Everything you care about in one place
Follow feeds: blogs, news, RSS and more. An effortless way to read and digest content of your choice.
Get Feedermicrosoft.com
Microsoft Research
Get the latest updates from Microsoft Research directly as they happen.
Follow now 728 followers
Latest posts
Last updated 3 days ago
AutoAdapt: Automated domain adaptation for large language models
3 days ago
At a glance Problem: Adapting large language models to specialized, high-stakes domains...
Can we AI our way to a more sustainable world?
5 days ago
Technical advancement is moving at such a rapid pace that it can...
New Future of Work: AI is driving rapid change, uneven benefits
16 days ago
At a glance AI is driving rapid changes in the workplace, more...
Ideas: Steering AI toward the work future we want
16 days ago
Behind every emerging technology is a great idea propelling it forward. In...
ADeLe: Predicting and explaining AI performance across tasks
24 days ago
At a glance AI benchmarks report performance on specific tasks but provide...
AsgardBench: A benchmark for visually grounded interactive planning
about 1 month ago
At a glance To successfully complete tasks, embodied AI agents must ground...
GroundedPlanBench: Spatially grounded long-horizon task planning for robot manipulation
about 1 month ago
At a glance VLM-based robot planners struggle with long, complex tasks because...
Will machines ever be intelligent?
about 1 month ago
Technical advances are moving at such a rapid pace that it can...
Systematic debugging for AI agents: Introducing the AgentRx framework
about 1 month ago
At a glance Problem: Debugging AI agent failures is hard because trajectories...
From raw interaction to reusable knowledge: Rethinking memory for AI agents
about 2 months ago
At a glance Today’s AI agents store long interaction histories but struggle...
PlugMem: Transforming raw agent interactions into reusable knowledge
about 2 months ago
At a glance Today’s AI agents store long interaction histories but struggle...
Phi-4-reasoning-vision and the lessons of training a multimodal reasoning model
about 2 months ago
At a glance Phi-4-reasoning-vision-15B is a compact and smart open‑weight multimodal reasoning...