Li

LLM-as-Jev: LLMs Are Already Jev-Style Decision Models -- When and How to Fine-Tune Them

microsoft

Submitted by

Sungho Park

ActiveSaddler: Automated Curriculum Learning for Agent Harness Optimization

microsoft

Submitted by

Soyeong

Follow the Entities: A Corpus Map for Agentic Search

microsoft

Submitted by

Milad Yazdani

Rubric Rewards from Item Response Theory

microsoft

Submitted by

Jaejun Shim

When2Think: Learning When and How Much to Reason

microsoft

Submitted by

Wenbo Pan

The Tasteful Agent: Measuring and Improving Taste in Long-Horizon Tasks

microsoft

Submitted by

Kaixiang Zhao

When EOS Tokens Disagree: Understanding Length Inflation in On-Policy Distillation

microsoft