Microsoft

company

Verified

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

AI & ML interests

None defined yet.

Recent Activity

pshlego submitted a paper about 19 hours ago

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

sarahalamdari updated a collection 1 day ago

nielsr submitted a paper 1 day ago

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

View all activity

Papers

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

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

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

submitted a paper to Daily Papers about 19 hours ago

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

Paper • 2608.23041 • Published 3 days ago • 49

updated a collection 1 day ago

Dayhoff Atlas

The models and datasets that comprise the Dayhoff Atlas • 11 items • Updated 1 day ago • 13

submitted a paper to Daily Papers 1 day ago

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

Paper • 2608.19741 • Published 7 days ago • 10

published a dataset 2 days ago

microsoft/ThinkingBox-Bench

Viewer • Updated 2 days ago • 513 • 144 • 8

updated a dataset 2 days ago

microsoft/ThinkingBox-Bench

Viewer • Updated 2 days ago • 513 • 144 • 8

submitted a paper to Daily Papers 8 days ago

Agent Lightning v1.0: Towards Harnessed Agentic RL

Paper • 2608.17528 • Published 9 days ago • 31

updated a dataset 8 days ago

microsoft/benchpress-score-matrix

Viewer • Updated 8 days ago • 995 • 201 • 2

updated a dataset 12 days ago

microsoft/RHELM

Viewer • Updated 12 days ago • 1.31k • 2.73k • 15

in microsoft/Fara-7B 14 days ago

Update README.md

#11 opened 28 days ago by

updated a dataset 14 days ago

microsoft/MuseVLA-dataset

Viewer • Updated 14 days ago • 1.74k • 4.28k

updated a model 14 days ago

microsoft/MuseVLA

Robotics • Updated 14 days ago • 2

submitted a paper to Daily Papers 16 days ago

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

Paper • 2608.08097 • Published 19 days ago • 25

updated a model 16 days ago

microsoft/Mage-VL

Image-Text-to-Text • 5B • Updated 16 days ago • 499k • 377

published a model 17 days ago

microsoft/MuseVLA

Robotics • Updated 14 days ago • 2

published a dataset 17 days ago

microsoft/MuseVLA-dataset

Viewer • Updated 14 days ago • 1.74k • 4.28k

in microsoft/Mage-VL 21 days ago

Fix <|image_pad|> misalignment when images= and videos= coexist

#3 opened 23 days ago by

submitted a paper to Daily Papers 22 days ago

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

Paper • 2608.00155 • Published 27 days ago • 25

in microsoft/Mage-VL 23 days ago

Fix <|image_pad|> misalignment when images= and videos= coexist

#3 opened 23 days ago by

in microsoft/mage-flow 24 days ago

Point model references at the mage-flow-community mirror

#10 opened 24 days ago by

in microsoft/mage-flow 26 days ago

Load all model variants at module scope for ZeroGPU

#7 opened 28 days ago by