Microsoft

company

Verified

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

microsoft

AI & ML interests

None defined yet.

Recent Activity

jpcorb20 updated a model about 6 hours ago

microsoft/MediPhi-MedCode

jpcorb20 updated a model about 6 hours ago

microsoft/MediPhi-Guidelines

jpcorb20 updated a model about 6 hours ago

microsoft/MediPhi-MedWiki

View all activity

Papers

DoVer: Intervention-Driven Auto Debugging for LLM Multi-Agent Systems

Gold-Medal-Level Olympiad Geometry Solving with Efficient Heuristic Auxiliary Constructions

View all Papers

microsoft 's Papers 21

Submitted by

Jue Zhang

DoVer: Intervention-Driven Auto Debugging for LLM Multi-Agent Systems

microsoft

Submitted by

Xiao Liang

Gold-Medal-Level Olympiad Geometry Solving with Efficient Heuristic Auxiliary Constructions

microsoft

Submitted by

taesiri

Fara-7B: An Efficient Agentic Model for Computer Use

microsoft

Submitted by

Chaoyun Zhang

UFO^3: Weaving the Digital Agent Galaxy

microsoft

Submitted by

Chaoyun Zhang

GUI-360: A Comprehensive Dataset and Benchmark for Computer-Using Agents

microsoft

Submitted by

Huanyu_Zhang

Latent Sketchpad: Sketching Visual Thoughts to Elicit Multimodal Reasoning in MLLMs

microsoft

Submitted by

Jannis Vamvas

QueST: Incentivizing LLMs to Generate Difficult Problems

microsoft

3

Submitted by

Shun Zheng

Deep Self-Evolving Reasoning

microsoft

2

Submitted by

Jiayu Ding

Information-Preserving Reformulation of Reasoning Traces for Antidistillation

microsoft

Submitted by

taesiri

SwiReasoning: Switch-Thinking in Latent and Explicit for Pareto-Superior Reasoning LLMs

microsoft

Submitted by

taesiri

Just Do It!? Computer-Use Agents Exhibit Blind Goal-Directedness

microsoft

3

Submitted by

Minki Kang

ACON: Optimizing Context Compression for Long-horizon LLM Agents

microsoft

Submitted by

Miaosen Zhang

InfoAgent: Advancing Autonomous Information-Seeking Agents

microsoft

2

Submitted by

Pranjal A. Chitale

The role of synthetic data in Multilingual, Multi-cultural AI systems: Lessons from Indic Languages

microsoft

2

Submitted by

Ruiyu Wang

CAD-Tokenizer: Towards Text-based CAD Prototyping via Modality-Specific Tokenization

microsoft

2

Submitted by

Xiao Liu

Behind RoPE: How Does Causal Mask Encode Positional Information?

microsoft

Submitted by

Eric Lan

Contextual Integrity in LLMs via Reasoning and Reinforcement Learning

microsoft

1

TwT: Thinking without Tokens by Habitual Reasoning Distillation with Multi-Teachers' Guidance

microsoft

PromptIntern: Saving Inference Costs by Internalizing Recurrent Prompt during Large Language Model Fine-tuning

microsoft

Submitted by

AK

WizardCoder: Empowering Code Large Language Models with Evol-Instruct

microsoft

Table Meets LLM: Can Large Language Models Understand Structured Table Data? A Benchmark and Empirical Study

microsoft