Microsoft

company

Verified

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

AI & ML interests

None defined yet.

Recent Activity

akolobov published a model 4 minutes ago

microsoft/rho-roboeval

akolobov updated a collection 4 minutes ago

tnaumann updated a collection about 1 hour ago

View all activity

Papers

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

When2Think: Learning Difficulty-Aware Length Control for Efficient Hybrid Reasoning Models

View all Papers

Articles

Hugging Face Models on Foundry Managed Compute

Differential Transformer V2

Introducing OptiMind, a research model designed for optimization

View all articles

microsoft 's papers 76

Submitted by

Kaixiang Zhao

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

microsoft

Submitted by

Jaejun Shim

When2Think: Learning Difficulty-Aware Length Control for Efficient Hybrid Reasoning Models

microsoft

2

Submitted by

zhiliang

VibeVoice-ASR-Streaming Technical Report

microsoft

Submitted by

Alexia Jolicoeur-Martineau

Sliding-window beats linear attention

microsoft

2

Submitted by

Sungho Park

AutoSaddler: Automatic Harness Optimization with Durable Updates from Agent Execution Traces

microsoft

Submitted by

Niels Rogge

One Success Isn't Reliability: Thinkingbox, a Sandbox and Benchmark for Agents in Stateful Business Workflows

microsoft

Submitted by

Zhiyuan He

Agent Lightning v1.0: Towards Harnessed Agentic RL

microsoft

Submitted by

Sukmin Cho

OasisKV: Scaling In-Decode KV Cache Beyond HBM with Lookahead Sparse Prefetching

microsoft

Submitted by

Dong Yan

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks?

microsoft

Submitted by

Senqiao Yang

Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model

microsoft

Submitted by

Baolin Peng

OpenForgeRL: Train Harness-native Agents in Any Environment

microsoft

DocAtlas: Long-Document Understanding as Mutable-State Interaction

microsoft